The learning speed of the feed forward neural
network takes a lot of time to be trained which is a major
drawback in their applications since the past decades. The
key reasons behind may be due to the slow gradient-based
learning algorithms which are extensively used to train the
neural networks or due to the parameters in the networks
which are tuned iteratively using some learning algorithms.
Thus, in order to eradicate the above pitfalls, a new learning
algorithm was proposed known as Extreme Learning Machines
(ELM). This algorithm tries to compute Hidden-layer-output
matrix that is made of randomly assigned input layer and
hidden layer weights and randomly assigned biases. Unlike the
other feedforward networks, ELM has the access of the whole
training dataset before going into the computation part. Here,
we have devised a new two-layer-feedforward network (TFFN)
for ELM in a new manner with randomly assigning the weights
and biases in both the hidden layers, which then calculates the
output-hidden layer weights using the Moore-Penrose generalized
inverse. TFFN doesn’t restricts the algorithm to fix the number
of hidden neurons that the algorithm should have. Rather it
searches the space which gives an optimized result in the neurons
combination in both the hidden layers. This algorithm provides a
good generalization capability than the parent Extreme Learning
Machines at an extremely fast learning speed. Here, we have
experimented the algorithm on various types of datasets and
various popular algorithm to find the performances and report
a comparison.
PREVENTION OF HEART PROBLEM USING ARTIFICIAL INTELLIGENCEijaia
This document discusses building a machine learning model to predict the probability of patients experiencing heart problems based on their medical data. It analyzes data from 1000 patients across India on risk factors like family history, smoking, hypertension, cholesterol levels, blood sugar, obesity, lifestyle, previous bypass surgery, and iron levels. The model aims to help doctors make treatment decisions and minimize false negatives, where the model predicts no problem when one exists. It finds certain risk factors like family history, age over 50, and being male are correlated with higher heart problem rates. The model will be trained on this data to predict new patients' heart problem probability.
LDL Cholesterol Target :“ Lower the Better ”Arindam Pande
Lowering LDL cholesterol provides significant cardiovascular benefits and reduces risk, even in those with low baseline LDL levels or who achieve very low LDL levels with treatment. While residual risk remains even with intensive statin therapy to lower LDL well below current target levels, risk continues to decrease as LDL is further lowered. The lower the achieved LDL level, the lower the long-term risk of major cardiovascular events and atherosclerotic progression.
The Use of Artificial Neural Network and Logistic Regression to Predict the I...Crimsonpublisherscojnh
The Use of Artificial Neural Network and Logistic Regression to Predict the Influence of Lifestyle on Cardiovascular Risk Factors by Jahandideh S*, Jahandideh M, Asefzadeh S and Ziaee A in COJ Nursing & Healthcare
There was a time when Man was the son of nature, interacting and part of the whole process of life. Then, as his fate, man progressed, invented, produced, flourished and finally prevailed on earth. He created artificial systems in which he lived, and at times seemed so close to being protected and safe from any natural phenomenal impact. Then he realized that his own creation, byproducts, beside his aggression against his own kind were being his enemy. In recent years, disasters increased in frequency, where grade 4 or more, hurricanes attacked the southern parts of the USA, as well in Asia. Large ice bergs cracked in Greenland, North and South poles, dissolving in the sea. There is an increase or rise of the Sea level, although it is few cms a year but it became a reality
https://crimsonpublishers.com/eaes/fulltext/EAES.000501.php
For more open access journals in Crimson Publishers
Please click on link: https://crimsonpublishers.com
For More Articles on Environmental Analysis & Ecology Studies
Please click on: https://crimsonpublishers.com/eaes/
Fatty Acids and their role in Cardiometabolic HealthArindam Pande
This document discusses fatty acids and their role in cardiometabolic health. It summarizes that the conventional view of the diet-heart hypothesis, which links saturated fat and cholesterol to heart disease, may be an oversimplification. Different fatty acids, including saturated fatty acids found in dairy, can have varying metabolic effects. Replacing saturated fats with polyunsaturated fats may lower heart disease risk, but replacing them with carbohydrates does not. Ongoing research is exploring the cardiovascular impacts of omega-3 supplements and specific plant oils. In conclusion, the type of fat consumed is important for heart health, not just total fat intake, and dietary patterns rather than single nutrients should be the focus.
A comparative study for some atherogenic indices in sera ofAlexander Decker
This document summarizes a study that evaluated lipid profiles and atherogenic indices in patients with myocardial infarction (MI), ischemic heart disease (IHD), and a control group. The study found:
1) Levels of total cholesterol and triglycerides did not significantly differ between MI/IHD patients and controls, while LDL cholesterol was significantly higher in MI/IHD patients.
2) VLDL cholesterol was significantly lower in MI patients and lower in IHD patients compared to controls.
3) Atherogenic indices like cardiogenic risk ratio, atherogenic coefficient, and atherogenic index of plasma were significantly higher in MI patients compared to controls, but only non-significantly higher in IHD
This document summarizes a study that assessed lipid levels in cardiovascular patients. The study found that levels of blood sugar, triglycerides, and LDL cholesterol were higher in angina and heart attack patients compared to controls. HDL cholesterol was lower in patients. Lipid profiles did not significantly differ between angina and heart attack patients. Diabetic patients had higher lipid levels than non-diabetic patients. The study concludes that hyperlipidemia is present in both angina and heart attack patients, with no significant differences in lipid profiles between the two patient groups.
This document discusses the use of C-reactive protein (CRP) and low-density lipoprotein (LDL) cholesterol levels to predict cardiovascular risk. It summarizes a study that found CRP to be a stronger predictor of future cardiovascular events than LDL, with CRP and LDL providing complementary and non-correlated information. The document concludes that measuring both CRP and LDL provides superior risk detection compared to either marker alone, and that patients with high CRP but low LDL (<160 mg/dl) should be considered at increased risk.
PREVENTION OF HEART PROBLEM USING ARTIFICIAL INTELLIGENCEijaia
This document discusses building a machine learning model to predict the probability of patients experiencing heart problems based on their medical data. It analyzes data from 1000 patients across India on risk factors like family history, smoking, hypertension, cholesterol levels, blood sugar, obesity, lifestyle, previous bypass surgery, and iron levels. The model aims to help doctors make treatment decisions and minimize false negatives, where the model predicts no problem when one exists. It finds certain risk factors like family history, age over 50, and being male are correlated with higher heart problem rates. The model will be trained on this data to predict new patients' heart problem probability.
LDL Cholesterol Target :“ Lower the Better ”Arindam Pande
Lowering LDL cholesterol provides significant cardiovascular benefits and reduces risk, even in those with low baseline LDL levels or who achieve very low LDL levels with treatment. While residual risk remains even with intensive statin therapy to lower LDL well below current target levels, risk continues to decrease as LDL is further lowered. The lower the achieved LDL level, the lower the long-term risk of major cardiovascular events and atherosclerotic progression.
The Use of Artificial Neural Network and Logistic Regression to Predict the I...Crimsonpublisherscojnh
The Use of Artificial Neural Network and Logistic Regression to Predict the Influence of Lifestyle on Cardiovascular Risk Factors by Jahandideh S*, Jahandideh M, Asefzadeh S and Ziaee A in COJ Nursing & Healthcare
There was a time when Man was the son of nature, interacting and part of the whole process of life. Then, as his fate, man progressed, invented, produced, flourished and finally prevailed on earth. He created artificial systems in which he lived, and at times seemed so close to being protected and safe from any natural phenomenal impact. Then he realized that his own creation, byproducts, beside his aggression against his own kind were being his enemy. In recent years, disasters increased in frequency, where grade 4 or more, hurricanes attacked the southern parts of the USA, as well in Asia. Large ice bergs cracked in Greenland, North and South poles, dissolving in the sea. There is an increase or rise of the Sea level, although it is few cms a year but it became a reality
https://crimsonpublishers.com/eaes/fulltext/EAES.000501.php
For more open access journals in Crimson Publishers
Please click on link: https://crimsonpublishers.com
For More Articles on Environmental Analysis & Ecology Studies
Please click on: https://crimsonpublishers.com/eaes/
Fatty Acids and their role in Cardiometabolic HealthArindam Pande
This document discusses fatty acids and their role in cardiometabolic health. It summarizes that the conventional view of the diet-heart hypothesis, which links saturated fat and cholesterol to heart disease, may be an oversimplification. Different fatty acids, including saturated fatty acids found in dairy, can have varying metabolic effects. Replacing saturated fats with polyunsaturated fats may lower heart disease risk, but replacing them with carbohydrates does not. Ongoing research is exploring the cardiovascular impacts of omega-3 supplements and specific plant oils. In conclusion, the type of fat consumed is important for heart health, not just total fat intake, and dietary patterns rather than single nutrients should be the focus.
A comparative study for some atherogenic indices in sera ofAlexander Decker
This document summarizes a study that evaluated lipid profiles and atherogenic indices in patients with myocardial infarction (MI), ischemic heart disease (IHD), and a control group. The study found:
1) Levels of total cholesterol and triglycerides did not significantly differ between MI/IHD patients and controls, while LDL cholesterol was significantly higher in MI/IHD patients.
2) VLDL cholesterol was significantly lower in MI patients and lower in IHD patients compared to controls.
3) Atherogenic indices like cardiogenic risk ratio, atherogenic coefficient, and atherogenic index of plasma were significantly higher in MI patients compared to controls, but only non-significantly higher in IHD
This document summarizes a study that assessed lipid levels in cardiovascular patients. The study found that levels of blood sugar, triglycerides, and LDL cholesterol were higher in angina and heart attack patients compared to controls. HDL cholesterol was lower in patients. Lipid profiles did not significantly differ between angina and heart attack patients. Diabetic patients had higher lipid levels than non-diabetic patients. The study concludes that hyperlipidemia is present in both angina and heart attack patients, with no significant differences in lipid profiles between the two patient groups.
This document discusses the use of C-reactive protein (CRP) and low-density lipoprotein (LDL) cholesterol levels to predict cardiovascular risk. It summarizes a study that found CRP to be a stronger predictor of future cardiovascular events than LDL, with CRP and LDL providing complementary and non-correlated information. The document concludes that measuring both CRP and LDL provides superior risk detection compared to either marker alone, and that patients with high CRP but low LDL (<160 mg/dl) should be considered at increased risk.
