Contextual Challenges in Implementing Artificial Intelligence for Healthcare in Low-Resource Environments: Insights from the SPEC-AI Nigeria Trial

Demilade A Adedinsewo ^1* Damilola Onietan ² Andrea Carolina Morales-Lara ¹ Serin Moideen Sheriff ¹ Bosede B Afolabi ² Oyewole A Kushimo ³ Amam C Mbakwem ³ Kehinde F Ibiyemi ⁴ James Ayodele Ogunmodede ⁵ Hadijat Olaide Raji ⁴ Sadiq H Ringim ⁶ Abdullahi A Habib ⁷ Sabiu M Hamza ⁶ Okechukwu S Ogah ⁸ Gbolahan Obajimi ⁹ Olugbenga Oluseun Saanu ⁹ Solomon Aborisade ⁸ Olusoji E Jagun ¹⁰ Francisca O Inofomoh ¹⁰ Temitope Adeolu ¹⁰ Kamilu M Karaye ¹¹ Sule A Gaya ¹¹ Yahya Sa’ad ¹¹ Isiaka Alfa ¹¹ Cynthia Yohanna ¹² Peter A Noseworthy ¹³ Rickey E Carter ¹

• ¹ Mayo Clinic Florida, Jacksonville, United States
• ² University of Lagos, Lagos, Nigeria
• ³ Lagos University Teaching Hospital, Lagos, Nigeria
• ⁴ University of Ilorin Teaching Hospital, Ilorin, Kwara, Nigeria
• ⁵ University of Ilorin, Ilorin, Kwara, Nigeria
• ⁶ Rasheed Shekoni Specialist Hospital, Jigawa, Nigeria
• ⁷ Rasheed Shekoni Teaching Hospital, Jigawa, Nigeria
• ⁸ University of Ibadan, Ibadan, Oyo, Nigeria
• ⁹ University College Hospital Ibadan, Ibadan, Nigeria
• ¹⁰ Olabisi Onabanjo University Teaching Hospital, Shagamu, Nigeria
• ¹¹ Aminu Kano Teaching Hospital, Kano, Nigeria
• ¹² Lakeside Healthcare at Yaxley, the Health Centre, Peterborough, United Kingdom
• ¹³ Mayo Clinic, Rochester, Minnesota, United States

Nigeria is the most populous country in Africa with the highest gross domestic product(GDP)as of 2022. However,Nigeria is burdened by health challenges including a high maternal mortality ratio, inadequate human resources, poor healthcare, and population-level poverty rates as high as40%. Nigeria also has the highest-reported prevalence of peripartum cardiomyopathy worldwide which contributes to maternal mortality. Unfortunately,the diagnosis is often delayed and mortality rates following diagnosis are high (approximately50%). Thus,there is a unmet need for effective and accessible solutions for cardiomyopathy detection in this population. To address maternal mortality,we conducted a randomized controlled clinical trial(NCT05438576)of an artificial intelligence(AI) technology. The objective of the study was to evaluate the impact of AI-guidedscreening on cardiomyopathy detection in obstetric patients. The study found AI-guided screening doubled the detection of cardiomyopathy(defined as left ventricular ejection<50%)when compared to usual care with a number needed to screen of 47. As we explore next steps in relation to deploying this technology for clinical use in Nigeria,we sought to gather contextual information and share lessons learned from the completed trial. To that end,we convened a discussion with study site investigators aimed at identifying site-specific contextual challenges related to the development and conduct of the study. The SPEC-AINigeria study is the first published randomized controlled clinical trial of a healthAI intervention in Nigeria. Insights gained can inform futureAI intervention studies in clinical care,guide the development of implementation strategies to ensure effective interventions are successfully incorporated into clinicalcare,and provide a roadmap for keystakeholders to consider when evaluating AI-technologies in low-resourcesettings.