This document summarizes a student's research on developing models to aid in hospital-level pandemic influenza planning. It introduces FluPredict, a real-time prediction model that uses surveillance data and builds on the existing FluSurge model. FluPredict dynamically predicts pandemic impact on hospital resources using a SEIAR epidemiological model. The student describes validating FluPredict using local hospital data and outlines future enhancements like improving predictions, modeling staff impacts, and increasing bed resource granularity. The goal is to help hospitals better allocate resources during an influenza pandemic.
Comparative study of decision tree algorithm and naive bayes classifier for s...eSAT Journals
Abstract The modeling and analysis of the epidemic disease outbreaks in huge realistic populations is a data intensive task that requires immense computational resources. Such effective computational support becomes useful to study disease outbreak and to facilitate decision making. Epidemiology is one of the traditional approaches which are being used for studying and analyzing the outbreaks of epidemic diseases. Although useful for obtaining numbers of sick, infected and recovered individuals in a population, this traditional approach does not capture the complexity of human interactions. The model is only limited to the person to person interaction in order to track the surveillance of disease and it also having performance issues with large realistic data. In this paper we propose, the combination of computational epidemiology and modern data mining techniques with their comparative analysis for the Swine Flu prediction. The clustering algorithm K mean is used to make a group or cluster of Swine Flu suspects in a particular area. The Decision tree algorithm and Naive Bayes classifier are applied on the same inputs to find out the actual count of suspects and predict the possible surveillance of a Swine Flu in a nearby area from suspected area. The performances of these techniques are compared, based on accuracy. In our case the Naive Bayes classifier performs better than decision tree algorithm while finding the accurate count of suspects. Keywords: Computational Epidemiology, Aerosol-borne Disease, Clustering, Predictive analysis.
From simulated model by bio pepa to narrative language through sbmlijctcm
Many theoretical works and tools on epidemiological field reflect the emphasis on decision-making tools
by both public health and the scientific community, which continues to increase.
Indeed, in the epidemiological field, modeling tools are proving a very important way in helping to make
decision. However, the variety, the large volume of data and the nature of epidemics lead us to seek
solutions to alleviate the heavy burden imposed on both experts and developers.
Among the important steps of modeling and simulation: model validation. It refers to the process of
determining how well a model corresponds to the system that it intended to represent. So the question is:
what happens if the model is invalid? Do we need to reproduce another one, or just optimize the existing
one?
Factors Associated with Antenatal Care Service Utilization among Women with C...YogeshIJTSRD
Maternal and neonatal mortality remains a public health burden around the globe most especially in developing countries. A well utilized antenatal care ANC is however among the identified interventions to reduce this burden of maternal and neonatal mortality rates. A lot of factors therefore predispose, enable and cause mothers to identify the need to utilize this service ANC .This study employed descriptive cross sectional survey design. A semi structured questionnaire consisting of demographic profile of the respondents, their knowledge about ANC services and the level of ANC utilization. Logistic regression analysis techniques and chi square were used for the categorical variables to examine the associations between the dependent and independent variables. Data analysis was done using the Statistical Package for Social Science software SPSS version 22. Majority 87 of postpartum mothers in the Sunyani municipality attended ANC at least once during their last pregnancy of which 95.6 had four or more visits and 77.1 initiated their ANC attendance within their first trimester. It was further observed that 97.3 of the mothers had good knowledge about ANC. Marital status and ANC knowledge were found to be significantly associated with ANC attendance. Stephen Owusu Sekyere | Kodua Freda "Factors Associated with Antenatal Care Service Utilization among Women with Children under Five Years in Sunyani Municipality, Ghana" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-5 | Issue-3 , April 2021, URL: https://www.ijtsrd.com/papers/ijtsrd39882.pdf Paper URL: https://www.ijtsrd.com/other-scientific-research-area/other/39882/factors-associated-with-antenatal-care-service-utilization-among-women-with-children-under-five-years-in-sunyani-municipality-ghana/stephen-owusu-sekyere
Comparative study of decision tree algorithm and naive bayes classifier for s...eSAT Journals
Abstract The modeling and analysis of the epidemic disease outbreaks in huge realistic populations is a data intensive task that requires immense computational resources. Such effective computational support becomes useful to study disease outbreak and to facilitate decision making. Epidemiology is one of the traditional approaches which are being used for studying and analyzing the outbreaks of epidemic diseases. Although useful for obtaining numbers of sick, infected and recovered individuals in a population, this traditional approach does not capture the complexity of human interactions. The model is only limited to the person to person interaction in order to track the surveillance of disease and it also having performance issues with large realistic data. In this paper we propose, the combination of computational epidemiology and modern data mining techniques with their comparative analysis for the Swine Flu prediction. The clustering algorithm K mean is used to make a group or cluster of Swine Flu suspects in a particular area. The Decision tree algorithm and Naive Bayes classifier are applied on the same inputs to find out the actual count of suspects and predict the possible surveillance of a Swine Flu in a nearby area from suspected area. The performances of these techniques are compared, based on accuracy. In our case the Naive Bayes classifier performs better than decision tree algorithm while finding the accurate count of suspects. Keywords: Computational Epidemiology, Aerosol-borne Disease, Clustering, Predictive analysis.