This document discusses the use of C-reactive protein (CRP) and low-density lipoprotein (LDL) cholesterol levels to predict cardiovascular risk. It summarizes a study that found CRP to be a stronger predictor of future cardiovascular events than LDL, with CRP and LDL providing complementary and non-correlated information. The document concludes that measuring both CRP and LDL provides superior risk detection compared to either marker alone, and that patients with high CRP but low LDL (<160 mg/dl) should be considered at increased risk.
This document provides an agenda for a seminar on cardiovascular risk and dyslipidemias presented by Dr. Cesar Asenjo on October 9, 2013. The seminar will cover introductions, risk factors, diet, diabetes, and treatment. It includes the schedule, registration information, and collaborating organizations. The agenda lists several topics to be covered including factors of risk, diet, diabetes, and treatment. It also references several studies that will be discussed relating to these topics and cardiovascular disease.
Chronic heart disease and Anaemia. Heart failure is a very common disease, with severe morbidity and mortality, and is a frequent reason of hospitalization.
Anemia and a concurrent renal impairment are two major risk factors contributing to the severity of the outcome.
Heme iron is absorbed through a separate pathway and does not have to be discontinued when intravenous treatment is started. This can allow for longer intervals between resource-heavy, inconvenient and painful injections. Oxidative stress is also avoided.
Heme iron does not need to be discontinued during injection or EPO therapy like non-heme oral iron.
The metabolic syndrome is a cluster of risk factors that increases the risk of cardiovascular diseases like coronary heart disease, stroke, peripheral arterial disease, and aortic disease. It requires meeting criteria for increased waist circumference plus two of four factors like high blood pressure and cholesterol. Patients with metabolic syndrome have two times higher risk of cardiovascular diseases due to effects like endothelial dysfunction and arterial stiffness. Coronary heart disease is the most common and deadly cardiovascular disease, accounting for over 2 million deaths in Europe annually. Lifestyle changes like diet, exercise and smoking cessation can help treat metabolic syndrome and reduce disease risk.
This document discusses coronary heart disease (CHD), including its causes, presentations, burden, measurements, risk factors, prevention strategies, and intervention trials. It notes that CHD is caused by inadequate blood flow to the heart and is a leading cause of death. Risk factors include smoking, hypertension, high cholesterol, diabetes, genetics, physical inactivity, and alcohol consumption. Prevention strategies involve population-wide approaches like diet/lifestyle changes and controlling risk factors, identifying and counseling high-risk individuals, and secondary prevention after events. Several trials showed community programs and clinical interventions can significantly reduce CHD incidence.
This document discusses strategies for reducing cardiovascular risk, including modifying risk factors through lifestyle changes. It emphasizes addressing multiple risk factors simultaneously and implementing an individualized plan. Lifestyle interventions like the SELFTM method are recommended to avoid oxidative damage and inflammation from foods and to rely on high-fiber, plant-based diets. Specific dietary strategies are outlined to reduce post-prandial glucose and lipid levels through food choices and timing of meals.
The document summarizes a study that evaluated the combined use of computed tomography (CT) coronary calcium scoring and high-sensitivity C-reactive protein (CRP) testing to predict cardiovascular events in a cohort of 967 non-diabetic adults over 6.4 years. The study found that higher calcium scores and CRP levels were both associated with increased risk of myocardial infarction, coronary death, and other cardiovascular events. Participants with high calcium scores and high CRP had the highest risks, with relative risks up to 6-7 times higher than those with low scores/levels. The results suggest that calcium scoring and CRP testing provide complementary predictive information and assess different disease mechanisms.
The document summarizes a study that evaluated the combined use of computed tomography (CT) coronary artery calcium scoring and high-sensitivity C-reactive protein (CRP) testing to predict cardiovascular events in a cohort of 967 non-diabetic adults over 6.4 years. The study found that higher calcium scores and CRP levels were both associated with increased risk of myocardial infarction, coronary death, and other cardiovascular events. Participants with high calcium scores and high CRP had the highest risks, with relative risks up to 6.1 for heart attack/death and up to 7.5 for any cardiovascular event. The results suggest that calcium scoring and CRP testing provide complementary predictive power and assess different disease mechanisms.
ABSTRACT- In today’s modern lifestyle high blood cholesterol is one of the most dreaded causes of heart diseases among the global population. Fast lifestyle, lack of exercise, obesity and improper food intake all sum up to deranged lipid profile as well as diabetes. Diabetes and high blood cholesterol goes hand in hand which leads to an increased incidence of coronary artery and cardiovascular disorders which still remains as one of the leading causes of mortality overall. In the present study there has been an effort put to draw a correlation between glycosylated hemoglobin which is a marker for level of blood glucose in diabetic patients as well as deranged lipid profile. Blood samples collected in sterile vials were first centrifuged and then put into analyzer for the computation of the lipid profile and the glycosylated hemoglobin. Results computed were made a note of and then prepared for statistical analysis. Results thus obtained showed that females showed significantly higher levels of total serum cholesterol and Non-HDL compared to males other than that their lipid parameters were a little higher than males in general. Diabetic female patients showed a significantly higher level of glycosylated hemoglobin. There was a significant difference in the HDL values of patients in pre diabetic state and worst control of glycemic hemoglobin. There were also significant differences observed in the TGL, TGL/HDL and VLDL values between Diabetic and control patients. In general there were increased correlation of HbA1c with TSC and LDL and the respective ratios as HbA1c increases while LDL/HDL showed a significant increase with HbA1c.
Key-words- Cholesterol, Diabetes mellitus, Lipid profile, HDL, LDL, Lipid ratios
1. The new AHA/ACC cholesterol guidelines were published in November 2018 and feature several major changes from prior guidelines, including new definitions of risk categories, more detailed guidance on treatment options, and a focus on percentage LDL-C reductions in addition to statin potency.
2. The guidelines emphasize lifestyle therapy and risk factor modification across all ages and risk groups. For very high risk patients, they recommend using a LDL-C threshold of 70 mg/dL to consider adding nonstatins to statin therapy.
3. The guidelines provide new recommendations for patients with severe hypercholesterolemia, diabetes, and those undergoing clinician-patient risk discussions regarding primary prevention statin therapy.
Prediction of cardiovascular disease with machine learningPravinkumar Landge
This document discusses using machine learning to predict cardiovascular disease. It begins with an introduction to heart disease and cardiovascular disease. It then discusses the motivation for using machine learning to predict disease given the large amount of healthcare data and multiple risk factors. The document describes the Cleveland Heart Disease dataset that is used, which contains 14 attributes on individuals. It concludes that machine learning techniques are useful for predicting cardiovascular disease outcomes based on risk factor data.
Serum uric acid as a marker of left ventricular failure in acute myocardial i...iosrjce
IOSR Journal of Dental and Medical Sciences is one of the speciality Journal in Dental Science and Medical Science published by International Organization of Scientific Research (IOSR). The Journal publishes papers of the highest scientific merit and widest possible scope work in all areas related to medical and dental science. The Journal welcome review articles, leading medical and clinical research articles, technical notes, case reports and others.
Cardiovascular disease is very common in patients with chronic kidney disease.
- CVD is the leading cause of death in patients with CKD, even in early stages of kidney disease and those with low levels of albuminuria. Reduced kidney function and increased albuminuria are associated with higher risk of CVD events and mortality.
- The prevalence of CVD is extremely high in patients on dialysis, with over 70% of dialysis patients having CVD. CVD is responsible for about 40% of all deaths in dialysis patients.
- Both traditional CVD risk factors like hypertension and diabetes as well as nontraditional risk factors related to CKD contribute to the elevated CVD risk in this population. Targeting modifiable
HDL-cholesterol concentrations are inversely associated with CVD.When we consider cardiovascular mortality in women in terms of HDL.Causes of low HDL cholesterol.Lipoprotein subfractions suffer a shift after menopause towards a more atherogenic lipid profile.associations of HDL-C and HDL-P with cIMT and CHD.MESA (Multi-Ethnic Study of therosclerosis. Functional Versus Dysfunctional HDL. High concentrations of HDL - cholesterol are associated with high all-cause mortality in men and women.Improvement of HDL function without necessarily raising HDL-C
Marc Penn, MD, PhD, FACC - Trials and Tribulations of Assessing CVD Risk in ...Cleveland HeartLab, Inc.
This document discusses the importance of assessing cardiovascular risk through inflammatory markers in addition to traditional lipid markers. It provides evidence that atherosclerosis is driven by inflammation and markers like hsCRP and MPO can help identify patients at higher risk of events. The document also discusses how statins work through multiple anti-inflammatory pathways beyond just lowering lipids. A multimarker inflammation approach is presented as a way to better stratify risk and identify high-risk patients within populations that may otherwise appear low risk based on traditional metrics alone.
Diabetes increases the risk of atherosclerosis and heart disease through metabolic abnormalities like high blood sugar and insulin resistance. These alterations affect the function of endothelial cells, platelets, and smooth muscle cells in the arteries, leading to atherosclerosis and destruction of the arteries. A typical type 2 diabetic patient has equal risk of future heart attack as a past heart attack survivor without any other heart problems. Over 75% of people with diabetes die from coronary atherosclerosis and managing diabetes involves following a healthy diet, regular exercise, medication adherence, and regular blood glucose testing.
ABSTRACT- Background: Microalbuminuria in hypertension has been described as an early sign of kidney damage
and a predictor for end stage renal disease and cardiovascular disease. More specifically it is seen amongst patients
suffering from hypertension.
Methods: This study was conducted at Dr. Ram Manohar Lohia Institute of Medical Sciences, Lucknow, India in the
department of emergency medicine and 84 subjects were included in the evaluation in the age of more than 30 years.
All patients were diagnosed by clinical examination, anthropometric measurement, blood pressure, urinary
microalbumin, and urinary creatinine. Statistical analysis was done by using SPSS, version 16.0 p-values were
calculated by chi-square test, ANOVA unpaired t-test. The p <0.05 was considered statistically significant.
Results: It was found that microalbuminuria among hypertensive patients increased steadily with the advancing age and
the duration of hypertension. The features of high urinary microalbumin 52.09±8.62 mg/24hr and the urinary creatinine
2.37±0.86mg/dl were prevalent in hypertensive patients and it increased in both male and female patients.
