Predictive Models for Healthcare Analytics

Size: px
Start display at page:

Download "Predictive Models for Healthcare Analytics"

Transcription

1 Predictive Models for Healthcare Analytics A Case on Retrospective Clinical Study Mengling Mornin Feng mfeng@mit.edu mornin@gmail.com 1

2 Learning Objectives After the lecture, students should be able to: Define what are predictive models Apply appropriate metrics to assess the performance of predictive models Explain some basic predictive models, such as logistic regression, decision tree, neural network etc Conduct retrospective clinical studies with appropriate predictive models Interpret results from predictive models Understand the future trend of predictive models 2

3 What are Predictive Models? To predict or to guess 3

4 What are Predictive Models? To predict or to guess 3

5 What are Predictive Models? To predict or to guess 3

6 What are Predictive Models? To predict or to guess 3

7 What are Predictive Models? To predict or to guess 3

8 What are Predictive Models? To predict or to guess 3

9 What are Predictive Models? 4

10 Classification (Supervised Learning) 5

11 Classification (Supervised Learning) 5

12 Classification (Supervised Learning) 5

13 Classification (Supervised Learning) 5

14 Classification (Supervised Learning) 5

15 Classification (Supervised Learning) 5

16 Classification (Supervised Learning) 5

17 Classification (Supervised Learning) 5

18 Assessment of Predictive Models 6

19 Assessment of Classification Models 7

20 Assessment of Classification Models Confusion Matrix 7

21 Assessment of Classification Models Confusion Matrix Predicted Yes Predicted No True Yes True No a True Position (TP) c False Positive (FP) b False Negative (FN) d True Negative (TN) 7

22 Assessment of Classification Models Confusion Matrix Predicted Yes Predicted No True Yes True No a True Position (TP) c False Positive (FP) b False Negative (FN) d True Negative (TN) 7

23 Assessment of Classification Models Confusion Matrix Predicted Yes Predicted No True Yes True No a True Position (TP) c False Positive (FP) b False Negative (FN) d True Negative (TN) 7

24 Assessment of Classification Models Confusion Matrix Predicted Yes Predicted No True Yes True No a True Position (TP) c False Positive (FP) b False Negative (FN) d True Negative (TN) 7

25 Assessment of Classification Models Confusion Matrix Predicted Yes Predicted No True Yes True No a True Position (TP) c False Positive (FP) b False Negative (FN) d True Negative (TN) 7

26 Assessment of Classification Models Confusion Matrix Predicted Yes Predicted No True Yes a True Position (TP) b False Negative (FN) True No c False Positive (FP) d True Negative (TN) Accuracy = Correct Predictions / All Predictions = (a+d)/(a+b+c+d) 7

27 Prediction Threshold 8

28 Limitations of Accuracy Hard to interpret Is 90% accuracy good? Is 20% accuracy bad? It depends! (on the base rate) Assume equal costs/weights on errors Again it depends on the problem and applications E.q. 9

29 Assessment of Classification Models 10

30 Assessment of Classification Models Error weights (costs) 10

31 Assessment of Classification Models Error weights (costs) Predicted Yes Predicted No True Yes a, w a True Position (TP) b,w b False Negative (FN) True No c, w c False Positive (FP) d, w d True Negative (TN) 10

32 Assessment of Classification Models Error weights (costs) Predicted Yes Predicted No True Yes a, w a True Position (TP) b,w b False Negative (FN) True No c, w c False Positive (FP) d, w d True Negative (TN) Error Costs = w b *b + w c *c 10

33 Error cost 11

34 Error cost 11

35 Assessment of Classification Models Lift Commonly used in targeted marketing Not interested in the entire population How much more accurate the model is compared to random guessing when we predicted x% to be true a / (a + b) (a + c) / (a + b + c + d) 12

36 Assessment of Classification Models Lift Commonly used in targeted marketing Not interested in the entire population How much more accurate the model is compared to random guessing when we predicted x% to be true Predicted Yes Predicted No True Yes a b True No c d a / (a + b) (a + c) / (a + b + c + d) 12

37 Assessment of Classification Models Lift Commonly used in targeted marketing Not interested in the entire population How much more accurate the model is compared to random guessing when we predicted x% to be true Predicted Yes Predicted No True Yes a b True No c d Given a threshold, Lift = a / (a + b) (a + c) / (a + b + c + d) 12

38 Lift 13

39 Assessment of Classification Models Precision, Recall, F-measure & Breakeven-Point 2 *(precision *recall) precision + recall 14

40 Assessment of Classification Models Precision, Recall, F-measure & Breakeven-Point Predicted Yes Predicted No True Yes a b True No c d 2 *(precision *recall) precision + recall 14

41 Assessment of Classification Models Precision, Recall, F-measure & Breakeven-Point Predicted Yes Predicted No True Yes a b True No c d Precision = Pr(True Predicted True) = a/(a+c) Recall = Pr(Predicted True True) = a/(a+b) F-measure = 2 *(precision *recall) precision + recall Breakeven Point: Precision = Recall 14

42 Precision & Recall 15

43 Assessment of Classification Models Sensitivity, Specificity and ROC 16

44 Assessment of Classification Models Sensitivity, Specificity and ROC Predicted Yes Predicted No True Yes a b True No c d 16

45 Assessment of Classification Models Sensitivity, Specificity and ROC Predicted Yes Predicted No True Yes a b True No c d Sensitivity = Pr(Predicted True True) = a/(a+b) Specificity = Pr(Predicted False False) = d/(c+d) Receiver Operator Characteristic (ROC) Curve Sensitivity vs (1-Specificity) 16

46 ROC curve 17

47 Assessment for Training Training and Testing Datasets n-fold Cross-Validation Jackknife Bootstrapping 18

48 Applications of Predictive Models 19

49 Outcome Predictions Applications Mortality, long-term outcome & quality of life Quality assessment, decision support, cost-effectiveness Clinical event predictions Early or timely intervention Adverse effect/risk assessment Treatment response Evidence generation: clinical studies 20