From simulated model by bio pepa to narrative language through sbmlijctcm
Many theoretical works and tools on epidemiological field reflect the emphasis on decision-making tools
by both public health and the scientific community, which continues to increase.
Indeed, in the epidemiological field, modeling tools are proving a very important way in helping to make
decision. However, the variety, the large volume of data and the nature of epidemics lead us to seek
solutions to alleviate the heavy burden imposed on both experts and developers.
Among the important steps of modeling and simulation: model validation. It refers to the process of
determining how well a model corresponds to the system that it intended to represent. So the question is:
what happens if the model is invalid? Do we need to reproduce another one, or just optimize the existing
one?
Factors Associated with Antenatal Care Service Utilization among Women with C...YogeshIJTSRD
Maternal and neonatal mortality remains a public health burden around the globe most especially in developing countries. A well utilized antenatal care ANC is however among the identified interventions to reduce this burden of maternal and neonatal mortality rates. A lot of factors therefore predispose, enable and cause mothers to identify the need to utilize this service ANC .This study employed descriptive cross sectional survey design. A semi structured questionnaire consisting of demographic profile of the respondents, their knowledge about ANC services and the level of ANC utilization. Logistic regression analysis techniques and chi square were used for the categorical variables to examine the associations between the dependent and independent variables. Data analysis was done using the Statistical Package for Social Science software SPSS version 22. Majority 87 of postpartum mothers in the Sunyani municipality attended ANC at least once during their last pregnancy of which 95.6 had four or more visits and 77.1 initiated their ANC attendance within their first trimester. It was further observed that 97.3 of the mothers had good knowledge about ANC. Marital status and ANC knowledge were found to be significantly associated with ANC attendance. Stephen Owusu Sekyere | Kodua Freda "Factors Associated with Antenatal Care Service Utilization among Women with Children under Five Years in Sunyani Municipality, Ghana" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-5 | Issue-3 , April 2021, URL: https://www.ijtsrd.com/papers/ijtsrd39882.pdf Paper URL: https://www.ijtsrd.com/other-scientific-research-area/other/39882/factors-associated-with-antenatal-care-service-utilization-among-women-with-children-under-five-years-in-sunyani-municipality-ghana/stephen-owusu-sekyere
Practical Methods To Overcome Sample Size ChallengesnQuery
Watch the video at: https://www.statsols.com/webinars/practical-methods-to-overcome-sample-size-challenges
In this webinar hosted by Ronan Fitzpatrick - Head of Statistics and nQuery Lead Researcher at Statsols - we will examine some of the most common practical challenges you will experience while calculating sample size for your study. These challenges will be split into two categories:
1. Overcoming Sample Size Calculation Challenges
(Survival Analysis Example)
We will examine practical methods to overcome common sample size calculation issues by focusing in on one of the more complex areas for sample size determination; Survival analysis. We will cover difficulties and potential issues surrounding challenges such as:
Drop Out: How to deal with expected dropouts or censoring. We compare the simple loss-to-follow-up method and integrating a dropout process into the sample size model?