Conclusions: The prevalence of microalbuminuria in hypertensive individuals is high, and it revealed strong
association between microalbuminuria and hypertension. Our findings suggest that microalbuminuria could be a useful
marker to assess risk stratification and management of cardiovascular disease and renal disease.
Key words: Hypertension, Cardiovascular disease, Renal disease, Risk factors, Age factors, Urinary creatinine,
Urinary microalbumin
Heart is the most important organ of a human body. It circulates oxygen and other vital nutrients through blood to different parts of the body and helps in the metabolic activities. Apart from this it also helps in removal of the metabolic wastes. Thus, even minor problems in heart can affect the whole organism. Researchers are diverting a lot of data analysis work for assisting the doctors to predict the heart problem. So, an analysis of the data related to different health problems and its functioning can help in predicting with a certain probability for the wellness of this organ. In this paper we have analysed the different prescribed data of 1094 patients from different parts of India. Using this data, we have built a model which gets trained using this data and tries to predict whether a new out-of-sample data has a probability of having any heart attack or not. This model can help in decision making along with the doctor to treat the patient well and creating a transparency between the doctor and the patient. In the validation set of the data, it’s not only the accuracy that the model has to take care, rather the True Positive Rate and False-Negative Rate along with the AUC-ROC helps in building/fixing the algorithm inside the model.
Papua New Guinea has about seven active mining and exploration activities for minerals like gold, copper, and other minor minerals. Each is managed by different company and
together employs about ten thousand workers. A fifth of this would be foreign workers. Most of the Mine workers that are screened at the Employees Health and Wellness clinics tend to
have similar compounding health risks
Perspective of Cardiac Troponin and Membrane Potential in People Living with ...asclepiuspdfs
Background: Hypertension is an event in which the force of the blood against the artery walls is too high leading to severe health complications and increases the risk of heart disease, stroke, and sometimes death. Aim: This study was carried out to determine the levels of cardiac troponin 1 and membrane potential in hypertensive subjects in Owerri, Imo state. Materials and Methods: A total of 120 subjects within the age 30–70 years were recruited for this study. The study consists of 60 subjects who were diagnosed of hypertension and 60 were apparently healthy individuals who served as controls subjects of the same age bracket. The levels of cardiac troponin 1 and membrane potential were analyzed using enzyme-linked immunosorbent assay technique. Data were assessed using SPSS version 20, the mean value with P ˂ 0.05 was considered statistically significant. Results: The result revealed that the levels of cardiac troponin 1 in hypertension were significantly increased when compared with control subjects while the levels of membrane potential were significantly decreased when compared to control at P < 0.05. Conclusion: The increased serum level of cardiac troponin 1 and decreased membrane potential in hypertensive subjects may contribute some risk factors in patients with hypertension.
The document summarizes analyses of two heart disease datasets: LA Heart and Cardiovas. For LA Heart, logistic regression found systolic blood pressure highly predicts heart disease probability, while other factors were less predictive. For Cardiovas, multiple regressions found hemoglobin A1C levels best explained by waist size, age, cholesterol, and blood glucose. Blood glucose was best explained by age, and other factors showed moderate-high significance. Overall, the analyses indicate systolic blood pressure and hemoglobin A1C/blood glucose levels along with associated risk factors provide useful information for understanding heart disease outcomes.
This document discusses the use of C-reactive protein (CRP) and low-density lipoprotein (LDL) cholesterol levels to predict cardiovascular risk. It summarizes a study that found CRP to be a stronger predictor of future cardiovascular events than LDL, with CRP and LDL providing complementary and non-correlated information. The document concludes that measuring both CRP and LDL provides superior risk detection compared to either marker alone, and that patients with high CRP but low LDL (<160 mg/dl) should be considered at increased risk.
This document provides an agenda for a seminar on cardiovascular risk and dyslipidemias presented by Dr. Cesar Asenjo on October 9, 2013. The seminar will cover introductions, risk factors, diet, diabetes, and treatment. It includes the schedule, registration information, and collaborating organizations. The agenda lists several topics to be covered including factors of risk, diet, diabetes, and treatment. It also references several studies that will be discussed relating to these topics and cardiovascular disease.
Chronic heart disease and Anaemia. Heart failure is a very common disease, with severe morbidity and mortality, and is a frequent reason of hospitalization.
Anemia and a concurrent renal impairment are two major risk factors contributing to the severity of the outcome.
Heme iron is absorbed through a separate pathway and does not have to be discontinued when intravenous treatment is started. This can allow for longer intervals between resource-heavy, inconvenient and painful injections. Oxidative stress is also avoided.
Heme iron does not need to be discontinued during injection or EPO therapy like non-heme oral iron.
The metabolic syndrome is a cluster of risk factors that increases the risk of cardiovascular diseases like coronary heart disease, stroke, peripheral arterial disease, and aortic disease. It requires meeting criteria for increased waist circumference plus two of four factors like high blood pressure and cholesterol. Patients with metabolic syndrome have two times higher risk of cardiovascular diseases due to effects like endothelial dysfunction and arterial stiffness. Coronary heart disease is the most common and deadly cardiovascular disease, accounting for over 2 million deaths in Europe annually. Lifestyle changes like diet, exercise and smoking cessation can help treat metabolic syndrome and reduce disease risk.
This document discusses coronary heart disease (CHD), including its causes, presentations, burden, measurements, risk factors, prevention strategies, and intervention trials. It notes that CHD is caused by inadequate blood flow to the heart and is a leading cause of death. Risk factors include smoking, hypertension, high cholesterol, diabetes, genetics, physical inactivity, and alcohol consumption. Prevention strategies involve population-wide approaches like diet/lifestyle changes and controlling risk factors, identifying and counseling high-risk individuals, and secondary prevention after events. Several trials showed community programs and clinical interventions can significantly reduce CHD incidence.
This document discusses strategies for reducing cardiovascular risk, including modifying risk factors through lifestyle changes. It emphasizes addressing multiple risk factors simultaneously and implementing an individualized plan. Lifestyle interventions like the SELFTM method are recommended to avoid oxidative damage and inflammation from foods and to rely on high-fiber, plant-based diets. Specific dietary strategies are outlined to reduce post-prandial glucose and lipid levels through food choices and timing of meals.
The document summarizes a study that evaluated the combined use of computed tomography (CT) coronary calcium scoring and high-sensitivity C-reactive protein (CRP) testing to predict cardiovascular events in a cohort of 967 non-diabetic adults over 6.4 years. The study found that higher calcium scores and CRP levels were both associated with increased risk of myocardial infarction, coronary death, and other cardiovascular events. Participants with high calcium scores and high CRP had the highest risks, with relative risks up to 6-7 times higher than those with low scores/levels. The results suggest that calcium scoring and CRP testing provide complementary predictive information and assess different disease mechanisms.
The document summarizes a study that evaluated the combined use of computed tomography (CT) coronary artery calcium scoring and high-sensitivity C-reactive protein (CRP) testing to predict cardiovascular events in a cohort of 967 non-diabetic adults over 6.4 years. The study found that higher calcium scores and CRP levels were both associated with increased risk of myocardial infarction, coronary death, and other cardiovascular events. Participants with high calcium scores and high CRP had the highest risks, with relative risks up to 6.1 for heart attack/death and up to 7.5 for any cardiovascular event. The results suggest that calcium scoring and CRP testing provide complementary predictive power and assess different disease mechanisms.
ABSTRACT- In today’s modern lifestyle high blood cholesterol is one of the most dreaded causes of heart diseases among the global population. Fast lifestyle, lack of exercise, obesity and improper food intake all sum up to deranged lipid profile as well as diabetes. Diabetes and high blood cholesterol goes hand in hand which leads to an increased incidence of coronary artery and cardiovascular disorders which still remains as one of the leading causes of mortality overall. In the present study there has been an effort put to draw a correlation between glycosylated hemoglobin which is a marker for level of blood glucose in diabetic patients as well as deranged lipid profile. Blood samples collected in sterile vials were first centrifuged and then put into analyzer for the computation of the lipid profile and the glycosylated hemoglobin. Results computed were made a note of and then prepared for statistical analysis. Results thus obtained showed that females showed significantly higher levels of total serum cholesterol and Non-HDL compared to males other than that their lipid parameters were a little higher than males in general. Diabetic female patients showed a significantly higher level of glycosylated hemoglobin. There was a significant difference in the HDL values of patients in pre diabetic state and worst control of glycemic hemoglobin. There were also significant differences observed in the TGL, TGL/HDL and VLDL values between Diabetic and control patients. In general there were increased correlation of HbA1c with TSC and LDL and the respective ratios as HbA1c increases while LDL/HDL showed a significant increase with HbA1c.
Key-words- Cholesterol, Diabetes mellitus, Lipid profile, HDL, LDL, Lipid ratios
1. The new AHA/ACC cholesterol guidelines were published in November 2018 and feature several major changes from prior guidelines, including new definitions of risk categories, more detailed guidance on treatment options, and a focus on percentage LDL-C reductions in addition to statin potency.
2. The guidelines emphasize lifestyle therapy and risk factor modification across all ages and risk groups. For very high risk patients, they recommend using a LDL-C threshold of 70 mg/dL to consider adding nonstatins to statin therapy.
3. The guidelines provide new recommendations for patients with severe hypercholesterolemia, diabetes, and those undergoing clinician-patient risk discussions regarding primary prevention statin therapy.
Prediction of cardiovascular disease with machine learningPravinkumar Landge
This document discusses using machine learning to predict cardiovascular disease. It begins with an introduction to heart disease and cardiovascular disease. It then discusses the motivation for using machine learning to predict disease given the large amount of healthcare data and multiple risk factors. The document describes the Cleveland Heart Disease dataset that is used, which contains 14 attributes on individuals. It concludes that machine learning techniques are useful for predicting cardiovascular disease outcomes based on risk factor data.
Serum uric acid as a marker of left ventricular failure in acute myocardial i...iosrjce
IOSR Journal of Dental and Medical Sciences is one of the speciality Journal in Dental Science and Medical Science published by International Organization of Scientific Research (IOSR). The Journal publishes papers of the highest scientific merit and widest possible scope work in all areas related to medical and dental science. The Journal welcome review articles, leading medical and clinical research articles, technical notes, case reports and others.
Cardiovascular disease is very common in patients with chronic kidney disease.
