Nan Liu
Profile Url: nan-liu
Researcher at Tsinghua University
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.
BackgroundSepsis is a potentially life threatening condition that requires prompt recognition and treatment for optimal outcomes. There is little consensus on an objective way to assess for sepsis severity and risk for mortality. In recent years, heart rate variability (HRV), a measure of the cardiac autonomic regulation derived from short electrocardiogram tracings, has been found to correlate with sepsis mortality, and its use as a prognostic variable and for risk stratification has been promising. In this paper, we present using novel heart rate n-variability (HRnV) measures for sepsis mortality risk prediction and compare against current mortality prediction scores. MethodsThis study was a retrospective cohort study on a convenience sample of patients presenting to the emergency department (ED) of Singapore General Hospital between September 2014 to April 2017. Patients were included in the study if they were above 21 years old, were suspected to have sepsis by their attending physician, triaged as emergency or urgent cases, and if they met two or more of the Systemic Inflammatory Response Syndrome (SIRS) criteria. Demographic and clinical variables were obtained from the electronic medical records, and HRV and novel HRnV parameters were calculated from five minute ECG tracings. Univariable analysis was conducted on variables obtained, with the primary outcome being 30-day in-hospital mortality (IHM). Variables selected through univariable analysis and stepwise selection were included in a multivariable logistic regression model, the results of which were presented using receiver operating curve (ROC) analysis. ResultsOf 342 patients included for final analysis, 66 (19%) met with the primary outcome. On univariable analysis, 85 out of 142 analysed HRV and HRnV parameters showed statistical difference between groups. The final multivariable logistic regression model comprised of 21 variables including four vital signs, two HRV parameters, and 15 HRnV parameters. The area under the curve (AUC) of the model was 0.86 (95% confidence interval 0.81-0.90), outperforming several established clinical scores. ConclusionThe use of novel HRnV measures can provide adequate power to predictive models in the risk stratification of patients presenting to the ED with sepsis. When included in a multivariable logistic regression model, the HRnV-based model outperformed traditional risk stratification scoring systems. The HRnV measures may have potential to allow for a rapid, objective, and accurate means of patient risk stratification for sepsis severity and mortality.
Background: Chest pain is among the most common presenting complaints in the emergency department (ED). Swift and accurate risk stratification of chest pain patients in the ED may improve patient outcomes and reduce unnecessary costs. Traditional logistic regression with stepwise variable selection has been used to build risk prediction models for ED chest pain patients. In this study, we aimed to investigate if machine learning dimensionality reduction methods can achieve superior performance than the stepwise approach in deriving risk stratification models. Methods: A retrospective analysis was conducted on the data of patients >20 years old who presented to the ED of Singapore General Hospital with chest pain between September 2010 and July 2015. Variables used included demographics, medical history, laboratory findings, heart rate variability (HRV), and HRnV parameters calculated from five to six-minute electrocardiograms (ECGs). The primary outcome was 30-day major adverse cardiac events (MACE), which included death, acute myocardial infarction, and revascularization. Candidate variables identified using univariable analysis were then used to generate the stepwise logistic regression model and eight machine learning dimensionality reduction prediction models. A separate set of models was derived by excluding troponin. Receiver operating characteristic (ROC) and calibration analysis was used to compare model performance. Results: 795 patients were included in the analysis, of which 247 (31%) met the primary outcome of 30-day MACE. Patients with MACE were older and more likely to be male. All eight dimensionality reduction methods marginally but non-significantly outperformed stepwise variable selection; The multidimensional scaling algorithm performed the best with an area under the curve (AUC) of 0.901. All HRnV-based models generated in this study outperformed several existing clinical scores in ROC analysis. Conclusions: HRnV-based models using stepwise logistic regression performed better than existing chest pain scores for predicting MACE, with only marginal improvements using machine learning dimensionality reduction. Moreover, traditional stepwise approach benefits from model transparency and interpretability; in comparison, machine learning dimensionality reduction models are black boxes, making them difficult to explain in clinical practice.
Background: Little 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. Methods: We 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. Results: Of 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. Conclusions: Current 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.