Background: Previous observational studies have demonstrated inconsistent and inconclusive results of changes in the intestinal microbiota in patients with obesity and metabolic disorders. We performed a systematic review to explore evidence for this association across different geography and populations. Methods: We performed a systematic search of MEDLINE (OvidSP) and Embase (OvidSP) of articles published from Sept 1, 2010, to July 10, 2021, for case–control studies comparing intestinal microbiome of individuals with obesity and metabolic disorders with the microbiome of non-obese, metabolically healthy individuals (controls). The primary outcome was bacterial taxonomic changes in patients with obesity and metabolic disorders as compared to controls. Taxa were defined as “lean-associated” if they were depleted in patients with obesity and metabolic disorders or negatively associated with abnormal metabolic parameters. Taxa were defined as “obesity-associated” if they were enriched in patients with obesity and metabolic disorders or positively associated with abnormal metabolic parameters. Results: Among 2390 reports screened, we identified 110 full-text articles and 60 studies were included. Proteobacteria was the most consistently reported obesity-associated phylum. Thirteen, nine, and ten studies, respectively, reported Faecalibacterium, Akkermansia, and Alistipes as lean-associated genera. Prevotella and Ruminococcus were obesity-associated genera in studies from the West but lean-associated in the East. Roseburia and Bifidobacterium were lean-associated genera only in the East, whereas Lactobacillus was an obesity-associated genus in the West. Conclusions: We identified specific bacteria associated with obesity and metabolic disorders in western and eastern populations. Mechanistic studies are required to determine whether these microbes are a cause or product of obesity and metabolic disorders.

This study aimed to construct machine learning (ML) models for predicting prolonged length of stay (pLOS) in intensive care units (ICU) among general ICU patients. A multicenter database called eICU (Collaborative Research Database) was used for model derivation and internal validation, and the Medical Information Mart for Intensive Care (MIMIC) III database was used for external validation. We used four different ML methods (random forest, support vector machine, deep learning, and gradient boosting decision tree (GBDT)) to develop prediction models. The prediction performance of the four models were compared with the customized simplified acute physiology score (SAPS) II. The area under the receiver operation characteristic curve (AUROC), area under the precision-recall curve (AUPRC), estimated calibration index (ECI), and Brier score were used to measure performance. In internal validation, the GBDT model achieved the best overall performance (Brier score, 0.164), discrimination (AUROC, 0.742; AUPRC, 0.537), and calibration (ECI, 8.224). In external validation, the GBDT model also achieved the best overall performance (Brier score, 0.166), discrimination (AUROC, 0.747; AUPRC, 0.536), and calibration (ECI, 8.294). External validation showed that the calibration curve of the GBDT model was an optimal fit, and four ML models outperformed the customized SAPS II model. The GBDT-based pLOS-ICU prediction model had the best prediction performance among the five models on both internal and external datasets. Furthermore, it has the potential to assist ICU physicians to identify patients with pLOS-ICU risk and provide appropriate clinical interventions to improve patient outcomes.

Next-generation live biotherapeutics are promising to aid the treatment of obesity and metabolic diseases. Here, we reported a novel anti-obesity probiotic candidate, Roseburia hominis, that was depleted in stool samples of obese subjects compared with lean controls, and its abundance was negatively correlated with body mass index and serum triglycerides. Supplementation of R. hominis prevented body weight gain and disorders of glucose and lipid metabolism, prevented fatty liver, inhibited white adipose tissue expansion and brown adipose tissue whitening in mice fed with high-fat diet, and boosted the abundance of lean-related species. The effects of R. hominis could be partially attributed to the production of nicotinamide riboside and upregulation of the Sirtuin1/mTOR signaling pathway. These results indicated that R. hominis is a promising candidate for the development of next-generation live biotherapeutics for the prevention of obesity and metabolic diseases.