- CVD is the leading cause of death in patients with CKD, even in early stages of kidney disease and those with low levels of albuminuria. Reduced kidney function and increased albuminuria are associated with higher risk of CVD events and mortality.
- The prevalence of CVD is extremely high in patients on dialysis, with over 70% of dialysis patients having CVD. CVD is responsible for about 40% of all deaths in dialysis patients.
- Both traditional CVD risk factors like hypertension and diabetes as well as nontraditional risk factors related to CKD contribute to the elevated CVD risk in this population. Targeting modifiable
HDL-cholesterol concentrations are inversely associated with CVD.When we consider cardiovascular mortality in women in terms of HDL.Causes of low HDL cholesterol.Lipoprotein subfractions suffer a shift after menopause towards a more atherogenic lipid profile.associations of HDL-C and HDL-P with cIMT and CHD.MESA (Multi-Ethnic Study of therosclerosis. Functional Versus Dysfunctional HDL. High concentrations of HDL - cholesterol are associated with high all-cause mortality in men and women.Improvement of HDL function without necessarily raising HDL-C
Marc Penn, MD, PhD, FACC - Trials and Tribulations of Assessing CVD Risk in ...Cleveland HeartLab, Inc.
This document discusses the importance of assessing cardiovascular risk through inflammatory markers in addition to traditional lipid markers. It provides evidence that atherosclerosis is driven by inflammation and markers like hsCRP and MPO can help identify patients at higher risk of events. The document also discusses how statins work through multiple anti-inflammatory pathways beyond just lowering lipids. A multimarker inflammation approach is presented as a way to better stratify risk and identify high-risk patients within populations that may otherwise appear low risk based on traditional metrics alone.
Diabetes increases the risk of atherosclerosis and heart disease through metabolic abnormalities like high blood sugar and insulin resistance. These alterations affect the function of endothelial cells, platelets, and smooth muscle cells in the arteries, leading to atherosclerosis and destruction of the arteries. A typical type 2 diabetic patient has equal risk of future heart attack as a past heart attack survivor without any other heart problems. Over 75% of people with diabetes die from coronary atherosclerosis and managing diabetes involves following a healthy diet, regular exercise, medication adherence, and regular blood glucose testing.
ABSTRACT- Background: Microalbuminuria in hypertension has been described as an early sign of kidney damage
and a predictor for end stage renal disease and cardiovascular disease. More specifically it is seen amongst patients
suffering from hypertension.
Methods: This study was conducted at Dr. Ram Manohar Lohia Institute of Medical Sciences, Lucknow, India in the
department of emergency medicine and 84 subjects were included in the evaluation in the age of more than 30 years.
All patients were diagnosed by clinical examination, anthropometric measurement, blood pressure, urinary
microalbumin, and urinary creatinine. Statistical analysis was done by using SPSS, version 16.0 p-values were
calculated by chi-square test, ANOVA unpaired t-test. The p <0.05 was considered statistically significant.
Results: It was found that microalbuminuria among hypertensive patients increased steadily with the advancing age and
the duration of hypertension. The features of high urinary microalbumin 52.09±8.62 mg/24hr and the urinary creatinine
2.37±0.86mg/dl were prevalent in hypertensive patients and it increased in both male and female patients.
Conclusions: The prevalence of microalbuminuria in hypertensive individuals is high, and it revealed strong
association between microalbuminuria and hypertension. Our findings suggest that microalbuminuria could be a useful
marker to assess risk stratification and management of cardiovascular disease and renal disease.
Key words: Hypertension, Cardiovascular disease, Renal disease, Risk factors, Age factors, Urinary creatinine,
Urinary microalbumin
Heart is the most important organ of a human body. It circulates oxygen and other vital nutrients through blood to different parts of the body and helps in the metabolic activities. Apart from this it also helps in removal of the metabolic wastes. Thus, even minor problems in heart can affect the whole organism. Researchers are diverting a lot of data analysis work for assisting the doctors to predict the heart problem. So, an analysis of the data related to different health problems and its functioning can help in predicting with a certain probability for the wellness of this organ. In this paper we have analysed the different prescribed data of 1094 patients from different parts of India. Using this data, we have built a model which gets trained using this data and tries to predict whether a new out-of-sample data has a probability of having any heart attack or not. This model can help in decision making along with the doctor to treat the patient well and creating a transparency between the doctor and the patient. In the validation set of the data, it’s not only the accuracy that the model has to take care, rather the True Positive Rate and False-Negative Rate along with the AUC-ROC helps in building/fixing the algorithm inside the model.
Papua New Guinea has about seven active mining and exploration activities for minerals like gold, copper, and other minor minerals. Each is managed by different company and
together employs about ten thousand workers. A fifth of this would be foreign workers. Most of the Mine workers that are screened at the Employees Health and Wellness clinics tend to
have similar compounding health risks
Perspective of Cardiac Troponin and Membrane Potential in People Living with ...asclepiuspdfs
Background: Hypertension is an event in which the force of the blood against the artery walls is too high leading to severe health complications and increases the risk of heart disease, stroke, and sometimes death. Aim: This study was carried out to determine the levels of cardiac troponin 1 and membrane potential in hypertensive subjects in Owerri, Imo state. Materials and Methods: A total of 120 subjects within the age 30–70 years were recruited for this study. The study consists of 60 subjects who were diagnosed of hypertension and 60 were apparently healthy individuals who served as controls subjects of the same age bracket. The levels of cardiac troponin 1 and membrane potential were analyzed using enzyme-linked immunosorbent assay technique. Data were assessed using SPSS version 20, the mean value with P ˂ 0.05 was considered statistically significant. Results: The result revealed that the levels of cardiac troponin 1 in hypertension were significantly increased when compared with control subjects while the levels of membrane potential were significantly decreased when compared to control at P < 0.05. Conclusion: The increased serum level of cardiac troponin 1 and decreased membrane potential in hypertensive subjects may contribute some risk factors in patients with hypertension.
The document summarizes analyses of two heart disease datasets: LA Heart and Cardiovas. For LA Heart, logistic regression found systolic blood pressure highly predicts heart disease probability, while other factors were less predictive. For Cardiovas, multiple regressions found hemoglobin A1C levels best explained by waist size, age, cholesterol, and blood glucose. Blood glucose was best explained by age, and other factors showed moderate-high significance. Overall, the analyses indicate systolic blood pressure and hemoglobin A1C/blood glucose levels along with associated risk factors provide useful information for understanding heart disease outcomes.
The Indian Consensus Document on Cardiac BiomarkerApollo Hospitals
Despite recent advances, the diagnosis and management of heart failure evades the clinicians. The etiology of congestive heart failure (CHF) in the Indian scenario comprises of coronary artery disease, diabetes mellitus and hypertension. With better insights into the pathophysiology of CHF, biomarkers have evolved rapidly and received diagnostic and prognostic value. In CHF biomarkers prove as measures of the extent of pathophysiological derangement; examples include biomarkers of myocyte necrosis, myocardial remodeling,
neurohormonal activation, etc.
This study develops a sequential decision model to quantify the risk value of life-years on statin treatment, as perceived by various national lipid management guidelines. The model considers the progression of patients' cholesterol levels using Markov chains calibrated by clinical data. Results show the guidelines imply penalty factors for treatment disutility ranging from 0.04-0.29% per life-year, with some guidelines favoring nearly 30 years of treatment. While guidelines aim to reduce cardiovascular risk, treatment durations could be shortened by up to 4 years without increasing overall risk. The approach quantifies adverse effects of treatment to help evaluate guidelines and facilitate better clinical decision making.
This document summarizes a student's data analysis project that aims to predict heart attack risk factors. The student analyzes a dataset containing information on 303 patients, including demographic data, medical information, and whether they had a heart attack. The objectives are to investigate relationships between attributes and heart disease risk, identify which chest pain types are most associated with heart attacks, and examine the impact of exercise. Preliminary results include checking the data structure, distributions, outliers, and visualizing relationships through histograms, boxplots, and scatter plots. Future work involves further investigating variable relationships, applying advanced statistical techniques, and collecting additional data to better understand and prevent heart disease.
Risk factors of Acute Coronary Syndrome at Prince Ali Bin Alhussein hospitalMinistry of Health
Objective:The aim of this survey to identify the relationship between ACS and its risk factors and the association between the risks factors themselves. Method: A retrospective study depends on the registered files of the admitted patients to Prince Ali Bin Alhussein hospital with ACS since April 2013 till October of 2013 included 174 patients. Result:The above mentioned data and results show a strong relationship between ACS and the mentioned risk factors. Conclusion: There is a strong relationship between risks factors themselves as D.M and hypertension, and between hypertension with the sex and smoking.There's an association between D.M and the patient's gender
Assessment of the Prevalence of Some Cardiovascular Risk Factors among the O...Scientific Review SR
This document summarizes a study that assessed cardiovascular risk factors among two ethnic groups in Rivers State, Nigeria.
The study measured blood pressure, body mass index, fasting blood sugar levels, smoking status, and other factors in 200 subjects from the Ogoni and Ikwerre ethnic groups. Mean values for factors like age, blood pressure, and BMI were calculated and compared between males and females within each ethnic group. Several cardiovascular risk factors like hypertension, diabetes, smoking, and obesity were found to be prevalent. The highest BMI values indicating obesity were found in male smokers, diabetics, and hypertensives, showing their higher risk for cardiovascular disease.
This study examined 273 patients admitted with acute coronary syndrome (ACS) to Sohag University Hospital in Egypt. The researchers found:
1) The overall prevalence of low high-density lipoprotein cholesterol (HDL-C) was 73.3% among the patients.
2) Patients with low HDL-C had higher rates of in-hospital mortality (12% vs 11%) and congestive heart failure (18% vs 5.5%) compared to those with satisfactory HDL-C.
3) Low HDL-C was more common in women and was associated with insignificantly higher in-hospital mortality and congestive heart failure in women, but not in men.
Diagnosis of Early Risks, Management of Risks, and Reduction of Vascular Dise...asclepiuspdfs
In a recent issue of the Journal of Circulation, American Heart Association has published a scientific statement, related to the excess heart disease and acute vascular events in South Asians living in the USA. The same group of experts, also have published a complementary article in Circulation titled, “call to action: Cardiovascular disease (CVD) in Asian Americans.”I being a South Asian immigrant living in the USA, have always wondered as to why we do not have the same benefits as the other resident Americans in terms of the advantages of living in a highly advanced country? According to a study done in 2013, cardiovascular mortality has declined and diabetes mortality has increased in high-income countries. The study done in 26 industrialized nations, estimated the potential role of trends in population, for body mass index, systolic blood pressure, serum total cholesterol, and smoking, the modifiable risk factors identified as the promoters of CVD, and acute vascular events, by the Framingham Heart Study (FHS) group.
