A Web-Based Analytical Framework for Infectious-Disease Forecasting and Chest X-Ray Image Analysis in Emergency Conditions

The spread of infectious diseases under wartime and resource-constrained conditions creates a need for analytical tools that support both population-level epidemiological monitoring and preliminary patient-level image analysis. This study develops and evaluates a web-based analytical framework incorporating two complementary modules: infectious-disease forecasting and chest X-ray image analysis. For epidemiological forecasting, ARIMA, deep neural network (DNN), and long short-term memory (LSTM) models were evaluated to compare statistical, feed-forward neural-network, and recurrent neural-network approaches to one-month-ahead prediction using Ukrainian epidemiological data from 2020 to 2023. For chest X-ray analysis, YOLOv8 and YOLOv11 nano and small configurations were compared in a proof-of-concept experiment involving five pulmonary categories. The two analytical modules were integrated at the application level within a common web-based interface providing data upload, model selection, analysis, and result visualization. Under the adopted one-month-ahead hold-out evaluation, DNN and LSTM generally provided lower forecasting errors than the ARIMA baseline. In the image-analysis experiment, YOLOv11s produced the highest validation mAP@0.5:0.95 among the evaluated configurations, reaching 0.74. However, the public chest X-ray dataset had been augmented by its provider before acquisition, and the present image-analysis evaluation used training and validation partitions without an independent test subset for final performance assessment. Therefore, the reported image-analysis metrics characterize only the adopted validation partition, may overestimate performance on independent data, and should not be interpreted as estimates of clinical or external generalization. In addition, the manually prepared bounding-box annotations were not independently verified by a qualified clinical expert. Accordingly, the image-analysis component should be regarded as a proof-of-concept computational evaluation rather than a clinically validated diagnostic system. The developed prototype demonstrates the technical feasibility of providing epidemiological forecasting and preliminary chest X-ray image analysis within a common application environment for emergency and resource-constrained settings.