Enhancing Lung Disease Diagnosis: A High Performance Hybrid Deep Learning Framework for Multi‐Class Chest X‐Ray Analysis

ABSTRACT This study presents a high performance hybrid deep learning model for the classification of 14 lung diseases using chest X‐ray (CXR) images. Manual evaluation of CXR images is labor‐intensive and prone to human error. Therefore, automated systems are required to improve diagnostic accuracy and efficiency. Our model integrates ResNet18 and EfficientNet‐V2‐S architectures, combining residual connections with efficient scaling to achieve high accuracy while maintaining computational efficiency. Trained on the NIH ChestX‐ray14 dataset, comprising 112 120 images across 14 disease classes, the model mitigates class imbalances with extensive data augmentation techniques. Achieving an impressive average AUC of 0.872, the model outperforms previous approaches. This performance was enhanced by a refined, anatomically‐aware data augmentation strategy that improved the model's robustness and clinical relevance, particularly in challenging disease categories such as Pneumothorax, Emphysema, and Hernia. To further validate its generalizability, the proposed model was tested on three additional datasets for pneumonia, COVID‐19, and tuberculosis. The results demonstrate superior performance, achieving an accuracy of 0.958, F 1 score of 0.944, and ROC AUC of 0.989 for pneumonia; an accuracy of 0.974, F 1 score of 0.969, and ROC AUC of 0.995 for COVID‐19; and an accuracy of 0.999, F 1 score of 0.999, and ROC AUC of 0.999 for tuberculosis. These outstanding results confirm the robustness and clinical applicability of the model across diverse datasets. This research introduces a reliable and efficient diagnostic tool that enhances the potential of automated lung disease classification. By alleviating radiologists' workload and promoting timely, accurate diagnostic outcomes, the model contributes significantly to medical imaging applications and demonstrates its capacity for practical use in real‐world clinical settings.