Objectives: Acute kidney injury (AKI) is common in intensive care unit (ICU) patients and is associated with high mortality, prolonged ICU stays, and increased costs. Early prediction is crucial for timely intervention and improved outcomes. Various prediction models, including machine learning, deep learning, and dynamic prediction frameworks, have been developed, but their modeling approaches, data utilization, and clinical applicability require further investigation. This review comprehensively assesses the modeling methods, data utilization strategies, and clinical applicability of AKI prediction models in the ICU, identifies current challenges, and proposes future research directions. Materials and Methods: A systematic search was conducted in PubMed, Embase, Scopus, Web of Science, IEEE Xplore, and ACM Digital Library up to December 12, 2024. Studies were included if they reported AKI prediction models using ICU-specific data, included at least 2 predictors, and evaluated model performance. Extracted data included study characteristics, model details, data sources, performance metrics, and validation methods. The risk of bias was assessed using PROBAST (Prediction Model Risk of Bias Assessment Tool), and the reporting quality was evaluated using the TRIPOD (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis) guideline. Results: From 1305 screened studies, 47 met the inclusion criteria. Models ranged from machine learning to advanced deep learning techniques. Only 14 studies conducted external validation. Most studies (n = 44) had a high risk of bias, particularly in generalizability and clinical applicability. Discussion: Although AI models have shown promise in predicting AKI in ICU settings, key challenges remain. These include limited external validation, lack of dynamic modeling, insufficient interpretability, and poor consideration of clinical integration. Different study designs, prediction windows, and data sources also hinder model comparability. Conclusions: Future research should prioritize dynamic, interpretable, and externally validated models. These efforts are critical to bridge the gap between model development and clinical implementation and to enhance the real-world applicability of AI in AKI prediction.

Obesity is associated with altered gut microbiome composition but data across different populations remain inconsistent. We meta-analyzed publicly available 16S-rRNA sequence datasets from 18 different studies and identified differentially abundant taxa and functional pathways of the obese gut microbiome. Most differentially abundant genera (Odoribacter, Oscillospira, Akkermansia, Alistipes, and Bacteroides) were depleted in obesity, indicating a deficiency of commensal microbes in the obese gut microbiome. From microbiome functional pathways, elevated lipid biosynthesis and depleted carbohydrate and protein degradation suggested metabolic adaptation to high-fat, low-carbohydrate, and low-protein diets in obese individuals. Machine learning models trained on the 18 studies were modest in predicting obesity with a median AUC of 0.608 using 10-fold cross-validation. The median AUC increased to 0.771 when models were trained in eight studies designed for investigating obesity-microbiome association. By meta-analyzing obesity-associated microbiota signatures, we identified obesity-associated depleted taxa that may be exploited to mitigate obesity and related metabolic diseases.

Accurate estimation of in-hospital outcomes for patients with acute kidney injury (AKI) is crucial for aiding physicians in making optimal clinical decisions. We aimed to review prediction models constructed by machine learning methods for predicting AKI prognosis using administrative databases. A systematic review following PRISMA guidelines. Adult patients diagnosed with AKI who are admitted to either hospitals or intensive care units. We searched PubMed, Embase, Web of Science, Scopus, and Cumulative Index to Nursing and Allied Health for studies published between January 1, 2014 and February 29, 2024. Eligible studies employed machine learning models to predict in-hospital outcomes of AKI based on administrative databases. Extracted data included prediction outcomes and population, prediction models with performance, feature selection methods, and predictive features. The included studies were qualitatively synthesized with assessments of quality and bias. We calculated the pooled model discrimination of different AKI prognoses using random-effects models. Of 3,029 studies, 27 studies were eligible for qualitative review. In-hospital outcomes for patients with AKI included acute kidney disease, chronic kidney disease, renal function recovery or kidney failure, and mortality. Compared with models predicting the mortality of patients with AKI during hospitalization, the prediction performance of models on kidney function recovery was less accurate. Meta-analysis showed that machine learning methods outperformed traditional approaches in mortality prediction (area under the receiver operating characteristic curve, 0.831; 95% CI, 0.799-0.859 vs 0.772; 95% CI, 0.744-0.797). The overlapping predictive features for in-hospital mortality identified from ≥6 studies were age, serum creatinine level, serum urea nitrogen level, anion gap, and white blood cell count. Similarly, age, serum creatinine level, AKI stage, estimated glomerular filtration rate, and comorbid conditions were the common predictive features for kidney function recovery. Many studies developed prediction models within specific hospital settings without broad validation, restricting their generalizability and clinical application. Machine learning models outperformed traditional approaches in predicting mortality for patients with AKI, although they are less accurate in predicting kidney function recovery. Overall, these models demonstrate significant potential to help physicians improve clinical decision making and patient outcomes. CRD42024535965.