50 Case Study: Value of Echocardiogram for Critical Care Patients 21

51 The Question Whether Echocardiogram independently contribute to the improvement of critical care patients outcomes? Outcome: 28 days mortality Patient cohort: MICU and SICU Data: the MIMIC data How? 22

52 Causal Inference with Predictive Model Uni-variate Study 23

53 Co-founding Factors Demographics or admission info Age, Gender, Weight, BMI, Service Unit, Severity at admission, Day of Admission, Hour of Admission Co-morbidity (chronic) conditions CHF, Afib, Liver, Renal, COPD, Stroke, Cancer Vital Signs Blood pressure, Heart Rate, Respiration Rate, Temptation, Oxygen Saturation Lab tests: WBC, HGB, Creatinine, etc 24

54 Causal Inference with Predictive Model Multi-variate Study 25

55 Causal Inference with Predictive Model Propensity Score Study 26

56 Propensity Score Based Study Step 1: Build the predictive model to estimate the likelihood of intervention Step 2: Assess the performance of the predictive model Step 3: Match up patients based on the predicted Propensity Score Step 4: Evaluate the balancing after matching Step 5: Compare the matched cohort 27

57 Estimation of Propensity Score with Gradient Boosting Model (GBM) Gradient Boosting Model (GBM) An ensemble learning model based on decision tress 28

58 Decision Tress for Classification Echo 29 Non-echo

59 Decision Tress for Classification Age <=79 Echo 29 Non-echo

60 Decision Tress for Classification Age <=79 HR<=98 Echo 29 Non-echo

61 Decision Tress for Classification HR<=82 Age <=79 HR<=98 Echo 29 Non-echo

62 Decision Tress for Classification 30

63 Ensemble Learning 31

64 Ensemble Learning 31

65 Propensity Score Study with Gradient Boosting Model (GBM) 32

66 What is Trending in Machine Learning Deep Learning 33

67 What is Deep Learning? 34

68 What is Neural Network? 35

69 Success Stories 36

70 Success Stories 36

71 Success Stories 36

72 Success Stories 36

73 Success Stories 36

An Improved Patient-Specific Mortality Risk Prediction in ICU in a Random Forest Classification Framework

An Improved Patient-Specific Mortality Risk Prediction in ICU in a Random Forest Classification Framework An Improved Patient-Specific Mortality Risk Prediction in ICU in a Random Forest Classification Framework Soumya GHOSE, Jhimli MITRA 1, Sankalp KHANNA 1 and Jason DOWLING 1 1. The Australian e-health and

More information

Knowledge Discovery and Data Mining. Testing. Performance Measures. Notes. Lecture 15 - ROC, AUC & Lift. Tom Kelsey. Notes

Knowledge Discovery and Data Mining. Testing. Performance Measures. Notes. Lecture 15 - ROC, AUC & Lift. Tom Kelsey. Notes Knowledge Discovery and Data Mining Lecture 15 - ROC, AUC & Lift Tom Kelsey School of Computer Science University of St Andrews http://tom.home.cs.st-andrews.ac.uk twk@st-andrews.ac.uk Tom Kelsey ID5059-17-AUC

More information

WP9: CVD RISK IN OBESE CHILDREN AND ADOLESCENTS

WP9: CVD RISK IN OBESE CHILDREN AND ADOLESCENTS WP9: CVD RISK IN OBESE CHILDREN AND ADOLESCENTS MD-Paedigree EU Review Olivier Pauly, Siemens Healthineers Our vision: a screening approach for identifying obese children with high cardiovascular risk

More information

INTRODUCTION TO MACHINE LEARNING. Decision tree learning

INTRODUCTION TO MACHINE LEARNING. Decision tree learning INTRODUCTION TO MACHINE LEARNING Decision tree learning Task of classification Automatically assign class to observations with features Observation: vector of features, with a class Automatically assign

More information

Feature selection methods for early predictive biomarker discovery using untargeted metabolomic data

Feature selection methods for early predictive biomarker discovery using untargeted metabolomic data Feature selection methods for early predictive biomarker discovery using untargeted metabolomic data Dhouha Grissa, Mélanie Pétéra, Marion Brandolini, Amedeo Napoli, Blandine Comte and Estelle Pujos-Guillot

More information

Week 2 Video 3. Diagnostic Metrics

Week 2 Video 3. Diagnostic Metrics Week 2 Video 3 Diagnostic Metrics Different Methods, Different Measures Today we ll continue our focus on classifiers Later this week we ll discuss regressors And other methods will get worked in later

More information

7/17/2013. Evaluation of Diagnostic Tests July 22, 2013 Introduction to Clinical Research: A Two week Intensive Course

7/17/2013. Evaluation of Diagnostic Tests July 22, 2013 Introduction to Clinical Research: A Two week Intensive Course Evaluation of Diagnostic Tests July 22, 2013 Introduction to Clinical Research: A Two week Intensive Course David W. Dowdy, MD, PhD Department of Epidemiology Johns Hopkins Bloomberg School of Public Health

More information

Worksheet for Structured Review of Physical Exam or Diagnostic Test Study

Worksheet for Structured Review of Physical Exam or Diagnostic Test Study Worksheet for Structured Review of Physical Exam or Diagnostic Study Title of Manuscript: Authors of Manuscript: Journal and Citation: Identify and State the Hypothesis Primary Hypothesis: Secondary Hypothesis:

More information

3. Model evaluation & selection

3. Model evaluation & selection Foundations of Machine Learning CentraleSupélec Fall 2016 3. Model evaluation & selection Chloé-Agathe Azencot Centre for Computational Biology, Mines ParisTech chloe-agathe.azencott@mines-paristech.fr

