HAP 786: Workshop in Health Informatics

Lecture: Advice System

 
  Home  
 

Analyze antidepressant data
Generated by ChatGPT

Overview

Objectives

  1. Analyze data using one of the methods of health informatics program
  2. Review work done in prior classes

Assigned Reading

The reading material for this section of the course come from your previous courses and depend on the method you choose to use.  In analyzing response to antidepressants we use regression models derived from the knowledgebase of the AI system:

  1. Overview on progress in creating an AI system for management of depression Slides► Video► YouTube►
  2. EHR Augmented Knowledgebase for AI inferences
    • Sample knowledgebase for calculating likelihood of outcomes Download►
  3. The Medical Artificial General Knowledge (MAGI) algorithms
    • Sign and return by email to instructor the NDA agreement Download►
    • Description of MAGI algorithm and an example application Download►
  4. Background information
    • Learning network models through regressions Slides► Narrated slides► Video► YouTube►
    • SAFE procedure allows discarding a large number of variables prior to LASSO regression Read►
    • SAFE procedure using likelihood ratios Slides► Video►
    • Predicting response to antidepressants in general population PubMed►
    • Source Code Part 2: Adding AI Predictors, Generating Prediction, and Executing Regressions PDF►
    • Reference regression coefficients for predicting response to antidepressants  CSV►
    • Divya Bhavanam's Teach One on predicting from the AI system and All of Us data YouTube►
    • Reduce computational and memory problems in All of Us data analysis YouTube►

Assignment

Instruction for Submission of Assignments: Submission should follow these rules:

  1. Include a statement by the project manger that submission is correct and assignments was done on time
  2. Submit your answers in a Jupyter Notebook Download► YouTube► Slides►
  3. Submit you answers in Canvas.

Task 1

Predict response to citalopram for a patient that presents with following medical history:

Patient's Expressions and Matched Medical History Events
Matched Code What the Patient Said Short Name
px_CPT4_0025T "I had a test to measure the thickness of both my corneas, and the doctor reviewed the results." Cornea
dx_SNOMED_47639008 "I had a cyst near my tailbone." Cyst
px_CPT4_00840 "They gave me anesthesia for a lower abdominal surgery, but I’m not sure what kind.” Anesthesia
aa_meas_citalopram_rem "Citalopram helped improve my mood." Response

Resources for Task 1:

  • The sample MAGI knowledgebase is available here: Download►
  • Sign and return by email to instructor the NDA agreement Download►
  • Description of MAGI algorithm with example calculations Download►

Task 2

Write the method section of your final project report  Write the result section of your final project report.

 

 

Farrokh Alemi, Ph.D. Most recent revision 06/09/2025.  This page is part of the course on Workshop in Health Informatics