clinical-machine-learning

Early warning for sepsis with a calibrated alert budget. It states how often it will alert and how often it will be right, then checks both on a hospital it never trained on. Open data, no credentials, every number reproducible.

Research project on missing data, calibration, and trustworthy prediction in clinical machine learning.

Independent research project investigating feature reliability in machine learning prediction of cognitive impairment from sleep-derived physiological signals.

Retrospective feasibility study and research pipeline for short-horizon ICU hypotension forecasting using ABP, ECG, PPG, and EHR context, with leakage-aware evaluation and sensor-missingness robustness tests.

A-ICF: Auditing, Not Predicting — A Causal Bias-Decomposition Framework for Clinical Fairness. Code, Figures, and Tables for OMLET 2026 (Paper ID: 596).

Research collaboration on explainable federated learning for predicting cardiac complications following THA/TKA.

Selective prediction for fetal ultrasound plane classification by pairing a ResNet-18 with diffusion reconstruction uncertainty and softmax confidence for calibrated human-AI deferral. Includes an honest ablation of uncertainty methods.

Classifying joint-angle gait dynamics under bracing conditions with ML and deep learning: Random Forest, HMM, LSTM, ST-GCN.

This repository contains the data and analysis code for the study "Machine Learning-driven biomarker discovery for stratifying treatment response in tick-borne illness". It investigates the identification of robust and reproducible baseline predictors of treatment response using a stability-aware, multi-method machine learning framework.

Research code for the published study on recurrent lumbar disc herniation after lumbar discectomy. Journal of Korean Neurosurgical Society · DOI: 10.3340/jkns.2025.0120.

Open, reproducible implementation of the CMS Hospital-Wide Readmission (HWR) measure on MIMIC-IV: faithful 30-day unplanned-readmission labels, a calibrated gradient-boosted baseline with fairness and drift monitoring, and a leakage-controlled test of whether clinical-note LLM embeddings add signal.

Auditable clinical tabular benchmark for hospital and measurement-policy shift, with reconstructable evidence and explicit claim boundaries.

Auditable EHR data infrastructure for patient world models and clinical agents: source-linked conversion of hospital exports into OMOP CDM 5.4 and MEDS, with 55 checks that read the published artifacts