More information

4. Model evaluation & selection

4. Model evaluation & selection Foundations of Machine Learning CentraleSupélec Fall 2017 4. Model evaluation & selection Chloé-Agathe Azencot Centre for Computational Biology, Mines ParisTech chloe-agathe.azencott@mines-paristech.fr

More information

OBSERVATIONAL MEDICAL OUTCOMES PARTNERSHIP

OBSERVATIONAL MEDICAL OUTCOMES PARTNERSHIP OBSERVATIONAL Patient-centered observational analytics: New directions toward studying the effects of medical products Patrick Ryan on behalf of OMOP Research Team May 22, 2012 Observational Medical Outcomes

More information

An Improved Algorithm To Predict Recurrence Of Breast Cancer

An Improved Algorithm To Predict Recurrence Of Breast Cancer An Improved Algorithm To Predict Recurrence Of Breast Cancer Umang Agrawal 1, Ass. Prof. Ishan K Rajani 2 1 M.E Computer Engineer, Silver Oak College of Engineering & Technology, Gujarat, India. 2 Assistant

More information

Machine learning II. Juhan Ernits ITI8600

Machine learning II. Juhan Ernits ITI8600 Machine learning II Juhan Ernits ITI8600 Hand written digit recognition 64 Example 2: Face recogition Classification, regression or unsupervised? How many classes? Example 2: Face recognition Classification,

More information

Diagnosis of Breast Cancer Using Ensemble of Data Mining Classification Methods

Diagnosis of Breast Cancer Using Ensemble of Data Mining Classification Methods International Journal of Bioinformatics and Biomedical Engineering Vol. 1, No. 3, 2015, pp. 318-322 http://www.aiscience.org/journal/ijbbe ISSN: 2381-7399 (Print); ISSN: 2381-7402 (Online) Diagnosis of

More information

Diagnostic Test. H. Risanto Siswosudarmo Department of Obstetrics and Gynecology Faculty of Medicine, UGM Jogjakarta. RS Sardjito

Diagnostic Test. H. Risanto Siswosudarmo Department of Obstetrics and Gynecology Faculty of Medicine, UGM Jogjakarta. RS Sardjito ب س م الل ه الر ح م ن الر ح يم RS Sardjito Diagnostic Test Gold standard New (test Disease No Disease Column Total Posi*ve a b a+b Nega*ve c d c+d Row Total a+c b+d N H. Risanto Siswosudarmo Department

More information

TITLE: A Data-Driven Approach to Patient Risk Stratification for Acute Respiratory Distress Syndrome (ARDS)

TITLE: A Data-Driven Approach to Patient Risk Stratification for Acute Respiratory Distress Syndrome (ARDS) TITLE: A Data-Driven Approach to Patient Risk Stratification for Acute Respiratory Distress Syndrome (ARDS) AUTHORS: Tejas Prahlad INTRODUCTION Acute Respiratory Distress Syndrome (ARDS) is a condition

More information

In-hospital Intensive Care Unit Mortality Prediction Model

In-hospital Intensive Care Unit Mortality Prediction Model In-hospital Intensive Care Unit Mortality Prediction Model COMPUTING FOR DATA SCIENCES GROUP 6: MANASWI VELIGATLA (24), NEETI POKHARNA (27), ROBIN SINGH (36), SAURABH RAWAL (42) Contents Impact Problem

More information

A Prospective Comparison of Two Commercially Available Hospital Admission Risk Scores

A Prospective Comparison of Two Commercially Available Hospital Admission Risk Scores A Prospective Comparison of Two Commercially Available Hospital Admission Risk Scores Dale Eric Green, MD MHA FCCP: Chief Medical Information Officer, Cornerstone Health Care AMGA April, 2014 Disclosure

More information

BMI 541/699 Lecture 16

BMI 541/699 Lecture 16 BMI 541/699 Lecture 16 Where we are: 1. Introduction and Experimental Design 2. Exploratory Data Analysis 3. Probability 4. T-based methods for continous variables 5. Proportions & contingency tables -

More information

Anirudh Kamath 1, Raj Ramnani 2, Jay Shenoy 3, Aditya Singh 4, and Ayush Vyas 5 arxiv: v2 [stat.ml] 15 Aug 2017.

Anirudh Kamath 1, Raj Ramnani 2, Jay Shenoy 3, Aditya Singh 4, and Ayush Vyas 5 arxiv: v2 [stat.ml] 15 Aug 2017. Optimization of Ensemble Supervised Learning Algorithms for Increased Sensitivity, Specificity, and AUC of Population-Based Colorectal Cancer Screenings Anirudh Kamath 1, Raj Ramnani 2, Jay Shenoy 3, Aditya

More information

Leveraging Analytics and Artificial Intelligence to Predict Health Risk

Leveraging Analytics and Artificial Intelligence to Predict Health Risk Leveraging Analytics and Artificial Intelligence to Predict Health Risk A case study on using machine learning to boost atrial fibrillation identification and anticoagulant drug use Arthur L. Forni, MD,

More information

An Introduction to ROC curves. Mark Whitehorn. Mark Whitehorn

An Introduction to ROC curves. Mark Whitehorn. Mark Whitehorn An Introduction to ROC curves Mark Whitehorn Mark Whitehorn It s all about me Prof. Mark Whitehorn Emeritus Professor of Analytics Computing University of Dundee Consultant Writer (author) m.a.f.whitehorn@dundee.ac.uk

More information

Application of AI in Healthcare. Alistair Erskine MD MBA Chief Informatics Officer

Application of AI in Healthcare. Alistair Erskine MD MBA Chief Informatics Officer Application of AI in Healthcare Alistair Erskine MD MBA Chief Informatics Officer 1 Overview Why AI in Healthcare topic matters Is AI just another shiny objects? Geisinger AI collaborations Categories

