Machine Learning in Healthcare (no coding required!)

Course Curriculum

Chapter 1: Introduction

Lecture 1: Course Structure

Lecture 2: Case study

Chapter 2: Health data 101

Lecture 1: Health Insurance claims

Lecture 2: Electronic health records

Lecture 3: Research reports

Lecture 4: Public health

Lecture 5: Wearables

Lecture 6: Structured data

Lecture 7: Unstructured data

Lecture 8: Features of data – Hierarchical Diagnoses

Lecture 9: Features of data – Hierarchical Drugs

Lecture 10: Features of data – Hierarchical Procedures

Lecture 11: Features of data – Hierarchical LOINCs and other

Lecture 12: Disease Etiology, Chronology, Supply vs Demand

Lecture 13: Errors and error handling

Chapter 3: Logistics of machine learning

Lecture 1: Steps to Predictive Modeling

Lecture 2: Planning the analysis

Lecture 3: Getting Buy in for the analysis

Lecture 4: Data use considerations

Chapter 4: Data preparation and Feature engineering

Lecture 1: Initial exploration of the data

Lecture 2: Data preparation

Lecture 3: Feature engineering

Lecture 4: From raw data to training dataset

Chapter 5: Statistical Primer

Lecture 1: Statistical Primer intro

Lecture 2: Logistic regression – intro

Lecture 3: Logistic regression Pros and Cons

Lecture 4: Bias Variance trade off

Lecture 5: Decision tree

Lecture 6: Random forest

Lecture 7: Neural net

Chapter 6: Machine learning in Healthcare – case study

Lecture 1: Intro to KNIME

Lecture 2: Model training in KNIME

Chapter 7: Model assessment and Output

Lecture 1: Cross validation

Lecture 2: Sensitivity vs Specificity

Lecture 3: Cross validation in KNIME

Lecture 4: Sensitivity/Scenario testing

Lecture 5: Presenting the results

Lecture 6: Implementation and Future improvements

Lecture 7: Practice practice practice!

Chapter 8: Bonus Sections

Lecture 1: 5 key elements of health insurance products

Lecture 2: Intro to the Payors lines of business (health insurers)

Lecture 3: Health data 101 – Health Insurance Claims