key: cord-0027214-w5t59wg4 authors: Tsai, Sang-Bing; Wu, Tao; Wu, Chia-Huei; Yue, Xiaohang title: Editorial for the special issue on “Transforming public health through artificial intelligence, machine learning and internet of things” date: 2022-02-15 journal: Socioecon Plann Sci DOI: 10.1016/j.seps.2022.101267 sha: 10b1d7cfc315f7e3876709e02b6317b361c941e0 doc_id: 27214 cord_uid: w5t59wg4 nan In recent years, information technologies such as Artificial Intelligence (AI), Machine Learning (ML) and Internet of Things (IoT) have received unprecedented attention and have caused profound changes in traditional lifestyles. In particular, these technologies had a significant impact on social change and public health innovation transformation. For example, Ahamed and Farid [1] proposed the application of IoT and ML in personalized healthcare. Chui et al. [2] also discussed the application of these technologies in healthcare. In addition, considering the current outbreak of COVID-19, these information technologies can also be used to deal with healthcare emergencies, such as speeding up the diagnosis of viruses and monitoring the movement of personnel. Based on this background, this editorial briefly describes 16 articles published in this special issue, focusing on the latest development of "changing public health through AI, ML and the IOT". In the article titled "Outlier knowledge management for extreme public health events: Understanding public opinions about COVID-19 based on microblog data", Xia et al. [3] used an advanced natural language processing (NLP) technology based on the complex adaptive system theory and the information theory of heterogeneous situation investigation to mine and extract the microblog data of 2019 coronavirus in Wuhan province and Henan Province, which further proves the credibility of their abnormal value knowledge management framework. Starting from three aspects of dimension object and situation, this framework provides a new idea and method for outlier knowledge management in medical environment. Due to the wide spread and spatiotemporal nature of COVID-19, combined with its influencing factors, Huang et al. [4] proposed a COVID-19Net framework to predict the disease in three European countries with serious epidemic situation, which combined 1D convolutional neural network, 2D convolutional neural network, and bidirectional gated recurrent units. The results verified the accuracy of the framework and provided a certain reference for the formulation of public health strategies. Meanwhile, the authors call for maintaining a certain social distance and reducing unnecessary travel, which is more beneficial to epidemic prevention and control. In contrast, Masum et al. [5] applied mathematical epidemic model (MEM), statistical model and recursive neural network (RNN) variables to predict the cumulative confirmed cases. The results show that the prediction of RNN variants is more accurate, but MEM can provide more comprehensive insights into virus transmission and control strategies. The application of these next-generation information technologies to effectively improve the health of urban residents is a hot topic of research. Using three years of panel data from the CHARLS national baseline survey, Wu et al. [6] found the evidence that the establishment of smart city can reduce the use of outpatient services and improve the utilization of inpatient services, which is conducive to the improvement of urban medical care, and this effect is more significant in rural areas. Similarly, Vȃidean et al. [7] studied the healthcare constructions at the country level from the perspective of information and communication technology (ICT). Using parametric regression analysis of unbalanced panel data, the article investigates the impact of ICT on life expectancy, mortality and measles immunization rate in 185 countries over the past 14 years. In another article, Wu et al. [8] studied the impact of the management model of IoT on the equalization of public services by means of quantitative analysis and comparative research. The results show that the equalization of public services is developing better under this model. For example, the government's investment in public services has increased by nearly a quarter, and the application of education in the IoT has been further improved. In addition, Popkova et al. [9] supplies intelligent monitoring and smart digital public health management based on the IoT. The article presents a successfully applied development of new datasets and offers an innovative solutions through interactive platforms to gather, process, and analyze big data in digital public health amid virus threats. How to obtain a certain level of sustainability in the health system has also been widely explored by scholars. Pereira et al. [18] proposed a sunshine regulation model using multi criteria decision analysis to enable the health system to play a full role in the accountability and transparency of the new public governance. In the field of health services, the health 4.0 paradigm can effectively improve the participation of patients and nurses in the process of value creation. Ciasullo et al. [10] found that health 4.0 can bring double benefits and provide health services more effectively and timely, which will help to provide solutions to enhance the economic feasibility and social sustainability of the health care system in the future. Zhu et al. [11] tried to investigate the contribution of AI and modern social science technologies to public health emergencies. Using