ObjectivesThe diversity of food preferences and the need for personalized care can be challenging for renal dietitians. We explored ChatGPT-4 to support nutritional advice given to dialysis patients. DesignIn this simulation study, we tasked ChatGPT-4 with generating a personalized daily meal plan, including nutritional information. SettingThe study used virtual “patients” generated through Monte Carlo simulation. SubjectsData from a randomly selected virtual patient were presented to ChatGPT. InterventionWe provided to ChatGPT patient demographics, food preferences, laboratory data, clinical characteristics, and available budget, to generate a one-day sample menu with recipes and nutritional analyses. The generated content was rated by a renal dietitian and compared with a USDA-approved nutrient analysis software. ChatGPT also analyzed nutrition information of two recipes published online. We also requested a translation of the output into Spanish, Mandarin, Hungarian, German, and Dutch. Main outcome measureThe outcome measures were the accuracy of ChatGPT's nutritional analysis, the quality of recipe and cooking instructions on a five-point Likert scale, and a quantitative nutritional analysis. ResultsChatGPT generated a daily menu with five recipes. The renal dietitian rated the recipes at 3 (3,3) [median (Q1, Q3)], the cooking instructions at 5 (5,5), and the nutritional analysis at 2 (2,2) on the five-point Likert scale. ChatGPT’s nutritional analysis underestimated calories by 36% (95% CI: 44-88%), protein by 28% (25-167%), fat 48% (29-81%), phosphorus 54% (15-102%), potassium 49% (40-68%), and sodium 53% (14-139%). The nutritional analysis of online available recipes differed only by 0 to 35%. The translations were rated as reliable by native speakers (4 on the five-point Likert scale). ConclusionWhile ChatGPT-4 shows promise in providing personalized nutritional guidance for diverse dialysis patients, improvements are necessary. This study highlights the importance of thorough qualitative and quantitative evaluation of AI-generated content, especially regarding medical use cases.
Read full abstract