Classification of Infertility Risk in Female Patients Based on Medical Record Data Using Naive Bayes Algorithm

Infertility is a reproductive health problem that has a significant impact globally, especially in developing countries such as Indonesia. This study aims to classify the risk of infertility in female patients at Rantauprapat Regional Hospital by utilizing the Naive Bayes algorithm based on electronic medical record data. The data used consisted of 500 medical records of female patients of childbearing age during the period 2019–2022, which had been processed and divided into training data (70%) and testing data (30%). The analysis and modeling process was carried out using the RapidMiner application without requiring programming skills. The results showed that the Naive Bayes model was able to classify the risk of infertility with an accuracy level of 86.7%, precision of 91.0%, recall of 93.2%, and F1-score of 92.1%. The main factors that most influence the classification of infertility include a history of reproductive disease, patient age, hormonal examination results, body mass index, and history of sexually transmitted infections. These findings indicate that the integration of the Naive Bayes algorithm into medical record data can be an effective solution for early detection of infertility clinically and support data-based decision making. This study also recommends increasing data and attribute coverage, as well as comparison with other algorithms for more optimal results in the future