This work investigates the impact of climate change characteristics on population health and employs the deep neural network (DNN) and hyperautomation mechanisms to achieve this goal. It aims to rapidly analyze climate changes using DNN, establish accurate models, and apply these models to predict and diagnose human health conditions. Hence, this work introduces the role of artificial intelligence (AI) in the realms of climate change and human health, followed by a detailed description of the Back-Propagation Neural Network (BPNN) training process. Subsequently, with Shaanxi Province as the climate study area, this work discusses the relationship between climate change features and population health. Then, it selects meteorological change conditions that easily lead to urticaria, a skin condition triggered by climate changes, as predictive factors to develop a population disease prediction model. This model forecasts climate changes to validate the BPNN method's practicality. To be specific, this work utilizes the national climate assessment datasets of the Environmental Protection Agency and the national health and nutrition examination survey datasets to predict the occurrence of urticaria in the human body. These datasets encompass physiological parameters, lifestyles, and health status information of urban residents, aiming to evaluate the impact of climate change on people's health. The results show that the BPNN model has a 29.45% higher prediction accuracy than the Logistic regression model and a 30.27% higher accuracy than the SVM model. Compared to the Transformer and the Generative Adversarial Network, the BPNN model also outperforms, exhibiting higher prediction accuracy and lower prediction errors. This indicates that the BPNN model exhibits a high level of accuracy when predicting the relationship between meteorological characteristics and urticaria prevalence. The high predictive accuracy of the BPNN model in the study of the relationship between climate change and human health holds significant prospects for ensuring public health and enhancing the scientific and targeted nature of medical decision-making.