Planning Uncertainty: How best to deal with the inevitable uncertainty at the planning stage? We examine how best to apply a sensitivity analysis and Bayesian approaches to explore the uncertainty in your sample size calculations.
Choosing the Effect Size: Various approaches and interpretations exist for how to find the effect size value. We examine those contrasting interpretations and determine the best method and also how to deal with parameterization options.
2. Overcoming Study Design Challenges
(Vaccine Efficacy Example)
The Randomised Controlled Trial (RCT) is considered the gold standard in trial design in drug development. However, there are often practical impediments which mean that adjustments or pragmatic approaches are needed for some trials and studies.
We will examine practical methods how to overcome common study design challenges and how these affect your sample size calculations. In this webinar, we will use common issues in vaccine study design to examine difficulties surrounding issues such as:
Case-Control Analysis: We will examine how to deal with study constraints and how to deal with analyses done during an observational study.
Alternative Randomization Methods: How best to address randomization in your vaccine trial design when full randomization is difficult, expensive or impractical. We examine how sample size calculations are affected with cluster or Mendelian randomization.
Rare Events: How does an outcome being rare affect the types of study design and statistical methods chosen in your study.
Risk Assessment with “Actuarial Data”, George GrayOECD Governance
Presentation by Prof. George Gray, Director of the Centre for Risk Science and Public Health, George Washington University, at the Workshop on Risk Assessment in Regulatory Policy Analysis (RIA), Session 7, Mexico, 9-11 June 2014. Further information is available at http://www.oecd.org/gov/regulatory-policy/
Methodological Challenges in Evaluating Malaria Control Program Impact: How d...MEASURE Evaluation
Presented by Tom Smith, Swiss Tropical and Public Health Institute, as part of a symposium organized by MEASURE Evaluation and MEASURE DHS at the 6th MIM Pan-African Malaria Conference.
Data for Impact hosted a one-hour webinar sharing guidance for using routine data in evaluations. More: https://www.data4impactproject.org/resources/webinars/routine-data-use-in-evaluation-practical-guidance/
In an interactive presentation for the Wessex Academic Health Science Network Learning Lab, Dr Catherine Matheson-Monnet explains how she used Force Field Analysis as a structured focus group activity.
Data Management: Alternative Models for Source Data VerificationKCR
KCR's presentation on alternative models for Source Data Verification (SDV) Risk Based Monitoring (RBM) is evolving into a standard expectation for SDV and study management in general.
A Typology of Strategic Environments Extracted from a Cross-tabulated SWOT An...Peter J Stavroulakis
From the plethora of instruments concerned with strategic management, one may be easily led to remark that SWOT analysis surfaces as the most resilient of techniques, for it is a readily available methodology facilitating the formulation of an effective strategic framework through situation analysis. Although to this day its origin remains obscure, it has proven time and time again to be the strategic instrument of choice for over half a century and for a good reason: SWOT analysis provides a concise snapshot of the strategic environment involving the case at hand and at the same time hints towards strategic directions that should be pursed in order to achieve strategic might. Cross-tabulation on the other hand, provides a methodology from which we can extract an interrelation of causality between categorical data. We investigate the applicability of epidemiological instruments (including but not limited to measures of association) to strategic management topics. From the model formulated, a typology of strategic environments is proposed and can be utilized in order to categorize strategic ventures according to the external environment wherein they are operating (or are about to operate). This work proposes a novel approach concerning SWOT analysis, implicating a correlation of the methodology concerning the critical and analytic review of strategic factors with methodologies contained in epidemiology. The procedure of typology formulation and cross-tabulation can be applied in other cases of study, thus expanding the scope and applicability of SWOT analysis even further.
Practical Methods To Overcome Sample Size ChallengesnQuery
Watch the video at: https://www.statsols.com/webinars/practical-methods-to-overcome-sample-size-challenges
In this webinar hosted by Ronan Fitzpatrick - Head of Statistics and nQuery Lead Researcher at Statsols - we will examine some of the most common practical challenges you will experience while calculating sample size for your study. These challenges will be split into two categories:
1. Overcoming Sample Size Calculation Challenges
(Survival Analysis Example)
We will examine practical methods to overcome common sample size calculation issues by focusing in on one of the more complex areas for sample size determination; Survival analysis. We will cover difficulties and potential issues surrounding challenges such as:
Drop Out: How to deal with expected dropouts or censoring. We compare the simple loss-to-follow-up method and integrating a dropout process into the sample size model?
