Document Forgery and Deepfake Detection
NHA Hackathon - Problem Statement 3
Team Sushurutha Health AI - Felicitation Ceremony - IISc Bengaluru
The Event
The AB PM-JAY Auto-Adjudication Hackathon was organized by the National Health Authority in collaboration with IndiaAI Mission (under MeitY) and the Indian Institute of Science, Bengaluru. Over 3,500 participants registered nationwide, with solutions evaluated by an expert jury from government, academia, healthcare, and technology institutions. The hackathon addressed three critical problem statements aimed at strengthening speed, transparency, accuracy, and programme integrity in health claims adjudication under Ayushman Bharat PM-JAY, the world's largest publicly funded health insurance scheme.
The Problem
The healthcare insurance ecosystem faces an increasing threat from forged and manipulated medical documents, including tampered discharge summaries, manipulated bills, fabricated prescriptions, and even deepfake-generated identity documents. These fraudulent documents are submitted as part of insurance claims to extract illegitimate reimbursements from public health programmes.
The National Health Authority challenged participants to build AI-driven systems capable of detecting document forgery and deepfakes within healthcare claims pipelines. The system needed to identify tampered discharge summaries, manipulated billing documents, ghost identities created through deepfake technology, and other forms of document manipulation used to defraud AB PM-JAY.
Our Approach
Team Sushurutha Health AI developed a multi-layered AI/ML-based fraud detection system. The solution combines document forensic analysis, examining pixel-level inconsistencies, metadata anomalies, and font/layout irregularities, with deep learning models trained to detect manipulated images and deepfake-generated content. The system uses SHA-256 hash verification for document integrity checks, OCR-based text extraction for cross-referencing claim details, and anomaly scoring to prioritize suspicious documents for human review. The pipeline was designed to integrate directly into existing claims processing workflows with minimal disruption.
Results and Impact
The solution addresses one of the most pressing challenges in public healthcare: programme leakage through document fraud. By automating the detection of forged documents, the system reduces the manual burden on claims reviewers while catching sophisticated fraud that would otherwise slip through. The jury recognized the solution for its practical approach to AI/ML-based healthcare insurance fraud detection.
Technology Stack
Gallery
All winning teams with cheques at IISc Bengaluru
Andhra Prabha newspaper coverage - Telugu engineers shine at NHA Hackathon
Press and Media Mentions
National Health Authority concludes AB PM-JAY Auto-Adjudication Hackathon Showcase 2026 at IISc Bengaluru
Press Information Bureau (Government of India) - 9 May 2026
NHA recognises innovators for developing AI systems for healthcare claims processing and fraud detection
The Hindu - May 2026
IndiaAI Mission and NHA Felicitate Winners of AB PM-JAY Auto-Adjudication Hackathon Showcase 2026
Ease My Prep - 13 May 2026
See this solution in action
Watch DemoKantaka Sodhana - Recognition Log - PS-03