More information

Predictive performance and discrimination in unbalanced classification

Predictive performance and discrimination in unbalanced classification MASTER Predictive performance and discrimination in unbalanced classification van der Zon, S.B. Award date: 2016 Link to publication Disclaimer This document contains a student thesis (bachelor's or master's),

More information

The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care

The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care SUPPLEMENTARY INFORMATION Articles https://doi.org/10.1038/s41591-018-0213-5 In the format provided by the authors and unedited. The Artificial Intelligence Clinician learns optimal treatment strategies

More information

Predicting Breast Cancer Survivability Rates

Predicting Breast Cancer Survivability Rates Predicting Breast Cancer Survivability Rates For data collected from Saudi Arabia Registries Ghofran Othoum 1 and Wadee Al-Halabi 2 1 Computer Science, Effat University, Jeddah, Saudi Arabia 2 Computer

More information

When Overlapping Unexpectedly Alters the Class Imbalance Effects

When Overlapping Unexpectedly Alters the Class Imbalance Effects When Overlapping Unexpectedly Alters the Class Imbalance Effects V. García 1,2, R.A. Mollineda 2,J.S.Sánchez 2,R.Alejo 1,2, and J.M. Sotoca 2 1 Lab. Reconocimiento de Patrones, Instituto Tecnológico de

More information

COMP90049 Knowledge Technologies

COMP90049 Knowledge Technologies COMP90049 Knowledge Technologies Introduction Classification (Lecture Set4) 2017 Rao Kotagiri School of Computing and Information Systems The Melbourne School of Engineering Some of slides are derived

More information

Machine Learning! Robert Stengel! Robotics and Intelligent Systems MAE 345,! Princeton University, 2017

Machine Learning! Robert Stengel! Robotics and Intelligent Systems MAE 345,! Princeton University, 2017 Machine Learning! Robert Stengel! Robotics and Intelligent Systems MAE 345,! Princeton University, 2017 A.K.A. Artificial Intelligence Unsupervised learning! Cluster analysis Patterns, Clumps, and Joining

More information

Questionnaire design. Questionnaire Design: Content. Questionnaire Design. Questionnaire Design: Wording. Questionnaire Design: Wording OUTLINE

Questionnaire design. Questionnaire Design: Content. Questionnaire Design. Questionnaire Design: Wording. Questionnaire Design: Wording OUTLINE Questionnaire design OUTLINE Questionnaire design tests Reliability Validity POINTS TO CONSIDER Identify your research objectives. Identify your population or study sample Decide how to collect the information

More information

Copyright 2016 Aftab Hassan

Copyright 2016 Aftab Hassan Copyright 2016 Aftab Hassan Predictive Analytics and Decision Support for Heart Failure patients Aftab Hassan A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science

More information

Personalized Colorectal Cancer Survivability Prediction with Machine Learning Methods*

Personalized Colorectal Cancer Survivability Prediction with Machine Learning Methods* Personalized Colorectal Cancer Survivability Prediction with Machine Learning Methods* 1 st Samuel Li Princeton University Princeton, NJ seli@princeton.edu 2 nd Talayeh Razzaghi New Mexico State University

More information

Performance Evaluation of Machine Learning Algorithms in the Classification of Parkinson Disease Using Voice Attributes

Performance Evaluation of Machine Learning Algorithms in the Classification of Parkinson Disease Using Voice Attributes Performance Evaluation of Machine Learning Algorithms in the Classification of Parkinson Disease Using Voice Attributes J. Sujatha Research Scholar, Vels University, Assistant Professor, Post Graduate

More information

PREDICTION OF BREAST CANCER USING STACKING ENSEMBLE APPROACH

PREDICTION OF BREAST CANCER USING STACKING ENSEMBLE APPROACH PREDICTION OF BREAST CANCER USING STACKING ENSEMBLE APPROACH 1 VALLURI RISHIKA, M.TECH COMPUTER SCENCE AND SYSTEMS ENGINEERING, ANDHRA UNIVERSITY 2 A. MARY SOWJANYA, Assistant Professor COMPUTER SCENCE

More information

Next-Generation Remote Patient Monitoring for Heart Failure March 3, 2016

Next-Generation Remote Patient Monitoring for Heart Failure March 3, 2016 Next-Generation Remote Patient Monitoring for Heart Failure March 3, 2016 Raj Khandwalla, MD Cedars-Sinai Medical Center Martin S. Kohn, MD, Sentrian Conflict of Interest Raj Khandwalla, M.D. M.A. FACC

More information

Predicting Short Term Morbidity following Revision Hip and Knee Arthroplasty

Predicting Short Term Morbidity following Revision Hip and Knee Arthroplasty Predicting Short Term Morbidity following Revision Hip and Knee Arthroplasty A Review of ACS-NSQIP 2006-2012 Arjun Sebastian, M.D., Stephanie Polites, M.D., Kristine Thomsen, B.S., Elizabeth Habermann,

More information

Computer Age Statistical Inference. Algorithms, Evidence, and Data Science. BRADLEY EFRON Stanford University, California

Computer Age Statistical Inference. Algorithms, Evidence, and Data Science. BRADLEY EFRON Stanford University, California Computer Age Statistical Inference Algorithms, Evidence, and Data Science BRADLEY EFRON Stanford University, California TREVOR HASTIE Stanford University, California ggf CAMBRIDGE UNIVERSITY PRESS Preface

More information

Five-Year Outcomes of Transcatheter Aortic Valve Replacement (TAVR) in Inoperable Patients With Severe Aortic Stenosis: The PARTNER Trial

Five-Year Outcomes of Transcatheter Aortic Valve Replacement (TAVR) in Inoperable Patients With Severe Aortic Stenosis: The PARTNER Trial Five-Year Outcomes of Transcatheter Aortic Valve Replacement (TAVR) in Inoperable Patients With Severe Aortic Stenosis: The PARTNER Trial Samir R. Kapadia, MD On behalf of The PARTNER Trial Investigators

