Artificial Intelligence-Based Diets: A Role in the Nutritional Treatment of Metabolic Dysfunction-Associated Steatotic Liver Disease?

IF 2.9 3区医学 Q3 NUTRITION & DIETETICS

Journal of Human Nutrition and Dietetics Pub Date : 2025-02-27 DOI:10.1111/jhn.70033

Tugce Ozlu Karahan, Emre Batuhan Kenger, Yusuf Yilmaz

{"title":"Artificial Intelligence-Based Diets: A Role in the Nutritional Treatment of Metabolic Dysfunction-Associated Steatotic Liver Disease?","authors":"Tugce Ozlu Karahan, Emre Batuhan Kenger, Yusuf Yilmaz","doi":"10.1111/jhn.70033","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>Metabolic dysfunction-associated steatotic liver disease (MASLD) is a growing global health concern. Effective management of this condition relies heavily on lifestyle modifications and dietary interventions. In this study, we sought to evaluate the dietary plans for MASLD generated by ChatGPT (GPT-4o) according to current guideline recommendations.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>ChatGPT was used to create single-day meal plans for 48 simulated patients with MASLD, tailored to individual characteristics such as age, gender, height, weight and transient elastography parameters. The plans were assessed for appropriateness according to disease-specific guidelines.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>The mean energy content of the menus planned by ChatGPT was 1596.9 ± 141.5 kcal with a mean accuracy of 91.3 ± 11.0%, and fibre content was 22.0 ± 0.6 g with a mean accuracy of 88.1 ± 2.5%. However, they exhibited elevated levels of protein, fat and saturated fat acids. Conversely, the carbohydrate content was lower. ChatGPT recommended weight loss for obese patients but did not extend this advice to normal-weight and overweight individuals. Notably, recommendations for a Mediterranean diet and physical activity were absent.</p>\n </section>\n \n <section>\n \n <h3> Conclusions</h3>\n \n <p>ChatGPT shows potential in developing dietary plans for MASLD management. However, discrepancies in macronutrient distributions and the omission of key evidence-based recommendations highlight the need for further refinement. To enhance the effectiveness of AI tools in dietary recommendations, alignment with established guidelines must be improved.</p>\n </section>\n </div>","PeriodicalId":54803,"journal":{"name":"Journal of Human Nutrition and Dietetics","volume":"38 2","pages":""},"PeriodicalIF":2.9000,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Human Nutrition and Dietetics","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/jhn.70033","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"NUTRITION & DIETETICS","Score":null,"Total":0}

引用次数: 0

Abstract

Background

Metabolic dysfunction-associated steatotic liver disease (MASLD) is a growing global health concern. Effective management of this condition relies heavily on lifestyle modifications and dietary interventions. In this study, we sought to evaluate the dietary plans for MASLD generated by ChatGPT (GPT-4o) according to current guideline recommendations.

Methods

ChatGPT was used to create single-day meal plans for 48 simulated patients with MASLD, tailored to individual characteristics such as age, gender, height, weight and transient elastography parameters. The plans were assessed for appropriateness according to disease-specific guidelines.

Results

The mean energy content of the menus planned by ChatGPT was 1596.9 ± 141.5 kcal with a mean accuracy of 91.3 ± 11.0%, and fibre content was 22.0 ± 0.6 g with a mean accuracy of 88.1 ± 2.5%. However, they exhibited elevated levels of protein, fat and saturated fat acids. Conversely, the carbohydrate content was lower. ChatGPT recommended weight loss for obese patients but did not extend this advice to normal-weight and overweight individuals. Notably, recommendations for a Mediterranean diet and physical activity were absent.

Conclusions

ChatGPT shows potential in developing dietary plans for MASLD management. However, discrepancies in macronutrient distributions and the omission of key evidence-based recommendations highlight the need for further refinement. To enhance the effectiveness of AI tools in dietary recommendations, alignment with established guidelines must be improved.

查看原文本刊更多论文

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Human Nutrition and Dietetics 医学-营养学

CiteScore

5.30

自引率

15.20%

发文量

133

审稿时长

6-12 weeks

期刊介绍： Journal of Human Nutrition and Dietetics is an international peer-reviewed journal publishing papers in applied nutrition and dietetics. Papers are therefore welcomed on: - Clinical nutrition and the practice of therapeutic dietetics - Clinical and professional guidelines - Public health nutrition and nutritional epidemiology - Dietary surveys and dietary assessment methodology - Health promotion and intervention studies and their effectiveness - Obesity, weight control and body composition - Research on psychological determinants of healthy and unhealthy eating behaviour. Focus can for example be on attitudes, brain correlates of food reward processing, social influences, impulsivity, cognitive control, cognitive processes, dieting, psychological treatments. - Appetite, Food intake and nutritional status - Nutrigenomics and molecular nutrition - The journal does not publish animal research The journal is published in an online-only format. No printed issue of this title will be produced but authors will still be able to order offprints of their own articles.