Planning Uncertainty: How best to deal with the inevitable uncertainty at the planning stage? We examine how best to apply a sensitivity analysis and Bayesian approaches to explore the uncertainty in your sample size calculations.
Choosing the Effect Size: Various approaches and interpretations exist for how to find the effect size value. We examine those contrasting interpretations and determine the best method and also how to deal with parameterization options.
2. Overcoming Study Design Challenges
(Vaccine Efficacy Example)
The Randomised Controlled Trial (RCT) is considered the gold standard in trial design in drug development. However, there are often practical impediments which mean that adjustments or pragmatic approaches are needed for some trials and studies.
We will examine practical methods how to overcome common study design challenges and how these affect your sample size calculations. In this webinar, we will use common issues in vaccine study design to examine difficulties surrounding issues such as:
Case-Control Analysis: We will examine how to deal with study constraints and how to deal with analyses done during an observational study.
Alternative Randomization Methods: How best to address randomization in your vaccine trial design when full randomization is difficult, expensive or impractical. We examine how sample size calculations are affected with cluster or Mendelian randomization.
Rare Events: How does an outcome being rare affect the types of study design and statistical methods chosen in your study.
Risk Assessment with “Actuarial Data”, George GrayOECD Governance
Presentation by Prof. George Gray, Director of the Centre for Risk Science and Public Health, George Washington University, at the Workshop on Risk Assessment in Regulatory Policy Analysis (RIA), Session 7, Mexico, 9-11 June 2014. Further information is available at http://www.oecd.org/gov/regulatory-policy/
Methodological Challenges in Evaluating Malaria Control Program Impact: How d...MEASURE Evaluation
Presented by Tom Smith, Swiss Tropical and Public Health Institute, as part of a symposium organized by MEASURE Evaluation and MEASURE DHS at the 6th MIM Pan-African Malaria Conference.
Data for Impact hosted a one-hour webinar sharing guidance for using routine data in evaluations. More: https://www.data4impactproject.org/resources/webinars/routine-data-use-in-evaluation-practical-guidance/
In an interactive presentation for the Wessex Academic Health Science Network Learning Lab, Dr Catherine Matheson-Monnet explains how she used Force Field Analysis as a structured focus group activity.
Data Management: Alternative Models for Source Data VerificationKCR
KCR's presentation on alternative models for Source Data Verification (SDV) Risk Based Monitoring (RBM) is evolving into a standard expectation for SDV and study management in general.
A Typology of Strategic Environments Extracted from a Cross-tabulated SWOT An...Peter J Stavroulakis
From the plethora of instruments concerned with strategic management, one may be easily led to remark that SWOT analysis surfaces as the most resilient of techniques, for it is a readily available methodology facilitating the formulation of an effective strategic framework through situation analysis. Although to this day its origin remains obscure, it has proven time and time again to be the strategic instrument of choice for over half a century and for a good reason: SWOT analysis provides a concise snapshot of the strategic environment involving the case at hand and at the same time hints towards strategic directions that should be pursed in order to achieve strategic might. Cross-tabulation on the other hand, provides a methodology from which we can extract an interrelation of causality between categorical data. We investigate the applicability of epidemiological instruments (including but not limited to measures of association) to strategic management topics. From the model formulated, a typology of strategic environments is proposed and can be utilized in order to categorize strategic ventures according to the external environment wherein they are operating (or are about to operate). This work proposes a novel approach concerning SWOT analysis, implicating a correlation of the methodology concerning the critical and analytic review of strategic factors with methodologies contained in epidemiology. The procedure of typology formulation and cross-tabulation can be applied in other cases of study, thus expanding the scope and applicability of SWOT analysis even further.
Isolamento ambiental, identificação bioquímica e drogas antifúngicas suscetí...mauriciocoelhomicrobio
CRIPTOCOCOSE Cryptococcus neoformans
Infecção fúngica oportunista e sistêmica que afeta principalmente indivíduos com algum comprometimento no sistema imunológico associado à vírus.
