Matches in SemOpenAlex for { <https://semopenalex.org/work/W4284965492> ?p ?o ?g. }
- W4284965492 endingPage "557" @default.
- W4284965492 startingPage "546" @default.
- W4284965492 abstract "We assessed the performance of machine learning (ML) models in identifying clinically significant NAFLD-associated liver fibrosis and cirrhosis.We implemented ML models including logistic regression (LR), random forest (RF), and artificial neural network to predict histological stages of fibrosis using 17 demographic/clinical features in 1370 patients with NAFLD who underwent liver biopsy, FibroScan, and labs within a 6-month period at multiple U.S. centers. Histological stages of fibrosis (≥F2, ≥F3, and F4) were predicted using ML, FibroScan liver stiffness measurements, and Fibrosis-4 index (FIB-4). NASH with significant fibrosis (NAS ≥ 4 + ≥F2) was assessed using ML, FibroScan-AST (FAST) score, FIB-4, and NAFLD fibrosis score (NFS). We used 80% of the cohort to train and 20% to test the ML models. For ≥F2, ≥F3, F4, and NASH + NAS ≥ 4 + ≥F2, all ML models, especially RF, had primarily higher accuracy and AUC compared with FibroScan, FIB-4, FAST, and NFS. AUC for RF versus FibroScan and FIB-4 for ≥F2, ≥F3, and F4 were (0.86 vs. 0.81, 0.78), (0.89 vs. 0.83, 0.82), and (0.89 vs. 0.86, 0.85), respectively. AUC for RF versus FAST, FIB-4, and NFS for NASH + NAS ≥ 4 + ≥F2 were (0.80 vs. 0.77, 0.66, 0.63). For NASH + NAS ≥ 4 + ≥F2, all ML models had lower/similar percentages within the indeterminate zone compared with FIB-4 and NFS. Overall, ML models performed better in sensitivity, specificity, positive predictive value, and negative predictive value compared with traditional noninvasive tests.ML models performed better overall than FibroScan, FIB-4, FAST, and NFS. ML could be an effective tool for identifying clinically significant liver fibrosis and cirrhosis in patients with NAFLD." @default.
- W4284965492 created "2022-07-10" @default.
- W4284965492 creator A5002702247 @default.
- W4284965492 creator A5015051145 @default.
- W4284965492 creator A5019990218 @default.
- W4284965492 creator A5020725697 @default.
- W4284965492 creator A5024244120 @default.
- W4284965492 creator A5031201810 @default.
- W4284965492 creator A5031884118 @default.
- W4284965492 creator A5043846829 @default.
- W4284965492 creator A5049386611 @default.
- W4284965492 creator A5053405300 @default.
- W4284965492 creator A5060086401 @default.
- W4284965492 creator A5074225080 @default.
- W4284965492 creator A5083655008 @default.
- W4284965492 creator A5084292537 @default.
- W4284965492 creator A5091625375 @default.
- W4284965492 date "2022-08-09" @default.
- W4284965492 modified "2023-10-15" @default.
- W4284965492 title "Machine learning models are superior to noninvasive tests in identifying clinically significant stages of NAFLD and NAFLD‐related cirrhosis" @default.
- W4284965492 cites W1663303330 @default.
- W4284965492 cites W1919216911 @default.
- W4284965492 cites W1989380159 @default.
- W4284965492 cites W2000641576 @default.
- W4284965492 cites W2060205727 @default.
- W4284965492 cites W2067740038 @default.
- W4284965492 cites W2083039650 @default.
- W4284965492 cites W2087829753 @default.
- W4284965492 cites W2088337379 @default.
- W4284965492 cites W2105329556 @default.
- W4284965492 cites W2112496618 @default.
- W4284965492 cites W2131692102 @default.
- W4284965492 cites W2288325680 @default.
- W4284965492 cites W2321450778 @default.
- W4284965492 cites W2750268731 @default.
- W4284965492 cites W2887971464 @default.
- W4284965492 cites W2891968130 @default.
- W4284965492 cites W2908524400 @default.
- W4284965492 cites W3004695037 @default.
- W4284965492 cites W3004950447 @default.
- W4284965492 cites W3012883032 @default.
- W4284965492 cites W3036412257 @default.
- W4284965492 cites W3047557444 @default.
- W4284965492 cites W3133101076 @default.
- W4284965492 cites W3136175338 @default.
- W4284965492 cites W3147809485 @default.
- W4284965492 cites W3157759000 @default.
- W4284965492 cites W3166934300 @default.
- W4284965492 cites W3186380763 @default.
- W4284965492 doi "https://doi.org/10.1002/hep.32655" @default.
- W4284965492 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35809234" @default.
- W4284965492 hasPublicationYear "2022" @default.
- W4284965492 type Work @default.
- W4284965492 citedByCount "5" @default.
- W4284965492 countsByYear W42849654922023 @default.
- W4284965492 crossrefType "journal-article" @default.
- W4284965492 hasAuthorship W4284965492A5002702247 @default.
- W4284965492 hasAuthorship W4284965492A5015051145 @default.
- W4284965492 hasAuthorship W4284965492A5019990218 @default.
- W4284965492 hasAuthorship W4284965492A5020725697 @default.
- W4284965492 hasAuthorship W4284965492A5024244120 @default.
- W4284965492 hasAuthorship W4284965492A5031201810 @default.
- W4284965492 hasAuthorship W4284965492A5031884118 @default.
- W4284965492 hasAuthorship W4284965492A5043846829 @default.
- W4284965492 hasAuthorship W4284965492A5049386611 @default.
- W4284965492 hasAuthorship W4284965492A5053405300 @default.
- W4284965492 hasAuthorship W4284965492A5060086401 @default.
- W4284965492 hasAuthorship W4284965492A5074225080 @default.
- W4284965492 hasAuthorship W4284965492A5083655008 @default.
- W4284965492 hasAuthorship W4284965492A5084292537 @default.
- W4284965492 hasAuthorship W4284965492A5091625375 @default.
- W4284965492 hasConcept C126322002 @default.
- W4284965492 hasConcept C151956035 @default.
- W4284965492 hasConcept C2775934546 @default.
- W4284965492 hasConcept C2777214474 @default.
- W4284965492 hasConcept C2777766500 @default.
- W4284965492 hasConcept C2780559512 @default.
- W4284965492 hasConcept C2994217296 @default.
- W4284965492 hasConcept C58471807 @default.
- W4284965492 hasConcept C71924100 @default.
- W4284965492 hasConcept C90924648 @default.
- W4284965492 hasConceptScore W4284965492C126322002 @default.
- W4284965492 hasConceptScore W4284965492C151956035 @default.
- W4284965492 hasConceptScore W4284965492C2775934546 @default.
- W4284965492 hasConceptScore W4284965492C2777214474 @default.
- W4284965492 hasConceptScore W4284965492C2777766500 @default.
- W4284965492 hasConceptScore W4284965492C2780559512 @default.
- W4284965492 hasConceptScore W4284965492C2994217296 @default.
- W4284965492 hasConceptScore W4284965492C58471807 @default.
- W4284965492 hasConceptScore W4284965492C71924100 @default.
- W4284965492 hasConceptScore W4284965492C90924648 @default.
- W4284965492 hasIssue "2" @default.
- W4284965492 hasLocation W42849654921 @default.
- W4284965492 hasLocation W42849654922 @default.
- W4284965492 hasOpenAccess W4284965492 @default.
- W4284965492 hasPrimaryLocation W42849654921 @default.
- W4284965492 hasRelatedWork W1555899594 @default.
- W4284965492 hasRelatedWork W2005074764 @default.