Development and Validation of a Machine Learning-based Model for Prediction of Liver Fibrosis and MASH DOI

Maojie Liu,

Longfeng Jiang,

Juan Yang

и другие.

Journal of Clinical Gastroenterology, Год журнала: 2025, Номер unknown

Опубликована: Апрель 25, 2025

Background and Aim: The development of accurate noninvasive tests to identify individuals with metabolic dysfunction–associated steatohepatitis (MASH) liver fibrosis is great clinical importance. In this study, we aimed develop 2 diagnostic models on the basis routine laboratory data, using machine learning, patients MASH significant (fibrosis stages 4), respectively. Methods: This analysis included training (n=456) validation (n=105) sets who underwent biopsy testing for disease at hospitals in China. Logistic regression, random forest, support vector machine, XGBoost algorithm were used construct models, best compared 7 existing scoring systems including AAR, AST platelet ratio index (APRI), BARD score, fibrosis-4 (FIB-4), fibrotic non-alcoholic (NASH) (FNI), homeostatic model assessment insulin resistance (HOMA-IR), fatty score (NFS). Performance was estimated by area under receiver operating characteristic curve (AUROC). Results: final integrated 19 indicators derived from tests. exhibited superior performance an improved AUROC value (MASH, 0.670, 95% CI 0.530-0.811; fibrosis, 0.713, 0.611-0.815) other set. Conclusions: Utilizing learning can assist diagnosing based epidemiological information good performance.

Язык: Английский

Metabolic dysfunction-associated steatotic liver disease and malignancies: Unmasking a silent saboteur DOI
Stergios A. Pοlyzos,

Christos S. Mantzoros

Metabolism, Год журнала: 2025, Номер unknown, С. 156253 - 156253

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

1
Brown adipose tissue transplantation ameliorates hindlimb ischemic damage in diabetic mice DOI Creative Commons

Ting Lu,

Amin Liu, Chunchun Li

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Март 14, 2025

Peripheral arterial disease (PAD) is a common complication associated with diabetes, which can lead to foot ischemia. The condition often accompanied by infection and necrosis, ultimately leading diabetic ulcers the risk of amputation. Brown adipose tissue (BAT) its secreted cytokines play an essential role in regulation glucose homeostasis, modulation inflammatory responses, vascular endothelial cell proliferation. transplantation BAT into ischemic regions may offer therapeutic benefits alleviating symptoms PAD. A mouse model was established via intraperitoneal administration streptozocin. Subsequently, lower limb ulcer constructed transection femoral artery ligation vein. harvested from subscapular region employed as graft. research utilized Laser Doppler monitoring, Western blot analysis, hematoxylin-eosin (HE) staining, immunofluorescence enzyme-linked immunosorbent assay (ELISA) evaluate blood flow recovery regions, histopathological changes, angiogenesis remodeling, M1/M2 macrophage polarization. significantly enhanced mice while concurrently reducing necrotic tissue. Pathological analyses demonstrate that mitigates damage, stimulates angiogenesis, supports remodeling. Furthermore, blotting, immunofluorescence, ELISA results revealed reduces levels tissues, increases expression angiogenic factors, promotes polarization macrophages M1 M2 phenotype. has demonstrated mitigate injury mice, attenuate facilitate restoration flow. These effects be linked alterations

Язык: Английский

Процитировано

0
Metabolic Dysfunction-Associated Steatotic Liver Disease Induced by Microplastics: An Endpoint in the Liver–Eye Axis DOI Open Access
Ivan Šoša,

Loredana Labinac,

Manuela Perković

и другие.

International Journal of Molecular Sciences, Год журнала: 2025, Номер 26(7), С. 2837 - 2837

Опубликована: Март 21, 2025

There is a significant, rather than just anecdotal, connection between the liver and eyes. This evident in noticeable cases such as jaundice, where sclera has yellow tint. But this can be seen through even more subtle indicators, molecules known hepatokines. relationship not merely anecdotal; some studies, it referred to “liver–eye axis”. Ubiquitous environmental contaminants, microplastics (MPs), enter bloodstream human body conjunctival sac, nasolacrimal duct, upper respiratory tract mucosa. Once absorbed, these substances accumulate various organs cause harm. Toxic from surface of eye lead local oxidative damage by inducing apoptosis corneal cells, irregularly shaped microparticles exacerbate effect. Even other toxicants ocular may absorbed into distributed throughout body. Environmental toxicology presents challenge because many pollutants same route that used certain medications. Previous research indicated accumulation MPs play major role development chronic disease humans. It crucial investigate whether buildup potential fibrosis, or simply consequence conditions cirrhosis portal hypertension.