Coronary artery disease (CAD) is the most common form of heart disease and is caused by a buildup of plaque in the arteries that supply the heart. Regular exercise provides significant benefits for reducing CAD risk by increasing HDL cholesterol and decreasing LDL cholesterol. Both aerobic and resistance training are shown to improve lipid profiles and cardiac risk factors. Aerobic exercise increases HDL levels the most, while resistance training also lowers LDL and triglycerides. Guidelines recommend at least 30 minutes per day of moderate exercise on most days of the week for cardiac patients. Higher intensity exercise produces the greatest benefits for lipid profiles. Overall, exercise training improves cardiac health and management of CAD by enhancing cardiovascular function and modifying risk factors.
This document outlines a study on jointly modeling longitudinal measurements of blood pressure and survival time to cardiovascular disease among hypertensive patients in Ethiopia. The study aimed to identify factors affecting changes in blood pressure and survival time. 178 patients were included and followed from 2017-2019. Key findings included that patients with diabetes or a family history of hypertension or cardiovascular disease had higher rates of developing cardiovascular disease.
Background and Aim: Many studies have found association between Red Cell Distribution Width (RDW) values and hypertension, dipping pattern, and end-organ damage. RDW values are affected by blood vitamin B12, iron, and folic acid levels, parameters that were not assessed in the previous studies. The aim of our study was to evaluate the relation between RDW and hypertension, dipper pattern, and end-organ damage independently from vitamin B12, folic acid, and ferritin levels in newly diagnosed hypertensive patients.
Hypertension is a major public health problem and important area of research due to its high prevalence and being major risk factor for cardiovascular diseases and other complications. Objectives 1. To assess the prevalence of hypertension and its associated factors and 2. to estimate awareness, treatment, and adequacy of control of hypertension among study subjects. According to the Joint National Committee 7 JNC7 , normal blood pressure is a systolic BP 120 mmHg and diastolic BP 80 mm Hg. Hypertension is defined as systolic BP level of =140 mmHg and or diastolic BP level = 90 mmHg. A number of factors increase BP, including 1 obesity, 2 insulin resistance, 3 high alcohol intake, 4 high salt intake in salt sensitive patients , 5 aging and perhaps 6 sedentary lifestyle, 7 stress, 8 low potassium intake, and 9 low calcium intake. Shweta Pawar | Sujit Kakde | Ashok Bhosale "A Review: Hypertension" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-5 | Issue-4 , June 2021, URL: https://www.ijtsrd.compapers/ijtsrd42416.pdf Paper URL: https://www.ijtsrd.commedicine/other/42416/a-review-hypertension/shweta-pawar
HEART DISEASE PREDICTION USING MACHINE LEARNING AND DEEP LEARNINGIJDKP
Heart disease is most common disease reported currently in the United States among both the genders and
according to official statistics about fifty percent of the American population is suffering from some form of
cardiovascular disease. This paper performs chi square tests and linear regression analysis to predict
heart disease based on the symptoms like chest pain and dizziness. This paper will help healthcare sectors
to provide better assistance for patients suffering from heart disease by predicting it in beginning stage of
disease. Chi square test is conducted to identify whether there is a relation between chest pain and heart
disease cases in the United States by analyzing heart disease dataset from IEEE Data Port. The test results
and analysis show that males in the United States are most likely to develop heart disease with the
symptoms like chest pain, dizziness, shortness of breath, fatigue, and nausea. This test also shows that
there is a week corelation of 0.5 is identified which shows people with all ages including teens can face
heart diseases and its prevalence increase with age. Also, the tests indicate that 90 percent of the
participant who are facing severe chest pain is suffering from heart disease where majority of the
successful heart disease identified is in males and only 10 percent participants are identified as healthy.
The evaluated p-values are much greater than the statistical threshold of 0.05 which concludes factors like
sex, Exercise angina, Cholesterol, old peak, ST_Slope, obesity, and blood sugar play significant role in
onset of cardiovascular disease. We have tested the dataset with prediction model built on logistic
regression and observed an accuracy of 85.12 percent.
Background; Myocardial Infarction (MI) is a term which is used for defining the necrosis in the heart muscle due to the lack of the oxygen need of myocardium which cannot be supplied by the coronaries. Aim: This study was carried out to determine the effects of some lifestyle and anthropometric parameters on some cardiac enzymes. Methods: A total of 146 students of sex, age bracket, (16 - 30) were recruited for this study. Enzymatic methods were used in the determination of AST, ALT, CKMB activities. Anthropometric measurements of the participants were taken. The result showed that there was significant increase in systolic blood pressure (SBP), weight and height (p<0.05), but there was no significant increase in their diastolic blood pressure (DBP) and body mass index (BMI) (p>0.05) in the serum ALT, AST, and CKMB activities. However, there was significant difference in ALT and AST activities (P<0.05) but there was no significant difference in serum CKMB activity (P>0.05). Statistically the percentage of the participants that had their serum ALT activity above the reference range were 16.6%, those within the reference range were 83.4%,. In serum AST activity, the percentage above the reference range were 19.9%, those within the reference range were 80.1%. Meanwhile, in serum CK-MB activity, those above the reference range were 25.2% while those within the reference range were 74.8%. Conclusion: This could be probably indicate that the leakage of AST and ALT activities may be of hepatic origin. . The non-significant increase in CKMB which is a specific marker of myocardial injury, could suggest that the subjects were not at risk of developing of myocardial infarction as regards their age.
Mangement of chronic heart failure 93432-rephrasedIrfan iftekhar
Cardiac resynchronization therapy significantly reduces morbidity and mortality in patients with heart failure. A randomized controlled trial found that cardiac resynchronization reduced the primary endpoint of death from any cause by 36% compared to medical therapy alone. Mortality was lower in the cardiac resynchronization group, demonstrating improved outcomes. While cardiac resynchronization is an effective treatment, its cost-effectiveness remains uncertain due to the therapy's expense. Further research is still needed to determine its overall value.
Similar to HPPS : Heart Problem Prediction System using Machine Learning (20)
TFFN: Two Hidden Layer Feed Forward Network using the randomness of Extreme L...Nimai Chand Das Adhikari
Generating forecast is undoubtedly one of the most
important sector in any industry. It not only helps the demand
planner of the company which is focusing primarily on the future
forecasting of the sales but also the inventory management and
its handling cost. Down the line of the companys supply chain,
a wrong forecast can impact in an alternate way of incurring
heavy cost. Apart from this a correct forecasting leading to a
good accuracy says how the profit and loss of the company
depends upon. This heavily depends upon the predicting machine
that the company is using for the forecasting. Demand planners
look for a consistently accurate results over a period of time.
Where the accuracy of the forecast is not only good but also
the algorithm is stable in a long period of time. This we have
illustrated through the analysis and the model takes care of the
stability of a particular algorithm selected for a SKU. In this
paper we want to highlight a new ensemble technique using the
averaging method which not only gives priority to the algorithm
which consistently maintains a good accuracy but also decreases
the deviation from the actual sales. Based upon the history it
tries to give the importance to the one which predicts better and
penalizes other algorithms which deviate from the actual sales.
Blockchain technology involves distributing a central ledger of transactions among various nodes and miners. Transactions are first stored and then made visible through the ledger. This central ledger is then distributed among miners, who vote to validate new transactions and add them to the distributed ledger. Winners who validate transactions are rewarded. This process makes the ledger visible to all nodes, maintains security through digital signatures, and ensures invalid transactions are cancelled.
A survey on different Facial recognition algorithms as well implemented on various standard dataset. Tested different feature extraction and dimensionality reduction methods to arrive at a better accuracy.
TFFN: Two Hidden Layer Feed Forward Network using the randomness of Extreme L...Nimai Chand Das Adhikari
The learning speed of the feed forward neural
network takes a lot of time to be trained which is a major
drawback in their applications since the past decades. The
key reasons behind may be due to the slow gradient-based
learning algorithms which are extensively used to train the
neural networks or due to the parameters in the networks
which are tuned iteratively using some learning algorithms.
Thus, in order to eradicate the above pitfalls, a new learning
algorithm was proposed known as Extreme Learning Machines
(ELM). This algorithm tries to compute Hidden-layer-output
matrix that is made of randomly assigned input layer and
hidden layer weights and randomly assigned biases. Unlike the
other feedforward networks, ELM has the access of the whole
training dataset before going into the computation part. Here,
we have devised a new two-layer-feedforward network (TFFN)
for ELM in a new manner with randomly assigning the weights
and biases in both the hidden layers, which then calculates the
output-hidden layer weights using the Moore-Penrose generalized
inverse. TFFN doesn’t restricts the algorithm to fix the number
of hidden neurons that the algorithm should have. Rather it
searches the space which gives an optimized result in the neurons
combination in both the hidden layers. This algorithm provides a
good generalization capability than the parent Extreme Learning
Machines at an extremely fast learning speed. Here, we have
experimented the algorithm on various types of datasets and
various popular algorithm to find the performances and report
a comparison.
This document discusses an intelligent approach to demand forecasting using an ensemble model. It first pre-processes input data to clean errors and impute missing values. It then runs two parallel forecasting engines using machine learning and time series algorithms. The final forecast combines the outputs of these models and applies further seasonality and trend corrections. This ensemble approach generates more stable and accurate forecasts compared to conventional techniques.
The document discusses the development of a credit default prediction model called Def_Catch using machine learning algorithms. Def_Catch was trained on a dataset of 100,000 examples with 11 attributes related to borrowers' credit histories and demographics. Random forest achieved the highest accuracy of 93.14% at predicting which borrowers would default in the next 2 years, outperforming logistic regression, naive bayes, decision trees, and multi-layer perceptron models. The top predictors of default included credit utilization, age, number of late payments, debt ratio, and income. Def_Catch provides insights into borrower risk that are difficult to discern from raw data alone.
