ASHA workers, the backbone of India’s primary healthcare system, will soon add another important task to their home call. As the first point of contact for healthcare in remote villages and towns, these workers already handle tasks such as vaccinations and health checks. Now, they will also conduct detailed conversations with families about their personal health status and family history of illnesses, guided by a structured questionnaire.
The goal is to collect important data that can help AI tools identify breast cancer risk factors and patterns specific to Indian women. The initiative is part of AIIMS Delhi’s ambitious project aimed at early detection and reduction of breast cancer mortality, which remains high globally.
The project is the first under the government’s flagship plan to set up three Centers of Excellence (CoE) in AI with a focus on healthcare, agriculture and sustainable cities. AIIMS has secured ₹300 crore in funding to lead a Healthcare CoE in partnership with IIT Delhi, working on various national programs to address non-communicable diseases.
“Unfortunately, most of the breast cancer cases we are picking up in India are still in stage three or four, which are difficult to treat. AI will help us on two fronts. First, it can interpret the data pool and identify which women need mammograms – breast “Special X-rays to check for signs of cancer – reassuring others with low-risk profiles. This can facilitate early screening,” says Dr Krithika Rangarajan, associate professor of radiology. Institute-Rotary Cancer Hospital (IRCH), AIIMS, Delhi.
Second, AI tools can accurately read mammograms, picking up even the smallest signs of cancer. “This allows for advanced breast cancer screening in remote areas where there is a lack of trained radiologists. Otherwise, a lot of time is wasted in diagnosis,” he added.
How will the AI model work?
For the first time, the AI model will scan a five-year database of women screened for breast cancer at AIIMS, NCI Jhajjar and PGI Chandigarh, whether they were found to be clear or have cancer. By analyzing them, it will predict a patient’s risk of developing breast cancer by combining the patient’s general test results with data on their lifestyle and family history. This would then allow doctors to screen out those at high risk and recommend interventions.
The first part of the study involved identifying Indian risk factors for breast cancer. “For this, we will use ASHA workers to collect data, which will be fed into an AI tool. It will extract common risk factors and then recommend mammograms for women thought to be cancer-prone. It will also help codify what constitutes a no-risk category. ,’ says Dr Rangarajan.
The second part will include an analysis of AI’s mammography based on risk factors found in participants. “AI-trained systems can learn to identify complex features in mammograms that indicate cancer. So there’s no need for an on-site radiologist. So AI can help reduce the amount of manual work involved in screening.” can, which can reduce costs,” says Dr. Rangarajan.
Mammography is a very complex modality and a radiologist needs many years of experience to be able to read it correctly. “Can we now, with the help of AI, allow relatively less trained people to read mammograms? We are working on enabling a large number of women to undergo mammograms,” she says. Even those numbers can be reduced.
When will a large scale rollout be possible?
The pilot study has a fixed set of questions, which will be updated and refined over time. “The ultimate goal is to bring such a screening tool into the national health program and integrate it into the workflow of all ASHA workers,” says Dr. Rangarajan. In studies and trials worldwide, AI has been able to analyze genetic and molecular data to create personalized treatment strategies even for individual patients.
“The next four years will have many components in developing these tools, clinical studies and implementation research,” says Dr. Rangarajan. If the AI tool is found to be effective, then an economic evaluation will be done on the costs required to scale it up in India and obtain a license. Then it can be brought to the market through companies or NGOs.
Data protection
What about data protection, considering they cover a large part of the population? “Data security will be our top priority and we will build a mechanism so that our data is secure and encrypted. We will also start studies without disrupting the way we treat patients. are using AI for analysis. There will be both human and expert oversight,” assures Dr. Rangarajan.
Why should you buy our membership?
You want to be the smartest in the room.
You want access to our award-winning journalism.
You don’t want to be confused and misinformed.
Choose your subscription package