Django, Python, and Health Care Data
summary
Uses electronic health record and claims data with regression and machine learning to predict postdischarge risk and guide placement. D2S2 scores use six factors — age walking ability length of stay comorbid count depression and self rated health — and implementation via Right Care Solutions shows reduced 30 and 60 day readmissions. About one quarter of recommended patients refuse postacute care. Predictive diabetes and hospitalization models move to prospective testing; visualization and tooling use Python and Django and projects like Dr. Chrono and Open Data Philly appear.
AI-written summary · about
chapters (7)
- 0:00Introduction and background
- 2:29Working with older adults
- 3:27Healthcare data sources
- 6:42Discharge decision support
- 13:02Understanding care refusal
- 16:15Predictive analytics projects
- 19:07Open data and tech tools
related talks
31mDjango for life (sciences)
41mFootball's data analytics in python
24mDjango as a Database Documentation Tool: The Hidden Power... with Ryan Cheley
16mBrazil: How we are gaining space with Django
36mPython in Medicine: analysing data from mechanical...
47mCreating a Contemporary Risk Management System Using Python
21mConnecting Patients to Doctors in Real-Time Using Django
20mMachine Learning in Cardiology