Yongdong Shi

Currently, individual artificial intelligence (AI) algorithms face significant challenges in effectively diagnosing and predicting early stage emerging serious diseases. Our investigation indicates that these challenges primarily arise from insufficient clinical treatment data, leading to inadequate model training and substantial disparities among algorithm outcomes. Therefore, this study introduces an adaptive framework aimed at increasing prediction accuracy and mitigating instability by integrating various AI algorithms. In analyzing two cohorts of early cases of the coronavirus disease 2019 (COVID-19) in Wuhan, China, we demonstrate the reliability and precision of the adaptive combined learning algorithm. Employing an adaptive combination with three feature importance methods (Random Forest (RF), Scalable end-to-end Tree Boosting System (XGBoost), and Sparsity Oriented Importance Learning (SOIL)) for two cohorts, we identified 23 clinical features with significant impacts on COVID-19 outcomes. Subsequently, the adaptive combined prediction leveraged and enhanced the advantages of individual methods based on three forecasting algorithms (RF, XGBoost, and Logistic regression). The average accuracy for both cohorts exceeded 0.95, with the area under the receiver operating characteristics curve (AUC) values of 0.983 and 0.988, respectively. We established a severity grading system for COVID-19 based on the combined probability of death. Compared to the original classification, there was a significant decrease in the number of patients in the severe and critical levels, while the levels of mild and moderate showed a substantial increase. This severity grading system provides a more rational grading in clinical treatment. Clinicians can utilize this system for effective and reliable preliminary assessments and examinations of patients with emerging diseases, enabling timely and targeted treatment.

COVID-19 may not only pose threats but also provided opportunities for innovation and growth for many high-tech small- and medium-sized enterprises (SMEs). This study investigates the relationship between entrepreneurial passion (EP), dynamic capability (DC) for innovation and product innovation performance in SMEs during COVID-19. Hierarchical regression and bootstrapping methods were employed per the survey data of 195 Chinese SMEs. The results reveal that EP is an imperative antecedent of DC and product innovation. DC also positively mediates the relationship between SMEs’ product innovation performance and top managers’ EP. In addition, this mediation effect of DC becomes more pronounced when firms are facing more opportunities. These findings advance the existing literature by specifying the process top managers use to cultivate product innovation within SMEs in times of crisis.

Tourism destinations are now facing a dilemma choice of controlling the epidemic or developing the economy. This paper takes Macao, a typical international tourist city, as an example to study the strategy of tourist source control during the COVID-19 period. According to the published epidemic data of Macao, this study has established an improved SEIR (Susceptible-Exposed-Infected-Recovered) model, formulated six control strategies against the current epidemic, and used the model above to simulate the time required for all confirmed cases to recover and discharge under different strategies. By taking into consideration the gross revenue of Macao’s gambling industry from 2017 to 2019, the impact of different strategies on the economy is predicted and three control strategies are found to be feasible. This study shows that an effective way to break through the above dilemma is to design the tourist management strategy by screening the source of passengers and controlling the upper limit of capacity of destination. These findings provide a scientific basis for tourism destinations in formulating public policies. The improved SEIR model is more consistent with the actual conversion rule of patients in the current COVID-19 epidemic, and it can be applied to further public health related research.

Recently, most countries have entered the outbreak period of the novel coronavirus epidemic. This sudden outbreak has caused a huge impact on the global economy, which has intensified the division of globalization and the recession of the global economy. Although the epidemic situation in China has gradually stabilized, the severe situation in the world still inevitably impacts China's economy. Based on the uncertainty of future epidemic, this paper sets up three scenarios to analyze the impact of the epidemic on China's economy. The first is that in June, the epidemic both at home and abroad is under control without rebound; the second is that the domestic epidemic is basically controlled but the foreign situation is not effectively controlled; the third is that the epidemic situation in China has a serious rebound due to the influence of the imported cases from abroad, which destroy the economy again. At the same time, some corresponding guidelines are put forward for the recovery of economy, and to minimize the economic losses as well as accelerate the pace of national economic recovery. In addition, it is believed that these suggestions may have certain reference value to other countries.

With the rapid development of the global economy, crude oil is becoming more and more prominent in terms of national stability. However, oil prices dramatically fluctuate during emergencies. Meanwhile, network search data have been widely used for prediction during the era of big data. Herein, a suggestion is introduced for improving the traditional case analysis. An autoregressive distributed lag model is established, considering emergency and network search data. Moreover, a network attention index of specific emergencies is used to explain fluctuations of the oil price and the influence of this attention is analyzed. Results show: 1) major emergencies have a significant short‐term impact on the international oil market and a remarkable influence on the cumulative abnormal return of an event window, and 2) market attention can aggravate fluctuations of oil prices. It is found that the individual network attention paid to each of four emergencies has a significant impact on oil prices. The network attention related to Hurricane Katrina and the Libyan war has positive effects on oil prices. However, the effects of network attention paid to the subprime crisis and the Mexico oil spill of 2010 are negative. The attention paid to the subprime crisis has both the greatest and the longest lasting impact.

The investigation of the interface between psychological constructs, compulsive consumption of alcohol and pathological gambling is an important avenue for development of future initiatives in social marketing or prevention programs. This cross-cultural study attempts to bridge the gap in literature by providing an evaluation of the predictive ability of psychological variables such as gambling urge, gambling-related erroneous cognitions and comorbid alcohol consumption on pathological gambling behaviour and its impact on overall quality of life indicators. Participants consist of 445 Macao and Australian young adults (Mean age = 23 years). Results indicate that probable pathological gamblers as compared with non-gamblers reported significantly lower quality of life in all domains—physical health, psychological well-being, social relationships and environment. Adults who drank more alcohol and have stronger erroneous cognitions evidenced higher pathological gambling behavior. Our research model fits both cohorts and interestingly, erroneous gambling-related cognitions serve as a full mediator for the predictive relationship between gambling urge and pathological gambling in the Macao sample, but serve as a partial mediator in the Australian sample. Targeting erroneous cognitions in future social marketing or preventive campaigns should demonstrate to be an important strategy in reducing the effects of urge to gamble among at-risk individuals. Further implications for the industry, marketing and governmental strategies are discussed.