Related Experiment Video
Updated: May 5, 2026

Studying Food Reward and Motivation in Humans
Published on: March 19, 2014
ChatGPT-4o and 4o1 Preview as Dietary Support Tools in a Real-World Medicated Obesity Program: A Prospective
Louis Talay1, Leif Lagesen2, Adela Yip3
1Faculty of Arts and Social Sciences, University of Sydney, Sydney, NSW 2050, Australia.
Advanced large language models (LLMs) show comparable performance to human dietitians in obesity services. These AI tools may support patient care and improve access to weight loss programs.
Area of Science:
- Artificial Intelligence in Healthcare
- Obesity Medicine
- Digital Health
Background:
- Clinicians are exploring large language models (LLMs) for obesity services, balancing potential efficiency gains against concerns about scientific accuracy and empathy.
- Previous research indicated ChatGPT-3 could mimic dietitian responses to basic dietary queries.
Purpose of the Study:
- To compare the performance of two ChatGPT-4o models against human dietitians in responding to complex questions within a medicated digital weight loss service.
Main Methods:
- Two ChatGPT-4o models and human dietitians responded to 10 complex questions (5 broad, 5 narrow) from real-world patient interactions.
- Responses were evaluated on scientific correctness, comprehensibility, empathy/relatability, and actionability.
Main Results:
- Neither ChatGPT-4o model was statistically outperformed by human dietitians across any of the 10 questions (p < 0.05).
- Aggregated scores across all four criteria also showed no statistically significant difference between AI models and human dietitians.
Conclusions:
- Advanced LLMs demonstrate potential as a supportive tool in medicated obesity services.
- Further research is required in diverse obesity contexts to confirm LLM capabilities in lifestyle coaching and impact on care access.
Related Concept Videos
Pharmacokinetic Models: Comparison and Selection Criterion
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
Bioavailability Study Design: Healthy Subjects Versus Patients
Drug Dosing: Obese Patients
Pharmacokinetics in Obese Patients: Drug Absorption and Distribution
Pharmacokinetics in Obese Patients: Drug Metabolism and Excretion
Dipeptidyl Peptidase 4 Inhibitors