CRIPTOCOCOSE Cryptococcus gattii
Infecção fungica primária que afeta indivíduos aparentemente imunocompetetes.
El movimiento es practicamente inherente a toda dinámica de los seres animados e inamimados. Todo se mueve, en diferentes formas y desde diferentes sistemas de referencia. EL movimiento siempre hay que describirlo respecto a sun sistema de referencia que se toma como fijo
Parallel Programming Approaches for an Agent-based Simulation of Concurrent P...Subhajit Sahu
Highlighted notes while preparing for project on Computational Epidemics:
Parallel Programming Approaches for an Agent-based Simulation of Concurrent Pandemic and Seasonal Influenza Outbreaks
Milton Soto-Ferraria
Peter Holvenstot
Diana Prietoa
Elise de Doncker
John Kapenga
2013 International Conference on Computational Science
Procedia Computer Science 18 ( 2013 ) 2187 – 2192
In this paper we propose parallelized versions of an agent-based simulation for concurrent pandemic and seasonal influenza outbreaks. The objective of the implementations is to significantly reduce the replication time and allow faster evaluation of mitigation strategies during an ongoing emergency. The simulation was initially parallelized using the g++ OpenMP library. We simulated the outbreak in a population of 1,000,000 individuals to evaluate algorithm performance and results. In addition to the OpenMP parallelization, a proposed CUDA implementation is also presented.
HEART DISEASES PREDICTION USING MACHINE LEARNING ALGORITHMPoojaSri45
Implemented a machine learning project aimed at predicting heart diseases using various algorithms and techniques. Developed as a part of academic or professional endeavor, the project demonstrates proficiency in data preprocessing, feature selection, model training, and evaluation.
An excellent article that uses predictive and optimization methods to reduce hospital readmissions.
Another great article, "Reducing hospital readmissions by integrating empirical prediction with resource optimization" (Helm, Alaeddini, Stauffer, Bretthaur, and Skolarus, 2016) describes how Machine Learning modeling tools were used to determine the root-causes and individualized estimation of readmissions. The post-discharge monitoring schedule and workplans were then optimized to patient changes in health states.
Project pressure ulcer reductionRunning head HEALTH C.docxbriancrawford30935
Project pressure ulcer reduction
Running head: HEALTH CARE CHANGE PROJECT MATRIX
1
HEALTH CARE CHANGE PROJECT MATRIX
4
Health Care Change Project Matrix
Objective:
To reduce the incidence of newly acquired pressure ulcers development in California Health Medical Center (CHMC) to 10% within six months of implementing the new evidence-based protocol.
Objectives
Content
Describe the methods to be used to implement the proposed solution
An electronic system to document pressure ulcer risk assessment and incidence will be created within the hospital’s current electronic medical record system, EPIC.
The system facilitates recording pressure ulcer incidence that would trigger wound consult nurses to provide timely advice on and validation of the categories of pressure ulcers.
Staff charge nurses will conduct pressure ulcer assessments in admission. Instead of documenting in paper form, they will directly record these findings on an initial risk assessment electronic form and simultaneously make an e-referral to the wound consult nurse if a patient has a pressure ulcer that is a stage 2 or higher.
Having an electronic pressure ulcer risk and incidence form for each patient allows various healthcare professionals and members of the interdisciplinary team to have secure access to reliable and current information in real-time (Plaskitt, Heywood, and Arrowsmith, 2015).
Develop a plan for implementing the proposed solution
Per Wager et al (2009), it is crucial that a team is organized that serves “to plan, coordinate, budget, and manage all aspects of the new system implementation” (p. 244). A team will be assembled to gain much-needed support for the program. This implementation team is vital in engaging various stakeholders in providing support and commitment to the project. The team members include charge nurses, wound consultant nurses, quality improvement nurses, an MD champion and department managers from areas such as education, equipment and information technology (IT) and administration.
An immersion event will be launched to inform and engage all staff members in the project. The event will allow necessary information to be disseminated, share goals and desired outcomes as well as the rationale behind the project.
