Regular use of the service has been associated with improved behavioural and health outcomes for women and their babies. (Image source: Freepik)
Despite medical advances, maternal mortality remains a global concern, with 287,000 women dying in pregnancy and childbirth across the world in 2020, according to United Nations agencies. In India alone, a woman dies in childbirth every 15 minutes. What's striking is that most of these deaths are avoidable if women receive timely intervention.
Many non-governmental organisations (NGOs) have leveraged the wide-spread availability of mobile phones and launched health programmes to deliver information via voice or text to beneficiaries in underserved communities, with maternal and infant health being a key area. However, their efforts are often stymied by a dwindling listenership and general lack of interest.
ARMMAN is trying to do things differently here; the Mumbai-based NGO has integrated artificial intelligence (AI)-based predictive modeling technology, developed with pro bono support from volunteers from Google's research team in India, into its outreach efforts. It delivers timely and targeted preventive health information to expectant and new mothers in underserved communities in languages and at time slots of their choice via its free mobile voice call service.
Regular use of the service has been associated with improved behavioural and health outcomes for women and their babies. Using AI analysis of millions of anonymised call records, the programme accurately identifies participants most at risk of disengaging from the initiative, prioritising them for additional personalised outreach, including in-person support and resources for specific concerns, by the NGO's call centre staff and community partners.
Approximately 30% of those at highest risk of dropping out have been retained in the programme and received vital health information. Initially piloted with 175,000 women in 2019, the AI powering this programme was scaled across the database of approximately 350,000 women who used the service in Maharashtra. "This programme continues to inspire us, and it's been really gratifying for us to see our AI models moving from the lab into the real world, improving lives in deeply meaningful ways," said Milind Tambe, director, AI for Social Good, Google DeepMind.
Highlighting the importance of AI, Aparna Hegde, founder, ARMMAN said, "We found that almost 50% of women were not consistently listening to the calls; they weren't picking up the calls or not listening completely. With limited staff, it was very difficult to reach out to all these women. We needed a method to preempt which of these women were at high risk of dropping out and prioritise them. I knew that AI could possibly point us in the right direction, and has enabled us to reach out to more and more women each week, get them back into the fold, and save lives because of AI. Our quest in the next five years is to adopt multimedia approaches, and use the power of AI and predictive analytics to better serve our mothers and children."
ARMMAN is now also implementing the Kilkari programme, a mobile health information initiative with the government that has reached over 49 million women and their children across 20 Indian states and Union Territories. Volunteers from Google's research team in India are developing AI models to help improve Kilkari participation.
According to Anurag Pratap, vice-president & head of CSR -- Inda, Capgemini, AI-driven technologies have the potential to greatly improve India's healthcare system, especially in rural regions where access to high-quality medical treatment is a challenge. "At Capgemini, we have developed an AI-powered app called Maatr to tackle maternal mortality. It aims to help community health workers support women throughout their journey of pregnancy, childbirth, and caring for babies and young children. We have partnered with multiple stakeholders to develop this solution and it has been rolled out in several parts of Maharashtra," he added.
