Muhammad Irsyad, Benny Sukma Negara, Sarifah Muliani
X-ray imaging is an effective tool for detecting lung diseases such as COVID-19 and pneumonia, and its capabilities can be enhanced using artificial intelligence-based systems. This study develops a chest X-ray image classification system using a Convolutional Neural Network (CNN) with the VGG-16 architecture and integrates Shapley Additive Explanations (SHAP) to make the model’s predictions explainable. The model is trained on a dataset of 3,030 X-ray images divided into three classes (COVID-19, pneumonia, and normal), using several configurations; the best performance is achieved with an 80%:20% train-validation split, a learning rate of 0.001, a batch size of 32, and 50 epochs. The trained model attains 95.75% accuracy on the training data and 96.00% on the validation data. SHAP is then applied to generate heatmap visualizations that highlight the image regions most influential to each prediction, thereby improving interpretability and supporting clinical decision-making. The results demonstrate that combining deep learning with SHAP can produce both highly accurate and visually interpretable lung disease detection from chest X-ray images.
@article{a676577d-875c-45c4-8dac-b04858597cbc,
title={Explainable Deep Learning for Lung Disease Detection on Chest X-Ray Images Using Shapley Additive Explanations (SHAP)},
author={Muhammad Irsyad and Benny Sukma Negara and Sarifah Muliani},
year={2026},
language={en}
}TY - JOUR TI - Explainable Deep Learning for Lung Disease Detection on Chest X-Ray Images Using Shapley Additive Explanations (SHAP) AU - Muhammad Irsyad AU - Benny Sukma Negara AU - Sarifah Muliani PY - 2026 LA - en ER -
Introduction Concerns over air pollution and the environmental problem of acid rain have made governments all over the world tighten their regulations
Roger Rumbu check
Huan Li, Elsayed Oraby, Jacques Eksteen
Waste printed circuit boards (WPCBs) are a complicated and valuable fraction of electric and electronic waste. The recycling of them is critical to av
Roger Rumbu
PNAS Nexus
This article reports the design and characterization of a high-performance, truly solid polymer electrolyte for lithium-based batteries, addressing lo
Riken
This article reports the development of a room-temperature hydride ion (H⁻)-conducting solid electrolyte, representing a significant advance toward pr