An R-based machine learning workflow with applications in personalized medicine - Thesis

Aug 2, 2026

This creative component presents an end-to-end R-based machine learning workflow designed to support personalized medicine use cases. The work covers data understanding through source description, exploratory data analysis, and data summarization, then proceeds to model building using the tidymodels ecosystem. Model assessment emphasizes performance evaluation with ROC and AUC along with residual diagnostics. Interpretation is strengthened via variable importance, partial dependence profiles, and local explanations, followed by deployment using a Shiny application.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages32

Reading Time1 h 21 min

AccessFree to download

Table of Contents

List of Tables

List of Figures

Acknowledgments

Abstract

Chapter 1. Introduction

Chapter 2. Data Understanding

2.1 Data Source

2.2 Exploratory Data Analysis

2.3 Data Summary

Chapter 3. Model Building

3.1 Tidymodels Overview

3.2 Modeling Procedure

Chapter 4. Model Assessment

4.1 ROC and AUC

4.2 Residual Diagnostics

Chapter 5. Model Interpretation

5.1 Variable Importance

5.2 Partial Dependence Profiles

5.3 Local Interpretation

Chapter 6. Model Deployment

Chapter 7. Conclusion

References

An R-based machine learning workflow with applications in personalized medicine by Ashirwad Barnwal A creative component submitted to the graduate faculty in partial fulfillment of the requirements for the degree of MASTER OF SCIENCE Major: Statistics Program of Study Committee: Stephen Vardeman, Co-major Professor Daniel Nordman, Co-major Professor Anuj Sharma Soumik Sarkar The student author, whose presentation of the scholarship herein was approved by the program of study committee, is solely responsible for the content of this creative component. The Graduate College will ensure this creative component is globally accessible and will not permit alterations after a degree is conferred. Iowa State University Ames, Iowa 2023 Copyright © Ashirwad Barnwal, 2023. All rights reserved. ii DEDICATION I would like to dedicate this creative component to my parents, to my sisters Aditi and Anushka, and to my wife Anchala without whose support I would not have been able to complete this work. iii TABLE OF CONTENTS Page LIST OF TABLES .......................................... iv LIST OF FIGURES ......................................... v [ACKNOWLEDGMENTS ...................................... vi](ACKNOWLEDGMENTS ...................................... vi) [ABSTRACT ............................................. vii](ABSTRACT ............................................. vii) [CHAPTER 1. INTRODUCTION ................................. 1](CHAPTER 1. INTRODUCTION ................................. 1) [CHAPTER 2. DATA UNDERSTANDING ............................ 2](CHAPTER 2. DATA UNDERSTANDING ............................ 2) [2.1 Data Source ......................................... 2](2.1 Data Source ......................................... 2) [2.2 Exploratory Data Analysis ................................. 3](2.2 Exploratory Data Analysis ................................. 3) [2.3 Data Summary ....................................... 5](2.3 Data Summary ....................................... 5) [CHAPTER 3. MODEL BUILDING ................................ 10](CHAPTER 3. MODEL BUILDING ................................ 10) [3.1 Tidymodels Overview ................................... 10](3.1 Tidymodels Overview ................................... 10) [3.2 Modeling Procedure .................................... 11](3.2 Modeling Procedure .................................... 11) [CHAPTER 4. MODEL ASSESSMENT .............................. 13](CHAPTER 4. MODEL ASSESSMENT .............................. 13) [4.1 ROC and AUC ....................................... 13](4.1 ROC and AUC ....................................... 13) [4.2 Residual Diagnostics .................................... 13](4.2 Residual Diagnostics .................................... 13) [CHAPTER 5. MODEL INTERPRETATION ........................... 16](CHAPTER 5. MODEL INTERPRETATION ........................... 16) [5.1 Variable Importance .................................... 16](5.1 Variable Importance .................................... 16) [5.2 Partial Dependence Profiles ................................ 18](5.2 Partial Dependence Profiles ................................ 18) [5.3 Local Interpretation .................................... 19](5.3 Local Interpretation .................................... 19) [CHAPTER 6. MODEL DEPLOYMENT ............................. 22](CHAPTER 6. MODEL DEPLOYMENT ............................. 22) [CHAPTER 7. CONCLUSION ................................... 24](CHAPTER 7. CONCLUSION ................................... 24) [REFERENCES ............................................ 25](REFERENCES ............................................ 25) iv LIST OF TABLES Page Table 2.1 Cross table of treatments assigned to patients ................. 6 Table 2.2 Cross table of treatment by outcome ...................... 6 Table 2.3 Descriptive statistics for predictor

FAQs

What are the main stages of the R-based machine learning workflow described in the document?

The document follows data understanding, model building, model assessment, model interpretation, and model deployment.

How does the document assess model performance?

Performance is evaluated using ROC and AUC, and residual diagnostics are used to examine model fit through residual behavior.

What tools and methods are used for model interpretation and deployment?

Interpretation uses variable importance, partial dependence profiles, and local explanations, while deployment is implemented with a Shiny app.

Aug 2, 2026

Upload by Emma Wilson