Agricultural and Biological Research

Developing a self-learning knowledge-based system for the follow-up and treatment of pregnancy-induced hypertension

Geleta Negasa, Chala Diriba and Worku Jimma*

Background: Managing follow-up and treatment complications in pregnant women with pregnancy-induced hypertension poses a significant global health challenge, being a leading cause of maternal and perinatal morbidity and mortality. Addressing this issue requires the development of a self-learning knowledge-based system that can aid health professionals in timely follow-up and treatment of pregnancy-induced hypertension to minimize maternal deaths. Thus, this study aimed to develop a self-learning knowledge-based system that helps patients and physician’s follow-up on pregnancy-induced hypertension and its treatment.

Methods: An experimental research design was employed to create the proposed system. Domain experts, selected purposively from Jimma Medical Center, contributed knowledge through structured and unstructured interviews. The acquired knowledge was then odelled and represented using a decision tree and production rules.

Results: A self-learning knowledge-based system for the follow-up and treatment of pregnancy-induced hypertension was successfully developed. The system’s performance was 81.25%, which demonstrated its effectiveness. Additionally, user acceptance of the system was assessed through visual interaction with domain experts, yielding a positive result of 83.44%.

Conclusion: The developed system plays a vital role in saving the lives of pregnant women, particularly in health centers where healthcare professionals are scarce. Moreover, it has the potential to reduce the time and cost associated with follow-up and treatment in health centers. Therefore, the researchers recommend the adoption of this system by hospitals and health centers to enhance healthcare services.