Many low and middle-income countries face significant challenges in clinical diagnosis and guideline-based care. Limited resources, overstretched health care systems, and a shortage of health care professionals mean clinicians see a high volume of patients with a wide range of health complaints daily and make rapid diagnosis and treatment decisions, often with limited information.

Now a large trial in Nairobi, Kenya – the largest of its kind to take place in Africa – will test AI’s real-world effectiveness at scale with 9,000 participants being recruited. Results are anticipated by the end of 2025. It will use a Large Language Model-based tool – an application that synthesizes vast sums of data and generate a response like a human. The LLM tool acts as an assistant to primary health care clinicians, providing guidance throughout the clinical encounter (from supporting diagnosis to providing treatment recommendations) based on the patient’s health history, clinical visit notes, and any laboratory results.

The trial is being launched by PATH, a non-profit global health organization, in collaboration with a consortium of research [the Kenya Paediatric Research Consortium (Keprecon), and the University of Birmingham] and clinical partners (Penda Health), 

A landmark Phase 3 randomized controlled trial, the largest of its kind to take place in Africa, will assess the impact of a Large Language Model-based tool on improving quality of care in a clinical setting in low- and middle-income countries. LLMs are applications of AI that synthesize vast sums of data and generate a response like a human. The LLM tool in this trial acts as an assistant to primary health care clinicians, providing guidance throughout the clinical encounter (from supporting diagnosis to providing treatment recommendations) based on the patient’s health history, clinical visit notes, and any laboratory results.

“This is a massive step forward for evaluating the potential of GenAI tools to improve clinical decision-making,” says Prof. Bilal Mateen, Chief AI Officer at PATH. “Potential applications must be backed by rigorous research that demonstrates benefits for both patients and healthcare systems, and we’re excited to demonstrate that it is possible to deliver a best-in-class study, at record pace, to dispel the myth that good quality science can’t match the pace of innovation in tech.”

Kenya has a growing reputation as a leader in digital health innovation. “This trial marks an important milestone for our health sector,” said Dr. Deborah Mlongo Barasa, Kenya’s Cabinet Secretary of Health. “AI has the potential to bridge health care gaps, particularly in underserved regions. We look forward to the insights it will generate to guide responsible and effective AI adoption.”

To date, trials assessing LLM-based clinical decision support systems have largely been based on simulated cases and historical clinical interactions, not real patients in real time. Only three RCTs have rigorously evaluated AI-based clinical decision tools in Africa, and greater investment from donors and governments is required to build the evidence base at scale.

“With South Africa and Canada prioritizing AI in their G20 and G7 agendas this year, this is a critical moment to scale investments in AI evidence generation,” says Sir Jeremy Farrar, Chief Scientist at the World Health Organization. “This trial is a crucial step in informing global policies and approaches to AI-driven healthcare solutions.”

PATH is a global nonprofit dedicated to achieving health equity. With more than 40 years of experience forging multisector partnerships, and with expertise in science, economics, technology, advocacy, and dozens of other specialties, PATH develops and scales up innovative solutions to the world’s most pressing health challenges.

Founded in 2012, Penda Health has a mission to deliver high-quality health care to underserved communities in Kenya, ensuring accessible, affordable care for middle- to low-income families. Penda’s services include comprehensive outpatient services, preventive care, maternal health, chronic disease management, and digital health services. Penda operates 16 branches in Kenya.

The Kenya Paediatric Research Consortium (Keprecon) is a non-governmental organization registered in Kenya. Keprecon focuses on health systems strengthening, implementation research, advocacy, social and behavior change, and clinical trials to improve reproductive, maternal, newborn, child, and adolescent health, nutrition, immunization, and Primary Health Care service delivery in Kenya. Keprecon membership comprises paediatricians, researchers, health workers, social scientists, and other professionals who have experience and interest in health research and those who have project grants being administered at the organization.

Cover image: PATH