Pune based Froncort.AI has received $2.3 million from Google.org to expand its AI based disease screening platform across India. The grant will fund mAI-NETRA, a mobile app that tells frontline health workers where to screen for infectious diseases.
The support also includes $200,000 in Google Cloud credits and pro bono technical expertise from Google specialists. Froncort.AI is one of 15 organisations picked from more than 2,600 proposals for the Google.org Impact Challenge, a $30 million global initiative. The grant was announced on 10 November.
Froncort.AI was founded in 2024 by physician scientist Dr Ujjwal Rao. The company works with India’s Central TB Division and the Maharashtra Directorate of Health Services, and it also builds RegDoc, an AI platform for regulatory work in life sciences.
How mAI-NETRA guides a health worker
mAI-NETRA is the mobile version of Froncort.AI’s AI-NETRA platform. It combines government health programme data with Google Earth AI satellite models and local signals such as settlement density, land use, rainfall and flooding.
The system flags high risk areas within 300 metre zones and turns them into ranked household work paths for each worker. The app works offline and in local languages, and the company says government health data stays stored and processed in India.
India has more than one million frontline health workers, and they still plan much of their screening from registers and instinct. mAI-NETRA replaces that guesswork with one daily plan that says where to go, whom to screen and where to send the next sample.
The Pune pilot behind the grant
Froncort.AI built AI-NETRA with FIND and the Maharashtra State TB Cell, and ASHA workers in Pune began using its AI generated screening plans in May 2026. A validation study with the state TB programme tested the approach against routine screening.
AI guided teams screened 66,095 people and found 10 confirmed pulmonary TB cases. Teams using standard methods screened 177,322 people and found nine cases. That meant about 6,610 people screened per confirmed case with AI guidance, against 19,702 without it.
The company also reported that the cost per confirmed case fell from about $29,000 to about $10,000, and 92% of participating frontline workers reported a lower workload. These are the company’s own pilot figures, and the rollout will be independently monitored.
Six diseases and eight districts
The new funding will extend the platform from tuberculosis to five more diseases, taking the total to six. The list covers TB, leprosy, malaria, dengue, cholera and leptospirosis.
Froncort.AI plans to deploy the app across up to eight high burden districts in three Indian states, covering two to three million people. The rollout will be judged against five targets, including at least 20% more TB cases found and more than 50% fewer people screened per case.
The company also plans to publish mAI-NETRA as an open source blueprint so other governments can adopt and adapt it for their own public health programmes. Google.org had earlier backed the AI-NETRA validation study in 2025.
Why the timing matters
India carries the world’s largest tuberculosis burden. The World Health Organization’s Global Tuberculosis Report 2025 puts India at 25% of global TB cases, though incidence has fallen 21% since 2015.
That gap between burden and detection is what Froncort.AI is built for. Blanket screening campaigns test large numbers of people to find few cases, and the Pune pilot suggests targeted screening can find the same cases with far less effort.
“The world does not lack experts. It lacks their reach. AI-NETRA puts that expertise in the health worker’s hands at the door: where to go, whom to screen, and when.”
Dr Ujjwal Rao, Founder and Chief Executive Officer, Froncort.AI
The real test now is the eight district rollout. Meeting its five targets would turn targeted screening into a model other states can copy, and the independent monitoring means the results will be judged on evidence rather than promise. You can read more about the app on the company’s mAI-NETRA page.
