Personalized AI Prompt Generator and ChatGPT for Weight Loss: Randomized Controlled Trial in Adults with Overweight and Obesity
preprint
OA: closed
Abstract
Background: The global prevalence of overweight and obesity continues escalating, driven by environmental factors and lifestyle behaviors leading to cardiovascular disease, diabetes, and cancer. Digital health interventions offer scalable solutions for weight management, yet personalized artificial intelligence applications remain underexplored. Large language model chatbots present opportunities for individualized behavioral interventions, but evidence comparing personalized versus manual prompt AI-driven approaches is limited. Objectives: This randomized controlled trial evaluated the effectiveness of a personalized exercise and dietary prompt generator integrated with ChatGPT versus structured manual ChatGPT guidance for weight management. Methods: Adults aged 18-65 years with BMI 27.5-34.9 kg/m 2 (n=160) from Greater Kuala Lumpur were randomized to NExGEN personalized prompt system with ChatGPT (NEX; n=81) or structured manual ChatGPT control (CON; n=79). The NExGEN system generated individualized prompts based on 111 assessment variables including demographics, health status, and preferences. CON participants received structured manual ChatGPT prompts. Assessments occurred at baseline, 12 weeks, and 24 weeks. Primary outcome was body weight measured using bioelectrical impedance analysis. Secondary outcomes included body composition, dietary intake, physical activity, and cardiometabolic markers. Linear mixed models analyzed intervention effects. Results: The NEX group achieved significantly greater weight loss than CON at 12 weeks (6.6 kg vs 3.0 kg, P<0.001) and 24 weeks (5.5 kg vs 1.7 kg, P<0.001). Fat mass decreased significantly in NEX participants (3.7 kg at 12 weeks, P<0.001) while preserving fat-free mass. Energy density, fat intake, and physical activity improved significantly in the NEX group. Cardiometabolic variables showed minimal between-group differences. Conclusions: The personalized AI-driven intervention produced superior weight loss and body composition improvements compared with structured manual prompt guidance. Limited cardiometabolic improvements reflected the metabolically healthy study population at baseline.
Full text
3,808 characters
· extracted from
oa-doi-fallback
· 5 sections
· click to expand
Abstract
Background The global prevalence of overweight and obesity continues escalating, driven by environmental factors and lifestyle behaviors leading to cardiovascular disease, diabetes, and cancer. Digital health interventions offer scalable solutions for weight management, yet personalized artificial intelligence applications remain underexplored. Large language model chatbots present opportunities for individualized behavioral interventions, but evidence comparing personalized versus manual prompt AI-driven approaches is limited.
Objectives
This randomized controlled trial evaluated the effectiveness of a personalized exercise and dietary prompt generator integrated with ChatGPT versus structured manual ChatGPT guidance for weight management.
Methods
Adults aged 18-65 years with BMI 27.5-34.9 kg/m2 (n=160) from Greater Kuala Lumpur were randomized to NExGEN personalized prompt system with ChatGPT (NEX; n=81) or structured manual ChatGPT control (CON; n=79). The NExGEN system generated individualized prompts based on 111 assessment variables including demographics, health status, and preferences. CON participants received structured manual ChatGPT prompts. Assessments occurred at baseline, 12 weeks, and 24 weeks. Primary outcome was body weight measured using bioelectrical impedance analysis. Secondary outcomes included body composition, dietary intake, physical activity, and cardiometabolic markers. Linear mixed models analyzed intervention effects.
Results
The NEX group achieved significantly greater weight loss than CON at 12 weeks (6.6 kg vs 3.0 kg, P<0.001) and 24 weeks (5.5 kg vs 1.7 kg, P<0.001). Fat mass decreased significantly in NEX participants (3.7 kg at 12 weeks, P<0.001) while preserving fat-free mass.
Energy density, fat intake, and physical activity improved significantly in the NEX group. Cardiometabolic variables showed minimal between-group differences.
Conclusions
The personalized AI-driven intervention produced superior weight loss and body composition improvements compared with structured manual prompt guidance. Limited cardiometabolic improvements reflected the metabolically healthy study population at baseline.
Competing Interest Statement
The authors have declared no competing interest.
Clinical Trial
UMIN000053570
Funding Statement
Pragraph Digital Resources partly funded this study but had no role in study design, data collection, analysis, interpretation of results, or preparation of this manuscript.
Author Declarations
I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.
Yes
The details of the IRB/oversight body that provided approval or exemption for the research described are given below:
Universiti Teknologi MARA Institutional Review Board
I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.
Yes
I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).
Yes
I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.
Yes
Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.
My notes (saved in your browser only)
Ask this paper
Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works
Citation neighborhood (no data yet)
We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.
Source provenance
- europepmc
- last seen: 2026-05-20T01:45:00.602351+00:00