More information

Various performance measures in Binary classification An Overview of ROC study

Various performance measures in Binary classification An Overview of ROC study Various performance measures in Binary classification An Overview of ROC study Suresh Babu. Nellore Department of Statistics, S.V. University, Tirupati, India E-mail: sureshbabu.nellore@gmail.com Abstract

More information

Identifying Parkinson s Patients: A Functional Gradient Boosting Approach

Identifying Parkinson s Patients: A Functional Gradient Boosting Approach Identifying Parkinson s Patients: A Functional Gradient Boosting Approach Devendra Singh Dhami 1, Ameet Soni 2, David Page 3, and Sriraam Natarajan 1 1 Indiana University Bloomington 2 Swarthmore College

More information

Behavioral Data Mining. Lecture 4 Measurement

Behavioral Data Mining. Lecture 4 Measurement Behavioral Data Mining Lecture 4 Measurement Outline Hypothesis testing Parametric statistical tests Non-parametric tests Precision-Recall plots ROC plots Hardware update Icluster machines are ready for

More information

MACHINE LEARNING BASED APPROACHES FOR PREDICTION OF PARKINSON S DISEASE

MACHINE LEARNING BASED APPROACHES FOR PREDICTION OF PARKINSON S DISEASE Abstract MACHINE LEARNING BASED APPROACHES FOR PREDICTION OF PARKINSON S DISEASE Arvind Kumar Tiwari GGS College of Modern Technology, SAS Nagar, Punjab, India The prediction of Parkinson s disease is

More information

PREDICTION OF HEART DISEASE USING HYBRID MODEL: A Computational Approach

PREDICTION OF HEART DISEASE USING HYBRID MODEL: A Computational Approach PREDICTION OF HEART DISEASE USING HYBRID MODEL: A Computational Approach 1 G V N Vara Prasad, 2 Dr. Kunjam Nageswara Rao, 3 G Sita Ratnam 1 M-tech Student, 2 Associate Professor 1 Department of Computer

More information

Predictive Analytics for Retention in HIV Care

Predictive Analytics for Retention in HIV Care Predictive Analytics for Retention in HIV Care Jessica Ridgway, MD, MS; Arthi Ramachandran, PhD; Hannes Koenig, MS; Avishek Kumar, PhD; Joseph Walsh, PhD; Christina Sung; Rayid Ghani, MS; John A. Schneider,

More information

Evidence Based Medicine

Evidence Based Medicine Course Goals Goals 1. Understand basic concepts of evidence based medicine (EBM) and how EBM facilitates optimal patient care. 2. Develop a basic understanding of how clinical research studies are designed

More information

Probability Revision. MED INF 406 Assignment 5. Golkonda, Jyothi 11/4/2012

Probability Revision. MED INF 406 Assignment 5. Golkonda, Jyothi 11/4/2012 Probability Revision MED INF 406 Assignment 5 Golkonda, Jyothi 11/4/2012 Problem Statement Assume that the incidence for Lyme disease in the state of Connecticut is 78 cases per 100,000. A diagnostic test

More information

Diagnosis of Coronary Arteries Stenosis Using Data Mining

Diagnosis of Coronary Arteries Stenosis Using Data Mining Original Article Received: 2012-06-21 Accepted: 2012-07-16 JMSS/ July 2012, Vol 2, No3 Diagnosis of Coronary Arteries Stenosis Using Data Mining Roohallah Alizadehsani 1, Jafar Habibi 1, Behdad Bahadorian

More information

A PRACTICAL APPROACH FOR IMPLEMENTING THE PROBABILITY OF LIQUEFACTION IN PERFORMANCE BASED DESIGN

A PRACTICAL APPROACH FOR IMPLEMENTING THE PROBABILITY OF LIQUEFACTION IN PERFORMANCE BASED DESIGN A PRACTICAL APPROACH FOR IMPLEMENTING THE PROBABILITY OF LIQUEFACTION IN PERFORMANCE BASED DESIGN Thomas Oommen, Ph.D. Candidate, Department of Civil and Environmental Engineering, Tufts University, 113

More information

Critical reading of diagnostic imaging studies. Lecture Goals. Constantine Gatsonis, PhD. Brown University

Critical reading of diagnostic imaging studies. Lecture Goals. Constantine Gatsonis, PhD. Brown University Critical reading of diagnostic imaging studies Constantine Gatsonis Center for Statistical Sciences Brown University Annual Meeting Lecture Goals 1. Review diagnostic imaging evaluation goals and endpoints.

More information

Assessment of diabetic retinopathy risk with random forests

Assessment of diabetic retinopathy risk with random forests Assessment of diabetic retinopathy risk with random forests Silvia Sanromà, Antonio Moreno, Aida Valls, Pedro Romero2, Sofia de la Riva2 and Ramon Sagarra2* Departament d Enginyeria Informàtica i Matemàtiques

More information

MODEL DRIFT IN A PREDICTIVE MODEL OF OBSTRUCTIVE SLEEP APNEA

MODEL DRIFT IN A PREDICTIVE MODEL OF OBSTRUCTIVE SLEEP APNEA MODEL DRIFT IN A PREDICTIVE MODEL OF OBSTRUCTIVE SLEEP APNEA Brydon JB Grant, Youngmi Choi, Airani Sathananthan, Ulysses J. Magalang, Gavin B. Grant, and Ali A El-Solh. VA Healthcare System of WNY, The

More information

Modelling and Application of Logistic Regression and Artificial Neural Networks Models

Modelling and Application of Logistic Regression and Artificial Neural Networks Models Modelling and Application of Logistic Regression and Artificial Neural Networks Models Norhazlina Suhaimi a, Adriana Ismail b, Nurul Adyani Ghazali c a,c School of Ocean Engineering, Universiti Malaysia

