Background: Follow-up and treatment complications among pregnant women with pregnancy-induced hypertension is one of the significant global health challenges. It is one of the leading causes of maternal and perinatal morbidity and mortality. Thus, to address the problem, it is crucial to develop a self-learning knowledge-based system that assists health professionals in the timely follow-up and treatment of pregnancy-induced hypertensive and minimizes maternal death.
Methods: Experimental research design was used to develop the proposed system. The domain
experts were selected from Jimma Medical Center purposively to acquire knowledge using structured and unstructured interviews. The acquired knowledge was modelled and represented by a decision tree and a production rule, respectively.
Results: Developing a self-learning knowledge-based system for follow-up and treatment of pregnancy-induced hypertension was developed. The system's performance was evaluated and produced a result of 81.25%. In addition, user acceptance of the developed system was done by a visual interaction method, namely, by showing the system to the domain experts, and it was found that it produced 83.44%.
Conclusions: The developed system helps save the life of pregnant women in health centers where health professionals are scarce. In addition, it can reduce the time and cost of follow-up and treatment in the health center. Therefore, the researchers recommend that hospitals and health centers use the developed system to improve health services.