Machine learning model identification and prediction of patients' need for ICU admission: A systematic review.

BACKGROUND: The emergency department (ED) triage process serves as a crucial first step for patients seeking acute care, This initial assessment holds crucial implications for patient survival and prognosis. In this study, a systematic review of the existing literature was performed to investigate the performance of machine learning (ML) models in recognizing and predicting the need for intensive care among ED patients. METHODS: Four prominent databases (PubMed, Embase, Cochrane Library and Web of Science) were searched for relevant literature published up to April 28, 2023. The Prediction model study Risk of Bias Assessment Tool (PROBAST) was employed to evaluate the risk of bias and feasibility of prediction models. RESULTS: In ten studies, the main algorithms used were Gradient Boostin, Logistic Regressio, Neural Network, Support Vector Machines, Random Forest. The performance of each model was as follows: Gradient Boosting had a sensitivity range of 0.3 to 0.96, specificity range of 0.6 to 0.99, accuracy range of 0.37 to 0.99, precision range of 0.3 to 0.96, and AUC value range of 0.68 to 0.93; Logistic Regression had a sensitivity range of 0.46 to 0.97, specificity range of 0.28 to 0.99, accuracy range of 0.66 to 0.97, precision range of 0.27 to 0.63, and AUC value range of 0.72 to 0.97; Neural Networks had a sensitivity range of 0.45 to 0.96, specificity range of 0.58 to 0.99, accuracy range of 0.36 to 0.97, precision range of 0.27 to 0.96, and AUC value range of 0.67 to 0.91; Support Vector Machines had a sensitivity range of 0.49 to 0.83, specificity range of 0.94 to 0.98, accuracy range of 0.33 to 0.97, precision range of 0.53 to 0.94, and AUC values were not reported; Random Forests had a sensitivity range of 0.75 to 0.91, specificity range of 0.77 to 0.94, accuracy range of 0.35 to 0.77, precision range of 0.36 to 0.94, and AUC value of 0.83. CONCLUSION: ML models have demonstrated good performance in identifying and predicting critically ill patients in ED triage. However, because of the limited number of studies on each model, further high-quality prospective research is needed to validate these findings.

Efficacy and safety of sacubitril-valsartan in patients with heart failure: a systematic review and meta-analysis of randomized clinical trials: A PRISMA-compliant article.

BACKGROUND: To investigate the efficacy and safety of sacubitril-valsartan in patients with heart failure, relevant randomized clinical trials (RCTs) were analyzed. METHODS: We used Cochrane Library, PubMed web of science, CNKI, VIP, Medline, ISI Web of Science, CBMdisc, and Wanfang database to conduct a systematic literature research. A fixed-effects model was used to evaluate the standardized mean differences (SMDs) with 95% confidence intervals. We conducted sensitivity analysis and analyzed publication bias to comprehensively estimate the efficacy and safety of sacubitril-valsartan in patients with heart failure. RESULTS: Among 132 retrieved studies, 5 relevant RCTs were included in the meta-analysis. The result showed that left ventricular ejection fraction (LVEF) was improved after sacubitril-valsartan in patients with heart failure, with an SMD (95% CI of 1.1 [1.01, 1.19] and P < .00001 fixed-effects model). Combined outcome indicators showed that, combined outcome indicators showed that, compared with control group, the left ventricular volume index (LAVI) (WMD = -2.18, 95% CI [-3.63, -0.74], P = .003), the E/e' (WMD = -1.01, 95% CI [-1.89, -0.12], P = .03), the cardiovascular death (RR = 0.89, 95% CI [0.83, 0.96], P = .003], and the rehospitalization rate of heart failure (RR = 0.83, 95% CI [0.78, 0.88], P < .01) decreased more significantly, but it had no effect on renal function (WMD = 0.74, 95% CI [0.54, 1.01], P = .06). CONCLUSIONS: The present meta-analysis suggested that sacubitril-valsartan may improve the cardiac function of heart failure. Given the limited number of included studies, additional large sample-size RCTs are required to determine the long-term effect of cardiac function of sacubitril-valsartan in patients with heart failure.

Functional analysis of ceRNA network of lncRNA TSIX/miR-34a-5p/RBP2 in acute myocardial infarction based on GEO database.

The identification of innovative gene biomarkers with clinical efficacy is warranted for the treatment of acute myocardial infarction (AMI). The current study sought to screen potential target genes in AMI via bioinformatic analysis and analyze their effects on cardiomyocyte apoptosis. The differentially expressed long non-coding RNAs (lncRNAs) of AMI were screened, and the downstream microRNAs (miRNAs) and mRNAs of lncRNA antisense for X-inactive-specific transcript (lncRNA TSIX) were predicted accordingly. The diagnostic relationship between the 12 differentially expressed lncRNAs and AMI was analyzed by receiver operating characteristic (ROC). Next, the expressions of 12 lncRNAs, including miR-34a-5p and retinol binding protein 2 (RBP2) were all detected. The targeting relationships of miR-34a-5p with lncRNA TSIX and RBP2 were verified. AMI model was established and treated with Ad-TSIX and/or agomiR-34a-5p to evaluate the cardiac function and cardiomyocyte apoptosis of AMI mice. LncRNA TSIX was identified as the most differentially expressed lncRNA in AMI. Our findings revealed that LncRNA TSIX could function as an AMI diagnostic marker. LncRNA TSIX could target miR-34a-5p and miR-34a-5p could target RBP2. Upregulation of lncRNA TSIX could ameliorate cardiac injury inflicted by AMI and mitigate cardiomyocyte apoptosis. Upregulation of miR-34a-5p reversed the effect of lncRNA TSIX overexpression to ameliorate cardiomyocyte apoptosis in AMI mice. Overall, the overexpression of lncRNA TSIX inhibits cardiomyocyte apoptosis by competing with RBP2 to bind to miR-34a-5p and promoting RBP2.

The epidemiology of acute occupational hand injuries treated in emergency departments in Foshan City, South China.

BACKGROUND: Despite the magnitude of occupational hand injuries, there are no authoritative guidelines for hand injury prevention, and little research has been done to investigate the epidemiology of acute occupational hand injuries in South China or other developing areas. In this study, the epidemiology of acute occupational hand injuries treated in emergency departments (EDs) in Foshan City, South China, was examined and data were supplied to assist with preventive strategies in similar developing regions. METHODS: A multicenter study was prospectively designed and conducted in 5 large hospital EDs in Foshan City from July 2010 to June 2011. An anonymous questionnaire was designed specifically to collect the data for this study. RESULTS: A total of 2142 patients with acute occupational hand injury completed the questionnaire within the 1-year study period. Results indicated that most occupational hand injuries were caused by machinery. Hand injury type and site of the injury did not correspond to age, but were related to gender and job category. July and August 2010 were the peak periods of admission to EDs, while January and February 2010 were the trough periods. CONCLUSION: Epidemiological data enhance our knowledge of acute occupational hand injuries and could play a role in the prevention and treatment of future occupational hand injuries.