Shedenhelm et al (2010), states that providing education through a variety of methods allows training to be received well for recipients with diverse learning styles. Furthermore, ongoing training should be developed and advertised through educational newsletters and emails that provide education reminders and other important information. Shedenhelm et al (2010), also emphasizes provision of multiple opportunities through multiple sites locations at varied times increases turnout. Furthermore, each nursing units will be provided pressure ulcer training bundles that including competencies will be presented.
Regular communication with various constituent groups such be conducted and a means for reporting problems.
Great article on how to integrate machine learning and optimization technique.
One group of researchers was able to reduce heart failure readmissions by 35% by combining machine learning and decision science technique, see "Data-driven decisions for reducing readmissions for heart failure: general methodology and case study" (Bayati, et. al., 2014).
There has been increasing demand in improving service provisioning in hospital resources management. Hospital industries work with strict budget constraint at the same time assures quality care. To achieve quality care with budget constraint an efficient prediction model is required. Recently there has been various time series based prediction model has been proposed to manage hospital resources such ambulance monitoring, emergency care and so on. These models are not efficient as they do not consider the nature of scenario such climate condition etc. To address this artificial intelligence is adopted. The issues with existing prediction are that the training suffers from local optima error. This induces overhead and affects the accuracy in prediction. To overcome the local minima error, this work presents a patient inflow prediction model by adopting resilient backpropagation neural network. Experiment are conducted to evaluate the performance of proposed model inter of RMSE and MAPE. The outcome shows the proposed model reduces RMSE and MAPE over existing back propagation based artificial neural network. The overall outcomes show the proposed prediction model improves the accuracy of prediction which aid in improving the quality of health care management.
There has been increasing demand in improving service provisioning in hospital resources
management. Hospital industries work with strict budget constraint at the same time assures quality care.
To achieve quality care with budget constraint an efficient prediction model is required. Recently there has
been various time series based prediction model has been proposed to manage hospital resources such
ambulance monitoring, emergency care and so on. These models are not efficient as they do not consider
the nature of scenario such climate condition etc. To address this artificial intelligence is adopted. The
issues with existing prediction are that the training suffers from local optima error. This induces overhead
and affects the accuracy in prediction. To overcome the local minima error, this work presents a patient
inflow prediction model by adopting resilient backpropagation neural network. Experiment are conducted to
evaluate the performance of proposed model inter of RMSE and MAPE. The outcome shows the proposed
model reduces RMSE and MAPE over existing back propagation based artificial neural network. The
overall outcomes show the proposed prediction model improves the accuracy of prediction which aid in
improving the quality of health care management
Modeling and Analysis of Influenza A H1N1 Outbreaks in IndiaYogeshIJTSRD
Influenza A H1N1 incidence in India, which is a highly contagious acute respiratory disease in humans caused by type A influenza virus. This study employs retrospective comparative study of the data from National Centre for Disease Control CDC yearly reports from April 2010 to April 2019. The case fatality rates of Influenza A H1N1 incidence in India was forecasted using autoregressive integrated moving average ARIMA models in order to build a predictive tool for Influenza A H1N1 surveillance. Clearly from the study, lack of rainfall spread the virus more efficiently and Maharashtra stood first in total number of cases and deaths of Influenza A H1N1 whereas Lakshadweep had no signs of disease. Further, number of Cases were reported in the year 2015 i.e. 28 and 25 of cases have been reported in 2017 when compared to ten years data. ARIMA 2, 1, 3 model was selected for its minimum value of normalized BIC, MAPE and good R Square among all other models. The model forecasted the decrease in case fatality rate of Influenza A H1N1 for next 10years. Thus, results indicate that, ARIMA models provide a means to better understand Influenza A H1N1 incidence yielding forecasts that can be used for public health planning at the national level. Stavelin Abhinandithe K | Sathya Velu R | Dr. Madhu B | Sahana S | Sowmyavalli R |Bibin John | Dr. Balasubramanian S "Modeling and Analysis of Influenza A H1N1 Outbreaks in India" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-5 | Issue-3 , April 2021, URL: https://www.ijtsrd.com/papers/ijtsrd39862.pdf Paper URL: https://www.ijtsrd.com/other-scientific-research-area/applied-mathamatics/39862/modeling-and-analysis-of-influenza-a-h1n1-outbreaks-in-india/stavelin-abhinandithe-k
PERFORMANCE OF DATA MINING TECHNIQUES TO PREDICT IN HEALTHCARE CASE STUDY: CH...ijdms
With the promises of predictive analytics in big data, and the use of machine learning algorithms,
predicting future is no longer a difficult task, especially for health sector, that has witnessed a great
evolution following the development of new computer technologies that gave birth to multiple fields of
research. Many efforts are done to cope with medical data explosion on one hand, and to obtain useful
knowledge from it, predict diseases and anticipate the cure on the other hand. This prompted researchers
to apply all the technical innovations like big data analytics, predictive analytics, machine learning and
learning algorithms in order to extract useful knowledge and help in making decisions. In this paper, we
will present an overview on the evolution of big data in healthcare system, and we will apply three learning
algorithms on a set of medical data. The objective of this research work is to predict kidney disease by
using multiple machine learning algorithms that are Support Vector Machine (SVM), Decision Tree (C4.5),
and Bayesian Network (BN), and chose the most efficient one.
