“NPC-based risk stratification model for necrotizing fasciitis using bootstrap and permutation methods.”

Real-time clinical risk stratification system using multi-factor analysis, vital sign monitoring, and machine learning for intelligent healthcare decision support.

Machine Learning for Patient Risk Stratification for Acute Respiratory Distress Syndrome (Zeiberg & Prahlad et al.), PLOS ONE, March 2019. https://doi.org/10.1371/journal.pone.0214465

Colorectal cancer risk mapping through Bayesian Networks

Real-world hemodialysis data analysis focused on intradialytic hypotension, clinical risk patterns, and patient-level hemodynamic phenotyping.

Presentation on risk stratification model

AI-powered Early Childhood Development Intelligence Platform for risk stratification, predictive insights, and personalized intervention planning. Built for scalable public health governance with role-based decision support, longitudinal tracking, and secure, explainable AI architecture.

A worked example to support the e-Learning for Health (e-LfH) PHM Risk Stratification Module.

Portfolio project: Clinical risk stratification & population health analytics using Python and Pandas.

Discovering healthcare insights through data-driven analysis of EHRs. This project comprises three subprojects: data cleaning & preparation, exploratory data analysis and lastly, predictive modeling for in-hospital mortality and clinical risk stratification.

Healthcare analytics system identifying hospitals at risk for CMS readmission penalties. Analyzes $5.96B in financial exposure, predicts intervention opportunities, saves $1.46B. Python • scikit-learn • CMS data • Healthcare policy

Capacity-aware hospital readmission prioritization with calibrated ML, workflow simulation, fairness analysis, and a Streamlit demo.

This repository features a high-integrity machine learning pipeline developed to assist clinical researchers in stratifying patient risk for lung cancer. By utilizing an optimized Logistic Regression framework and UMAP, the project emphasizes model interpretability—a critical requirement for clinical validation and regulatory transparency.

Interpretable medical cost risk model with explainable analytics, fairness evaluation, and Jupyter notebooks

Transformer-based non-communicable disease risk stratification using longitudinal IHME GBD (47M rows), WHO expenditure, and World Bank socioeconomic indicators

A Python toolkit (riskaudit) to audit any healthcare risk-stratification model for label-choice bias - how much real need it leaves behind when trained on cost. Reproduces the Obermeyer et al. (2019) audit; worked example on MEPS.

METABRIC breast cancer survival analysis & ML workflow. Features KM curves, Cox models, Decision Trees, RFs, risk calibration, and Decision Curve Analysis.

Hypertension Risk Stratification Using Machine Learning: Lift-Based Evaluation on SAS® Viya With the Framingham Heart Study

A data analytics project analyzing healthcare cost drivers and patient risk factors, built with SQL, Python, and an interactive Plotly Dash dashboard.

AI Clinical Decision Support System for Risk Stratification and Differential Diagnosis using NEWS2, CURB,ect. Streamlit-based Digital Health AI prototype.