Personalized AI Prompt Generator and ChatGPT for Weight Loss: Randomized Controlled Trial in Adults with Overweight and Obesity

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.

Ähnliche Arbeiten