We sought to develop and validate a machine learning (ML) model for predicting multidimensional frailty based on clinical and laboratory data. Moreover, an explainable ML model utilizing SHapley Additive exPlanations (SHAP) was constructed. This study enrolled 622 patients hospitalized due to decompensating episodes at a tertiary hospital. The cohort data were randomly divided into training and test sets. External validation was carried out using 131 patients from other tertiary hospitals. The frail phenotype was defined according to a self-reported questionnaire (Frailty Index). The area under the receiver operating characteristics curve was adopted to compare the performance of five ML models. The importance of the features and interpretation of the ML models were determined using the SHAP method. The proportions of cirrhotic patients with nonfrail and frail phenotypes in combined training and test sets were 87.8% and 12.2%, respectively, while they were 88.5% and 11.5% in the external validation dataset. Five ML algorithms were used, and the random forest (RF) model exhibited substantially predictive performance. Regarding the external validation, the RF algorithm outperformed other ML models. Moreover, the SHAP method demonstrated that neutrophil-to-lymphocyte ratio, age, lymphocyte-to-monocyte ratio, ascites, and albumin served as the most important predictors for frailty. At the patient level, the SHAP force plot and decision plot exhibited a clinically meaningful explanation of the RF algorithm. We constructed an ML model (RF) providing accurate prediction of frail phenotype in decompensated cirrhosis. The explainability and generalizability may foster clinicians to understand contributors to this physiologically vulnerable situation and tailor interventions.
The development and advancement of malnutrition is associated not only with the progression of hepatic dysfunction, but also with cirrhosis-related complications. However, the prevalence of malnutrition reported in different studies varies widely due to differences in diagnostic methods and patient investigation settings. Therefore, we need to identify malnourished patients promptly and accurately. The purpose of this review was to compare the validity and reliability of nutritional screening tools and to select the most appropriate nutritional risk screening for patients with cirrhosis. We compared nutritional risk screening tools such as the Nutritional Risk Screening 2002 (NRS-2002), Malnutrition Universal Screening Tool (MUST), Royal Free Hospital-Nutritional Prioritizing Tool (RFH-NPT) and Liver Disease Undernutrition Screening Tool (LDUST). Royal Free Hospital-Nutritional Prioritizing Tool (RFH-NPT) is more feasible to screen cirrhotic patients for nutritional risk, and is highly reproducible, considering the impact of sodium and water retention; so it is practical to screen cirrhotic patients via RFH-NPT for nutritional risk, subsequently, to evaluate the nutritional status of patients with nutritional risk via the Global Leadership Initiative on Malnutrition (GLIM) diagnostic criteria. L3-SMI (third lumbar-skeletal muscle index) can accurately define sarcopenia in cirrhotic patients and also be used for clinical nutritional status assessment.
8 November 2022 in Scandinavian Journal of Gastroenterology
Functional dyspepsia (FD) is a common functional gastrointestinal (GI) disorder, but its pathophysiology is poorly understood. Mast cells (MCs) may play a critical role in the development of FD. Th...
Mast cell (MC) plays a central role in intestinal permeability; however, few MC-targeting drugs are currently available for protection of the intestinal barrier in clinical practice. A nonfluorinated Lidocaine analog 2-diethylamino-N-2,5-dimethylphenyl acetamide (JM25-1) displays anti-allergic effect, but its impact on MC remains elusive. In this study, we explored whether JM25-1 has therapeutic potential on intestinal barrier defect through stabilizing MC. JM25-1 alleviated release of β-hexosaminidase and cytokine production of MC. The paracellular permeability was redressed by JM25-1 in intestinal epithelial cell monolayers co-cultured with activated MC. In vivo, JM25-1 diminished intestinal mucosal MC amount and cytokine production, especially downregulating the expression of CRHR1, accompanied by an increase of CRHR2. Protective effects appeared in JM25-1-treated stress rats with a recovery of weight and intestinal barrier integrity. Through network pharmacology analysis, JM25-1 showed a therapeutic possibility for irritable bowel syndrome (IBS) with predictive targeting on PI3K/AKT/mTOR signaling. As expected, JM25-1 reinforced p-PI3K, p-AKT, p-mTOR signaling in MC, while the mTOR inhibitor Rapamycin reversed the action of JM25-1 on the expression of CRHR1 and CRHR2. Moreover, JM25-1 successfully remedied intestinal defect and declined MC and CRHR1 expression in rat colon caused by colonic mucus of IBS patients. Our data implied that JM25-1 possessed therapeutic capacity against intestinal barrier defects by targeting the CRH receptors of MC through PI3K/AKT/mTOR signaling.
Background: Malnutrition in patients with chronic liver disease (CLD) is linked to increased mortality and a high risk of morbidity. Assessing the nutritional status of patients with CLD is challenging. The Global Leadership Initiative for Malnutrition (GLIM) offers a novel diagnostic framework for malnutrition. However, the efficacy of GLIM in CLD patients has not been validated.Methods: A systematic review and meta-analysis were conducted to evaluate the utility and diagnostic accuracy of the GLIM criteria in adult patients with CLD, involving a search of seven databases for relevant studies. The evaluation of quality was conducted with the QUADAS-2 tool.Results: The analysis included a total of five studies. Sample size ranged from 109 to 406 among different studies. According to the GLIM criteria, around 21.2 to 69.9% of individuals were identified as having malnutrition. Simultaneously, the subjective global assessment (SGA) detected malnourished patients ranging from 35.0 to 86.0%. Five studies compared the GLIM with the SGA. The nutritional assessment process in the studies was not clear according to the QUADAS-2 tool. The overall specificity of the meta-analysis was 85.8% (95% CI: 82.5–88.7%) and the overall sensitivity was 49.1% (95% CI: 45.5–52.8%).Conclusion: This is the first systematic review and meta-analysis on GLIM criteria, SGA and CLD patients. The applicability and reliability of the GLIM criteria in CLD patients remain constrained. Furthermore, certain validation studies that are parallel and predictive may have methodological limitations. Additional research is needed to confirm the applicability of the GLIM criteria in patients with CLD.Systematic review registration: PROSPERO, CRD420251010347.