SHAHID||Portfolio
A collection of end-to-end AI systems and analytical platforms designed to solve high-stakes challenges.
Engineered a high-precision deep learning model using PyTorch to classify respiratory diseases from chest X-rays with state-of-the-art accuracy. Implemented XAI techniques to interpret the model's predictions, providing insights into the decision-making process.
An Integrated eXplainable Clinical Decision Support System (X-CDSS) for Precision Cardiovascular Risk Assessment. CardioSense AI demonstrates the perceived tradeoff between accuracy and interpretability is a false dichotomy. Post-hoc attribution (SHAP) alongside a high-capacity model (XGBoost) achieves state-of-the-art accuracy with full clinical transparency.
Developed a predictive diagnostic tool using Scikit-learn, deploying the model via a professional Streamlit command center for real-time support.
An interactive sales intelligence dashboard using Dash & Plotly to visualize historical trends and forecast future product demand cycles.
Architected a secure database platform to manage criminal records, implementing full CRUD with optimized SQL systems.
Advanced regression on Ames Housing dataset, conducting extensive EDA to uncover key market drivers and price sensitivities.