An external validation study of the Score for Emergency Risk Prediction (SERP), an interpretable machine learning-based triage score for the emergency department.

Emergency departments (EDs) are experiencing complex demands. An ED triage tool, the Score for Emergency Risk Prediction (SERP), was previously developed using an interpretable machine learning framework. It achieved a good performance in the Singapore population. We aimed to externally validate the SERP in a Korean cohort for all ED patients and compare its performance with Korean triage acuity scale (KTAS). This retrospective cohort study included all adult ED patients of Samsung Medical Center from 2016 to 2020. The outcomes were 30-day and in-hospital mortality after the patients' ED visit. We used the area under the receiver operating characteristic curve (AUROC) to assess the performance of the SERP and other conventional scores, including KTAS. The study population included 285,523 ED visits, of which 53,541 were after the COVID-19 outbreak (2020). The whole cohort, in-hospital, and 30 days mortality rates were 1.60%, and 3.80%. The SERP achieved an AUROC of 0.821 and 0.803, outperforming KTAS of 0.679 and 0.729 for in-hospital and 30-day mortality, respectively. SERP was superior to other scores for in-hospital and 30-day mortality prediction in an external validation cohort. SERP is a generic, intuitive, and effective triage tool to stratify general patients who present to the emergency department.

Psychological health intervention for children and adolescents during outbreak of novel coronavirus

The COVID-19 pandemic has severely affected people's daily life globally, especially for the physical and mental health of children and adolescents, the vulnerable group. This paper reviews the studies, up to August 24, 2020, focusing on the following four aspects. Firstly, the mental stressors among children and adolescents are discussed from national and society, school and community, family and individual perspectives, such as the social isolation, the health care facility closures, the school closures, the economic deterioration, the home quarantine, the domestic violence and abuse, the increased screen time, and others. Secondly, the main types of psychological problems in teenagers during the COVID-19 are discussed. Emotional problems mainly include the anxiety, the depression, the loneliness, the sleep problems, the psychosomatic problems and the stress-related problems. Behavioral problems mainly include:the internet addiction, the sexual abuse behaviors, the parent-child conflicts, and others. Finally, children and adolescents are divided into five categories according to different risks under the background of COVID-19:the ordinary children, the children living in high exposure risk areas, the children with their caregivers being affected or being frontline workers, the quarantined children, the children with other diseases and the infected children. And intervention recommendations include the health education, the epidemic prevention, the knowledge popularization, the parent accompaniment;the hospital 24-hour on-duty nursing system, the online consultation and the online pharmacy;the remote interactive online education, the remote psychiatry, the book therapy, the music therapy, the emotion-focused therapy (EFT), the parent-child interaction therapy (PCIT), the cognitive behavioral writing therapy(CBWT), the eye movement desensitization and reprocessing (EMDR) and the drug therapy.

An external validation study of the Score for Emergency Risk Prediction (SERP), an interpretable machine learning-based triage score for the emergency department (preprint)

Emergency departments (EDs) are experiencing complex demands. An ED triage tool, the Score for Emergency Risk Prediction (SERP), was previously developed using an interpretable machine learning framework. It achieved a good performance in the Singapore population. We aimed to externally validate the SERP in a Korean cohort for all ED patients and compare its performance with Korean triage acuity scale (KTAS). This retrospective cohort study included all adult ED patients of Samsung Medical Center from 2016 to 2020. The outcomes were 30-day and in-hospital mortality after the patients’ ED visit. We used the area under the receiver operating characteristic curve (AUROC) to assess the performance of the SERP and other conventional scores, including KTAS. The study population included 285,523 ED visits, of which 53,541 were after the COVID-19 outbreak (2020). The whole cohort, in-hospital, and 30 days mortality rates were 1.60%, and 3.80%. The SERP achieved an AUROC of 0.821 and 0.803, outperforming KTAS of 0.679 and 0.729 for in-hospital and 30-day mortality, respectively. SERP was superior to other scores for in-hospital and 30-day mortality prediction in an external validation cohort. SERP is a generic, intuitive, and effective triage tool to stratify general patients who present to the emergency department

Epicasting: An Ensemble Wavelet Neural Network (EWNet) for Forecasting Epidemics (preprint)