Язык: Английский

Процитировано

0
Machine learning models for predicting metabolic dysfunction-associated steatotic liver disease prevalence using basic demographic and clinical characteristics DOI Creative Commons

Gangfeng Zhu,

Yipeng Song, Zenghong Lu

и другие.

Journal of Translational Medicine, Год журнала: 2025, Номер 23(1)

Опубликована: Март 28, 2025

Metabolic dysfunction-associated steatotic liver disease (MASLD) is a global health concern that necessitates early screening and timely intervention to improve prognosis. The current diagnostic protocols for MASLD involve complex procedures in specialised medical centres. This study aimed explore the feasibility of utilising machine learning models accurately screen large populations based on combination essential demographic clinical characteristics. A total 10,007 outpatients who underwent transient elastography at First Affiliated Hospital Gannan Medical University were enrolled form derivation cohort. Using eight characteristics (age, educational level, height, weight, waist hip circumference, history hypertension diabetes), we built predictive (classified as none or mild: controlled attenuation parameter (CAP) ≤ 269 dB/m; moderate: 269-296 severe: CAP > 296 dB/m) employing 10 algorithms: logistic regression (LR), multilayer perceptron (MLP), extreme gradient boosting (XGBoost), bootstrap aggregating, decision tree, K-nearest neighbours, light machine, naive Bayes, random forest, support vector machine. These externally validated using National Health Nutrition Examination Survey (NHANES) 2017-2023 datasets. In hospital outpatient cohort, algorithms demonstrated robust capabilities. Notably, LR achieved highest accuracy (ACC) 0.711 test cohort 0.728 validation coupled with areas under receiver operating characteristic curve (AUC) values 0.798 0.806, respectively. Similarly, MLP XGBoost showed promising results, achieving an ACC 0.735 registering AUC 0.798. External NHANES datasets yielded consistent (0.831), (0.823), (0.784) performing robustly. constructed can general population. approach significantly enhances feasibility, accessibility, compliance provides effective tool large-scale assessments strategies.

Язык: Английский

Процитировано

0
Metabolic Syndrome and Liver Disease: Re-Appraisal of Screening, Diagnosis, and Treatment Through the Paradigm Shift from NAFLD to MASLD DOI Open Access

Marin Pecani,

P. Andreozzi, Roberto Cangemi

и другие.

Journal of Clinical Medicine, Год журнала: 2025, Номер 14(8), С. 2750 - 2750

Опубликована: Апрель 16, 2025

Metabolic dysfunction-associated steatotic liver disease (MASLD), previously known as non-alcoholic fatty (NAFLD), encompasses a spectrum of diseases characterized by hepatic steatosis, the presence at least one cardiometabolic risk factor, and no other apparent cause. syndrome (MetS) is cluster clinical conditions associated with increased cardiovascular disease, type 2 diabetes, overall morbidity mortality. This narrative review summarizes changes in management people MetS NAFLD/MASLD from screening to therapeutic strategies that have occurred last decades. Specifically, we underline importance considering different impacts simple steatosis advanced fibrosis provide an up-to-date overview on non-invasive diagnostic tests (i.e., imaging serum biomarkers), which now offer acceptable accuracy are globally more accessible. Early detection MASLD top priority it allows for timely interventions, primarily through lifestyle modification. The benefits global multidimensional approach not negligible. Therefore, holistic both conditions, related chronic should be applied improve health longevity.

Язык: Английский

Процитировано

0
Development and Validation of a Machine Learning-based Model for Prediction of Liver Fibrosis and MASH DOI

Maojie Liu,

Longfeng Jiang,

Juan Yang

и другие.

Journal of Clinical Gastroenterology, Год журнала: 2025, Номер unknown

Опубликована: Апрель 25, 2025

Background and Aim: The development of accurate noninvasive tests to identify individuals with metabolic dysfunction–associated steatohepatitis (MASH) liver fibrosis is great clinical importance. In this study, we aimed develop 2 diagnostic models on the basis routine laboratory data, using machine learning, patients MASH significant (fibrosis stages 4), respectively. Methods: This analysis included training (n=456) validation (n=105) sets who underwent biopsy testing for disease at hospitals in China. Logistic regression, random forest, support vector machine, XGBoost algorithm were used construct models, best compared 7 existing scoring systems including AAR, AST platelet ratio index (APRI), BARD score, fibrosis-4 (FIB-4), fibrotic non-alcoholic (NASH) (FNI), homeostatic model assessment insulin resistance (HOMA-IR), fatty score (NFS). Performance was estimated by area under receiver operating characteristic curve (AUROC). Results: final integrated 19 indicators derived from tests. exhibited superior performance an improved AUROC value (MASH, 0.670, 95% CI 0.530-0.811; fibrosis, 0.713, 0.611-0.815) other set. Conclusions: Utilizing learning can assist diagnosing based epidemiological information good performance.

Язык: Английский

Процитировано

0