Using a Convolutional Neural Network for Early Infectious Disease Detection During Public Health Emergencies

Proactively detecting infectious illnesses aids in delivering superior therapy and improves preventing and managing such diseases. This work proposed a Convolutional Neural Network for early Infectious Disease Detection during Public Health Emergencies (CNN-IDD-PHE). The objective is to mitigate the significant damages that Public Health Emergencies (PHE) inflicted on individuals' well-being, everyday routines, and the whole national economy. Statistics on Tuberculosis (TB) cases in a city were gathered from July 2020 to 2022. The Structural Equation Model (SEM) is designed to ascertain the correlation between latent and observed variables by identifying the appropriate indicators and estimating the parameters. A prediction model using Convolutional Neural Network (CNN) has been developed. The strategy's efficacy is validated by assessing the loss value and accuracy of the detection model during both the training and testing phases. Hence, using CNN in Deep Learning (DL) for early warning systems performs better in predicting and alerting Public Health (PH) situations. This advancement is of great importance in enhancing the capabilities of early warning systems.