This repository contains the materials for Day 2 and Day 4 of the short course EPID731: Analysis Of Electronic Health Record (EHR) Data, offered at the University of Michigan.
For a detailed guide on setting up your environment (for R and Python), navigating the repository, and using the materials in Google Colab, please see the Crash Course Guide. This guide provides step-by-step instructions, links to external tutorials, and other useful information to get you started.
The materials for Day 2 focus on accessing and analyzing EHR data using the R programming language. The Jupyter Notebook Day2/EPID731_Accessing_EHR_Data.ipynb provides a hands-on introduction to this topic. A bonus notebook, Day2/EPID731_BonusWhiteRabbit.ipynb, provides a tutorial on using the White Rabbit tool for data quality assessment.
Note for Live Session: Participants should open the notebook in Google Colab by clicking the link above or the "Open in Colab" badge at the top of the notebook.
The focus of Day 4, taught by Lars Fritsche, is on using Generative Pre-trained Transformers (GPTs) to harmonize medication data. The materials include:
- A Jupyter Notebook (
Day4/EPID731_Medication_Classification_with_OpenAI_GPT_API.ipynb) that demonstrates how to use the OpenAI GPT API for medication classification. - Python scripts for batch processing of medication data.
- Example configuration files, prompts, and input data.
Note for Live Session: Participants should open the notebook in Google Colab by clicking the link above or the "Open in Colab" badge at the top of the notebook.
This short course offers an overview of modern analytical methods and research applications using EHR data, with a specific focus on epidemiologic inferences.