Klasifikasi Kondisi Penyakit Asma Menggunakan Algoritma Naïve Bayes

Abstract

Asthma is a chronic respiratory disease characterized by symptoms such as shortness of breath, coughing, and wheezing, and can be life-threatening if not properly treated. Delayed diagnosis and difficulty in assessing symptom severity are often the main causes of serious complications. This study aims to develop a classification model for asthma conditions using the Naïve Bayes algorithm based on clinical symptoms and patient demographic data. The dataset used was obtained from the public Kaggle platform, consisting of 316,800 samples with 19 attributes. The research stages included data pre-processing, model training, application of the Synthetic Minority Oversampling Technique (SMOTE), and model performance evaluation using accuracy, precision, recall, and F1-score metrics. The initial classification results showed an accuracy of 75.19%, which increased to 83.59% after applying SMOTE. The F1-score also improved from 77% to 83%. These findings indicate that the Naïve Bayes algorithm is capable of classifying asthma conditions reliably, quickly, and efficiently. Therefore, the model is considered suitable to be implemented as an initial classification system to support timely and accurate clinical diagnosis of asthma