EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Unpacking the Adoption of AI Decision Support for High-Risk Pregnancy Detection by Health Workers in Morocco: Embedded implementation research

Zakaria Belrhiti, Imad El Badisy, Brahim Ariani, Malika Asbayou, Djibrine Diallo, Mohamed Ait Moh, Souad El Hassani, Nour El Arnaout, Radouane Belouali, Bouchra Assarag

Oxford Open Digital Health · 13.11.2026

DOI: 10.1093/oodh/oqag014 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Oxford Open Digital Health, online erschienen am 13.11.2026. Verfasst von Zakaria Belrhiti und 9 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial intelligence (AI) Clinical decision support systems (CDSS-AI) have proven useful for early screening, detection, and rapid diagnosis of maternal and perinatal morbidity and mortality, as well as for timely referrals of high-risk maternal cases. Only a few CDSS-AI have been implemented in maternal and neonatal health (MNH) in the Middle East and North Africa (MENA) region. In Morocco, reducing the maternal mortality ratio remains a significant challenge, particularly in remote rural areas. These high mortality rates are attributed to the first and third delays in the Three Delay Model. To address these delays, we co-developed a web-based and mobile app CDSS-AI, called “Oumoumati”, with the Ministry of Health, and implemented it in eight rural primary health centres in Al Haouz province. We adopted an embedded implementation design. We interviewed twelve purposefully selected stakeholders, including midwives and health managers. Data analysis employed deductive coding informed by a realist synthesis while remaining sensitive to emergent inductive findings. Thematic analysis was structured using the Context-Mechanisms-Outcomes heuristic. Our study findings showed that the utilisation and adoption of CDSS-AI is conditioned by systemic intertwined multilayered factors: The general context (e.g., resources), health system context (e.g. professional recognition), organisational context (e.g. managerial support), intervention characteristics (e.g. ease of use), and individual capacities (self-confidence). Our project highlighted that the ethical, responsible, and contextualised use of AI may contribute to alleviating gender issues and inequitable access to care for women residing in remote, underserved areas, provided it is co-designed with trained frontline workers and empowered local communities.

Zitieren

APA

Belrhiti, Z., Badisy, I. E., Ariani, B., Asbayou, M., Diallo, D., Moh, M. A., Hassani, S. E., Arnaout, N. E., Belouali, R., & Assarag, B. (2026). Unpacking the Adoption of AI Decision Support for High-Risk Pregnancy Detection by Health Workers in Morocco: Embedded implementation research. Oxford Open Digital Health. https://doi.org/10.1093/oodh/oqag014

Vancouver

Belrhiti Z, Badisy IE, Ariani B, Asbayou M, Diallo D, Moh MA, et al. Unpacking the Adoption of AI Decision Support for High-Risk Pregnancy Detection by Health Workers in Morocco: Embedded implementation research. Oxford Open Digital Health. 2026. doi:10.1093/oodh/oqag014

BibTeX
@article{Belrhiti2026,
  author = {Belrhiti, Zakaria and Badisy, Imad El and Ariani, Brahim and Asbayou, Malika and Diallo, Djibrine and Moh, Mohamed Ait and Hassani, Souad El and Arnaout, Nour El and Belouali, Radouane and Assarag, Bouchra},
  title = {Unpacking the Adoption of AI Decision Support for High-Risk Pregnancy Detection by Health Workers in Morocco: Embedded implementation research},
  journal = {Oxford Open Digital Health},
  year = {2026},
  doi = {10.1093/oodh/oqag014}
}
Kostenlos starten →