Nutritional patterns as machine learning predictors of liver health in a population of elderly subjects
Nutrition, Metabolism and Cardiovascular Diseases · 2023
DOI: 10.1016/j.numecd.2023.07.009 ↗Kurz gefasst
Fachartikel in der Zeitschrift Nutrition, Metabolism and Cardiovascular Diseases, 2023. Verfasst von Luisa Lampignano und 9 weiteren Autor:innen. Beteiligte Einrichtung: Local Healthcare Authority of Bari, ASL Bari, Bari, Italy. Electronic address: luisa.lampignano@planet-npo.eu. Hauptthemen laut MEDLINE: Machine Learning, Non-alcoholic Fatty Liver Disease, Diet, Healthy, Liver Cirrhosis. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 53 Literaturangaben.
Abstract (Originalsprache)
BACKGROUND AND AIMS: Non-alcoholic hepatic steatosis affects 25% of adults worldwide and its prevalence increases with age. There is currently no definitive treatment for NAFLD but international guidelines recommend a lifestyle-based approach, including a healthy diet. The aim of this study was to investigate the interactions between eating habits and the risk of steatosis and/or hepatic fibrosis, using a machine learning approach, in a non-institutionalized elderly population. METHODS AND RESULTS: We recruited 1929 subjects, mean age 74 years, from the population-based Salus in Apulia Study. Dietary habits and the risk of steatosis and hepatic fibrosis were evaluated with a validated food frequency questionnaire, the Fatty Liver Index (FLI) and the FIB-4 score, respectively. Two dietary patterns associated with the risk of steatosis and hepatic fibrosis have been identified. They are both similar to a "western" diet, defined by a greater consumption of refined foods, with a rich content of sugars and saturated fats, and alcoholic and non-alcoholic calorie drinks. CONCLUSION: This study further supports the concept of diet as a factor that significantly influences the development of the most widespread liver diseases. However, longitudinal studies are needed to better understand the causal effect of the consumption of particular foods on fat accumulation in the liver.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Local Healthcare Authority of Bari, ASL Bari, Bari, Italy. Electronic address: luisa.lampignano@planet-npo.eu.
- National Institute of Gastroenterology IRCCS "Saverio de Bellis", Research Hospital, Castellana Grotte, Italy.
- Department of Translational Biomedicine and Neuroscience "DiBraiN", University of Bari Aldo Moro, Bari, Italy.
- Local Healthcare Authority of Bari, ASL Bari, Bari, Italy.
- Department of Interdisciplinary Medicine, University "Aldo Moro", Bari, Italy.
- "Cesare Frugoni" Internal and Geriatric Medicine and Memory Unit, University of Bari "Aldo Moro", Bari, Italy.
Zitieren
APA
Lampignano, L., Tatoli, R., Donghia, R., Bortone, I., Castellana, F., Zupo, R., Lozupone, M., Panza, F., Conte, C., & Sardone, R. (2023). Nutritional patterns as machine learning predictors of liver health in a population of elderly subjects. Nutrition, Metabolism and Cardiovascular Diseases. https://doi.org/10.1016/j.numecd.2023.07.009
Vancouver
Lampignano L, Tatoli R, Donghia R, Bortone I, Castellana F, Zupo R, et al. Nutritional patterns as machine learning predictors of liver health in a population of elderly subjects. Nutrition, Metabolism and Cardiovascular Diseases. 2023. doi:10.1016/j.numecd.2023.07.009
BibTeX
@article{Lampignano2023,
author = {Lampignano, Luisa and Tatoli, Rossella and Donghia, Rossella and Bortone, Ilaria and Castellana, Fabio and Zupo, Roberta and Lozupone, Madia and Panza, Francesco and Conte, Caterina and Sardone, Rodolfo},
title = {Nutritional patterns as machine learning predictors of liver health in a population of elderly subjects},
journal = {Nutrition, Metabolism and Cardiovascular Diseases},
year = {2023},
doi = {10.1016/j.numecd.2023.07.009}
}
EUVIMED