Search

To examine the association between cognitive frailty and the risk of future falls among older adults. Systematic review and meta-analysis. Older people aged ≥60 years with cognitive frailty from community, hospital, or both. PubMed, EMBASE, Web of Science, the Cochrane Library, Wanfang Database, China Knowledge Resource Integrated Database (CNKI), Weipu Database (VIP), and Chinese Biomedical Database (CBM) were searched for relevant studies published from the inception of the database until June 14, 2022. Stata 16.0 software was used to perform the meta-analysis. A random effects model was used to pool the prevalence of falls in older adults over age 60 years with cognitive frailty and the strength of the association between cognitive frailty and falls [odds ratios (ORs) and 95% CIs]. Quality assessment, heterogeneity, and sensitivity analyses were also conducted. A study protocol was registered in PROSPERO (CRD42022331323). The review included 18 studies in qualitative synthesis, 14 of which were in meta-analysis. Eleven sets of cross-sectional data involving 23,025 participants and 5 sets of longitudinal data involving 11,924 participants were used in the meta-analysis. The results showed that the overall prevalence of falls in 1742 people with cognitive frailty was 36.3% (95% CI 27.9-44.8, I 2 = 93.4%). Longitudinal study results showed that cognitively frail individuals had a higher risk of falls (OR 3.02, 95% CI 2.11-4.32, I 2 = 0.0%, P =.406), compared to robust participants without cognitive impairment; physically frail people (alone) had a moderate risk of falls (OR 2.16, 95% CI 1.42-3.30, I 2 = 9.7%, P =.351); cognitively impaired people (alone) had a lower risk of falls (OR 1.36, 95% CI 1.03-1.79, I 2 = 0.0%, P =.440). Among cross-sectional studies, cognitive frailty was associated with the risk of falls (OR 2.74, 95% CI 2.20-3.40, I 2 = 53.1%, P =.019). Although high heterogeneity was noted among 11 cross-sectional studies reporting ORs, the sensitivity analysis showed that no single study significantly affected the final pooled results. This systematic review and meta-analysis confirms the findings that cognitive frailty was demonstrated to be a significant predictor of future falls in older adults. However, further prospective investigations are warranted. [ABSTRACT FROM AUTHOR]

To critically appraise and quantify the performance studies by employing machine learning (ML) to predict delirium. A systematic review and meta-analysis. Articles reporting the use of ML to predict delirium in adult patients were included. Studies were excluded if (1) the primary goal was only the identification of various risk factors for delirium; (2) the full-text article was not found; and (3) the article was published in a language other than English/Chinese. PubMed, Embase, Cochrane Library database, Web of Science, Grey literature, and other relevant databases for the related publications were searched (from inception to December 15, 2021). The data were extracted using a standard checklist, and the risk of bias was assessed through the prediction model risk of bias assessment tool. Meta-analysis with the area under the receiver operating characteristic curve, sensitivity, and specificity as effect measures, was performed with Metadisc software. Cochran Q and I 2 statistics were used to assess the heterogeneity. Meta-regression was performed to determine the potential effect of adjustment for the key covariates. A total of 22 studies were included. Only 4 of 22 studies were quantitatively analyzed. The studies varied widely in reporting about the study participants, features and selection, handling of missing data, sample size calculations, and the intended clinical application of the model. For ML models, the overall pooled area under the receiver operating characteristic curve for predicting delirium was 0.89, sensitivity 0.85 (95% confidence interval 0.84‒0.85), and specificity 0.80 (95% confidence interval 0.81–0.80). We found that the ML model showed excellent performance in predicting delirium. This review highlights the potential shortcomings of the current approaches, including low comparability and reproducibility. Finally, we present the various recommendations on how these challenges can be effectively addressed before deploying these models in prospective analyses. [ABSTRACT FROM AUTHOR]