Search

Research objectives Clostriodiodes difficile infection (CDI) is a major cause of healthcare-associated diarrhoea with high mortality. There is a lack of validated predictors for severe outcomes in CDI. The aim of this study is to derive and validate a clinical prediction tool for CDI in-hospital mortality using a large critical care database.Methodology The demographics, clinical parameters, laboratory results and mortality of CDI were extracted from the Medical Information Mart for Intensive Care-III (MIMIC-III) database. We subsequently trained three machine learning models: logistic regression (LR), random forest (RF) and gradient boosting machine (GBM) to predict in-hospital mortality. The individual performances of the models were compared against current severity scores (Clostridiodes difficile Associated Risk of Death Score (CARDS) and ATLAS (Age, Treatment with systemic antibiotics, leukocyte count, Albumin and Serum creatinine as a measure of renal function) by calculating area under receiver operating curve (AUROC). We identified factors associated with higher mortality risk in each model.Summary of results From 61 532 intensive care unit stays in the MIMIC-III database, there were 1315 CDI cases. The mortality rate for CDI in the study cohort was 18.33%. AUROC was 0.69 (95% CI, 0.60 to 0.76) for LR, 0.71 (95% CI, 0.62 to 0.77) for RF and 0.72 (95% CI, 0.64 to 0.78) for GBM, while previously AUROC was 0.57 (95% CI, 0.51 to 0.65) for CARDS and 0.63 (95% CI, 0.54 to 0.70) for ATLAS. Albumin, lactate and bicarbonate were significant mortality factors for all the models. Free calcium, potassium, white blood cell, urea, platelet and mean blood pressure were present in at least two of the three models.Conclusion Our machine learning derived CDI in-hospital mortality prediction model identified pertinent factors that can assist critical care clinicians in identifying patients at high risk of dying from CDI.

Introduction Regardless of having effective vaccines against COVID-19, containment measures such as enhanced physical distancing and good practice of personal hygiene remain the mainstay of controlling the COVID-19 pandemic. Countries across Asia have imposed these containment measures to varying extents. However, residents in different countries would have a differing degree of compliance to these containment measures potentially due to differences in the level of awareness and motivation in the early phase of pandemic.Objectives In our study, we aimed to describe and correlate the level of knowledge and attitude with the level of compliance with personal hygiene and physical distancing practices among Asian countries in the early phase of pandemic.Methods A multinational cross-sectional study was carried out using electronic surveys between May and June 2020 across 14 geographical areas. Subjects aged 21 years and above were invited to participate through social media, word of mouth and electronic mail.Results Among the 2574 responses obtained, 762 (29.6%) participants were from East Asia and 1812 (70.4%) were from Southeast Asia (SEA). A greater proportion of participants from SEA will practise physical distancing as long as it takes (72.8% vs 60.6%). Having safe distancing practices such as standing more than 1 or 2 m apart (AdjOR 5.09 95% CI (1.08 to 24.01)) or more than 3 or 4 m apart (AdjOR 7.05 95% CI (1.32 to 37.67)), wearing a mask when they had influenza-like symptoms before the COVID-19 pandemic, preferring online news channels such as online news websites/applications (AdjOR 1.73 95% CI (1.21 to 2.49)) and social media (AdjOR 1.68 95% CI (1.13 to 2.50) as sources of obtaining information about COVID-19 and high psychological well-being (AdjOR 1.39 95% CI (1.04 to 1.87)) were independent factors associated with high compliance.Conclusions We found factors associated with high compliance behaviour against COVID-19 in the early phase of pandemic and it will be useful to consider them in risk assessment, communication and pandemic preparedness.