Jacaranda Health banks on AI-driven initiatives to support maternal healthcare

Jacaranda’s Director of Technology Jay Patel. [Courtesy]

Jacaranda Health is now banking on Artificial intelligence (AI-driven) initiatives to support women through their pregnancy journeys.

The Kenyan-based non-profit organization that aims to improve the quality of care and outcomes for mothers and babies in the public health system said the AI technology will improve maternal and newborn health outcomes and push the boundaries of what's possible in healthcare.

This will be made possible through the development and deployment of multi-language LLMs that small local teams across Africa can easily customize to their contexts and use cases.

Maternal mortality rates in Kenya remain at an alarming 355 deaths per 100,000 live births, according to the 2022 Kenya Demographic and Health Survey.

This figure is over five times higher than the Sustainable Development Goals target of 70 maternal deaths per 100,000 live births by 2030.

Jacaranda’s Director of Technology Jay Patel said the move is in line with a new Fellowship partnership with Google.org.

Patel told The Standard that the Fellowship aimed at transforming the potential of Large Language Models (LLMs) for low-resourced communities across Sub-Saharan Africa.

“In this regard, six Google technical experts have been selected for the six-month program, which offers the chance to apply practical skills in research, machine learning, and software engineering, amongst others, to solve AI challenges in the ‘real world,” said Patel.

He said between the months of April and October, the six Fellows will work alongside Jacaranda’s teams to improve the accuracy, efficiency, and scale potential of Jacaranda’s technology to serve mothers across the country as it seeks to expand into new African countries.

This includes testing how to leverage AI and large, anonymised datasets to offer personalized support for high-risk mothers and babies, designing frameworks to manage biases related to gender and economics in Large Language Models.

The partnership also includes building the infrastructure to rapidly adapt PROMPTS to new contexts, and helping other implementers ‘plug and play’ the AI models in other sectors and use cases.

Patel said the Fellowship comes at a critical turning point in the global AI story where despite a rapidly-evolving landscape of AI technologies, few have been adequately adapted to low-resourced settings, limiting the potential of lifesaving AI-driven initiatives in sectors like health and education.

 Maternal mortality rates in Kenya remain at an alarming 355 deaths per 100,000 live births, according to the 2022 Kenya Demographic and Health Survey. [iStockphoto]

He said the fellowship follows a recent $1.4m grant from Google.org to help Jacaranda advance the field of generative AI, ensuring every mother accesses the right information and support during and after pregnancy.

He said Jacaranda’s digital health navigator, PROMPTS, currently uses AI to engage and provide personalised support to new and expecting mothers across the country via SMS.

According to him, recently, the organisation borrowed learnings from this work to develop new, open-source models that not only open the door for the Pan-African PROMPTS scale but also could support other implementers improve their own AI-driven services.

“The work we have planned with support from these Fellows will give us the springboard to significantly improve maternal and newborn health outcomes through the power of AI, and push the boundaries of what's possible in healthcare,” said Patel.

Agnes Gathaiya, Google's Country Director for East Africa said Jacaranda, with support from the Fellows, aims to push the boundaries of what language models can achieve, ensuring they are more accurate, fair, inclusive and scalable across different languages and contexts.

"Providing mothers with the support they need during pregnancy is a powerful example of how AI can be used to help more people at a wider scale," she said.

Gathaiya said Google is proud to have its employees help Jacaranda develop new technical solutions to drive their mission.

Last week,  Amref Health Africa urged county governments and the Ministry of Health to harness the power of artificial intelligence and data analytics to eliminate preventable maternal deaths across the country.

The 13 counties bearing the heaviest burden include Tana River, Garissa, West Pokot, Elgeyo Marakwet, Siaya, Makueni, Migori among others.