Novel Case-Based Reasoning System for Public Health Emergencies

Abstract

Purpose: Several threatening infectious diseases, including influenza, Ebola, SARS, and COVID-19, have affected human society over the past decades. These disease outbreaks naturally inspire a demand for sustained and advanced safety and suppression measures. To protect public health and safety, further research developments on emergency analysis methods and approaches for effective emergency treatment generation are urgently needed to mitigate the severity of the pandemic and save lives. Methods: To address these issues, a novel case-based reasoning (CBR) system is proposed using three phases. In the first phase, the similarity between the current case and the historical cases is calculated under a variety of heterogeneous information. In the second phase, a filter approach based on grey clustering analysis is created to retrieve relevant cases. In the third phase, the cases retrieved are taken as initial host nests in a cuckoo search (CS) algorithm, and our system searches an optimal solution through iteration of this algorithm. Results: The proposed model is compared with a CBR method improved by particle swarm optimization (PSO) and a CBR method improved by a differential evolution algorithm (DE), to confirm the efficiency of our CS algorithm in adapting solutions for public health emergencies. The results show that the proposed model is better than the existing algorithms. Conclusion: The proposed model improves the speed of case retrieval using grey clustering and increases solution accuracy with CS algorithms. The present research can contribute to government, CDC, and infectious disease emergency management fields with regard to the implementation of fast and accurate public biohazard prevention and control measures based on a variety of heterogeneous information.

Henipaviruses—A constant threat to livestock and humans

“…Recent outbreaks of EBOV in Democratic Republic of Congo (DRC) or Guinea in the End of 2020 and the beginning of this year, respectively, were declared as "public health emergency of international concern" due to spread into areas that had not been affected before [12]. Thus, effective emergency treatment is needed to respond faster for mitigation and to control disease outbreaks [13].…”

Public Health Events Emergency Management Supervision Strategy with Multi-agent Participation

“…Once the infectious disease breaks out, it will spread across the world, which will cause a huge impact on the world public health (Lu et al 2019). To protect public health and safety, there is an urgent need for further research on emergency analysis methods and approaches for effective emergency response methods to mitigate the severity of the pandemic and save lives (Duan et al 2021). The evolution process of emergency can be divided into four stages: potential stage, sudden stage, spreading stage and recovery stage (Deng et al 2020).…”

Optimization in the Context of COVID-19 Prediction and Control: A Literature Review

“…Finally, some studies [16] – [22] , [131] – [146] followed a model-agnostic approach and relied solely on the historical time series data of COVID-19 cases or other relevant predictors to forecast future cases. These methods employ machine learning models (neural networks [17] – [21] , [133] , [135] , [138] , [142] and deep learning [139] ) to make predictions while using various optimization algorithms (such as Gaussian process regression [16] , Bayesian optimization [17] , and metaheuristic algorithms [18] – [22] , [144] , [147] – [149] ) to optimize the model hyperparameters. When the only input was COVID-19 time series data, the optimization model was essentially a curve-fitting problem, where the objective function was to minimize the squared error between the predicted and actual values.…”