|
|
Generated by ChatGPT
Overview
Objectives
- Identify algorithm bias through hierarchical analysis
- Remove algorithm bias through conditional models
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:
- De-biasing algorithm for African Americans' response to
antidepressants
Read► (use instructor's last name as the password)
Instruction for Submission of Assignments: Submission
should follow these rules:
- Include a statement naming the project manager who has examined your
report and indicated that it was done on time.
- Submit your answers in a Jupyter Notebook
Download►
YouTube►
Slides►
- Submit you answers in Canvas.
Task 1: Using your All of Us database, predict response
to antidepressants among a subgroup of participants (e.g. Hispanics) in All of Us
database. Conduct the analysis in two steps:
-
Describe the Population. In this step you need to
create Table 1 in your eventual report. This Table should include
the description of the population. For examples of Table 1 see
PubMed. Provide a summary of your data that includes number of
antidepressants examined, number of individuals involved, number of
antidepressants discontinued, number of days individuals followed,
number of days antidepressants continued, number of medical conditions
at baseline of use of antidepressants, number of antidepressants used
prior to baseline, experience with previous antidepressants.
-
Fit a Regression Models in Subgroups of Data:
Select a subgroup in which you would like to remove algorithm bias.
Identify the number of cases, the percent in remission, and examine the
accuracy of risk neutral model. When appropriate increase the
accuracy of the AI system by using different models for different
subgroups of patients.
Task 2: Write the method section of your semester long
project report
|
