Employing institution: University of Gondar, Ethiopia
Host institution: Ethiopian Public Health Institute
Project title: Developing a novel risk prediction model for gestational diabetes mellitus in Ethiopia.
Dr Muche has a PhD in Reproductive Health and is currently an Assistant Professor of Reproductive Health and Epidemiology at the University of Gondar. His research interests focus on maternal and child health epidemiology, with a passion for risk prediction model application and implementation research on maternal and child health issues.
AREF Fellowship:
Gestational diabetes mellitus (GDM) is hyperglycaemia during pregnancy and can cause a range of complications. During his PhD, Dr Muche examined the epidemiology of GDM and postpartum glucose intolerance and its adverse effects on maternal and newborn health outcomes. During his fellowship he aims to develop a novel risk prediction model for GDM in Ethiopia.
The goal is to develop a validated risk prediction model for GDM involving providers and pregnant women to aid clinical decisions and risk-stratified models of care in low-resource settings. Identification of new biomarker predictors to construct a first-trimester risk prediction for GDM will be incorporated. During this capacity-building fellowship, he aims to develop the required technical skills in machine learning, focusing on risk prediction models.
Dr. Muche’s placement will take place at the Ethiopian Public Health Institute (EPHI). EPHI oversees capacity building of the public health workforce, national health data, and clinical and biomedical research in Ethiopia. He will be supervised by Dr Theodros Getachew, who is a well-established researcher in risk prediction modelling applications, and Professor Tadesse Awoke of the University of Gondar. Professor Yifru Berhan and Professor Alemayehu Worku will be collaborators as career mentors. The skills learned will be directly used to strengthen the research capacity of local universities and to mentor students.
“The AREF fellowship will be a tremendous opportunity and an eye opener for my research career. It will enhance my prospects in machine learning applications and contribute to stimulating global and local interest in risk prediction models for maternal and child health research.”