More information

Analysis of Classification Algorithms towards Breast Tissue Data Set

Analysis of Classification Algorithms towards Breast Tissue Data Set Analysis of Classification Algorithms towards Breast Tissue Data Set I. Ravi Assistant Professor, Department of Computer Science, K.R. College of Arts and Science, Kovilpatti, Tamilnadu, India Abstract

More information

Meta-analysis of diagnostic test accuracy studies with multiple & missing thresholds

Meta-analysis of diagnostic test accuracy studies with multiple & missing thresholds Meta-analysis of diagnostic test accuracy studies with multiple & missing thresholds Richard D. Riley School of Health and Population Sciences, & School of Mathematics, University of Birmingham Collaborators:

More information

Hayden Smith, PhD, MPH /\ v._

Hayden Smith, PhD, MPH /\ v._ Hayden Smith, PhD, MPH.. + /\ v._ Information and clinical examples provided in presentation are strictly for educational purposes, and should not be substituted for clinical guidelines or up-to-date medical

More information

Outcomes: Initially, our primary definitions of pneumonia was severe pneumonia, where the subject was hospitalized

Outcomes: Initially, our primary definitions of pneumonia was severe pneumonia, where the subject was hospitalized The study listed may include approved and non-approved uses, formulations or treatment regimens. The results reported in any single study may not reflect the overall results obtained on studies of a product.

More information

Introduction to Machine Learning. Katherine Heller Deep Learning Summer School 2018

Introduction to Machine Learning. Katherine Heller Deep Learning Summer School 2018 Introduction to Machine Learning Katherine Heller Deep Learning Summer School 2018 Outline Kinds of machine learning Linear regression Regularization Bayesian methods Logistic Regression Why we do this

More information

A Practical Approach for Implementing the Probability of Liquefaction in Performance Based Design

A Practical Approach for Implementing the Probability of Liquefaction in Performance Based Design Missouri University of Science and Technology Scholars' Mine International Conferences on Recent Advances in Geotechnical Earthquake Engineering and Soil Dynamics 2010 - Fifth International Conference

More information

Predicting Breast Cancer Survival Using Treatment and Patient Factors

Predicting Breast Cancer Survival Using Treatment and Patient Factors Predicting Breast Cancer Survival Using Treatment and Patient Factors William Chen wchen808@stanford.edu Henry Wang hwang9@stanford.edu 1. Introduction Breast cancer is the leading type of cancer in women

More information

Bias and confounding. Mads Kamper-Jørgensen, associate professor, Section of Social Medicine

Bias and confounding. Mads Kamper-Jørgensen, associate professor, Section of Social Medicine Bias and confounding Mads Kamper-Jørgensen, associate professor, maka@sund.ku.dk PhD-course in Epidemiology l 7 February 2017 l Slide number 1 The world according to an epidemiologist Exposure Outcome

More information

Review. Imagine the following table being obtained as a random. Decision Test Diseased Not Diseased Positive TP FP Negative FN TN

Review. Imagine the following table being obtained as a random. Decision Test Diseased Not Diseased Positive TP FP Negative FN TN Outline 1. Review sensitivity and specificity 2. Define an ROC curve 3. Define AUC 4. Non-parametric tests for whether or not the test is informative 5. Introduce the binormal ROC model 6. Discuss non-parametric

More information

Introduction to diagnostic accuracy meta-analysis. Yemisi Takwoingi October 2015

Introduction to diagnostic accuracy meta-analysis. Yemisi Takwoingi October 2015 Introduction to diagnostic accuracy meta-analysis Yemisi Takwoingi October 2015 Learning objectives To appreciate the concept underlying DTA meta-analytic approaches To know the Moses-Littenberg SROC method

More information

Assessment of performance and decision curve analysis

Assessment of performance and decision curve analysis Assessment of performance and decision curve analysis Ewout Steyerberg, Andrew Vickers Dept of Public Health, Erasmus MC, Rotterdam, the Netherlands Dept of Epidemiology and Biostatistics, Memorial Sloan-Kettering

More information

CHAPTER 5 DECISION TREE APPROACH FOR BONE AGE ASSESSMENT

CHAPTER 5 DECISION TREE APPROACH FOR BONE AGE ASSESSMENT 53 CHAPTER 5 DECISION TREE APPROACH FOR BONE AGE ASSESSMENT The decision tree approach for BAA makes use of the radius and ulna wrist bones to estimate the bone age. From the radius and ulna bones, 11

More information

Screening (Diagnostic Tests) Shaker Salarilak

Screening (Diagnostic Tests) Shaker Salarilak Screening (Diagnostic Tests) Shaker Salarilak Outline Screening basics Evaluation of screening programs Where we are? Definition of screening? Whether it is always beneficial? Types of bias in screening?

More information

INTERPRETATION OF STUDY FINDINGS: PART I. Julie E. Buring, ScD Harvard School of Public Health Boston, MA

INTERPRETATION OF STUDY FINDINGS: PART I. Julie E. Buring, ScD Harvard School of Public Health Boston, MA INTERPRETATION OF STUDY FINDINGS: PART I Julie E. Buring, ScD Harvard School of Public Health Boston, MA Drawing Conclusions TRUTH IN THE UNIVERSE Infer TRUTH IN THE STUDY Infer FINDINGS IN THE STUDY Designing

More information

Computer Models for Medical Diagnosis and Prognostication

Computer Models for Medical Diagnosis and Prognostication Computer Models for Medical Diagnosis and Prognostication Lucila Ohno-Machado, MD, PhD Division of Biomedical Informatics Clinical pattern recognition and predictive models Evaluation of binary classifiers

More information

PRINCIPLES OF EFFECTIVE MACHINE LEARNING APPLICATIONS IN REAL-WORLD EVIDENCE

PRINCIPLES OF EFFECTIVE MACHINE LEARNING APPLICATIONS IN REAL-WORLD EVIDENCE PRINCIPLES OF EFFECTIVE MACHINE LEARNING APPLICATIONS IN REAL-WORLD EVIDENCE Prepared and Presented by: Gorana Capkun-Niggli, PhD, Global Head of Innovation, Health Economics and Outcomes Research, Novartis,

