Machine learning improves the prediction of significant fibrosis in Asian patients with metabolic dysfunction‐associated steatotic liver disease – The Gut and Obesity in Asia (GO‐ASIA) Study
Alimentary Pharmacology & Therapeutics · 2024-03 · 59 (6) · 774-788
DOI: 10.1111/apt.17891 ↗Kurz gefasst
Fachartikel in der Zeitschrift Alimentary Pharmacology & Therapeutics, 2024-02. Verfasst von Nipun Verma und 25 weiteren Autor:innen. Beteiligte Einrichtung: Department of Hepatology, Postgraduate Institute of Medical Education and Research, Chandigarh, India. Hauptthemen laut MEDLINE: Non-alcoholic Fatty Liver Disease, Metabolic Syndrome. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 37 Literaturangaben.
Abstract (Originalsprache)
Background
The precise estimation of cases with significant fibrosis (SF) is an unmet goal in non‐alcoholic fatty liver disease (NAFLD/MASLD).
Aims
We evaluated the performance of machine learning (ML) and non‐patented scores for ruling out SF among NAFLD/MASLD patients.
Methods
Twenty‐one ML models were trained ( N = 1153), tested ( N = 283), and validated ( N = 220) on clinical and biochemical parameters of histologically‐proven NAFLD/MASLD patients ( N = 1656) collected across 14 centres in 8 Asian countries. Their performance for detecting histological‐SF (≥F2fibrosis) were evaluated with APRI, FIB4, NFS, BARD, and SAFE (NPV/F1‐score as model‐selection criteria).
Results
Patients aged 47 years (median), 54.6% males, 73.7% with metabolic syndrome, and 32.9% with histological‐SF were included in the study. Patients with SFvs.no‐SF had higher age, aminotransferases, fasting plasma glucose, metabolic syndrome, uncontrolled diabetes, and NAFLD activity score ( p < 0.001, each). ML models showed 7%–12% better discrimination than FIB‐4 to detect SF. Optimised random forest (RF) yielded best NPV/F1 in overall set (0.947/0.754), test set (0.798/0.588) and validation set (0.852/0.559), as compared to FIB4 in overall set (0.744/0.499), test set (0.722/0.456), and validation set (0.806/0.507). Compared to FIB‐4, RF could pick 10 times more patients with SF, reduce unnecessary referrals by 28%, and prevent missed referrals by 78%. Age, AST, ALT fasting plasma glucose, and platelet count were top features determining the SF. Sequential use of SAFE < 140 and FIB4 < 1.2 (when SAFE > 140) was next best in ruling out SF (NPV of 0.757, 0.724 and 0.827 in overall, test and validation set).
Conclusions
ML with clinical, anthropometric data and simple blood investigations perform better than FIB‐4 for ruling out SF in biopsy‐proven Asian NAFLD/MASLD patients.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Hepatology, Postgraduate Institute of Medical Education and Research, Chandigarh, India.
- Department of Medicine and Therapeutics, The Chinese University of Hong Kong, Hong Kong, China.
- Gastroenterology and Hepatology Unit, Department of Medicine, Faculty of Medicine, University of Malaya Medical Centre, Kuala Lumpur, Malaysia.
- NAFLD Research Centre Department of Hepatology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China.
- Department of Endocrinology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China.
- Division of Gastroenterology, King Chulalongkorn Memorial Hospital, Chulalongkorn University, Bangkok, Thailand.
ORCID-Profile: Nipun Verma, Ajay Duseja, Arka De, Vincent Wai-Sun Wong, Sanjiv Mahadeva, Ming-Hua Zheng, Phunchai Charatcharoenwitthaya, Anand Kulkarni, Yeong Yeh Lee
Zitieren
APA
Verma, N., Duseja, A., Mehta, M., De, A., Lin, H., Wong, V. W., Wong, G. L., Rajaram, R. B., Chan, W. K., Mahadeva, S., Zheng, M. H., Liu, W. Y., Treeprasertsuk, S., Prasoppokakorn, T., Kakizaki, S., Seki, Y., Kasama, K., Charatcharoenwitthaya, P., Sathirawich, P., …, & Young, D. Y. (2024). Machine learning improves the prediction of significant fibrosis in Asian patients with metabolic dysfunction‐associated steatotic liver disease – The Gut and Obesity in Asia (GO‐ASIA) Study. Alimentary Pharmacology & Therapeutics, 59(6), 774-788. https://doi.org/10.1111/apt.17891
Vancouver
Verma N, Duseja A, Mehta M, De A, Lin H, Wong VW, et al. Machine learning improves the prediction of significant fibrosis in Asian patients with metabolic dysfunction‐associated steatotic liver disease – The Gut and Obesity in Asia (GO‐ASIA) Study. Alimentary Pharmacology & Therapeutics. 2024;59(6):774-788. doi:10.1111/apt.17891
BibTeX
@article{Verma2024,
author = {Verma, Nipun and Duseja, Ajay and Mehta, Manu and De, Arka and Lin, Huapeng and Wong, Vincent Wai-Sun and Wong, Grace Lai-Hung and Rajaram, Ruveena Bhavani and Chan, Wah-Kheong and Mahadeva, Sanjiv and Zheng, Ming-Hua and Liu, Wen-Yue and Treeprasertsuk, Sombat and Prasoppokakorn, Thaninee and Kakizaki, Satoru and Seki, Yosuke and Kasama, Kazunori and Charatcharoenwitthaya, Phunchai and Sathirawich, Phalath and Kulkarni, Anand and Purnomo, Hery Djagat and Kamani, Lubna and Lee, Yeong Yeh and Wong, Mung Seong and Tan, Eunice X X and Young, Dan Yock},
title = {Machine learning improves the prediction of significant fibrosis in Asian patients with metabolic dysfunction‐associated steatotic liver disease – The Gut and Obesity in Asia (GO‐ASIA) Study},
journal = {Alimentary Pharmacology & Therapeutics},
year = {2024},
volume = {59},
number = {6},
pages = {774--788},
doi = {10.1111/apt.17891}
}
EUVIMED