OBJECTIVE To review and critically appraise published and preprint reports of prediction models for diagnosing coronavirus disease 2019 (covid-19) in patients with suspected infection, for prognosis of patients with covid-19, and for detecting people in the general population at increased risk of becoming infected with covid-19 or being admitted to hospital with the disease.
DESIGNLiving systematic review and critical appraisal.
DATA SOURCESPubMed and Embase through Ovid, Arxiv, medRxiv, and bioRxiv up to 7 April 2020.Cite this as: BMJ 2020;369:m1328 http://dx.
Objective: To compare performance of logistic regression (LR) with machine learning (ML) for clinical prediction modeling. Study design and setting: We conducted a Medline literature search (1/2016 to 8/2017), and extracted comparisons between LR and ML models for binary outcomes. Results: We included 71 out of 927 studies. The median sample size was 1250 (range 72-3,994,872), with 19 predictors considered (range 5-563) and 8 events per predictor (range 0.3-6,697). The most common ML methods were classification trees (30 studies), random forests (28), artificial neural networks (26), and support vector machines (24). Sixty-four (90%) studies used the area under the receiver operating characteristic curve (AUC) to assess discrimination. Calibration was not addressed in 56 (79%) studies. We identified 282 comparisons between a LR and ML model (AUC range, 0.52-0.99). For 145 comparisons at low risk of bias, the difference in logit(AUC) between LR and ML was 0.00 (95% confidence interval,-0.18 to 0.18). For 137 comparisons at high risk of bias, logit(AUC) was 0.34 (0.20 to 0.47) higher for ML. Conclusions: We found no evidence of superior performance of ML over LR for clinical prediction modeling, but improvements in methodology and reporting are needed for studies that compare modeling algorithms.
Decision curve analysis can identify risk models that can help us make better clinical decisions. We illustrate appropriate reporting and interpretation of decision curve analysis.
COVID-19 also affects pregnant and breastfeeding women. Hence, clinicians and policymakers require reliable evidence on COVID-19 epidemiology and consequences in this population. We aimed to assess the susceptibility of pregnant women to SARS-CoV-2 and women’s perceived impact of the pandemic on their breastfeeding practices, medical counseling and social support. We performed a cross-sectional study using an online survey in primary care in Belgium. Pregnant and breastfeeding women and women who breastfed in the preceding four weeks were eligible to participate. The survey was distributed through social media in April 2020. In total, 6470 women participated (i.e., 2647 pregnant and 3823 breastfeeding women). Overall, 0.3% of all respondents reported to have tested positive for SARS-CoV-2, not indicating a higher susceptibility of pregnant women to contracting COVID-19. More than 90% refuted that the pandemic affected their breastfeeding practices, nor indicated that the coronavirus was responsible for breastfeeding cessation. Half of the women even considered giving longer breastmilk because of the coronavirus. In contrast, women’s medical counseling and social support were negatively affected by the lockdown. Women without previous breastfeeding experience and in the early postpartum period experienced a higher burden in terms of reduced medical counseling and support. In the future, more consideration and alternative supportive measures such as tele-visits by midwives or perinatal organizations are required for these women.
In view of their high frequency, EPLs can significantly contribute to the overall burden of psychopathology within a population. Recognition of this impact is important, so that severely affected individuals may be screened and treated appropriately. Further research to establish risk factors to promptly identify and treat these patients, and to optimize their management, is crucial.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.