Expert System for Early Detection of Postpartum Complications Using Certainty Factor Method

Abstract

Postpartum complications are one of the main causes of maternal mortality. The objective of this study was to design and build an expert system capable of early detection and providing consultation regarding health complications that occur during the postpartum period using the certainty factor method. The certainty factor approach is utilized to overcome the uncertainty that arises during the diagnosis process by combining the confidence values ​​of each symptom entered by the user. The research methods included needs identification, data collection, knowledge acquisition, knowledge base development, software design, software development, and testing. Needs identification generated 10 data sets, data collection was conducted through literature studies, and knowledge acquisition was obtained through interviews. The knowledge base was compiled based on information from experienced medical personnel. The software design included data flow, interface, and database. The software development resulted in a good early detection expert system. The expert system trial indicated superior performance in identifying health complications during the postpartum period with an accuracy rate of 91%. The ability to recognize positive cases reached 90.9%, and the error rate was 10%, indicating this system is reliable and accurate in decision-making.Postpartum complications are one of the main causes of maternal mortality. The objective of this study was to design and build an expert system capable of early detection and providing consultation regarding health complications that occur during the postpartum period using the certainty factor method. The certainty factor approach is utilized to overcome the uncertainty that arises during the diagnosis process by combining the confidence values ​​of each symptom entered by the user. The research methods included needs identification, data collection, knowledge acquisition, knowledge base development, software design, software development, and testing. Needs identification generated 10 data sets, data collection was conducted through literature studies, and knowledge acquisition was obtained through interviews. The knowledge base was compiled based on information from experienced medical personnel. The software design included data flow, interface, and database. The software development resulted in a good early detection expert system. The expert system trial indicated superior performance in identifying health complications during the postpartum period with an accuracy rate of 91%. The ability to recognize positive cases reached 90.9%, and the error rate was 10%, indicating this system is reliable and accurate in decision-making.