Improving the evaluation and prediction of prevention and treatment efficiency during public health emergencies by using the SBM-BPNN algorithm

Abstract

Crisis response is the key to reducing the impact and damage of public health emergencies. Previous studies only focused on specific measures for emergency response, but the effectiveness of these measures has seldom been discussed. How about the effective of the crisis response on public health emergencies? What will happen to the effectiveness of crisis response after the transformation of public health emergency measures? To address these questions, a novel research framework was constructed by combining slacks-based measure (SBM) and back propagation neural network (BPNN) algorithms. At Stage I, an efficiency evaluation was conducted on SBM with undesirable outputs to evaluate the prevention and treatment efficiency during public health emergencies, and stochastic frontier analysis was performed to mitigate the influence of environmental factors and statistical noise. At Stage II, the adjusted efficiency was predicted with the BPNN model. The decision-making units were effectively improved by incorporating slack variables, thus enabling the prediction and optimization of optimal cases given the epidemic resources. An empirical analysis of the response of 43 G20 member countries to the COVID-19 pandemic showed that the novel framework could evaluate prevention and treatment efficiency across regions and predict the efficiency and optimal case outputs following shifts in epidemic preventive measures. After evaluation, the mean squared error of the BPNN efficiency prediction model was only 0.0014, whereas that of the BPNN optimal output prediction model was 0.126. Therefore, this novel framework is suitable for evaluating and predicting the effectiveness of crisis response on public health emergencies, which provides necessary assistance for crisis decision-making by the government and emergency management organizations.