1. SRI VENKATESWARA INSTITUTE OF TECHNOLOGY
(Affiliated to JNTUA, Anantapur, Approved by A.I.C.T.E. NEW DELHI)
NH-44, HAMPAPURAM, ANANTAPURAMU-515 722, www.svitatp.ac.in
BACHELOR OF TECHNOLOGY
In
COMPUTER SCIENCE AND ENGINEERING
During the academic year 2022-2023
Submitted By
A SAMIYA TABASSUM 199F1A0547
T.G.TASLEM AFSAN 199F1A0568
S.KASHIFA RUMIYA 199F1A0568
B.HARIKA 199F1A0568
Y.SRUTHI 199F1A0568
T.LATHASREE 199F1A0568
Under the esteemed guidance of
T.SIVA LAKSHMI MTECH
Assistant professor
2. A PROJECT REPORT ON
EFFECTIVE PREDICTION OF CARDIOVASCULAR
DISEASE USING MACHINE LEARNING
ALORITHMS
4. Abstract
Health diseases are increasing day by day due to life style and hereditary. In this aspect, heart disease
is the most important cause of demise in the human kind over past few years. The objective of this
paper is to predict the Heart Disease by applying Artificial Neural Network using swarm Intelligence
algorithm. Swarm intelligence (SI) is relatively new interdisciplinary field of research. The Swarm-
based algorithms have recently emerged as a family of nature-inspired, population-based algorithms
that are capable of producing low cost, fast, and robust solutions to several complex problems. This
paper proposes three most population Intelligence Algorithm and has good performance on
optimization. This paper aims to predict the heart disease using Genetic, BEE and BAT to classifying
patient as diseased and non diseased. We have evaluated our new classification approach via the
well-known data sets.
5. INTRODUCTION
According to the World Health Organization, every year 12 million deaths occur
worldwide due to Heart Disease. Heart disease is one of the biggest causes of morbidity.
Prediction of cardiovascular disease is regarded as one of the most important subjects in
the section of data analysis. The load of cardiovascular disease is rapidly increasing all over
the world from the past few years.
Many researches have been conducted in attempt to pinpoint the most influential factors
of heart disease as well as accurately predict the overall risk. Heart Disease is even
highlighted as a silent killer which leads to the death of the person without obvious
symptoms.
The early diagnosis of heart disease plays a vital role in making decisions on lifestyle
changes in high-risk patients and in turn reduces the complications.
6. In the current competitive world, we require an efficient technique to summarize,
analyze, present and maintain large datasets using data mining.
This requires the knowledge of all data mining techniques in order to choose the best
for desired datasets and these data mining techniques can answer the questions that
traditionally were too time consuming to resolve.
Research has shown that, data doubles every three years.
EXISTING SYSTEM
8. In this project student want to detect heart disease from dataset using Bio
Inspired 4 features optimizing algorithms such as Genetic Algorithm, Bat, Bee and
ACO.
Here ACO algorithm is design in python to solve Travelling Salesman Problem
to find shortest path and it cannot be implemented with heart disease dataset, so I
am implementing 3 algorithms called Genetic, Bat and Bee.
PROPOSED SYSTEM
9. ADVANTAGES
Finally, the performance was evaluated in terms of accuracy, sensitivity and
specificity and also compare to other well-known data sets.
It has been observed that these results are one of the best results compared with
the results obtained from related previous studies.
12. LITERATURE SURVEY
In literature a number of laptop mastering based totally analysis methods have been
proposed through researchers to analysis HD. This lookup find out about current some
current laptop getting to know based totally prognosis strategies in order to give an
explanation for the vital of the proposed work. Detrano et al. [11] developed HD
classification gadget via the usage of laptop studying classification methods and the overall
performance of the machine used to be 77% in phrases of accuracy. Cleveland dataset was
once utilized with the technique of international evolutionary and with elements decision
method. In every other find out about Gudadhe et al. [22] developed a prognosis machine the
usage of multi-layer Perceptron and assist vector computer (SVM) algorithms for HD
classification and finished accuracy 80.41%.
