Simple non‐invasive scoring systems and histological scores in predicting mortality in patients with non‐alcoholic fatty liver disease: A systematic review and meta‐analysis

Liu, Changhai; Ampuero, Javier; Pavlides, Michael; Wong, Vincent Wai‐Sun; Fan, Jian‐Gao; Bai, Lan; Li, Hong; Wu, Dongbo; Zhou, Lingyun; Du, Lingyao; Yang, Tiankuo; Shi, Ying; Gil‐Gómez, Antonio; Zhang, Wenting; Liang, Jia-Xu; Romero‐Gómez, Manuel; Tang, Hong

doi:10.1111/jgh.15431

Cited by 6 publications

(5 citation statements)

References 51 publications

(121 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A recent study based on a large European cohort of over 1100 patients reported NFS and FIB-4 were the best predictors of future LREs but had AUCs below 0.80 15 . Furthermore, a recent systematic review and meta-analysis confirmed the relatively poor performance of NFS and FIB-4 in the prediction of liver-related outcomes in patients with NAFLD and underscored the need for a more accurate model such as the NOS to assist clinicians in management decisions 52 . A recent study from Sweden has highlighted stratification by age, FIB-4, Gamma glutamyltransferase, and serum glucose aids identification of future risk of severe liver disease 53 .…”

Section: Discussionmentioning

confidence: 99%

“…[15] Furthermore, a recent systematic review and meta-analysis confirmed the relatively poor performance of NFS and FIB-4 in the prediction of liver-related outcomes in patients with NAFLD and underscored the need for a more accurate model such as the NOS to assist clinicians in management decisions. [52] A recent study from Sweden has highlighted stratification by age, FIB-4, Gamma glutamyltransferase, and serum glucose aids identification of future risk of severe liver disease. [53] Further comparison of the NOS with this method and other emerging fibrosis scores such as the NAFLD cirrhosis score is warranted to determine the optimal prognostic score.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting liver-related events in NAFLD: A predictive model

et al. 2023

Self Cite

View full text Add to dashboard Cite

Background and Aims: Management of NAFLD involves noninvasive prediction of fibrosis, which is a surrogate for patient outcomes. We aimed to develop and validate a model predictive of liver-related events (LREs) of decompensation and/or HCC and compare its accuracy with fibrosis models. Approach and Results: Patients with NAFLD from Australia and Spain who were followed for up to 28 years formed derivation (n = 584) and validation (n = 477) cohorts. Competing risk regression and information criteria were used for model development. Accuracy was compared with fibrosis models using time-dependent AUC analysis. During follow-up, LREs occurred in 52 (9%) and 11 (2.3%) patients in derivation and validation cohorts, respectively. Age, type 2 diabetes, albumin, bilirubin, platelet count, and international normalized ratio were independent predictors of LRE and were combined into a model [NAFLD outcomes score (NOS)]. The NOS model calibrated well [calibration slope, 0.99 (derivation), 0.98 (validation)] with excellent overall performance [integrated Brier score, 0.07 (derivation) and 0.01 (validation)]. A cutoff ≥1.3 identified subjects at a higher risk of LRE, (sub-HR 24.6, p < 0.001, 5-year cumulative incidence 38% vs 1.0%, respectively). The predictive accuracy at 5 and 10 years was excellent in both derivation (time-dependent AUC,0.92 and 0.90, respectively) and validation cohorts (time-dependent AUC,0.80 and 0.82, respectively). The NOS was more accurate than the fibrosis-4 or NAFLD fibrosis score for predicting LREs at 5 and 10 years (p < 0.001). Conclusions: The NOS model consists of readily available measures and has greater accuracy in predicting outcomes in patients with NAFLD than existing fibrosis models.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Predicting liver-related events in NAFLD: A predictive model

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, liver biopsy as the gold standard is inappropriate to screen clinically significant fibrosis because of its features like invasive, inconvenient and expensive. Some studies have shown that conventional non-invasive scores, such as NFS 9 , FIB-4 10 , and APRI 11 , have prognostic significance of death for NAFLD patients [12][13][14] . However, their results were controversial.…”

Section: Introductionmentioning

confidence: 99%

“…However, their results were controversial. A meta-analysis including 19 longitudinal studies showed that only the NFS > 0.676 was predictive of overall mortality, while FIB-4 and APRI failed 14 . And a retrospective analysis including 646 NAFLD patients proven by liver biopsy revealed that although FIB-4 and NFS could precisely predict the risk of overall mortality of NAFLD patients, owing to the AUC values were not high enough (FIB-4, 0.72 [95% CI, 0.68-0.76]; NFS, 0.72 [95% CI, 0.68-0.76] and APRI, 0.52 [95% CI, 0.47-0.57]), so they were not useful in the clinical practice and new methods are needed to confirm the prognosis of NAFLD patients 13 .…”

Section: Introductionmentioning

confidence: 99%

Machine learning-based mortality prediction models for non-alcoholic fatty liver disease in the general United States population

