CoolFace
Apppublic

tcmhwd/bsi-mortality-demo

sourceHugging Faceotherupdated 4mo agoView on Hugging Face
3likes
App README

BSI 30-Day Mortality Prediction — Research Demo

⚠ Research Demonstration Only — Not for clinical use.

Reviewer demo for a comparative study of structured ML and RAG-LLM approaches to 30-day mortality prediction in bloodstream infection (BSI).

Modes

TabDescription
Mode AStructured prediction via TabM (early arm) or XGBoost (AST-informed arm)
Mode BBrowse cached LLM explanations for 10 representative de-identified patients
Mode CLive LLM inference — disabled in public demo

Data

  • —External validation cohort only (Hospital 20, de-identified)
  • —10 representative patients spanning all risk bands and both outcomes
  • —No raw patient data beyond the 10 curated demo cases is included

Models

  • —TabM (early arm): deep learning tabular model, Optuna-tuned
  • —XGBoost (AST-informed arm): gradient boosting with microbiological features
  • —RAG-LLM: OpenAI embeddings + FAISS retrieval + GPT inference (cached)