In this Project we analyses the spread and impact of the novel coronavirus pandemic which has taken the world by storm with its rapid growth. In this we like to develop a machine learning model in Python to analyze what has been its impact so far and analyze the outbreak of COVID 19 across various regions, visualize them using charts and tables, and predict the number of upcoming confirmed cases.
1. Pandemic Influenza Planning FluPredict:A real-time prediction model for aid in hospital-level pandemic influenza planning Jonathan Wang Professor Michael Carter April 15, 2011
2. A little about me... BASc in Engineering Science at University of Toronto Specializing in Biomedical Engineering Currently, MASc in Industrial Engineering at University of Toronto Specializing in Healthcare Operations CHL5425 with Professor Fisman on mathematical epidemiology last semester
21. For the Pandemic H1N1 virus in 2009, there have been a total of 8,678 hospitalized cases in Canada with 428 deaths since the beginning of the pandemic [2]Background| Current Research | Methods | Results | Future Work | Conclusion [1] Skowronski, Danuta; Kendall, Perry. Pandemic Influenza--A primer for Physicians. BC Medical Journal. June 2007, Vol. 49, 5, pp. 236-239. [2] Health Canada.FluWatch. [Online] April 24, 2010. [Cited: July 26, 2010] http://www.phac-aspc.gc.ca/fluwatch/09-10/w16_10/index-eng.php
22. Impact of Pandemic Therefore, it is necessary to adequately plan for a pandemic to allocate resources effectively in a hospital setting Background| Current Research | Methods | Results | Future Work | Conclusion
27. Compares the number of persons hospitalized, the number of persons requiring ICU care, and the number of persons requiring ventilator support during a pandemic with existing hospital capacity.The FluSurge Model [3] Background |Current Research | Methods | Results | Future Work | Conclusion [3] Zhang, Xinzhi, Meltzer, Martin I. and Wortley, Pascale M.FluSurge - A Tool to Estimate Demand for Hospital Services during the Next Pandemic Influenza. Medical Decision Making. Nov-Dec, 2006, Vol. 26, 617. [4]Lum ME, McMillan AJ, Brook CW, et al. Impact of pandemic (H1N1) 2009 influenza on critical care capacity in Victoria. [28 September 2009] Med J Aust. eMJA rapid online publication. [5] http://www.health.gov.on.ca/english/providers/program/emu/pan_flu/pan_flu_plan.html
45. Patient volume estimation based on historical data scaled to the inputted dataThe FluSurge Model Background |Current Research | Methods | Results | Future Work | Conclusion
47. Goal: Dynamically predict the impact of pandemic influenza to hospital resources based on daily data inputs Outputs: Bed availabilities, ICU capacity and ventilator usage Inputs: Age Demographics, CDC FluSurge assumptions, surveillance tool data Introduction to FluPredict Background | Current Research |Methods| Results | Future Work | Conclusion
48. Difference Between Models FluSurge[6] FluPredict Background | Current Research |Methods| Results | Future Work | Conclusion [6] Meltzer, M et al. The Economic Impact of Pandemic Influenza in the United States: Priorities for Intervention. Emerging Infectious Diseases. Oct, 1999, Vol. 5, 5.
