HAP 464: EHR Configuration & Data Analysis

Likelihood of Response to Antidepressants

George Mason University

Assigned Reading

Background Reading

  1. Read "Introduction to Probability", pages 55 to 75 in required course textbook

Reading on Risk Assessment:

  1. Read "Risk Assessment", pages 101-133 in required course textbook

Other Learning Materials:

  1. Conditional probability Slides► YouTube►
  2. Likelihood ratio Slides► YouTube►
  3. Selecting the right predictors Slides► YouTube►
  4. SQL for calculating likelihood ratios Slides► YouTube►

Assignment for Scoring Multi-Morbidity Index

Instruction for Submission of Assignments: Assignments should be submitted directly on Blackboard.  In rare situations assignments can be sent directly by email to the instructor. Submission should follow these rules:

  1. Indicate in a summary statement if you have obtained the answers posted for the assignments.
  2. Submit your answers in a Jupyter Notebook Download► YouTube► Slides►
  3. Submit you answers in Blackboard.

Task 1: Clean the data in All of Us project by removing (1) patients who have negative age, and (2) repeated diagnoses for the same patient at same age. Provide the number of records left in the data after this two corrections are made.

Task 2: For the patient in the cleaned data in Task 1, calculate the likelihood ratios associated with response to antidepressants. 

  • Massive patient data (see Task 1)   
  • In required textbook see pages 66 to 68 for introduction to concept of likelihood ratios.  See section on "Contingency Tables and Likelihood Ratios"
  • In the required textbook examine code for calculation of likelihood ratios in Appendix 5.1 pages 125 to 132
  • Grace Buck's Teach One Slides► YouTube►
  • Saini's Teach One Slides► YouTube►
  • Rajan Atwal's Teach One Slides► YouTube►

Task 3: What is the assumption we make when we multiply likelihood ratios associated with patients medical history.


Copyright 2021 Farrokh Alemi, Ph.D. Most recent revision 01/06/2024.  This page is part of the course on Electronic Health Record Configuration and Data Analysis.