Guwahati: What do women in rural Assam actually want to know about cervical cancer?
Around 100 Accredited Social Health Activists (ASHAs) put that question at the centre of a workshop in Silchar, helping researchers shape an artificial intelligence-enabled training platform and multilingual voice chatbot that will eventually be used to support cervical cancer screening and counselling in rural communities.
The co-design workshop was organised by the George Institute for Global Health India in collaboration with Cachar Cancer Hospital and Research Centre (CCHRC), bringing together ASHAs, doctors, trainers, researchers, programme coordinators and technology experts.
One of the key exercises involved 155 questions commonly asked about cervical cancer and screening. Using a simple bindi-based voting exercise, the ASHAs identified the questions they encounter most often from women, husbands, family members and others during their field visits.
The exercise revealed an important gap: the questions that matter most to people in the community are not necessarily the same as those considered clinically important.
The findings will be used to build the knowledge base for the proposed voice chatbot, with researchers aiming to combine medically important information with the practical concerns ASHAs face in the field.
The workshop also looked at how comfortable ASHAs are with digital technology. Younger and middle-aged workers said they routinely use mobile phones for reporting, communication and accessing information, while some older ASHAs said digital tools and language can be challenging. However, they expressed interest in learning to use them more confidently.
The ASHAs also mapped their own work journey—from training and refreshing their knowledge to counselling women, explaining test results and making referrals. The exercise helped identify areas where additional support could be useful, including quick access to reliable information during community visits.
Several ASHAs called for the technology to work in Bangla and simple language. They suggested short audio-visual lessons, frequently asked questions, reminders, quizzes, progress tracking and search functions that reflect the way they naturally ask questions.
One ASHA participant said the workshop was different from conventional meetings because the interactive exercises made learning about cervical cancer easier and more engaging.
The project team said the technology would be designed to supplement—not replace—existing training and the relationships ASHAs have built with communities.
“This workshop starts with a simple principle: technology for ASHAs should be designed with ASHAs,” said Anita Gadgil, principal investigator of the project and senior research fellow at The George Institute for Global Health, and Co-Director of the WHO Collaboration Center for Emergency Critical and Operative Care.
“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,” she said.
The initiative is part of a three-year ICMR-funded pilot, Leveraging Artificial Intelligence for Strengthening Cervical Cancer Screening Through Capacity Building, running from November 2025 to November 2028.
The next phase will involve developing the AI learning platform and voice chatbot. Training materials and the chatbot’s content will undergo clinical review and repeated testing with ASHAs before rollout.
Researchers will then test the AI-supported approach against standard training methods through a two-arm cluster-randomised controlled trial covering 20 clusters and around 110 ASHAs.
The study will assess the tool’s usability, acceptance and actual use, as well as its potential for wider adoption. Researchers will also examine changes in ASHAs’ knowledge, attitudes and practices.
The proposed chatbot is intended to provide training and field-based information. It will not replace clinical assessment, diagnosis or established referral pathways.
For Assam’s rural health workers, the experiment is therefore not simply about putting AI into the hands of frontline workers. It is about building the technology around the questions they are already being asked—and the realities they face when they knock on a woman’s door.