Enhancing Ai-driven personalized exercise and nutrition planning for elderly through prompt refinement and expert consensus / Nur Athirah Rosli ... [et al.].

This study aims to refine the NExGEN Prompt Generator–ChatGPT Framework for personalized exercise and nutrition planning tailored to Malaysia's elderly population using the Fuzzy Delphi Method [1]. Addressing gaps in AI-driven health interventions, the research focuses on enhancing prompt accuracy, scalability, and adaptability to meet elderly-specific health needs effectively. A convenience sample of 18 elderly (>60 yrs old) Malaysians. A purposive sample of 21 experts was recruited to evaluate the NExGEN framework using a custom-designed questionnaire based on personalized nutrition and exercise constructs. The Fuzzy Delphi Method was employed for consensus-building, with responses analyzed using Triangular Fuzzy Numbers and defuzzification techniques to assess expert agreement [2]. Expert feedback, collected through Likert scales and open-ended responses, informed iterative framework improvements.