Research
Peer-reviewed papers at top ML and NLP venues, focused on deploying AI for public health impact at national scale.
A national-scale, real-time, multi-stage and multi-lingual disease outbreak detection pipeline deployed with India's NCDC, scanning 400M+ media sources, issuing 100K+ alerts, and verifying 5K+ outbreaks through the Media Scanning and Verification Cell.
A similarity-encoded ensemble model deployed across 15 Indian states that flags high-risk TB patients likely to drop off treatment, covering 100K+ patients with fairness-aware reweighting to ensure equitable recall in underserved districts.
Focus areas
Building ML systems that improve healthcare delivery, from disease surveillance to treatment adherence prediction, at population scale.
Multi-stage, multi-lingual systems that process millions of documents to extract actionable intelligence at speed and scale.
Ensuring equitable model performance across underserved populations through fairness-aware training and rigorous evaluation methodology.