Infectious diseases remain among the top contributors to human illness and death worldwide, among which many diseases produce epidemic waves of infection. The unavailability of specific drugs and ready-to-use vaccines to prevent most of these epidemics makes the situation worse. These force public health officials, health care providers, and policymakers to rely on early warning systems generated by reliable and accurate forecasts of epidemics. Accurate forecasts of epidemics can assist stakeholders in tailoring countermeasures, such as vaccination campaigns, staff scheduling, and resource allocation, to the situation at hand, which could translate to reductions in the impact of a disease. Unfortunately, most of these past epidemics (e.g., dengue, malaria, hepatitis, influenza, and most recent, Covid-19) exhibit nonlinear and non-stationary characteristics due to their spreading fluctuations based on seasonal-dependent variability and the nature of these epidemics. We analyze a wide variety of epidemic time series datasets using a maximal overlap discrete wavelet transform (MODWT) based autoregressive neural network and call it EWNet. MODWT techniques effectively characterize non-stationary behavior and seasonal dependencies in the epidemic time series and improve the forecasting scheme of the autoregressive neural network in the proposed ensemble wavelet network framework. From a nonlinear time series viewpoint, we explore the asymptotic stationarity of the proposed EWNet model to show the asymptotic behavior of the associated Markov Chain. We also theoretically investigate the effect of learning stability and the choice of hidden neurons in the proposed EWNet model. From a practical perspective, we compare our proposed EWNet framework with several statistical, machine learning, and deep learning models that have been previously used for epidemic forecasting.

Cover Image, Volume 94, Number 5, May 2022

Front Cover Caption: The cover image is based on the Research Article Aggregation of high-frequency RBD mutations of SARS-CoV-2 with three VOCs did not cause significant antigenic drift by Tao Li et al., https://doi.org/10.1002/jmv.27596.

Benchmarking emergency department triage prediction models with machine learning and large public electronic health records (preprint)

The demand for emergency department (ED) services is increasing across the globe, particularly during the current COVID-19 pandemic. Clinical triage and risk assessment have become increasingly challenging due to the shortage of medical resources and the strain on hospital infrastructure caused by the pandemic. As a result of the widespread use of electronic health records (EHRs), we now have access to a vast amount of clinical data, which allows us to develop predictive models and decision support systems to address these challenges. To date, however, there are no widely accepted benchmark ED triage prediction models based on large-scale public EHR data. An open-source benchmarking platform would streamline research workflows by eliminating cumbersome data preprocessing, and facilitate comparisons among different studies and methodologies. In this paper, based on the Medical Information Mart for Intensive Care IV Emergency Department (MIMIC-IV-ED) database, we developed a publicly available benchmark suite for ED triage predictive models and created a benchmark dataset that contains over 400,000 ED visits from 2011 to 2019. We introduced three ED-based outcomes (hospitalization, critical outcomes, and 72-hour ED reattendance) and implemented a variety of popular methodologies, ranging from machine learning methods to clinical scoring systems. We evaluated and compared the performance of these methods against benchmark tasks. Our codes are open-source, allowing anyone with MIMIC-IV-ED data access to perform the same steps in data processing, benchmark model building, and experiments. This study provides future researchers with insights, suggestions, and protocols for managing raw data and developing risk triaging tools for emergency care.

SARS-CoV-2 RdRp is a versatile enzyme with proofreading activity and ability to incorporate NHC into RNA by using diphosphate form molnupiravir as a substrate (preprint)

The coronavirus disease 2019 (COVID-19) has been ravaging throughout the world for almost two years and has severely impaired both human health and the economy. The causative agent, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) employs the viral RNA-dependent RNA polymerase (RdRp) complex for genome replication and transcription, making RdRp an appealing target for antiviral drug development. Although the structure of the RdRp complex has been determined, the function of RdRp has not been fully characterized. Here we reveal that in addition to RNA dependent RNA polymerase activity, RdRp also shows exoribonuclease activity and consequently proofreading activity. We observed that RdRp and nsp14-ExoN, when combined, exhibit higher proofreading activity compared to RdRp alone. Moreover, RdRp can recognize and utilize nucleoside diphosphate (NDP) as substrate to synthesize RNA and can also incorporate {beta}-d-N4-hydroxycytidine (NHC) into RNA while using diphosphate form molnupiravir as substrate.

