Artificial intelligence-driven fraud detection systems developed through a national healthcare hackathon could help prevent large-scale misuse of public funds under the Ayushman Bharat Pradhan Mantri Jan Arogya Yojana (AB-PMJAY), said officials of the National Health Authority (NHA) on Saturday.

As the AI-driven fraud detection can also speed up claims processing and improve patient care, one of the central problem statements of the hackathon focused specifically on detecting document forgery, deepfakes and fraudulent medical claims. 

Addressing presspersons at the finale of the two-day hackathon organised in collaboration with the IndiaAI Mission and the Indian Institute of Science (IISc), Bengaluru, Sunil Kumar Barnwal, NHA Chief Executive Officer (CEO), said the growing use of AI-generated fake medical records and forged claims had emerged as a serious challenge for public health insurance systems.

The anti-fraud systems deployed have already prevented fraudulent claims worth around ₹630 crore under the scheme. Additional penalties and recoveries imposed on hospitals were estimated at around ₹200 crore, he said.

Trend at an early stage

“We are now seeing AI-generated clinical notes, discharge summaries and diagnostic reports being submitted,” said Jyoti Yadav, Joint Secretary (AB-PMJAY). “The trend is still at an early stage, but we wanted to develop solutions before the problem becomes too large to handle,” Ms. Yadav said.

She said hospitals submit scanned medical records, diagnostic reports and patient documents while raising claims under the AB-PMJAY. These records are vulnerable to manipulation using AI tools, including alteration of images, removal of watermarks, copy-pasting of reports and changes in formatting or alignment.

The hackathon sought solutions that could identify forged or manipulated documents, classify medical records correctly and verify whether submitted reports actually supported the treatment claimed by hospitals, she said.

The official said several innovative solutions emerged during the event, including one fraud-detection model built entirely on mathematical techniques rather than conventional AI systems.

Fraud patterns

Pointing out that fraud patterns under the scheme ranged from inflated billing to fabricated treatment records, the Joint Secretary cited instances where patients diagnosed with minor ailments such as fever were shown as having undergone major procedures like total knee replacement.

“In some cases, photographs of one ICU patient were allegedly reused across multiple insurance claims by changing names and patient details. Under the AB-PMJAY, hospitals receive higher payments for ICU admissions compared to general ward admissions, creating incentives for misuse,” she said.

In another example, the officials said machine-learning systems were being trained to check whether laboratory parameters in diagnostic reports genuinely supported procedures such as dialysis. If creatinine levels did not match medical guidelines for dialysis treatment, claims could be flagged automatically.

Data analytics

Data analytics was also helping authorities identify unusual treatment patterns across States. The officials said systems could detect suspicious trends where multiple beneficiaries from one region travelled to a particular hospital in another State for the same treatment shortly after obtaining Ayushman cards.

“Individually these cases may not appear suspicious, but when data is analysed collectively, patterns emerge,” Ms. Yadav said.

The AI systems are also being used to identify irregularities in chemotherapy cycles, where hospitals allegedly bill for treatment sessions at medically impossible intervals.

“Healthcare fraud detection requires a careful balance, since overly rigid automated systems can also affect genuine patients. Health cannot function entirely on fixed rules because there are always exceptional cases,” she added.