A pilot study to implement artificial intelligence-enabled, point-of-care obstetric ultrasound for gestational age estimation in Zambia: An evaluation protocol

A multi-year pilot program designed to evaluate the integration of artificial intelligence-enabled point-of-care ultrasound (POCUS) into routine antenatal care (ANC) is currently underway in Zambia's Lusaka Province. Spearheaded by local and international researchers, the protocol focuses on assessing the acceptability, feasibility, and fidelity of deploying portable ultrasound probes paired with AI-driven tablet applications. This technological intervention aims to bridge critical healthcare gaps by empowering frontline medical workers with minimal training to accurately estimate gestational ages, a fundamental metric for safe obstetric care. Accurate pregnancy dating remains a persistent challenge across many low- and middle-income nations due to prohibitive equipment costs, unreliable electrical infrastructure, and an acute shortage of certified sonographers. Traditionally, pregnant women navigate antenatal clinics without knowing their precise gestational age, which can complicate decisions surrounding management of preterm labor, post-term pregnancies, and fetal growth monitoring. By leveraging deep learning models embedded in low-cost, handheld devices, the pilot program seeks to democratize diagnostic capabilities, bringing expert-level precision directly to primary healthcare clinics. The evaluation protocol—structured around the Piloting Integration, Knowledge and Acceptability of Baby Ultrasounds (PIKABU) initiative—spans six healthcare facilities across three districts. To ensure a comprehensive appraisal, researchers have adopted a mixed-methods framework involving patient register reviews, time-motion studies, focus-group discussions, and patient exit surveys. These metrics capture both the clinical utility and the lived experiences of patients and healthcare providers, shedding light on how seamlessly the technology fits into daily clinical workflows without overwhelming local staff. Medical experts note that this trial builds upon previous collabor