Impact of the COVID-19 pandemic on the epidemiology of out-of-hospital cardiac arrest: A systematic review and meta-analysis (preprint)

Background: The coronavirus disease 2019 (COVID-19) pandemic has significantly influenced epidemiology, yet its impact on out-of-hospital cardiac arrest (OHCA) remains unclear. We aimed to evaluate the impact of the pandemic on the incidence and case fatality rate (CFR) of OHCA. We also evaluated the impact on intermediate outcomes and clinical characteristics. Methods PubMed, EMBASE, Web of Science, Scopus, and Cochrane Library databases were searched from inception to May 3, 2021. Studies were included if they compared OHCA processes and outcomes between the pandemic and historical control time periods. Meta-analyses were performed for primary outcomes (annual incidence, mortality, and case fatality rate [CFR]), secondary outcomes (field termination of resuscitation [TOR], return of spontaneous circulation [ROSC]), survival to hospital admission, and survival to hospital discharge), and clinical characteristics (shockable rhythm and etiologies). This study was registered in the International Prospective Register of Systematic Reviews (PROSPERO) (CRD42021253879). Results The COVID-19 pandemic was associated with a 39.5% increase in pooled annual OHCA incidence (p 

Artificial Intelligence Applications for COVID-19 in Intensive Care and Emergency Settings: A Systematic Review (preprint)

BackgroundLittle is known about the role of artificial intelligence (AI) as a decisive technology in the clinical management of COVID-19 patients. We aimed to systematically review and critically appraise the current evidence on AI applications for COVID-19 in intensive care and emergency settings, focusing on methods, reporting standards, and clinical utility. MethodsWe systematically searched PubMed, Embase, Scopus, CINAHL, IEEE Xplore, and ACM Digital Library databases from inception to 1 October 2020, without language restrictions. We included peer-reviewed original studies that applied AI for COVID-19 patients, healthcare workers, or health systems in intensive care, emergency or prehospital settings. We assessed predictive modelling studies using PROBAST (prediction model risk of bias assessment tool) and a modified TRIPOD (transparent reporting of a multivariable prediction model for individual prognosis or diagnosis) statement for AI. We critically appraised the methodology and key findings of all other studies. ResultsOf fourteen eligible studies, eleven developed prognostic or diagnostic AI predictive models, all of which were assessed to be at high risk of bias. Common pitfalls included inadequate sample sizes, poor handling of missing data, failure to account for censored participants, and weak validation of models. Studies had low adherence to reporting guidelines, with particularly poor reporting on model calibration and blinding of outcome and predictor assessment. Of the remaining three studies, two evaluated the prognostic utility of deep learning-based lung segmentation software and one studied an AI-based system for resource optimisation in the ICU. These studies had similar issues in methodology, validation, and reporting. ConclusionsCurrent AI applications for COVID-19 are not ready for deployment in acute care settings, given their limited scope and poor quality. Our findings underscore the need for improvements to facilitate safe and effective clinical adoption of AI applications, for and beyond the COVID-19 pandemic.

Six-month follow-up of functional status in discharged patients with coronavirus disease 2019 (preprint)

Background The long-term functional outcome of discharged patients with coronavirus disease 2019 (COVID-19) remains unresolved. We aimed to describe a six-month follow-up of functional status of COVID-19 survivors.Methods We reviewed the data of COVID-19 patients who had been consecutively admitted to the Tumor Center of Union Hospital (Wuhan, China) between 15 February and 14 March 2020. We quantified a six-month functional outcome reflecting symptoms and disability in COVID-19 survivors using a post-COVID-19 functional status scale ranging from 0 to 5 (PCFS). We examined the risk factors for the incomplete functional status defined as a PCFS > 0 at a six-month follow-up after discharge.Results We included a total of 95 COVID-19 survivors with a median age of 62 (IQR 53-69) who had a complete functional status (PCFS grade 0) at baseline in this retrospective observational study. At six-month follow-up, 67 (70.5%) patients had a complete functional outcome (grade 0), 9 (9.5%) had a negligible limited function (grade 1), 12 (12.6%) had a mild limited function (grade 2), 7 (7.4%) had moderate limited function (grade 3). Univariable logistic regression analysis showed a significant association between the onset symptoms of muscle or joint pain and an increased risk of incomplete function (unadjusted OR 4.06, 95%CI 1.33 - 12.37). This association remained after adjustment for age and admission delay (adjusted OR 3.39, 95%CI 1.06 - 10.81, p = 0.039).Conclusions A small proportion of discharged COVID-19 patients may have an incomplete functional outcome at a six-month follow-up; intervention strategies are required.

