A clinical-grade malaria parasite detection system using YOLOv8 object detection with 99.14% mAP50 performance.

This repository provides a compact RAG evaluation harness tailored for clinical + genomic use cases. It operates on de-identified synthetic notes and curated genomic snippets, measures retrieval quality and grounding/faithfulness, and produces JSONL/CSV/HTML reports.

Clinical decision support system for chest X-ray analysis with explainable AI. Deep learning + Grad-CAM for transparent medical diagnosis. PyTorch | Medical Imaging | DICOM

Production-grade clinical intelligence system speedrun: 95% accuracy, full explainability, zero pretrained models. Trained on class-weighted data, tested with real anxiety, deployed to impress recruiters.

A modern ASD screening support system combining XGBoost, SHAP explainability, and an Apple-Health inspired UI — fully deployed with PDF reporting and a complete end-to-end ML pipeline.

[Project] Natural Language-Based Clinical Study Design Recommendation System

A multi-agent healthcare system that automates patient intake, triage, lab waiting, and clinician briefings using Google ADK.

An interpretable ML system for diabetes risk prediction using clinical data. Features SHAP explanations, model comparison (Random Forest vs XGBoost), and a deployment-ready pipeline. Achieves 0.85 AUC with clinical decision support.

Machine learning to support chest X-ray triage — prioritizing urgency rather than diagnosing.

AI-powered platform detecting autism and developmental delays 6+ months earlier through smartphone assessments. Clinical-grade analysis for early intervention.

explainability of models applied to obstetric medical imaging

Oloche's AI Oncologist is a diagnostic tool that detects breast cancer in its early stage using ML. The system analyzes measurements from breast mass characteristics to classify tumors as malignant or benign with high accuracy, providing medical professionals with a powerful decision-support tool

This project is designed for a simple LLM agent with tools on a clinical knowledge graph in Neo4j.

Clinical + Genomic **RAG evaluation (pro)** with hybrid retrieval (BM25 + embeddings), stronger faithfulness, YAML configs, and HTML dashboards. Python **3.10+**.

🔍 Predict cardiac mortality in real-time using AI, leveraging routine tests for fast and accurate risk assessments, ensuring timely intervention for patients.

Multimodal Agentic EHR Co-Pilot Stops The Expensive Crisis Hiding in Electronic Health Records

Comprehensive literature review on hybrid AI systems combining temporal knowledge graphs, clinical constraints, and generative models for emergency department decision support

In-hospital cardiac mortality predictor trained on 15,757 real Indian patient records. Achieves AUC 0.977 using only routine blood tests & echo. Nurse-ready Streamlit web dashboard works on any phone in <3 sec. Discovered alcohol J-curve automatically. Ready for real ward deployment to save lives today.

Framework using UMAP-DBSCAN for unsupervised discovery of multi-modal Hidden Bias Subgroups (HBSs) in AI failure spaces. Implements a scalable Multi-Domain MMD Objective to mitigate latent Acquisition Bias and enhance robustness in clinical Ocular Disease Recognition (ODR).

AI-powered thermal imaging system for early neonatal sepsis detection in NICUs. Non-invasive monitoring using deep learning to identify life-threatening infections before clinical symptoms appear. Collaboration with General University Hospital of Patras & Universitat Autònoma de Barcelona UAB.