I supervise several hundred cardiac stress tests a year and interpret the ECGs that come out of them. These projects are what happens when that clinical judgment meets code.
Lead II · 100 Hz · sinus rhythm at 60 bpm
Background
I am an ACSM Certified Clinical Exercise Physiologist at UW Medicine, where I direct exercise stress echocardiograms and treadmill tests for high-risk cardiac patients. Day to day that means interpreting arrhythmias and conduction abnormalities, screening for contraindications, and deciding in real time whether a test continues.
I hold a master's in clinical exercise physiology and am completing a master's in information management with an emphasis in data science at the University of Washington. The projects below are where clinical knowledge and data science intersect. I understand these problems from the bedside, and I am building the methods to solve them rigorously.
A machine learning system that reads an ECG and flags what warrants a clinician's attention. Version one detects atrial fibrillation; the roadmap extends to ischemic ST changes, conduction abnormalities, and ECGs captured as photographs.
Hospitals now publish what they charge. This project joins those rates to utilization data to estimate what cardiac diagnostics actually earn, and where hospitals negotiated below their peers.