The Image Panorama is a technique of stitching more images to create a more broader view which our normal eye does in a wider angle rather than that of the view which is restricted by the camera
The leaning speed of the feed forward neural networks is very much slower than
as expected and this is the major drawback/pitfall in their applications since the
past decades. The key reasons behind may
1. Due to the slow gradient-based learning algorithms which are extensively used
to train the neural networks.
2. All the parameters in the networks are tuned iteratively using some learning
algorithms.
Thus, in order to eradicate the above pitfalls, a new learning algorithm was pro
posed known as Extreme Learning Machine (ELMs). This algorithm is for the
single hiddenlayer feed forward networks(SLFNs) which randomly initializes the
input hidden node weights and biases of the hidden nodes after that calculates
the output weights. This algorithm provide the good generalization performance
at an extremely fast learning speed. In this thesis we have experiemented the
algorithm on various types of datasets and various popular algorithm to find the
performances and report a comparison.
We have devised a two-layer-feedforward network for ELM in a new manner with
randomly assigning the weights and biases in both the hidden layer. We have
also studied the ELM autoencoders and thoroughly experimented it with various
datasets and deep networks.
We have implemented ELM with recommender systems to build a new music app
to recommend the user some songs based on the history of the use.
Demand Forecasting, undeniably, is the single most important component of any organizations Supply Chain. It determines the estimated demand for the future and sets the level of preparedness that is required on the supply side to match the demand. It goes without saying that if an organization doesnt get its forecasting accurate to a reasonable level, the whole supply chain gets affected. Understandably, Over/Under forecasting has deteriorating impact on any organizations Supply Chain and thereby on P and L. Having ascertained the importance of Demand Forecasting, it is only fair to discuss about the forecasting techniqueswhichareusedtopredictthefuturevaluesofdemand. The input that goes in and the modeling engine which it goes through are equally important in generating the correct forecasts and determining the Forecast Accuracy. Here, we present a very unique model that not only pre-processes the input data, but also ensembles the output of two parallel advanced forecasting engines which uses state-of-the-art Machine Learning algorithms and Time-Series algorithms to generate future forecasts. Our technique uses data-driven statistical techniques to clean the data of any potential errors or outliers and impute missing values if any. Once the forecast is generated, it is post processed with Seasonality and Trend corrections, if required.Since the final forecast is the result of statistically pre-validated ensemble of multiple models, the forecasts are stable and accuracy variation is very minimal across periods and forecast horizons. Hence it is better at estimating the future demand than the conventional techniques.
India Home Healthcare Market: Driving Forces and Disruptive Trends [2029]Kumar Satyam
According to the TechSci Research report titled "India Home Healthcare Market - By Region, Competition, Forecast and Opportunities, 2029," the India home healthcare market is anticipated to grow at an impressive rate during the forecast period. This growth can be attributed to several factors, including the rising demand for managing health issues such as chronic diseases, post-operative care, elderly care, palliative care, and mental health. The growing preference for personalized healthcare among people is also a significant driver. Additionally, rapid advancements in science and technology, increasing healthcare costs, changes in food laws affecting label and product claims, a burgeoning aging population, and a rising interest in attaining wellness through diet are expected to escalate the growth of the India home healthcare market in the coming years.
Browse over XX market data Figures spread through 70 Pages and an in-depth TOC on "India Home Healthcare Market”
https://www.techsciresearch.com/report/india-home-healthcare-market/15508.html
nursing management of patient with Empyema pptblessyjannu21
prepared by Prof. BLESSY THOMAS, SPN
Empyema is a disease of respiratory system It is defines as the accumulation of thick, purulent fluid within the pleural space, often with fibrin development.
Empyema is also called pyothorax or purulent pleuritis.
It’s a condition in which pus gathers in the area between the lungs and the inner surface of the chest wall. This area is known as the pleural space.
Pus is a fluid that’s filled with immune cells, dead cells, and bacteria.
Pus in the pleural space can’t be coughed out. Instead, it needs to be drained by a needle or surgery.
Empyema usually develops after pneumonia, which is an infection of the lung tissue. it is mainly caused due in infectious micro-organisms. It can be treated with medications and other measures.
Ensure the highest quality care for your patients with Cardiac Registry Support's cancer registry services. We support accreditation efforts and quality improvement initiatives, allowing you to benchmark performance and demonstrate adherence to best practices. Confidence starts with data. Partner with Cardiac Registry Support. For more details visit https://cardiacregistrysupport.com/cancer-registry-services/
NURSING MANAGEMENT OF PATIENT WITH EMPHYSEMA .PPTblessyjannu21
Prepared by Prof. BLESSY THOMAS, VICE PRINCIPAL, FNCON, SPN.
Emphysema is a disease condition of respiratory system.
Emphysema is an abnormal permanent enlargement of the air spaces distal to terminal bronchioles, accompanied by destruction of their walls and without obvious fibrosis.
Emphysema of lung is defined as hyper inflation of the lung ais spaces due to obstruction of non respiratory bronchioles as due to loss of elasticity of alveoli.
It is a type of chronic obstructive
pulmonary disease.
It is a progressive disease of lungs.
CHAPTER 1 SEMESTER V COMMUNICATION TECHNIQUES FOR CHILDREN.pdfSachin Sharma
Here are some key objectives of communication with children:
Build Trust and Security:
Establish a safe and supportive environment where children feel comfortable expressing themselves.
Encourage Expression:
Enable children to articulate their thoughts, feelings, and experiences.
Promote Emotional Understanding:
Help children identify and understand their own emotions and the emotions of others.
Enhance Listening Skills:
Develop children’s ability to listen attentively and respond appropriately.
Foster Positive Relationships:
Strengthen the bond between children and caregivers, peers, and other adults.
Support Learning and Development:
Aid cognitive and language development through engaging and meaningful conversations.
Teach Social Skills:
Encourage polite, respectful, and empathetic interactions with others.
Resolve Conflicts:
Provide tools and guidance for children to handle disagreements constructively.
Encourage Independence:
Support children in making decisions and solving problems on their own.
Provide Reassurance and Comfort:
Offer comfort and understanding during times of distress or uncertainty.
Reinforce Positive Behavior:
Acknowledge and encourage positive actions and behaviors.
Guide and Educate:
Offer clear instructions and explanations to help children understand expectations and learn new concepts.
By focusing on these objectives, communication with children can be both effective and nurturing, supporting their overall growth and well-being.
This particular slides consist of- what is hypotension,what are it's causes and it's effect on body, risk factors, symptoms,complications, diagnosis and role of physiotherapy in it.
This slide is very helpful for physiotherapy students and also for other medical and healthcare students.
Here is the summary of hypotension:
Hypotension, or low blood pressure, is when the pressure of blood circulating in the body is lower than normal or expected. It's only a problem if it negatively impacts the body and causes symptoms. Normal blood pressure is usually between 90/60 mmHg and 120/80 mmHg, but pressures below 90/60 are generally considered hypotensive.
Emotional and Behavioural Problems in Children - Counselling and Family Thera...PsychoTech Services
A proprietary approach developed by bringing together the best of learning theories from Psychology, design principles from the world of visualization, and pedagogical methods from over a decade of training experience, that enables you to: Learn better, faster!
Digital Health in India_Health Informatics Trained Manpower _DrDevTaneja_15.0...DrDevTaneja1
Digital India will need a big trained army of Health Informatics educated & trained manpower in India.
Presently, generalist IT manpower does most of the work in the healthcare industry in India. Academic Health Informatics education is not readily available at school & health university level or IT education institutions in India.
We look into the evolution of health informatics and its applications in the healthcare industry.
HIMMS TIGER resources are available to assist Health Informatics education.
Indian Health universities, IT Education institutions, and the healthcare industry must proactively collaborate to start health informatics courses on a big scale. An advocacy push from various stakeholders is also needed for this goal.
Health informatics has huge employment potential and provides a big business opportunity for the healthcare industry. A big pool of trained health informatics manpower can lead to product & service innovations on a global scale in India.
Hypertension and it's role of physiotherapy in it.Vishal kr Thakur
This particular slides consist of- what is hypertension,what are it's causes and it's effect on body, risk factors, symptoms,complications, diagnosis and role of physiotherapy in it.
This slide is very helpful for physiotherapy students and also for other medical and healthcare students.
Here is summary of hypertension -
Hypertension, also known as high blood pressure, is a serious medical condition that occurs when blood pressure in the body's arteries is consistently too high. Blood pressure is the force of blood pushing against the walls of blood vessels as the heart pumps it. Hypertension can increase the risk of heart disease, brain disease, kidney disease, and premature death.
R3 Stem Cell Therapy: A New Hope for Women with Ovarian FailureR3 Stem Cell
Discover the groundbreaking advancements in stem cell therapy by R3 Stem Cell, offering new hope for women with ovarian failure. This innovative treatment aims to restore ovarian function, improve fertility, and enhance overall well-being, revolutionizing reproductive health for women worldwide.
The Importance of Black Women Understanding the Chemicals in Their Personal C...bkling
Certain chemicals, such as phthalates and parabens, can disrupt the body's hormones and have significant effects on health. According to data, hormone-related health issues such as uterine fibroids, infertility, early puberty and more aggressive forms of breast and endometrial cancers disproportionately affect Black women. Our guest speaker, Jasmine A. McDonald, PhD, an Assistant Professor in the Department of Epidemiology at Columbia University in New York City, discusses the scientific reasons why Black women should pay attention to specific chemicals in their personal care products, like hair care, and ways to minimize their exposure.
Joker Wigs has been a one-stop-shop for hair products for over 26 years. We provide high-quality hair wigs, hair extensions, hair toppers, hair patch, and more for both men and women.
Research, Monitoring and Evaluation, in Public Healthaghedogodday
This is a presentation on the overview of the role of monitoring and evaluation in public health. It describes the various components and how a robust M&E system can possitively impact the results or effectiveness of a public health intervention.
2024 Media Preferences of Older Adults: Consumer Survey and Marketing Implica...Media Logic
When it comes to creating marketing strategies that target older adults, it is crucial to have insight into their media habits and preferences. Understanding how older adults consume and use media is key to creating acquisition and retention strategies. We recently conducted our seventh annual survey to gain insight into the media preferences of older adults in 2024. Here are the survey responses and marketing implications that stood out to us.
