Authors :
Athira V. P.
Volume/Issue :
Volume 10 - 2025, Issue 10 - October
Google Scholar :
https://tinyurl.com/bx8huzas
Scribd :
https://tinyurl.com/mrxycx8b
DOI :
https://doi.org/10.38124/ijisrt/25oct784
Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.
Note : Google Scholar may take 30 to 40 days to display the article.
Abstract :
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.
Keywords :
Pneumonia, Machine Learning, Convolutional Neural Network, Random Forest, Clinical Data, Chest X-Ray.
References :
- Paul Mooney. “Chest X-Ray Images (Pneumonia) Dataset,” Kaggle, 2018. Link
- Chouhan, V., et al. “A Deep Learning Approach for Pneumonia Detection Using Chest X-ray Images.” Applied Sciences, 2019.
- Rajpurkar, P., et al. “CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning.” arXiv preprint arXiv:1711.05225, 2017.
- Hall, M., et al. “The WEKA Data Mining Software: An Update.” SIGKDD Explorations, 2009.
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.
Keywords :
Pneumonia, Machine Learning, Convolutional Neural Network, Random Forest, Clinical Data, Chest X-Ray.