More information

DIABETIC RISK PREDICTION FOR WOMEN USING BOOTSTRAP AGGREGATION ON BACK-PROPAGATION NEURAL NETWORKS

DIABETIC RISK PREDICTION FOR WOMEN USING BOOTSTRAP AGGREGATION ON BACK-PROPAGATION NEURAL NETWORKS International Journal of Computer Engineering & Technology (IJCET) Volume 9, Issue 4, July-Aug 2018, pp. 196-201, Article IJCET_09_04_021 Available online at http://www.iaeme.com/ijcet/issues.asp?jtype=ijcet&vtype=9&itype=4

More information

Evidence-Based Medicine Journal Club. A Primer in Statistics, Study Design, and Epidemiology. August, 2013

Evidence-Based Medicine Journal Club. A Primer in Statistics, Study Design, and Epidemiology. August, 2013 Evidence-Based Medicine Journal Club A Primer in Statistics, Study Design, and Epidemiology August, 2013 Rationale for EBM Conscientious, explicit, and judicious use Beyond clinical experience and physiologic

More information

MS&E 226: Small Data

MS&E 226: Small Data MS&E 226: Small Data Lecture 10: Introduction to inference (v2) Ramesh Johari ramesh.johari@stanford.edu 1 / 17 What is inference? 2 / 17 Where did our data come from? Recall our sample is: Y, the vector

More information

TABLE OF CONTENTS CHAPTER NO. TITLE PAGE NO. ABSTRACT

TABLE OF CONTENTS CHAPTER NO. TITLE PAGE NO. ABSTRACT vii TABLE OF CONTENTS CHAPTER NO. TITLE PAGE NO. ABSTRACT LIST OF TABLES LIST OF FIGURES LIST OF SYMBOLS AND ABBREVIATIONS iii xi xii xiii 1 INTRODUCTION 1 1.1 CLINICAL DATA MINING 1 1.2 OBJECTIVES OF

More information

CSE 255 Assignment 9

CSE 255 Assignment 9 CSE 255 Assignment 9 Alexander Asplund, William Fedus September 25, 2015 1 Introduction In this paper we train a logistic regression function for two forms of link prediction among a set of 244 suspected

More information

S4. Summary of the GALNS assay validation. Intra-assay variation (within-run precision)

S4. Summary of the GALNS assay validation. Intra-assay variation (within-run precision) S4. Summary of the GALNS assay validation (i.) Intra-assay variation (within-run precision) Intra-assay variation was determined by measuring standard blood samples (low activity standard; medium activity

More information

Sensitivity, Specificity, and Relatives

Sensitivity, Specificity, and Relatives Sensitivity, Specificity, and Relatives Brani Vidakovic ISyE 6421/ BMED 6700 Vidakovic, B. Se Sp and Relatives January 17, 2017 1 / 26 Overview Today: Vidakovic, B. Se Sp and Relatives January 17, 2017

More information

BIOSTATISTICAL METHODS

BIOSTATISTICAL METHODS BIOSTATISTICAL METHODS FOR TRANSLATIONAL & CLINICAL RESEARCH PROPENSITY SCORE Confounding Definition: A situation in which the effect or association between an exposure (a predictor or risk factor) and

More information

Statistics, Probability and Diagnostic Medicine

Statistics, Probability and Diagnostic Medicine Statistics, Probability and Diagnostic Medicine Jennifer Le-Rademacher, PhD Sponsored by the Clinical and Translational Science Institute (CTSI) and the Department of Population Health / Division of Biostatistics

More information

Predictive Models for Making Patient Screening Decisions

Predictive Models for Making Patient Screening Decisions Predictive Models for Making Patient Screening Decisions MICHAEL HAHSLER 1, VISHAL AHUJA 1, MICHAEL BOWEN 2, AND FARZAD KAMALZADEH 1 1 Southern Methodist University, 2 UT Southwestern Medical Center and

More information

Panel: Machine Learning in Surgery and Cancer

Panel: Machine Learning in Surgery and Cancer Panel: Machine Learning in Surgery and Cancer Professor Dimitris Bertsimas, SM 87, PhD 88, Boeing Leaders for Global Operations Professor of Management; Professor of Operations Research; Co-Director, Operations

More information

Analysis of Diabetic Dataset and Developing Prediction Model by using Hive and R

Analysis of Diabetic Dataset and Developing Prediction Model by using Hive and R Indian Journal of Science and Technology, Vol 9(47), DOI: 10.17485/ijst/2016/v9i47/106496, December 2016 ISSN (Print) : 0974-6846 ISSN (Online) : 0974-5645 Analysis of Diabetic Dataset and Developing Prediction

More information

Efficient AUC Optimization for Information Ranking Applications

Efficient AUC Optimization for Information Ranking Applications Efficient AUC Optimization for Information Ranking Applications Sean J. Welleck IBM, USA swelleck@us.ibm.com Abstract. Adequate evaluation of an information retrieval system to estimate future performance

More information

Zheng Yao Sr. Statistical Programmer

Zheng Yao Sr. Statistical Programmer ROC CURVE ANALYSIS USING SAS Zheng Yao Sr. Statistical Programmer Outline Background Examples: Accuracy assessment Compare ROC curves Cut-off point selection Summary 2 Outline Background Examples: Accuracy

More information

VU Biostatistics and Experimental Design PLA.216

VU Biostatistics and Experimental Design PLA.216 VU Biostatistics and Experimental Design PLA.216 Julia Feichtinger Postdoctoral Researcher Institute of Computational Biotechnology Graz University of Technology Outline for Today About this course Background