The Ultimate Guide in Setting Up Market Research System in Health-TechGokul Rangarajan
How to effectively start market research in the health tech industry by defining objectives, crafting problem statements, selecting methods, identifying data collection sources, and setting clear timelines. This guide covers all the preliminary steps needed to lay a strong foundation for your research.
"Market Research it too text-booky, I am in the market for a decade, I am living research book" this is what the founder I met on the event claimed, few of my colleagues rolled their eyes. Its true that one cannot over look the real life experience, but one cannot out beat structured gold mine of market research.
Many 0 to 1 startup founders often overlook market research, but this critical step can make or break a venture, especially in health tech.
But Why do they skip it?
Limited resources—time, money, and manpower—are common culprits.
"In fact, a survey by CB Insights found that 42% of startups fail due to no market need, which is like building a spaceship to Mars only to realise you forgot the fuel."
Sudharsan Srinivasan
Operational Partner Pitchworks VC Studio
Overconfidence in their product’s success leads founders to assume it will naturally find its market, especially in health tech where patient needs, entire system issues and regulatory requirements are as complex as trying to perform brain surgery with a butter knife. Additionally, the pressure to launch quickly and the belief in their own intuition further contribute to this oversight. Yet, thorough market research in health tech could be the key to transforming a startup's vision into a life-saving reality, instead of a medical mishap waiting to happen.
Example of Market Research working
Innovaccer, founded by Abhinav Shashank in 2014, focuses on improving healthcare delivery through data-driven insights and interoperability solutions. Before launching their platform, Innovaccer conducted extensive market research to understand the challenges faced by healthcare organizations and the potential for innovation in healthcare IT.
Identifying Pain Points: Innovaccer surveyed healthcare providers to understand their difficulties with data integration, care coordination, and patient engagement. They found widespread frustration with siloed systems and inefficient workflows.
Competitive Analysis: Analyzed competitors offering similar solutions in healthcare analytics and interoperability. Identified gaps in comprehensive data aggregation, real-time analytics, and actionable insights.
Regulatory Compliance: Ensured their platform complied with HIPAA and other healthcare data privacy regulations. This compliance was crucial to gaining trust from healthcare providers wary of data security issues.
Customer Validation: Conducted pilot programs with several healthcare organizations to validate the platform's effectiveness in improving care outcomes and operational efficiency. Gathered feedback to refine features and user interface.
At Malayali Kerala Spa Ajman, Full Service includes individualized care for every client. We specifically design each massage session for the individual needs of the client. Our therapists are always willing to adjust the treatments based on the client's instruction and feedback. This guarantees that every client receives the treatment they expect.
By offering a variety of massage services, our Ajman Spa Massage Center can tackle physical, mental, and emotional illnesses. In addition, efficient identification of specific health conditions and designing treatment plans accordingly can significantly enhance the quality of massaging.
At Malayali Kerala Spa Ajman, we firmly believe that everyone should have the option to experience top-quality massage services regularly. To achieve that goal we offer cheap massage services in Ajman.
If you are interested in experiencing transformative massage treatment at Malayali Kerala Spa Ajman, you can use our Ajman Massage Center WhatsApp Number to schedule your next massage session.
Contact @ +971 529818279
Visit @ https://malayalikeralaspaajman.com/
The facial nerve, also known as cranial nerve VII, is one of the 12 cranial nerves originating from the brain. It's a mixed nerve, meaning it contains both sensory and motor fibres, and it plays a crucial role in controlling various facial muscles, as well as conveying sensory information from the taste buds on the anterior two-thirds of the tongue.
HPPS : Heart Problem Prediction System using Machine Learning
1. HPPS : Heart Problem Prediction System using Machine
Learning
Nimai Chand Das Adhikari, Rajat Garg, Arpana Alka
November 28, 2017
Abstract
Heart is the most important organ of a human body. It circulates oxygen and other vital
nutrients through blood to different parts of the body and helps in the metabolic activities.
Apart from this it also helps in removal of the metabolic wastes. Thus, even a minor problem
in heart can affect the whole organism. Researchers are diverting a lot of data analysis work
for assisting the doctors to predict the heart problem. So, an analysis of the data related to
different health problems and its functioning can help in predicting with a particular proba-
bility of the wellness of this organ. In this paper we have analyzed the different prescribed
data of 1094 patients from different parts of India. Using this data we have built a model
which gets trained using this data and tries to predict whether a new out-of-sample data has
a probability of having any heart attack or not. This model can help in decision making along
with the doctor to treat the patient well and creating a transparency between the doctor and
the patient. In the validation set of the data, its not only the accuracy that the model has,
rather the True-Positive Rate and False-Negative Rate along with the AUC-ROC helps in
building/fixing the algorithm inside the model.
1 Introduction
The mortality rate in India and abroad is mainly due to heart attack. This calls for a vital check
of the organ periodically for the wellness of all human beings. From the below figure of heart,
Figure 1: Picture of Heart
the major heart problems occurs when there is a blockage in the major arteries that carries the
1
2. oxygenated blood [1]. The health care industry has huge amount of data that can be utilized to
find the different patterns related to the heart problems with a probabilistic score.
Here, we have collected the data from a survey of around 1000 patients from different parts of
India and found out the correlation among the risk factors that we have gathered. The risk factors
that has been taken input in this survey are Family History, Smoking, Hypertension, Dys-
lipidemia, Fasting Glucose, Obesity, Life Style, CABG and High Serum in blood. Apart
from the mentioned risk-factors, we have the demographic details as well. The most important
thing that each diagnosis should prevent is the exposure to a normal human body to the CT Scan
radioactive rays [2][3]. The CCTA (Coronary computed tomography angiography) is an imaging
test for the heart to find the plaque build up in its blood vessels. Plaque is majorly built up by the
circulating substances in the blood like fat, cholesterol and calcium, whose deposit in the inner side
of blood vessel can effect the normal blood flow and can result in excessive pressure on the heart
pump. This has an increased prone to the cancer for the human body exposed to high radiation
[4]. So, the main intension of this paper is to help in the decision making of a doctor. Apart from
this, the method should help in diminishing the False Negative Rate of the prediction. It is the
number of the actual positives which is negative through the prediction to the total negatives. In
statistical hypothesis testing, this ratio is represented by the letter β.
In the following sections we will discuss the different terminologies and factors related to this
project and the methodology of HPPS, which is going to be a partner of the doctor in the de-
cision making of whether the patient is going to be suffering from any heart attack or not. In
the next section we will discuss about the factors that we have taken for the survey and their
correlations with the predictor output, followed by the proposed model and scenarios and lastly
with the results for the selection of the algorithms.
2 Dataset Description and Analysis
The survey contains the data of 1094 patients from 5 different cities of India Delhi, Chennai,
Bangalore, Kolkata and Hyderabad. The attributes that define as the features for the model
are the different demographic details of the patients like Age and Sex with the different Risk
Factors which we have defined previously. Here the predictor variable is Heart Problem or
Not. Thus, there are many terminologies that define this. Some of them are:
Figure 2: Heart Blockage
1. Heart disease due to atherosclerosis [5]: In the walls of the arteries become stiff or hard due
to the fatty deposits which in medical term known as plaques.
2. Cerebrovascular disease [6]: This is mainly due to the blockage in the blood flow through the
blood vessels to the brain.
3. Ischemic heart disease [7]: This is mainly due to the deposit of the cholesterol on the walls
of the arteries. Figure 3 shows how the deposit looks like in this similar case.
2
3. 4. Hypertensive heart disease [8]:This happens mostly due to high blood pressure.
The above are some of the types of heart problems that we have discussed. There are many apart
from the ones described before as the heart is one of the vital organ that helps in the transporta-
tion of the oxygenated blood and nutrients and removal of wastes from the body. In the predicted
value, we have given the value as 1 for the heart related problems and 0 as no problem in the heart.
Below is the analysis of the different risk-factors for the heart problem detection.
2.1 Risk Factor 1: Family History
This is one of the important risk-factor as it depends on the hereditary behavior of the heart [9].
Here, we have the values of 1080 patients and the rest are NA or No values. For those missing
values we have assigned the value as 0 or the maximum. Which we will discuss in the results
section. In the analysis we found that, when Family History is 1, then 118 out of 215 patient
suffer from heart problem i.e 55%.
2.2 Risk Factor 2: Smoking
It leads to the developing of the cardiovascular diseases, which includes heart attack and stroke.
It leads to damaging the lining of the arteries which ultimately leads to atheroma. Below is the
analysis of the data for the smoking that we have established: The above curves shows that if the
patient has smoking in the characteristics, then 67.22%, he/she will suffer from the heart related
problems [10][11].
2.3 Risk Factor 3: Hypertension
This leads to the heart diseases that occur due to high blood pressure over a long period of time
[12][13]. Due to blood pressure, the heart has to do pump more against this pressure, adding extra
pressure to heart resulting int the thickening of the heart muscle.
In the analysis done and represented in the figure 3, we can find that 54% chances is there for a
hypertensive patient to suffer from any heart related problem.
2.4 Risk Factor 4: Dyslipedimia
This is a high level of lipids like cholesterol, triglycerides carried through the lipo-proteins present
in the blood. The risk of Atherosclerosis increases due to the increase in the above mentioned
lipids in the blood leading to excessive pressure on the blood flow [14].
3
4. Figure 3: RF3: Hypertension Analysis
In this analysis, we found that out of 1090 patients having the details of having suffering from
dyslipedimia been captured by the doctor, 548 suffer from the same. Out of 548, 296 patients
suffered from heart related problems, which is a little over 54%.
2.5 Risk Factor 5: Fasting Glucose
FG greater than a certain value leads to type 2 diabetes and it is proved that type 2 diabetes in-
crease marks the risk of Cardiovascular Disease(CVD) and ischemic heart disease(IHD) [15][16][17].
According to our analysis, we found that 1066 data of the patients had this risk factor captured.
Out of this, 319 had Fasting Glucose as marked 1. 62% of those having 1 in this risk-factor
suffered from the heart attack, which proved the analysis with that of the proven results.
2.6 Risk Factor 6: Obesity
The role of diet in the prevention of CVD, is very crucial as it is a very key risk factor for CVD.Thus
obesity leads to the development of hypertension, diabetes, musculoskeletal disorder, thus putting
in a high risk of CVD [18]. According to the analysis, we found that 194 patients having Obesity
suffered from heart related problems which accounts to 56%.
