Background: Acute kidney injury (AKI) is the most common and serious complication of sepsis, accompanied by high mortality and disease burden. The early prediction of AKI is critical for timely intervention and ultimately improves prognosis. This study aims to establish and validate predictive models based on novel machine learning (ML) algorithms for AKI in critically ill patients with sepsis.Methods: Data of patients with sepsis were extracted from the Medical Information Mart for Intensive Care III (MIMIC- III) database. Feature selection was performed using a Boruta algorithm. ML algorithms such as logistic regression (LR),k-nearest neighbors (KNN), support vector machine (SVM), decision tree, random forest, Extreme Gradient Boosting (XGBoost), and artificial neural network (ANN) were applied for model construction by utilizing tenfold cross-validation. The performances of these models were assessed in terms of discrimination, calibration, and clinical application. Moreover, the discrimination of ML-based models was compared with those of Sequential Organ Failure Assessment (SOFA) and the customized Simplified Acute Physiology Score (SAPS) II model.Results: A total of 3176 critically ill patients with sepsis were included for analysis, of which 2397 cases (75.5%) developed AKI during hospitalization. A total of 36 variables were selected for model construction. The models of LR, KNN, SVM, decision tree, random forest, ANN, XGBoost, SOFA and SAPS II score were established and obtained area under the receiver operating characteristic curves of 0.7365, 0.6637, 0.7353, 0.7492, 0.7787, 0.7547, 0.821, 0.6457 and 0.7015, respectively. The XGBoost model had the best predictive performance in terms of discrimination, calibration, and clinical application among all models.Conclusion: The ML models can be reliable tools for predicting AKI in septic patients. The XGBoost model has the best predictive performance, which can be used to assist clinicians in identifying high-risk patients and implementing early interventions to reduce mortality.

Association between tumor-stroma ratio and prognosis in solid tumor patients: a systematic review and meta-analysis

It’s difficult to differentiate sepsis from non-sepsis, especially non-infectious SIRS, because no good standard exists for proof of infection. Soluble CD14 subtype (sCD14-ST), recently re-named presepsin, was identified as a new marker for the diagnosis of sepsis in several reports. However, the findings were based on the results of individual clinical trials, rather than a comprehensive and overall estimation. Thus, we conducted this systematic review and meta-analysis to estimate the pooled accuracy of presepsin in patients with sepsis suspect. A comprehensive electronic search was performed via internet retrieval system up to 15 December 2014. Methodological quality assessment was applied by using the QUADAS2 tool. The diagnostic value of presepsin in sepsis was evaluated by using the pooled estimate of sensitivity, specificity, likelihood ratio, and diagnostic odds ratio, as well as summary receiver operating characteristics curve. Nine studies with 10 trials and 2159 cases were included in the study. Only two trials had low concerns regarding applicability, whereas all trials were deemed to be at high risk of bias. Heterogeneity existed in the non-threshold effect, but not in the threshold effect. The pooled sensitivity of presepsin for sepsis was 0.78 (0.76–0.80), pooled specificity was 0.83 (0.80–0.85), pooled positive likelihood ratio was 4.63 (3.27–6.55), pooled negative likelihood ratio was 0.22 (0.16–0.30), and pooled diagnostic odds ratio was 21.73 (12.81–36.86). The area under curve of summary receiver operating characteristics curve was 0.89 (95%CI: 0.84 to 0.94) and Q* index was 0.82 (95%CI: 0.77 to 0.87). This meta-analysis demonstrates that presepsin had some superiority in the management of patients, and may be a helpful and valuable biomarker in early diagnosis of sepsis. However, presepsin showed a moderate diagnostic accuracy in differentiating sepsis from non-sepsis which prevented it from being recommended as a definitive test for diagnosing sepsis in isolation, but the results should be interpreted cautiously.

Aim: Eating disorders have increasingly become a public health concern globally. This study aimed to reveal the burden of eating disorders at the global, regional and national levels using the Global Burden of Disease (GBD) Study 2017 data. Methods: We extracted the age-standardised rates (ASRs) of prevalence and disability-adjusted life years (DALYs) and their 95% uncertainty intervals (UIs) of eating disorders, including anorexia nervosa and bulimia nervosa, between 1990 and 2017 from the GBD 2017 data. The estimated annual percentage changes (EAPCs) were calculated to quantify the secular trends of the burden of eating disorders. Results: The ASRs of prevalence and the DALYs of eating disorders continuously increased worldwide from 1990 to 2017 by an average of 0.65 (95% UI: 0.59–0.71) and 0.66 (95% UI: 0.60–0.72), respectively. The burden of eating disorders was higher in females than in males, but the increment in ASRs was greater in males than in females over time. In 2017, the highest burden of eating disorders was observed in the high sociodemographic index (SDI) regions, especially Australasia (ASR of prevalence = 807.13, 95% UI: 664.20–982.30; ASR of DALYs = 170.74, 95% UI: 113.43–244.14, per 100 000 population), Western Europe and high-income North America. However, the most significant increment of the burden of eating disorders was observed in East Asia (EAPC for prevalence = 2.23, 95% UI: 2.14–2.32; EAPC for DALYs = 2.22, 95% UI: 2.13–2.31), followed by South Asia. An increasing trend in the burden of eating disorders at the national level was observed among most countries or territories. The countries with the top three highest increasing trends were Equatorial Guinea, Bosnia and Herzegovina and China. Positive associations were found between the burden estimates and the SDI levels in almost all geographic regions during the observed 28-year period. We also found that the human development indexes in 2017 were positively correlated with the EAPCs of the ASRs of prevalence (ρ = 0.222, P = 0.002) and DALYs (ρ = 0.208, P = 0.003). Conclusion: The highest burden of eating disorders remains in the high-income western countries, but an increasing trend was observed globally and in all SDI-quintiles, especially in Asian regions that were highly populous. These results could help governments worldwide formulate suitable medical and health policies for the prevention and early intervention of eating disorders.

Background: Eating disorders (ED) have increasingly become a global topic of concern for public health. A better understanding of ED incidence is a basic requirement for improving its management. However, the temporal trend of ED incidence in China is still unknown.Methods: The incidence rates of ED from 1990 to 2017 were collected from the Global Burden of Disease Study 2017 database according to the following: subtype, i.e. anorexia nervosa (AN) and bulimia nervosa (BN); sex; and age group. The average annual percent changes and relative risks were calculated using joinpoint regression and the age–period–cohort model, respectively.Results: From 1990 to 2017, age-standardized incidence rates of ED continued to increase in males and females, and this variation trend was observed in AN and BN. Joinpoint regression analysis showed that the incidence rates increased in all age groups. Adolescents had the highest risk of developing ED, followed by young adults. Age effects were the most influential risk factor for ED incidence. Period effects showed that the risk of developing ED continuously increased with increasing time periods in BN, but not in ED and AN. Concerning the cohort effects, people born after the 1990s presented a higher risk of ED, though they presented a lower risk of BN as compared to the whole cohort.Conclusions: ED incidence rates continue to increase in China, particularly among adolescents and young adults. Further etiological studies are needed to explain these increases and to facilitate the early identification of high-risk individuals.

Prognostic value of the pretreatment neutrophil-to-lymphocyte ratio in cervical cancer: a meta-analysis and systematic review Prognostic value of the pretreatment neutrophil-to-lymphocyte ratio in cervical cancer: a meta-analysis and systematic review