Open Source Project

Cardio-Sahayak India 🇮🇳 🫀

A Specialized Multimodal LLM for Complex Cardiology Care

Optimized for the South Asian demographic, addressing unique genetic predispositions, clinical profiles, and socio-economic contexts to democratize advanced cardiac care.

View Repository Read Preprint

The South Asian Cardiac Challenge

Myocardial Infarction (MI) in India occurs 5-10 years earlier than in Western populations. Despite standard BMIs, central obesity, genetic predispositions (like the MYBPC3 Δ25bp variant), and unique metabolic profiles present a distinct "South Asian Phenotype" often overlooked by generalized medical AI models.

🧬 Population-Specific Needs

Current models fail to account for lower BMI thresholds for MI, elevated Lp(a) levels, and specific variants prevalent in up to 4% of the Indian population.

Dual-Architecture AI

Combining MedGemma-27B for deep clinical reasoning and a Vision-Language Model (MedSigLIP) for native 12-lead ECG interpretation.

📊 Rigorous Clinical Guidelines

Fine-tuned directly on the Indian National Consensus on Cardiology and ICMR guidelines for precise, actionable diagnostic support.

Technical Architecture

Cardio-Sahayak implements a state-of-the-art dual-architecture design:

  • Text & Reasoning Backbone: google/medgemma-27b-it, quantized using 4-bit NormalFloat (NF4) via bitsandbytes and fine-tuned using QLoRA.
  • Multimodal ECG Processing: google/medsiglip-448 integrated via the MEIT framework, allowing raw 12-lead ECG ingestion and cross-modal diagnostic reasoning.
  • Data Pipeline: Trained on a synthetically generated but rigorously validated dataset integrating PTB-XL records, ECGInstruct sets, and South-Asian clinical case histories.

Democratizing Expert Care

By converting the fine-tuned model to GGUF format, Cardio-Sahayak India is designed to be deployed locally on resource-constrained hardware in rural Indian clinics. It acts as an expert clinical assistant (Sahayak), assisting physicians in early screening, accurate ECG interpretation, and personalized risk assessment.

Explore the Codebase on GitHub →

🔓 Open Source

Released to the community to foster collaboration, rigorous evaluation, and advancements in global health equity.

🌍 Targeted Impact

A specialized solution for the 1.4 billion people of India, directly addressing the region's rapidly growing burden of cardiovascular disease.