More information

Rapid appraisal of the literature: Identifying study biases

Rapid appraisal of the literature: Identifying study biases Rapid appraisal of the literature: Identifying study biases Rita Popat, PhD Clinical Assistant Professor Division of Epidemiology Stanford University School of Medicine August 7, 2007 What is critical

More information

Evidence-Based Medicine: Diagnostic study

Evidence-Based Medicine: Diagnostic study Evidence-Based Medicine: Diagnostic study What is Evidence-Based Medicine (EBM)? Expertise in integrating 1. Best research evidence 2. Clinical Circumstance 3. Patient values in clinical decisions Haynes,

More information

Biomarker adaptive designs in clinical trials

Biomarker adaptive designs in clinical trials Review Article Biomarker adaptive designs in clinical trials James J. Chen 1, Tzu-Pin Lu 1,2, Dung-Tsa Chen 3, Sue-Jane Wang 4 1 Division of Bioinformatics and Biostatistics, National Center for Toxicological

More information

Lecture 13: Finding optimal treatment policies

Lecture 13: Finding optimal treatment policies MACHINE LEARNING FOR HEALTHCARE 6.S897, HST.S53 Lecture 13: Finding optimal treatment policies Prof. David Sontag MIT EECS, CSAIL, IMES (Thanks to Peter Bodik for slides on reinforcement learning) Outline

More information

Leveraging Pharmacy Medical Records To Predict Diabetes Using A Random Forest & Artificial Neural Network

Leveraging Pharmacy Medical Records To Predict Diabetes Using A Random Forest & Artificial Neural Network Leveraging Pharmacy Medical Records To Predict Diabetes Using A Random Forest & Artificial Neural Network Stephen Lavery 1 and Jeremy Debattista 2 1 National College of Ireland, Dublin, Ireland, laverys@tcd.ie

More information

Predictive Models: Current and Future. November 9, Steve Wickstrom Vice President, Research and Methods OptumInsight

Predictive Models: Current and Future. November 9, Steve Wickstrom Vice President, Research and Methods OptumInsight Predictive Models: Current and Future November 9, 2011 Steve Wickstrom Vice President, Research and Methods OptumInsight Steven.wickstrom@optum.com OptumInsight Predictive Solutions: Overview OptumInsight

More information

An Empirical Assessment of Bivariate Methods for Meta-analysis of Test Accuracy

An Empirical Assessment of Bivariate Methods for Meta-analysis of Test Accuracy Number XX An Empirical Assessment of Bivariate Methods for Meta-analysis of Test Accuracy Prepared for: Agency for Healthcare Research and Quality U.S. Department of Health and Human Services 54 Gaither

More information

Supplementary Online Content

Supplementary Online Content Supplementary Online Content Pincus D, Ravi B, Wasserstein D. Association between wait time and 30-day mortality in adults undergoing hip fracture surgery. JAMA. doi: 10.1001/jama.2017.17606 eappendix

More information

UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Final, Fall 2014

UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Final, Fall 2014 UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Final, Fall 2014 Exam policy: This exam allows two one-page, two-sided cheat sheets (i.e. 4 sides); No other materials. Time: 2 hours. Be sure to write

More information

Classification with microarray data

Classification with microarray data Classification with microarray data Aron Charles Eklund eklund@cbs.dtu.dk DNA Microarray Analysis - #27612 January 8, 2010 The rest of today Now: What is classification, and why do we do it? How to develop

More information

CS2220 Introduction to Computational Biology

CS2220 Introduction to Computational Biology CS2220 Introduction to Computational Biology WEEK 8: GENOME-WIDE ASSOCIATION STUDIES (GWAS) 1 Dr. Mengling FENG Institute for Infocomm Research Massachusetts Institute of Technology mfeng@mit.edu PLANS

More information

Tactile Internet and Edge Computing: Emerging Technologies for Mobile Health

Tactile Internet and Edge Computing: Emerging Technologies for Mobile Health Tactile Internet and Edge Computing: Emerging Technologies for Mobile Health Zaher Dawy, PhD Department of Electrical and Computer Engineering American University of Beirut http://www.aub.edu.lb/~zd03

More information

Empirical assessment of univariate and bivariate meta-analyses for comparing the accuracy of diagnostic tests

Empirical assessment of univariate and bivariate meta-analyses for comparing the accuracy of diagnostic tests Empirical assessment of univariate and bivariate meta-analyses for comparing the accuracy of diagnostic tests Yemisi Takwoingi, Richard Riley and Jon Deeks Outline Rationale Methods Findings Summary Motivating

More information

sickness, disease, [toxicity] Hard to quantify

sickness, disease, [toxicity] Hard to quantify BE.104 Spring Epidemiology: Test Development and Relative Risk J. L. Sherley Agent X? Cause Health First, Some definitions Morbidity = Mortality = sickness, disease, [toxicity] Hard to quantify death Easy

More information

Lecture Outline Biost 517 Applied Biostatistics I. Statistical Goals of Studies Role of Statistical Inference

Lecture Outline Biost 517 Applied Biostatistics I. Statistical Goals of Studies Role of Statistical Inference Lecture Outline Biost 517 Applied Biostatistics I Scott S. Emerson, M.D., Ph.D. Professor of Biostatistics University of Washington Statistical Inference Role of Statistical Inference Hierarchy of Experimental

More information

Learning Decision Trees Using the Area Under the ROC Curve

Learning Decision Trees Using the Area Under the ROC Curve Learning Decision rees Using the Area Under the ROC Curve Cèsar erri, Peter lach 2, José Hernández-Orallo Dep. de Sist. Informàtics i Computació, Universitat Politècnica de València, Spain 2 Department

More information

Types of Biomedical Research

Types of Biomedical Research INTRODUCTION & MEASUREMENT IN CLINICAL RESEARCH Sakda Arj Ong Vallipakorn, MD MSIT, MA (Information Science) Pediatrics, Pediatric Cardiology Emergency Medicine, Ped Emergency Family Medicine Section of

More information