13. LITERATURE SURVEY
Heart failure (HF) is a major public health issue, with a prevalence of over 5.8 million in the
USA, and over 23 million worldwide, and rising. The lifetime risk of developing HF is one
in five. Although promising evidence shows that the age-adjusted incidence of HF may have
plateaued, HF still carries substantial morbidity and mortality, with 5-year mortality that
rival those of many cancers. HF represents a considerable burden to the health-care system,
responsible for costs of more than $39 billion annually in the USA alone, and high rates of
hospitalizations, readmissions, and outpatient visits. HF is not a single entity, but a clinical
syndrome that may have different characteristics depending on age, sex, race or ethnicity,
left ventricular ejection fraction (LVEF) status, and HF etiology. Furthermore,
pathophysiological differences are observed among patients diagnosed with HF and reduced
LVEF compared with HF and preserved LVEF, which are beginning to be better appreciated
in epidemiological studies. A number of risk factors, such as ischemic heart disease,
hypertension, smoking, obesity, and diabetes, among others, have been identified that both
predict the incidence of HF as well as its severity.
14. LITERATURE SURVEY
Between Western and Asian populations, the profile and prevalence of risk factors for
cardiovascular disease (CVD) differ. For the primary prevention of CVD in asymptomatic
people, the guidelines advocate individualised interventions based on risk stratification
based on CVD risk models. Current risk models for predicting CVD in Asian populations, on
the other hand, are restricted. A CVD risk model for predicting global cardiovascular risk
was constructed in a recent research of a large cohort of asymptomatic Korean individuals,
and it performed well in predicting cardiovascular events. This strategy could be effective in
the primary prevention of CVD in both East Asians and Koreans.
15. Working modules
Upload Dataset: We gather all the data from the kaggale website and upload to the
proposed model
Generate Train & Test Model: We have to preprocess the gathered data and then we
have to split the data into two parts training data with 80% and test data with 20%
Run Genetic Algorithm: we have to train the Genetic with train data and test the RF
with test data to get best result from the algorithm
Run BAT Algorithm: we have to train the BAT with train data and test the BAT with test
data to get best result from the algorithm
16. Working modules
Run BEE Algorithm: we have to train the BEE with train data and test the BEE with test
data to get best result from the algorithm
Accuracy Comparison Graph: we will find the best algorithm with highest accuracy in the
form of graph
Predict output : upload the test data to predict the output.and we predicted disease stages.
21. In above screen click on ‘Upload Heart Disease’ button
and upload heart disease dataset. See below screen.
22. In above screen uploading dataset file, after
uploading will get below screen.
23. Now click on ‘Run Genetic Algorithm’ button to run genetic algorithm on dataset
and to get its accuracy details. While running this algorithm u can see black console
to see feature selection process, while running it will open empty windows, u just
close all those empty windows except current window
24. In above screen for GA accuracy, precision and recall we got
100% result. Now click on ‘Run Bat’ algorithm button to get
its accuracy.
25. In above screen for BAT we got 45% accuracy, now click
on ‘Run BEE Algorithm’ button to get BEE accuracy.
26. In above screen I am uploading test file which contains test data
without class label, after uploading test data will get below screen.
27. In above screen I am uploading test file which contains test data
without class label, after uploading test data will get below screen.
28. In above graph x-axis represents Algorithm Name and
y-axis represents accuracy of those algorithms
29. In above graph x-axis represents Algorithm Name and
y-axis represents accuracy of those algorithms
30. CONCLUSION AND FUTURE SCOPE
In this work we use the PSO technique as a training algorithm for ANN to predict the
heart diseases.
After applying the PSO, We found that compare to different diseases was able to
improve the accuracy, sensitivity and specificity.
Based on these results it can be shows that the proposed system is able to good
performance in the category of optimization.