Zheng,

Wang,

Feng

2024

Preprint

View full text Add to dashboard Cite

Background & AimsNowadays, the global prevalence of non-alcoholic fatty liver disease (NAFLD) has reached about 25%, which is the most common chronic liver disease worldwide, and the mortality risk of NAFLD patients is higher. Our research created five machine learning (ML) models for predicting overall mortality in ultrasound-proven NAFLD patients and compared their performance with conventional non-invasive scoring systems, aiming to find a generalizable and valuable model for early mortality prediction in NAFLD patients.MethodsNational Health and Nutrition Examination Survey (NHANES)-III from 1988 to 1994 and NHANES-III related mortality data from 2019 were used. 70% of subjects were separated into the training set (N = 2262) for development, while 30% were in the testing set (N= 971) for validation. The outcome was all-cause death at the end of follow-up. Twenty-nine related variables were trained as predictor features for five ML–based models: Logistic regression (LR), K-nearest neighbors (KNN), Gradient-boosted decision tree (XGBoost), Random forest (RF) and Decision tree. Five typical evaluation indexes including area under the curve (AUC), F1 score, accuracy, sensitivity and specificity were used to measure the prediction performance.Results3233 patients with NAFLD in total were eligible for the inclusion criteria, with 1231 death during the average 25.3 years follow up time. AUC of the LR model in predicting the mortality of NAFLD was 0.888 (95% confidence interval [CI] 0.867-0.909), the accuracy was 0.808, the sensitivity was 0.819, the specificity was 0.802, and the F1 score was 0.765, which showed the best performance compared with other models (AUC were: RF, 0.876 [95%CI 0.852-0.897]; XGBoost, 0.875 [95%CI 0.853-0.898]; Decision tree, 0.793 [95%CI 0.766-0.819] and KNN, 0.787 [95%CI 0.759-0.816]) and conventional clinical scores (AUC were: Fibrosis-4 Score (FIB-4), 0.793 [95%CI 0.777-0.809]; NAFLD fibrosis score (NFS), 0.770 [95%CI 0.753-0.787] and aspartate aminotransferase-to-platelet ratio index (APRI), 0.522 [95%CI 0.502-0.543]).ConclusionsML–based models, especially LR model, had better discrimination performance in predicting all-cause mortality in patients with NAFLD compared to the conventional non-invasive scores, and an interpretable model like Decision tree, which only used three predictors: age, systolic pressure and glycated hemoglobin, is simple to use in clinical practice.

show abstract

“…On the other hand, the diagnosis of MAFLD emphasizes a diagnosis based on three alternative methods, i.e., “detected either by blood biomarkers/scores, imaging techniques or by liver histology”. Therefore, serum- and image-based methods were recently proposed in multiple studies for the screening and diagnosis of mild/severe hepatic steatosis and NAFLD/MAFLD [ 14 , 15 , 16 , 17 , 18 , 19 , 20 , 21 ].…”

Section: Introductionmentioning

confidence: 99%

Urine Proteome in Distinguishing Hepatic Steatosis in Patients with Metabolic-Associated Fatty Liver Disease

et al. 2022

Self Cite

View full text Add to dashboard Cite

Background: In patients with metabolic-associated fatty liver disease (MAFLD), hepatic steatosis is the first step of diagnosis, and it is a risk predictor that independently predicts insulin resistance, cardiovascular risk, and mortality. Urine biomarkers have the advantage of being less complex, with a lower dynamic range and fewer technical challenges, in comparison to blood biomarkers. Methods: Hepatic steatosis was measured by magnetic resonance imaging (MRI), which measured the proton density fat fraction (MRI-PDFF). Mild hepatic steatosis was defined as MRI-PDFF 5–10% and severe hepatic steatosis was defined as MRI-PDFF > 10%. Results: MAFLD patients with any kidney diseases were excluded. There were 53 proteins identified by mass spectrometry with significantly different expressions among the healthy control, mild steatosis, and severe steatosis patients. Gene Ontology (GO) and the Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses of these significantly changed urinary molecular features correlated with the liver, resulting in the dysregulation of carbohydrate derivative/catabolic/glycosaminoglycan/metabolic processes, insulin-like growth factor receptor levels, inflammatory responses, the PI3K–Akt signaling pathway, and cholesterol metabolism. Urine alpha-1-acid glycoprotein 1 (ORM1) and ceruloplasmin showed the most significant correlation with the clinical parameters of MAFLD status, including liver fat content, fibrosis, ALT, triglycerides, glucose, HOMA-IR, and C-reactive protein. According to ELISA and western blot (30 urine samples, normalized to urine creatinine), ceruloplasmin (ROC 0.78, p = 0.034) and ORM1 (ROC 0.87, p = 0.005) showed moderate diagnostic accuracy in distinguishing mild steatosis from healthy controls. Ceruloplasmin (ROC 0.79, p = 0.028) and ORM1 (ROC 0.81, p = 0.019) also showed moderate diagnostic accuracy in distinguishing severe steatosis from mild steatosis. Conclusions: Ceruloplasmin and ORM1 are potential biomarkers in distinguishing mild and severe steatosis in MAFLD patients.

show abstract

Simple non‐invasive scoring systems and histological scores in predicting mortality in patients with non‐alcoholic fatty liver disease: A systematic review and meta‐analysis

Cited by 6 publications

References 51 publications

Predicting liver-related events in NAFLD: A predictive model

Predicting liver-related events in NAFLD: A predictive model

Machine learning-based mortality prediction models for non-alcoholic fatty liver disease in the general United States population

Urine Proteome in Distinguishing Hepatic Steatosis in Patients with Metabolic-Associated Fatty Liver Disease

Contact Info

Product

Resources

About