The interpretation of Chest X-ray is an important diagnostic issue in clinical practice and especially in the resource-limited setting where the shortage of radiologists plays a role in delayed diagnosis and poor patient outcomes. Although the original CheXNet architecture has shown potential in automated analysis of chest radiographs, DenseNet-121 backbone is computationally inefficient and poorly single-label classifier. To eliminate such shortcomings, we suggest a better classification framework of chest disease that relies on EfficientNetV2-M and incorporates superior training approaches such as Automatic Mixed Precision training, AdamW, Cosine Annealing learning rate scheduling, and Exponential Moving Average regularization. We prepared a dataset of 18,080 chest X-ray images of three source materials of high authority and representing five key clinically significant disease categories which included Cardiomegaly, COVID-19, Normal, Pneumonia, and Tuberculosis. To achieve statistical reliability and reproducibility, nine independent experimental runs were run. The suggested architecture showed significant gains with mean test accuracy of 96.45 percent compared to 95.30 percent at baseline (p less than 0.001) and macro-averaged F1-score increased to 91.08 percent (p less than 0.001). Critical infectious diseases showed near-perfect classification performance with COVID-19 detection having 99.95 percent accuracy and Tuberculosis detection having 99.97 percent accuracy. Although 6.8 times more parameters are included, the training time was reduced by 11.4 percent and performance stability was increased by 22.7 percent. This framework presents itself as a decision-support tool that can be used to respond to a pandemic, screen tuberculosis, and assess thoracic disease regularly in various healthcare facilities.

Optimization techniques are pivotal in neural network training, shaping both predictive performance and convergence efficiency. This study introduces Foxtsage, a novel hybrid optimisation approach that integrates the Hybrid FOX-TSA with Stochastic Gradient Descent for training Multi-Layer Perceptron models. The proposed Foxtsage method is benchmarked against the widely adopted Adam optimizer across multiple standard datasets, focusing on key performance metrics such as training loss, accuracy, precision, recall, F1-score, and computational time. Experimental results demonstrate that Foxtsage achieves a 42.03% reduction in loss mean (Foxtsage: 9.508, Adam: 16.402) and a 42.19% improvement in loss standard deviation (Foxtsage: 20.86, Adam: 36.085), reflecting enhanced consistency and robustness. Modest improvements in accuracy mean (0.78%), precision mean (0.91%), recall mean (1.02%), and F1-score mean (0.89%) further underscore its predictive performance. However, these gains are accompanied by an increased computational cost, with a 330.87% rise in time mean (Foxtsage: 39.541 seconds, Adam: 9.177 seconds). By effectively combining the global search capabilities of FOX-TSA with the stability and adaptability of SGD, Foxtsage presents itself as a robust and viable alternative for neural network optimization tasks.