George Institute India & Cachar Cancer Hospital to Develop AI Voice Chatbot for Cervical Cancer Screening

The project, started in November 2025 and will run until November 2028, aims to build and test an AI-based learning platform for ASHAs, along with a chatbot that can answer questions by voice in multiple languages.

The George Institute for Global Health India, in collaboration with Cachar Cancer Hospital and Research Centre (CCHRC), Assam, is developing an AI-enabled training platform and multilingual voice chatbot to support cervical cancer screening and community counselling by Accredited Social Health Activists (ASHAs) in rural Assam.

Around 100 ASHAs participated in a co-design workshop organised as part of the initiative, along with trainers, doctors, programme coordinators, researchers and technologists.

The workshop focused on understanding the challenges ASHAs face during community visits, the support they need, and how technology could assist their screening and counselling work. It is part of a three-year pilot study, Leveraging Artificial Intelligence for Strengthening Cervical Cancer Screening Through Capacity Building, funded by the Indian Council of Medical Research (ICMR).

The project, started in November 2025 and will run until November 2028, aims to build and test an AI-based learning platform for ASHAs, along with a chatbot that can answer questions by voice in multiple languages.

As part of the workshop, ASHAs reviewed 155 common questions that people ask about cervical cancer and screening. Using a bindi based voting system, they identified the questions they encounter most frequently in the field from women, husbands, family members, and others in their communities.

The exercise showed that the questions ASHAs encounter most often are not always the same as those considered clinically important. The inputs will be used to develop the chatbot knowledge base, covering priority health information needs as well as practical concerns raised during community visits.

The workshop also examined ASHAs’ comfort and confidence with digital technology. Younger and middle aged ASHAs reported regularly using mobile phones for reporting, communication and accessing information, while ASHAs in older age groups said digital tools and language can be more challenging. They also expressed willingness to learn and become more confident in using digital tools.

ASHAs mapped their career paths, including training, retaining their knowledge, counselling women on pregnancy and childbirth concerns, explaining test results and making appropriate referrals. The exercise also helped many ASHAs identify knowledge gaps and discuss using tools such as flipcharts to refresh their knowledge when required.

The participants highlighted the value of voice-based interactions in Bangla, simple language content and search functions that reflect the way ASHAs naturally ask questions. They also suggested features including short audio visual lessons, frequently asked questions, reminders, quizzes and progress tracking.

One of the ASHA workers who participated in the workshop said, “I am very happy to attend this workshop. This is the first time I have attended something like this. I have attended many meetings before, but this was very different. Even the questions about cervical cancer, what is important and what is not, were explained through an exercise using bindis. It felt like a fun and interactive way of learning, almost like a game. We learnt so much today, and through this workshop we got to know many things that we did not know before.”

The discussions also emphasised that digital tools should complement existing training approaches and build on the experience, knowledge and community relationships of ASHAs. Practical considerations including limited internet connectivity, the time available during household visits and the need for reliable, clinically verified information were also considered.

Dr. Anita Gadgil, Principal Investigator of the project and Senior Research Fellow at The George Institute for Global Health; Co Director, WHO Collaboration Center for Emergency Critical and Operative Care, said, “This workshop starts with a simple principle: technology for ASHAs should be designed with ASHAs. Their experience of explaining screening, responding to concerns and finding answers in real time will guide the language, content and functions of this AI platform. Our aim is to develop clinically validated support that fits their work, rather than adding another digital burden.”

The inputs from the workshop will shape the next phase of the project, which involves building the AI learning platform and chatbot. The training content and questions will undergo clinical review and repeated testing with ASHAs before rollout.

The study will then evaluate AI-supported training and chatbot access against standard training methods through a two arm cluster randomised controlled trial across 20 clusters involving approximately 110 ASHAs. The study will assess the practicality and reception of the tool, its use and consistency, and its potential to scale. Researchers will also track ASHAs’ knowledge, attitudes and practices to build a case for a larger future trial.

The proposed chatbot is intended to support ASHAs with training and field based information and will not replace clinical assessment, diagnosis or referral pathways.

Stay tuned for more such updates on Digital Health News