IIIT Hyderabad, CMC Vellore build multilingual AI for cancer care

CMC Vellore and IIIT Hyderabad are developing BandhuCare, a multilingual AI companion that answers cancer patients' queries, records symptoms through conversations and supports clinicians with summaries between hospital visits. The platform currently supports eight Indian languages using clinically verified information

Hyderabad: A multi-partner consortium led by Christian Medical College (CMC), Vellore, in collaboration with the International Institute of Information Technology (IIIT) Hyderabad, is developing BandhuCare, a multilingual AI companion that answers cancer patients’ queries in their own language.

In addition, the technology captures a patient’s symptoms through natural conversations and helps clinicians understand what happens between hospital visits.

---

BandhuCare is the latest outcome of a long-standing partnership between CMC and IIIT Hyderabad’s Language Technologies Research Centre (LTRC).

The partnership began when CMC approached IIIT Hyderabad for help in translating patient information sheets and consent documents into Indian languages.

For hospitals serving patients from across the country, communicating complex medical information in a patient’s own language has long been a challenge. At the same time, for researchers at LTRC, it was an opportunity to develop language technologies in a real-world setting.

“We realised there was tremendous scope for language technology to make a difference in healthcare in India, a domain previously unexplored,” said Prof Dipti Misra Sharma, who has been heading machine translation efforts at IIIT Hyderabad for decades.

Unlike consumer AI assistants that answer virtually anything, BandhuCare emerged after years of working closely with oncology patients and understanding where healthcare delivery quietly breaks down, not during diagnosis or treatment, but between hospital visits.

While large language models are powerful, confidence without correctness can be dangerous in the healthcare domain. BandhuCare tackles this problem using retrieval-augmented generation (RAG). Rather than searching the internet, the AI answers questions only from information carefully curated and verified by clinicians.

Further, BandhuCare introduces journaling to capture patients’ everyday experiences. Patients can record simple diary entries such as, “Today I vomited three times. My mouth felt extremely dry. I couldn’t swallow properly.” These entries can also be recorded as voice notes. Over time, the app creates a summary of everything that happened between hospital visits. Instead of trying to remember weeks of symptoms during a brief consultation, patients arrive with a clear record.

The platform currently supports eight Indian languages, allowing patients to ask questions through text or voice in the language they are most comfortable with. Responses are delivered both as speech and written text.