the 3S technology closely related to AI technology, the authors designed and established a public health emergency response system, which found the evidence that the application of AI technology can effectively improve the government's response and decision-making capabilities to public health emergencies and reduce the occurrence of emergencies. Similarly, AI technology has been also applied to public medical centers. Since the existing literature rarely discusses the intelligent medical management system with quantitative and qualitative methods, a hybrid exploratory three-phased Multi-criteria Decision-making (MCDM) model that combines the Decision-Making Trial and Evaluation Laboratory Model (DEMATEL) approach, the Analytic Network Process (ANP), and Zero-One Goal Programming (ZOGP) was proposed by Yang et al. [12] ; which can effectively improve the reliability of Smart Healthcare Management System (SHMS) portfolio. The outbreak of SARS in 2003 has brought indelible influence on some people, which may also increase the fear of COVID-19. However, Yao et al. [13] applied AI and big data to the study and concluded that SARS experience affects people's anxiety and the fear of COVID-19, but the use of AI and big data can mitigate such imprinting effect. Since the outbreak of COVID-19, criminal acts endangering public health seriously threaten public health safety. How to effectively prevent crimes against public health in the era of big data, Wang et al. [14] gave their answer. Applying the machine learning algorithm, they established a predictive criminal behavior model based on support vector machine and random forest algorithm. The experimental results show that the prediction model established by artificial intelligence algorithm can effectively predict criminal behaviors that endanger public health and provide reliable data for prevention. The outbreak of COVID-19 not only affects public health safety, but also enlarges the social injustice caused by the gap between the rich and the poor. We have to admit that the spread of the epidemic makes poor communities and minorities more vulnerable than other groups. Based on this phenomenon, Anahideh et al. [15] proposed a collaborative intervention strategy to enable vulnerable groups to enjoy higher priority in the allocation of medical resources, so as to avoid injustice to a greater extent. It is worth mentioning that the high allocation method can be applied to the allocation of other scarce resources and social benefits. Huang et al. [16] proposed a data-driven strategy based on the machine learning method of logical regression and prioritization, in order to analyze the weaknesses of the current detection strategy of pandemic. They argued that the change of risk factors is the reason for the failure of current testing strategy, and suggested promoting the data-driven testing strategy to better respond to the global pandemic. The problem of ambulance offload delay (AOD) is becoming more and more serious in Canada. Serious delay will greatly reduce the efficiency of the healthcare system. Li et al. [17] developed a new decision support tool -hybrid decision tree model to predict the severity of AOD, so as to facilitate decision makers to take the initiative to alleviate AOD. This method can be applied to the management data in the medical and health care environment, and can be well extended to other emergency medical service (EMS) systems, which will greatly improve the operation efficiency of the system. This Special Issue has collected some good articles. It had great repercussions and success. We thank all authors for your participation. Applying internet of things and machine-learning for personalized healthcare: issues and challenges Disease diagnosis in smart healthcare: innovation, technologies and applications Outlier knowledge management for extreme public health events: Understanding public opinions about COVID-19 based on microblog data Novel spatiotemporal feature extraction parallel deep neural network for forecasting confirmed cases of coronavirus disease 2019 Comparative study of a mathematical epidemic model, statistical modeling, and deep learning for COVID-19 forecasting and management Empirical research on smart city construction and public health under information and communications technology When more is less: do information and communication technology (ICT) improve health outcomes? An empirical investigation in a nonlinear framework Development path based on the equalization of public services under the management mode of the Internet of Things Digital public health: automation based on new datasets and the Internet of Things Putting Health 4.0 at the service of Society 5.0: exploratory insights from a pilot study Can artificial intelligence enable the government to respond more effectively to major public health emergencies?--taking the prevention and control of Covid-19 in China as an example A hybrid multiple-criteria decision portfolio with the resource constraints model of a smart healthcare management system for public medical centers The imprinting effect of SARS experience on the fear of COVID-19: the role of AI and big data Preventing crimes against public health with artificial intelligence and machine learning capabilities Fair and diverse allocation of scarce resources Data-driven test strategy for COVID-19 using machine learning: a study in Lahore Predicting ambulance offload delay using a hybrid decision tree model Is sunshine regulation the new prescription to brighten up public hospitals in Portugal?