Home
Issues
Aim & Scope
Open Access
Editorial Board
Indexing
Supporting Midwifery Associations
Contact us
Manuscript Types
Manuscript Formatting
How to submit
Special publications and Reprints
Authorship & COI
Principles of Transparency Checklist
Publication Ethics and Publication Malpractice Statement
CONFERENCE PROCEEDING
MAM*AI - Developing an AI-powered chatbot for midwives in Zanzibar supporting evidence-based and real-time clinical decision making
1
Swiss Tropical and Public Health Institute- University of Basel, Digital Health Unit- Swiss Center for International Health, Basel, Switzerland
2
Yale University, Yale School of Medicine, New Haven, United States
3
Ecole polytechnique fédérale de Lausanne EPFL, Laboratory for Intelligent Global Health and Humanitarian Response Technologies LiGHT, Lausanne, Switzerland
4
Ministry of Health, Health Promotion Unit, Stonetown, Tanzania- United Republic of
5
D-Tree, Zanzibar Office, Stonetown, Tanzania- United Republic of
Eur J Midwifery 2026;10(Supplement 1):A85
ABSTRACT
BACKGROUND:
Maternal and neonatal mortality rates remain unacceptably high, particularly in sub-Saharan Africa. Improving the quality of care is an important factor in improving health outcomes. In Zanzibar, the midwifery profession does not exist so far. Instead, nurses with minimal midwifery training are the primary caregivers for pregnant and postpartum women.
OBJECTIVES:
During the exploration phase, we aimed to explore the pain points (i.e., needs) of nurses providing midwifery care and conduct a deep dive into the context. In the next step, we aimed to jointly brainstorm innovative solutions in close collaboration with end-users and diverse stakeholders.
METHODS:
We used a human-centered design approach to gain in-depth insight into the health system and the challenges nurses face, particularly in difficult clinical situations. During a co-design workshop with nurses and stakeholders, we jointly explored the development of an AI-powered clinical chatbot that would provide nurses with real-time access to information tailored to their clinical cases and support them in clinical decision-making.
RESULTS:
All nurses providing midwifery care reported a lack of access to evidence-based resources and support, and all had experienced highly stressful and traumatic situations. Access to information included supervisors, Google and Youtube. All reported of a high demand to access evidence-based and reliable information in real-time supporting them in clinical decision-making.
CONCLUSIONS:
We will build on Meditron, currently the best-performing AI-powered chatbot for physicians. The content will be aligned with relevant clinical, international, and national guidelines for midwives only. The prototype will be co-designed with end-users (i.e., nurses in Zanzibar) to ensure a user-centered and context-specific solution.
KEY MESSAGE:
It requires innovative solutions to improve maternal and newborn health outcomes. Supporting nurses providing high-quality midwifery care to make the right decisions at the right time has the potential to improve the quality of care, save lives, and contribute to Sustainable Development Goal 3. Marginalized - migrants
Maternal and neonatal mortality rates remain unacceptably high, particularly in sub-Saharan Africa. Improving the quality of care is an important factor in improving health outcomes. In Zanzibar, the midwifery profession does not exist so far. Instead, nurses with minimal midwifery training are the primary caregivers for pregnant and postpartum women.
OBJECTIVES:
During the exploration phase, we aimed to explore the pain points (i.e., needs) of nurses providing midwifery care and conduct a deep dive into the context. In the next step, we aimed to jointly brainstorm innovative solutions in close collaboration with end-users and diverse stakeholders.
METHODS:
We used a human-centered design approach to gain in-depth insight into the health system and the challenges nurses face, particularly in difficult clinical situations. During a co-design workshop with nurses and stakeholders, we jointly explored the development of an AI-powered clinical chatbot that would provide nurses with real-time access to information tailored to their clinical cases and support them in clinical decision-making.
RESULTS:
All nurses providing midwifery care reported a lack of access to evidence-based resources and support, and all had experienced highly stressful and traumatic situations. Access to information included supervisors, Google and Youtube. All reported of a high demand to access evidence-based and reliable information in real-time supporting them in clinical decision-making.
CONCLUSIONS:
We will build on Meditron, currently the best-performing AI-powered chatbot for physicians. The content will be aligned with relevant clinical, international, and national guidelines for midwives only. The prototype will be co-designed with end-users (i.e., nurses in Zanzibar) to ensure a user-centered and context-specific solution.
KEY MESSAGE:
It requires innovative solutions to improve maternal and newborn health outcomes. Supporting nurses providing high-quality midwifery care to make the right decisions at the right time has the potential to improve the quality of care, save lives, and contribute to Sustainable Development Goal 3. Marginalized - migrants
| eISSN: | 2585-2906 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