49.
50. Multiplicative factor that affects the height of the pandemic curve (i.e. Affects the number of people being infected)
55. Relate these parameters to the input parameters of a normal distributionTwo Important Parameters Background | Current Research |Methods| Results | Future Work | Conclusion
56. Pandemic Length For a given attack rate: 6 SD 3 SD SD = Duration/6 Mean = Duration/2 99.7% of all values lie within 3 standard deviations of the mean for normal distribution. Background | Current Research |Methods| Results | Future Work | Conclusion
57. Generated theoretical pandemic influenza curves (with different durations [1-12 weeks] and attack rates [1%-50%]) Can generate 1800 scenarios. But which scenario most accurately represents the data? Varying Pandemic Length Background | Current Research |Methods| Results | Future Work | Conclusion
58. The most likely scenario is defined by the duration and attack rate Q: How to determine these 2 variables? A: Fit the incoming ED (ILI) admission data to “standard” pandemic hospitalization curves Most likely Scenario Background | Current Research |Methods| Results | Future Work | Conclusion
59. Most likely Scenario- RMS Error Background | Current Research |Methods| Results | Future Work | Conclusion
60. Most likely Scenario- RMS Error Error = Difference between the curves Background | Current Research |Methods| Results | Future Work | Conclusion
61. To calculate the RMS error value: The RMS error is then compared against the RMS error for all other simulated curves The minimum RMS error indicates that the simulated curve is the best fit to the input data We then can attribute the attack rate and the duration of the best fit curve to the input data Most likely Scenario- RMS Error Background | Current Research |Methods| Results | Future Work | Conclusion
64. Details how many beds to open up during the pandemic depending on various “triggers”
65. “Triggers” = a pre-specified percentage of ED admissions after which the hospital will open a preset number of beds to increase capacity for incoming ILI patientsImpact on Hospital Resources Background | Current Research |Methods| Results | Future Work | Conclusion
66. Impact on WOHC – Resource Model Background | Current Research |Methods| Results | Future Work | Conclusion
68. SEIAR Model Compartmental, epidemiological model Characteristic of influenza Background | Current Research |Methods| Results | Future Work | Conclusion
72. Given the parameters, we can arrive at patient distributions Governing Equations Background | Current Research |Methods| Results | Future Work | Conclusion
75. For a given set of parameters, a set of curves were generated and compared to the real-time data of the hospitalParameterization Background | Current Research |Methods| Results | Future Work | Conclusion
82. Able to predict a 11 week surge with the given dataModel Validation - FluPredict Background | Current Research | Methods |Results| Future Work | Conclusion
83. Model Validation - FluPredict Background | Current Research | Methods |Results| Future Work | Conclusion
84. Model Validation - FluPredict Background | Current Research | Methods |Results| Future Work | Conclusion Prediction given 3 weeks of data input: 11 weeks with 10% attack rate
85. Model Validation – FluPredict Background | Current Research | Methods |Results| Future Work | Conclusion Prediction: 11 weeks with 10% attack rate
88. This can be remedied by applying a smoothing function to the data to eliminate unnecessary bumps in the data
89. NOTE: The prediction is only an estimate of what may happenLimitations to the Prediction Background | Current Research | Methods |Results| Future Work | Conclusion
90. Results from FluPredict Background | Current Research | Methods |Results| Future Work | Conclusion
91. Results from SEIAR model Background | Current Research | Methods |Results| Future Work | Conclusion
105. Take into account current pandemic plans, ward structure for beds, existing patients within WOHC systemModel Enhancements Background | Current Research | Methods | Results |Future Work | Conclusion
106. Leveraged hospital’s surveillance tool and pandemic preparedness plan An estimate of the duration and attack rate (or epidemiological properties) of the pandemic based on real-time surveillance data Ability to explore various scenarios to see the impact a pandemic will have on hospital’s resources The planning of procedures easier if pandemic length is able to be estimated (elective surgeries) Benefits to Hospitals Background | Current Research | Methods | Results | Future Work |Conclusion
113. At this stage, the FluPredict framework has shown promising preliminary resultsConclusion – In the Larger Picture Background | Current Research | Methods | Results | Future Work |Conclusion