Identification of clinical phenotypes associated with poor prognosis in patients with nonalcoholic fatty liver disease via unsupervised machine learning
Journal of Gastroenterology and Hepatology · 2023
DOI: 10.1111/jgh.16326 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Journal of Gastroenterology and Hepatology, 2023. Verfasst von Takanori Ito und 36 weiteren Autor:innen. Beteiligte Einrichtung: Department of Gastroenterology and Hepatology, Nagoya University Graduate School of Medicine, Nagoya, Japan. Hauptthemen laut MEDLINE: Non-alcoholic Fatty Liver Disease. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: Japan Strategic Medical Administration Research Center (J-SMARC).
Abstract (Originalsprache)
Background and Aims Both fibrosis status and body weight are important for assessing prognosis in nonalcoholic fatty liver disease (NAFLD). The aim of this study was to identify population clusters for specific clinical outcomes based on fibrosis‐4 (FIB‐4) index and body mass index (BMI) using an unsupervised machine learning method.
Methods
We conducted a multicenter study of 1335 biopsy‐proven NAFLD patients from Japan. Using the Gaussian mixture model to divide the cohort into clusters based on FIB‐4 index and BMI, we investigated prognosis for these clusters.
Results
The cohort consisted of 223 cases (16.0%) with advanced fibrosis (F3–4) as assessed from liver biopsy. Median values of BMI and FIB‐4 index were 27.3 kg/m 2 and 1.67. The patients were divided into four clusters by Bayesian information criterion, and all‐cause mortality was highest in cluster d, followed by cluster b ( P = 0.001). Regarding the characteristics of each cluster, clusters d and b presented a high FIB‐4 index (median 5.23 and 2.23), cluster a presented the lowest FIB‐4 index (median 0.78), and cluster c was associated with moderate FIB‐4 level (median 1.30) and highest BMI (median 34.3 kg/m 2 ). Clusters a and c had lower mortality rates than clusters b and d. However, all‐cause of death in clusters a and c was unrelated to liver disease.
Conclusions
Our clustering approach found that the FIB‐4 index is an important predictor of mortality in NAFLD patients regardless of BMI. Additionally, non‐liver‐related diseases were identified as the causes of death in NAFLD patients with low FIB‐4 index.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Gastroenterology and Hepatology, Nagoya University Graduate School of Medicine, Nagoya, Japan.
- Department of Emergency and Critical Care Medicine, Nagoya University Graduate School of Medicine, Nagoya, Japan.
- Liver Center, Saga University Hospital, Saga, Japan.
- Department of Hepatology, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan.
- Division of Gastroenterology and Hepatology, Yokohama City University Graduate School of Medicine, Yokohama, Japan.
- Department of Gastroenterology and Hepatology, Gifu Municipal Hospital, Gifu, Japan.
ORCID-Profile: Takanori Ito, Hirokazu Takahashi, Hidenori Toyoda, Asahiro Morishita, Tsubasa Tsutsumi, Koji Sawada, Hiroshi Tobita, Takumi Kawaguchi, Masatoshi Ishigami, Yoshio Sumida, Atsushi Nakajima
Förderung
- Japan Strategic Medical Administration Research Center (J-SMARC)
Zitieren
APA
Ito, T., Morooka, H., Takahashi, H., Fujii, H., Iwaki, M., Hayashi, H., Toyoda, H., Oeda, S., Hyogo, H., Kawanaka, M., Morishita, A., Munekage, K., Kawata, K., Tsutsumi, T., Sawada, K., Maeshiro, T., Tobita, H., Yoshida, Y., Naito, M., …, & Japan Study Group of Nonalcoholic Fatty Liver Disease (JSG-NAFLD) (2023). Identification of clinical phenotypes associated with poor prognosis in patients with nonalcoholic fatty liver disease via unsupervised machine learning. Journal of Gastroenterology and Hepatology. https://doi.org/10.1111/jgh.16326
Vancouver
Ito T, Morooka H, Takahashi H, Fujii H, Iwaki M, Hayashi H, et al. Identification of clinical phenotypes associated with poor prognosis in patients with nonalcoholic fatty liver disease via unsupervised machine learning. Journal of Gastroenterology and Hepatology. 2023. doi:10.1111/jgh.16326
BibTeX
@article{Ito2023,
author = {Ito, Takanori and Morooka, Hikaru and Takahashi, Hirokazu and Fujii, Hideki and Iwaki, Michihiro and Hayashi, Hideki and Toyoda, Hidenori and Oeda, Satoshi and Hyogo, Hideyuki and Kawanaka, Miwa and Morishita, Asahiro and Munekage, Kensuke and Kawata, Kazuhito and Tsutsumi, Tsubasa and Sawada, Koji and Maeshiro, Tatsuji and Tobita, Hiroshi and Yoshida, Yuichi and Naito, Masafumi and Araki, Asuka and Arakaki, Shingo and Kawaguchi, Takumi and Noritake, Hidenao and Ono, Masafumi and Masaki, Tsutomu and Yasuda, Satoshi and Tomita, Eiichi and Yoneda, Masato and Tokushige, Akihiro and Ishigami, Masatoshi and Kamada, Yoshihiro and Ueda, Shinichiro and Aishima, Shinichi and Sumida, Yoshio and Nakajima, Atsushi and Okanoue, Takeshi and Japan Study Group of Nonalcoholic Fatty Liver Disease (JSG-NAFLD), Japan Study Group of Nonalcoholic Fatty Liver Disease (JSG-NAFLD)},
title = {Identification of clinical phenotypes associated with poor prognosis in patients with nonalcoholic fatty liver disease via unsupervised machine learning},
journal = {Journal of Gastroenterology and Hepatology},
year = {2023},
doi = {10.1111/jgh.16326}
}
EUVIMED