A multistage multimodal deep learning model for disease severity assessment and early warnings of high-risk patients of COVID-19.

The outbreak of coronavirus disease 2019 (COVID-19) has caused massive infections and large death tolls worldwide. Despite many studies on the clinical characteristics and the treatment plans of COVID-19, they rarely conduct in-depth prognostic research on leveraging consecutive rounds of multimodal clinical examination and laboratory test data to facilitate clinical decision-making for the treatment of COVID-19. To address this issue, we propose a multistage multimodal deep learning (MMDL) model to (1) first assess the patient's current condition (i.e., the mild and severe symptoms), then (2) give early warnings to patients with mild symptoms who are at high risk to develop severe illness. In MMDL, we build a sequential stage-wise learning architecture whose design philosophy embodies the model's predicted outcome and does not only depend on the current situation but also the history. Concretely, we meticulously combine the latest round of multimodal clinical data and the decayed past information to make assessments and predictions. In each round (stage), we design a two-layer multimodal feature extractor to extract the latent feature representation across different modalities of clinical data, including patient demographics, clinical manifestation, and 11 modalities of laboratory test results. We conduct experiments on a clinical dataset consisting of 216 COVID-19 patients that have passed the ethical review of the medical ethics committee. Experimental results validate our assumption that sequential stage-wise learning outperforms single-stage learning, but history long ago has little influence on the learning outcome. Also, comparison tests show the advantage of multimodal learning. MMDL with multimodal inputs can beat any reduced model with single-modal inputs only. In addition, we have deployed the prototype of MMDL in a hospital for clinical comparison tests and to assist doctors in clinical diagnosis.

A multistage multimodal deep learning model for disease severity assessment and early warnings of high-risk patients of COVID-19

The outbreak of coronavirus disease 2019 (COVID-19) has caused massive infections and large death tolls worldwide. Despite many studies on the clinical characteristics and the treatment plans of COVID-19, they rarely conduct in-depth prognostic research on leveraging consecutive rounds of multimodal clinical examination and laboratory test data to facilitate clinical decision-making for the treatment of COVID-19. To address this issue, we propose a multistage multimodal deep learning (MMDL) model to (1) first assess the patient's current condition (i.e., the mild and severe symptoms), then (2) give early warnings to patients with mild symptoms who are at high risk to develop severe illness. In MMDL, we build a sequential stage-wise learning architecture whose design philosophy embodies the model's predicted outcome and does not only depend on the current situation but also the history. Concretely, we meticulously combine the latest round of multimodal clinical data and the decayed past information to make assessments and predictions. In each round (stage), we design a two-layer multimodal feature extractor to extract the latent feature representation across different modalities of clinical data, including patient demographics, clinical manifestation, and 11 modalities of laboratory test results. We conduct experiments on a clinical dataset consisting of 216 COVID-19 patients that have passed the ethical review of the medical ethics committee. Experimental results validate our assumption that sequential stage-wise learning outperforms single-stage learning, but history long ago has little influence on the learning outcome. Also, comparison tests show the advantage of multimodal learning. MMDL with multimodal inputs can beat any reduced model with single-modal inputs only. In addition, we have deployed the prototype of MMDL in a hospital for clinical comparison tests and to assist doctors in clinical diagnosis.

How culture orientation influences the COVID-19 pandemic: An empirical analysis.

Purpose: This study aims to investigate the mediational path of the influence of cultural orientation on the COVID-19 pandemic outcome at the national level and find out whether some culture-related factors can have a moderating effect on the influence of culture. Methodology: Cultural dimension theory of Hofstede is used to quantify the degree of each dimension of culture orientation. The cross-section regression model is adopted to test if culture orientations affect the pandemic outcome, controlling for democracy, economy, education, population, age, and time. Then, a mediational analysis is conducted to examine if policy response is the mediator that culture makes an impact on the pandemic outcome. Finally, a moderation analysis is carried out to determine how each control variable has moderated the influence. Findings: The cross-section regression results showed that culture orientation influences the outcome of the COVID-19 pandemic at the 99% confidence level and that among the six cultural dimensions, collectivism-individualism has the most significant impact. It has also been found that policy response is the mediator of cultural influence, and culture-related factors can moderate the influence. Contribution: The contribution of this research lies in developing the assertion that culture influences pandemic outcomes. Our findings indicate that collectivism-individualism culture orientation affects the effectiveness of epidemic controls the most among the six culture dimensions. Additionally, our research is the first to study the mediating effect of policy responses and the moderating effect of culture-related factors on the influence of cultural orientation on the pandemic outcome.

How culture orientation influences the COVID-19 pandemic: An empirical analysis

Purpose This study aims to investigate the mediational path of the influence of cultural orientation on the COVID-19 pandemic outcome at the national level and find out whether some culture-related factors can have a moderating effect on the influence of culture. Methodology Cultural dimension theory of Hofstede is used to quantify the degree of each dimension of culture orientation. The cross-section regression model is adopted to test if culture orientations affect the pandemic outcome, controlling for democracy, economy, education, population, age, and time. Then, a mediational analysis is conducted to examine if policy response is the mediator that culture makes an impact on the pandemic outcome. Finally, a moderation analysis is carried out to determine how each control variable has moderated the influence. Findings The cross-section regression results showed that culture orientation influences the outcome of the COVID-19 pandemic at the 99% confidence level and that among the six cultural dimensions, collectivism-individualism has the most significant impact. It has also been found that policy response is the mediator of cultural influence, and culture-related factors can moderate the influence. Contribution The contribution of this research lies in developing the assertion that culture influences pandemic outcomes. Our findings indicate that collectivism-individualism culture orientation affects the effectiveness of epidemic controls the most among the six culture dimensions. Additionally, our research is the first to study the mediating effect of policy responses and the moderating effect of culture-related factors on the influence of cultural orientation on the pandemic outcome.