Google said the National Health Authority (NHA) has adopted its Gemma 4 AI model and Medical Data Toolkit in the newly launched Aarogya Setu 2.0 app, allowing users to generate digital health profiles from unstructured medical records.
The search giant said that NHA is using Google’s Medical Data Toolkit alongside Gemma 4 to extract information from medical reports, including text and images, and present users with a consolidated view of their health history within the app.
The integration is part of a broader collaboration between Google and the NHA to strengthen India's digital public infrastructure for healthcare.
Google also announced that it has open-sourced the Medical Data Toolkit, allowing developers and healthcare organisations to use it at no cost.
“We are pleased that our AI capabilities are helping strengthen the country's digital health stack and Digital Public Infrastructure. These tools are designed to empower Indians to more closely control their health journeys, while the release of the toolkit reduces barriers to entry for health tech innovation," said Preeti Lobana, Vice President and Country Manager, Google India.
According to Google, the toolkit identifies the type of medical record and extracts information such as laboratory test names, methods and results. The extracted data is then mapped into Fast Healthcare Interoperability Resources (FHIR), a global standard for exchanging healthcare information across systems.
The company said the toolkit currently supports common health records, including laboratory reports and observations, with plans for developers to build applications that digitise and standardise legacy medical records while complying with interoperability standards under the Ayushman Bharat Digital Mission (ABDM).
Google said the Medical Data Toolkit uses a rules-based system to structure extracted information, while all health records and related information remain under the user's control within the Aarogya Setu 2.0 app.
Gemma 4, Google’s open AI model launched in April 2026, is used alongside the toolkit to process unstructured health records and help generate individual health profiles.


Your reaction
Discussion
What's your take on this story?
No comments yet — be the first to share your view.