Machine learning models are superior to noninvasive tests in identifying clinically significant stages of NAFLD and NAFLD‐related cirrhosis
Hepatology · 2023-02 · 77 (2) · 546-557
DOI: 10.1002/hep.32655 ↗Kurz gefasst
Fachartikel in der Zeitschrift Hepatology, online erschienen am 09.08.2022. Verfasst von Devon Chang und 14 weiteren Autor:innen. Beteiligte Einrichtung: Arnold O. Beckman High School , Irvine , California , USA. Hauptthemen laut MEDLINE: Non-alcoholic Fatty Liver Disease. Die Arbeit wurde bisher 94-mal zitiert (Crossref) und nennt 37 Literaturangaben.
Abstract (Originalsprache)
Background and Aims: We assessed the performance of machine learning (ML) models in identifying clinically significant NAFLD‐associated liver fibrosis and cirrhosis. Approach and Results: 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. Conclusions: 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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Arnold O. Beckman High School , Irvine , California , USA.
- Department of Medicine , Cedars Sinai Medical Center , Los Angeles , California , USA.
- California Liver Institute , Pasadena , California , USA.
- Department of Pathology , Cedars-Sinai Medical Center , Los Angeles , California , USA.
- Comprehensive Transplant Center , Cedars-Sinai Medical Center , Los Angeles , California , USA.
- Division of Gastroenterology , University of California at San Diego , La Jolla , California , USA.
ORCID-Profile: Ju Dong Yang
Zitieren
APA
Chang, D., Truong, E., Mena, E. A., Pacheco, F., Wong, M., Guindi, M., Todo, T. T., Noureddin, N., Ayoub, W., Yang, J. D., Kim, I. K., Kohli, A., Alkhouri, N., Harrison, S., & Noureddin, M. (2023). Machine learning models are superior to noninvasive tests in identifying clinically significant stages of NAFLD and NAFLD‐related cirrhosis. Hepatology, 77(2), 546-557. https://doi.org/10.1002/hep.32655
Vancouver
Chang D, Truong E, Mena EA, Pacheco F, Wong M, Guindi M, et al. Machine learning models are superior to noninvasive tests in identifying clinically significant stages of NAFLD and NAFLD‐related cirrhosis. Hepatology. 2023;77(2):546-557. doi:10.1002/hep.32655
BibTeX
@article{Chang2023,
author = {Chang, Devon and Truong, Emily and Mena, Edward A and Pacheco, Fabiana and Wong, Micaela and Guindi, Maha and Todo, Tsuyoshi T and Noureddin, Nabil and Ayoub, Walid and Yang, Ju Dong and Kim, Irene K and Kohli, Anita and Alkhouri, Naim and Harrison, Stephen and Noureddin, Mazen},
title = {Machine learning models are superior to noninvasive tests in identifying clinically significant stages of NAFLD and NAFLD‐related cirrhosis},
journal = {Hepatology},
year = {2023},
volume = {77},
number = {2},
pages = {546--557},
doi = {10.1002/hep.32655}
}
EUVIMED