4
5. 2.7 Risk Factor 7: Life Style
It is one of the most important factor in controlling the heart related problems. Some of the major
lifestyle effects that can control in the prevention and keeping the heart in a good shape are Stop
Smoking, Choosing Good Nutrition, High Blood Cholesterol , Lowering High Blood Pressure, Being
Physically Active, Aiming for a healthy weight, Managing Diabetes, Reducing Stress and drinking
alcohol etc. [19][20].
In the analysis above, we find that 306 cases out of 629 marked as 1, suffered from heart related
disease. Thus, this is around 49% of the cases. But if we see the two bar plots above we can find
that the conversion of the heart problem is in a greater percentage in case of the bad life style.
Thus marking this risk factor to be one of the most important factor in determining the CVD.
2.8 Risk Factor 8: CABG
Coronary Artery Bypass Grafting is a kind of surgery done for those patients who have suffered
from severe CHD. This is mostly whether a patient suffered from the serious heart attack and has
Figure 4: Bypass grafts in Heart
a graft anywhere in the heart. Thus, this will be having a very high correlation for the heart being
regularly checked up.
2.9 Risk Factor 9: High Serum
A Serum test is a measure of the amount of iron which is present in the left over liquid after the
red blood cells and the clotting factors being removed from the blood. Hence having too much
iron content in the blood can cause serious health problem. This has a direct correlation with the
heart related problems [21].
5
6. In this analysis, we found that 452 cases having suffered from heart problems out of 996 having
High Serum.
Apart from the above Risk Factors we have different other attributes like Age, Sex, Location
and Vascular Pattern. The analysis of the age is shown below in bin category: We have divided
the age continuous values into three groups ’age < 20years’, ’age between 20 years and 50 years’
and ’age > than 50 years’.We can find from the analysis that most of the cases the age group more
than 50 years have suffered from heart related problems which is not the case in case of the middle
age group. Thus, the heart problem is skewed towards the more than 50 age group.
In the below graph we are showing the analysis for the heart problem with that of the gender or
sex category of a patient. Males are more prone to heart related problems than female as can be
seen from the analysis.
3 Proposed System
In the proposed model, we want to give a brief idea about how our system looks like and behaves.
• Dataset: There is a common database for the patient from where the data will be taken by
the model to finalize the algorithm
6
7. Figure 5: Flow chart of the System
• Algorithms: We have used a wide range of algorithms and in the validation set, the algo-
rithm which gives a better Selection Value i.e
SelectionV alue = 0.6 ∗ (1 − FNR) + 0.4 ∗ Accuracy
Here, we have assigned 0.6 to the term having the FNR, as we wanted to diminish the False
Negative Rate more than the Accuracy. Using the above metric, the algorithm which gives
the maximum score in the validation set, is selected.
• Recommender System: When a new patient details is input, using the risk factor combi-
nation, all those similar patient details is made a cluster using the cosine-similarity.
scoresimilarity =
< patientnew.patientold >
|patientnew|2
2|patientold|2
2
• Recommender Score: The voted output of the recommended patient details will be shown
in the the dash board [figure 6]
Using the above informations, the doctor will have multiple scenarios and also help him in aiding
to his decision. This will also help to create a transparency among the doctor and the patient. So,
here we want to showcase a system which can create a confidence in the patients mind for he/she
is going to have any heart problem in the future or not, so as to take better care.
Figure 6: Dash Board of HPPS
7
8. 4 Results
In this section we want to present the comparison of the results for different algorithms that we
used in the model. Here, we have analyzed the details of 1094 patients having label as 1 or 0. Here
1 is represented for the patients suffering from any kinds of heart disease and vice versa. Also, for
small plaques, the label is given as 0.
For training and validation to check how the algorithm is performing, we have used the holdout
technique with 70:30 ratio. The metric Accuracy is the ration of the sum of TN and TP to the
Figure 7: Confusion Matrix
sum of TN, TP, FN and FP. Apart from the accuracy, we believe that we have to diminish the
False Negative Rate which is the ratio between the FN and sum of TN and FN. Using this two
metric we define our own metric which we use to select the best algorithm:
SelectionV alue = 0.6 ∗ (1 − FNR) + 0.4 ∗ Accuracy
We want to penalize the model for predicting wrong for a patient having the chance for heart
attack or heart problem but predictive No for that case. Below is the results for the verification of
different algorithms.
Figure 8: Results Analysis: type 1
In the figure 8, the results for the various algorithm is analyzed with the 0 imputation of the
missing values. In this if we check the accuracy alone, SVM with rbf kernel gives a better result
with 74.16 % accuracy followed by 72.34% with ensemble models like Random Forest, Bagging
8
9. and Logistic Regression l2 norm. Apart from the above accuracy measure, we want to minimize
the False Negative Rate i.e Actual is 1 but predicted is 0. The algorithm that best performed is
SVM-rbf with 29.118%.
Figure 9: Results Analysis: type 2
In the figure 9, we have imputed the missing values if present in the data, with the maximum
frequency present and we see increased values or accuracies for all the algorithms and SVM-rbf
performed better with 75.68% accuracy. But if we check the False-Negative Rate, Random Forest
performed better in this category. Even in the previous scenario, Random forest had this actual
number lesser but the rate was higher. When checked with the Selection Value, Random Forest
is the better algorithm with selection probability of 0.741 in comparison to 0.738 of SNM-rbf. This
results will pop up in the section 3 of the Dash board and will take a decision making in case of
the prediction.
Thus, with the view of the above results, we have used the type-2 case for the data processing and
as from the validation score from the Selection Value, Random Forest as the brain behind the
model. The algorithm can vary whenever a new patient details is fed into the system.
5 Conclusion
In the above procedure, we not only want to maximize the accuracy of the algorithm that we select
to help the doctor take a decision rather, we want to decrease and penalize the model for having a
bad prediction for the cases where the patient has a high probability for the heart attack but the
model predicting for no heart problem. We hence stated one new metric called Selection Value
which takes care of these scenarios and selects that algorithm which gives maximum S.V.
We do not want to bias the doctor with the results of the classification rather as discussed in the
proposed scenario section, we try to give the doctor with the better option with the history similar
data results. Using these data, teh doctor can have a transparency with the patient and the patient
wont feel cheated at the end. With the more amount of data being fed into the data base, the
system will be very intelligent.
9
10. 6 References
1. Predicting and Diagnosing of Heart Disease Using Machine Learning Algorithms, Sanjay Kumar
Sen
2. Peylan-Ramu, Nili, et al. "Abnormal CT scans of the brain in asymptomatic children with acute
lymphocytic leukemia after prophylactic treatment of the central nervous system with radiation
and intrathecal chemotherapy." New England Journal of Medicine 298.15 (1978): 815-818.
3. Decramer, Isabel, et al. "Effects of sublingual nitroglycerin on coronary lumen diameter and
number of visualized septal branches on 64-MDCT angiography." American Journal of Roentgenol-
ogy 190.1 (2008): 219-225.
4. Alkhorayef M, Babikir E, Alrushoud A, Al-Mohammed H, Sulieman A. Patient radiation bio-
logical risk in computed tomography angiography procedure. Saudi Journal of Biological Sciences.
2017;24(2):235-240. doi:10.1016/j.sjbs.2016.01.011.
5. Diaz, Marco N., et al. "Antioxidants and atherosclerotic heart disease." New England Journal
of Medicine 337.6 (1997): 408-416.
6. Rodgers, Anthony, et al. "Blood pressure and risk of stroke in patients with cerebrovascular
disease." Bmj 313.7050 (1996): 147.
7. Gertler, Menard M., et al. "Ischemic heart disease." Circulation46.1 (1972): 103-111.
8. Diamond, Joseph A., and Robert A. Phillips. "Hypertensive heart disease." Hypertension re-
search 28.3 (2005): 191-202.
9. Leander, Karin, et al. "Family history of coronary heart disease, a strong risk factor for my-
ocardial infarction interacting with other cardiovascular risk factors: results from the Stockholm
Heart Epidemiology Program (SHEEP)." Epidemiology 12.2 (2001): 215-221.
10. US Department of Health and Human Services. "The health consequences of smoking: a report
of the Surgeon General." (2004): 62.
11. Hjermann, I., et al. "Effect of diet and smoking intervention on the incidence of coronary
heart disease: report from the Oslo Study Group of a randomised trial in healthy men." The
Lancet318.8259 (1981): 1303-1310.
12. Collins, Rory, et al. "Blood pressure, stroke, and coronary heart disease: part 2, short-term
reductions in blood pressure: overview of randomised drug trials in their epidemiological context."
The Lancet 335.8693 (1990): 827-838.
13. Wolf, Philip A., Robert D. Abbott, and William B. Kannel. "Atrial fibrillation as an indepen-
dent risk factor for stroke: the Framingham Study." Stroke 22.8 (1991): 983-988.
14. Miller, M. "Dyslipidemia and cardiovascular risk: the importance of early prevention." QJM:
An International Journal of Medicine 102.9 (2009): 657-667.
15. Haffner, Steven M., et al. "Reduced coronary events in simvastatin-treated patients with
coronary heart disease and diabetes or impaired fasting glucose levels: subgroup analyses in the
Scandinavian Simvastatin Survival Study." Archives of Internal Medicine 159.22 (1999): 2661-2667.
16. Emerging Risk Factors Collaboration. "Diabetes mellitus, fasting blood glucose concentration,
and risk of vascular disease: a collaborative meta-analysis of 102 prospective studies." The Lancet
375.9733 (2010): 2215-2222.
17. Jee, Sun Ha, et al. "A coronary heart disease prediction model: the Korean Heart Study."
BMJ open 4.5 (2014): e005025.
18. Poirier, Paul, et al. "Obesity and cardiovascular disease: pathophysiology, evaluation, and
effect of weight loss." Circulation 113.6 (2006): 898-918.
19. Ornish, Dean, et al. "Can lifestyle changes reverse coronary heart disease?: The Lifestyle
Heart Trial." The Lancet336.8708 (1990): 129-133.
20. Villareal, Dennis T., et al. "Effect of lifestyle intervention on metabolic coronary heart disease
risk factors in obese older adults." The American journal of clinical nutrition 84.6 (2006): 1317-
1323.
21. Killip, Thomas, and Mary Ann Payne. "High serum transaminase activity in heart disease."
Circulation 21.5 (1960): 646-660.
10