Real engineering problems, measurable outcomes, and production results — spanning AI research, ML systems, and full-stack. Each entry has a deeper case study explaining the architecture and the decisions behind it.
★ Featured · Published
DiabetesSense
93% accurate clinical risk scoring with SHAP interpretability
Built at COMSATS — Random Forest + Gradient Boosting ensemble on clinical data, with SHAP TreeExplainer surfacing feature attribution to clinicians. React.js + Flask frontend for real-time risk scoring.