Bayesian Risk Analysis For Large Multi-Modal Data
summary
Claims concrete results: wastewater SEIR models estimate transmission parameters using viral loads and reported cases; 47,000 long COVID cases are matched one-to-one with controls and a Bayesian log‑normal survival GLM via MCMC finds a distinguishable survival decrement; a Bayesian hierarchical model on ~800,000 COVID‑associated ED visits from 54 sites (N3C has >22M patients, 33B rows) reveals underrepresented race/ethnicity groups are less likely to be hospitalized. Tools: hidden Markov/compartment models, MCMC, hierarchical priors, multimodal EHR sources.
AI-written summary · about
related talks
30mDisease Modeling with Scipy and PyMC
01h 24mBayesianism and Survival Analysis
27mBeyond a Machine Learning Model
31mCounterfactual Analysis with Bayesian Models
19mArya
04mINTERVIEW
28mThe COVID Scenario Pipeline: High Stakes Data Science
53mAre We Measuring the Right Thing? Distribution Shift Lessons for Federated Learning