Pneumonia Detection Using Machine Learning and Deep Learning Methods on Clinical and Chest X-Ray Data

Pneumonia remains a major global health problem requiring timely and accurate treatment to improve patient outcomes. This study presents a comparative analysis of machine learning and deep learning methods for pneumonia detection using both clinical and chest X-ray data. Clinical features such as age, sex, temperature, heart rate, and laboratory results were integrated with imaging data from the Kaggle Chest X-Ray Pneumonia Dataset. Data preprocessing involved normalization, feature encoding, and image resizing to 224×224 pixels. Traditional machine learning models—Random Forest, Support Vector Machine (SVM), and Naive Bayes—were developed and compared with a Convolutional Neural Network (CNN) designed for image-based classification. Evaluation metrics including accuracy, precision, recall, F1-score, and ROC-AUC were used to assess performance. Experimental results demonstrated that the CNN model achieved the highest accuracy of 95%, outperforming all traditional models, while Random Forest achieved the best results among classical algorithms with 91% accuracy. The findings highlight the effectiveness of integrating clinical and imaging data for improved diagnostic accuracy and reliability. Future work will explore multi- class classification, larger datasets, and real-time deployment in hospital environments.