User Tools

Site Tools



The widespread adoption of electronic health records (EHRs) has created a new source of “big data”—namely, the record of routine clinical practice—as a by-product of care. This graduate class will teach you how to use EHR and other patient data for better healthcare.

The course has 20 lectures. The first 8 lectures will review the primary sources of healthcare data, their advantages and limitations, methods to transform the raw data into an analysis substrate, and the use of ontologies in data-mining. The remaining lectures will review several problem areas and analysis methods used in that problem area ending with home work and assigned readings. In addition, there are 8 discussion sections that provide in depth explanation of the methods referred to in the lectures. For 2017, the discussions will NOT be recorded and will be used to hone our skills in critical reading of recent publications related to the topics covered in class.

The course will use real, de-identified, large size patient datasets for home work projects associated with the course. This course is also offered in a 2 credit version (BIOMEDIN 225) which meets at the same time but requires only one home work, which uses public data.

Prerequisites: CS 106A; familiarity with statistics and biology.
Highly recommended: STATS 216.
Recommended: one of CS 246, STATS 305, HRP 258 or CS 229.

Schedule and Syllabus

Schedule: TUE, THU 1:30 PM - 2:50 PM
Lectures: Gates B3 (Fall 2017). Lectures are recorded
Videos: (posted about two hours after the class ends)
Discussion Sections: Some Wednesdays 12 - 1 PM, in MSOB room 275 (see class announcements)
Office hours: Fridays 11:00 AM - 12:30 PM, in MSOB X237

TAs: Alejandro Schuler (aschuler AT, Stephen Pfohl (spfohl AT, Craig Smail (csmail AT

If nothing shows up in the space below, reload the page

Course Materials

Miscellaneous References

biomedin215.txt · Last modified: 2017/08/17 09:42 by nigam