<![CDATA[Pulmonary tuberculosis is an infectious disease that remains a major health problem in Indonesia. Early detection of this disease is very important to improve the effectiveness of treatment and prevention of its spread. The purpose of this study is to classify laboratory test data of pulmonary tuberculosis patients using the Probabilistic Neural Network method. The data used are medical records of patients with pulmonary tuberculosis disease at Puskesmas Telaga Sari, Balikpapan City in 2023-2024. The variables used are age, weight, systolic blood pressure, diastolic blood pressure, cough duration, fever duration, shortness of breath, and loss of appetite. The classification process involves the stages of encoding, data normalization, division of training data and testing data using a proportion of 80:20, and calculation of accuracy using confusion matrix. The results showed that classification using the Probabilistic Neural Network method was appropriate in classifying pulmonary tuberculosis disease and obtained the best smoothing parameter ( ) value of 0.1 with an accuracy value of 82.95% for training data and 95.45% for testing data.]]>
Copyrights © 2025