Structural basis for bivalent binding and inhibition of SARS-CoV-2 infection by human potent neutralizing antibodies (preprint)

Neutralizing monoclonal antibodies (nAbs) to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) represent promising candidates for clinical intervention against coronavirus virus diseases 2019 (COVID-19). We isolated a large number of nAbs from SARS-CoV-2 infected individuals capable of disrupting proper interaction between the receptor binding domain (RBD) of the viral spike (S) protein and the receptor angiotensin converting enzyme 2 (ACE2). In order to understand the mechanism of these nAbs on neutralizing SARS-CoV-2 virus infections, we have performed cryo-EM analysis and here report cryo-EM structures of the ten most potent nAbs in their native full-length IgG or Fab forms bound to the trimeric S protein of SARS-CoV-2. The bivalent binding of the full-length IgG is found to associate with more RBD in the "up" conformation than the monovalent binding of Fab, perhaps contributing to the enhanced neutralizing activity of IgG and triggering more shedding of the S1 subunit from the S protein. Comparison of large number of nAbs identified common and unique structural features associated with their potent neutralizing activities. This work provides structural basis for further understanding the mechanism of nAbs, especially through revealing the bivalent binding and their correlation with more potent neutralization and the shedding of S1 subunit.

Ambient air pollutants, meteorological factors and their interactions affect confirmed cases of COVID-19 in 120 Chinese cities (preprint)

Emerging evidences have confirmed effects of meteorological factors on novel coronavirus disease 2019 (COVID-19). However, few studies verify the impact of air pollutants on this pandemic. This study aims to explore the association of ambient air pollutants, meteorological factors and their interactions effect confirmed case counts of COVID-19 in 120 Chinese cities. Here, we collected total confirmed cases of COVID-19 by combining with meteorological factors and air pollutants data from 15th January 2020 to 18th March 2020 in 120 Chinese cities. Spearman correlation analysis was employed to estimate the association between two variables; univariate and multivariate negative binomial regression analysis were applied to explore the effect of air pollutants and meteorological parameters on the COVID-19 confirmed cases. Positive associations were found between the confirmed cases of COVID-19 and carbon monoxide (CO), aerodynamic particulate matter with aerodynamic diameter [≤]2.5 um (PM2.5), relative humidity (RH) and air pressure (AP). And negative association was found for sulfur dioxide (SO2). In addition, multivariate negative binomial regression analysis suggested that confirmed cases of COVID-19 was positively correlated with ozone (O3) in lag 0 day while it was negatively associated with wind velocity (WV) in lag 14 days, and the pollutants-meteorological factors interactions also associate with COVID-19. In conclusions, air pollutants and meteorological factors and their interactions all associate with COVID-19.

Coronavirus Disease 2019 (COVID-19): An Evidence Map of Medical Literature (preprint)

Since the beginning of the COVID-19 outbreak in December 2019, a substantial body of COVID-19 medical literature has been generated. As of May 2020, gaps in the existing literature remain unidentified and, hence, unaddressed. In this paper, we summarise the medical literature on COVID-19 between 1 January and 24 March 2020 using evidence maps and bibliometric analysis in order to systematically identify gaps and propose areas for valuable future research. The examined COVID-19 medical literature originated primarily from Asia and focussed mainly on clinical features and diagnosis of the disease. Many areas of potential research remain underexplored, such as mental health research, the use of novel technologies and artificial intelligence, research on the pathophysiology of COVID-19 within different body systems, and research on indirect effects of COVID-19 on the care of non-COVID-19 patients. Research collaboration at the international level was limited although improvements may aid global containment efforts.