In recent years, artificial intelligence (AI) tools such as ChatGPT have emerged as accessible and scalable platforms for generating dietary advice. While ChatGPT has demonstrated potential in providing general nutritional guidance, its capacity to create diet plans tailored to different weight categories and physical activity levels remains underexplored, particularly in comparison across popular dietary (ketogenic and intermittent fasting) models. This study aimed to evaluate the nutritional adequacy and variability of diet plans generated by ChatGPT‐4o for weight management. ChatGPT‐4o generated diet plans for 18 individuals (9 males, 9 females) representing overweight, class I, and class II obesity at varying physical activity levels. Fifty‐four menus were created across three dietary models and analyzed for energy, macro‐, and micronutrient content using the BeBiS nutritional analysis software. Diet variability was also assessed through repeated prompts over three different periods. The ketogenic diets produced by AI had significantly higher energy and saturated fat contents than other models ( p < 0.05). Regardless of prompt, AI often produced low‐carbohydrate, high‐fat diets. The menus created by ChatGPT had significantly higher fat, saturated fat, and protein content but lower carbohydrate content compared to the dietitian menus ( p < 0.05). Micronutrient analysis showed frequent inadequacy in calcium, potassium, and vitamin B1. Notably, menu content showed temporal inconsistencies, particularly in intermittent fasting and ketogenic diets. While ChatGPT‐4o shows promise in generating basic dietary models, concerns remain about its nutritional precision, consistency, and safety. The results revealed the necessity of professional supervision in AI‐assisted nutrition planning.
15 July 2023 in Turkish Journal of Gastroenterology
Background: Mediterranean diet, owing to its infla mmati on-mo dulat ory effects, is considered a beneficial dietary regimen for patients with inflammatory bowel disease. Despite promising results in the literature, studies on this subject are still limited. Therefore, the aim of this study was to evaluate adherence to the Mediterranean diet in patients with inflammatory bowel disease and examine its impact on disease activity and quality of life. Methods: A total of 83 patients were included in the study. Mediterranean Diet Adherence Scale was used to evaluate adherence to the Mediterranean diet. Crohn’s Disease Activity Index was used to evaluate disease activity in Crohn’s disease. Disease activity was determined by using the Mayo Clinic score for ulcerative colitis. Quality of Life Scale Short Form-36 was used to evaluate the quality of life of patients. Results: When the median Mediterranean Diet Adherence Scale score was 7 (1-12), only 18 patients (21.7%) showed strong adherence to the Mediterranean diet. Disease activity scores of patients with ulcerative colitis having low adherence to the Mediterranean diet were found to be higher (P < .05). In addition, some quality of life parameters were relatively higher in patients with ulcerative colitis who showed strong adherence to the Mediterranean diet (P < .05). For Crohn’s disease, no significant difference was found in disease activity and quality of life with respect to adherence to the Mediterranean diet (P > .05). Conclusions: Stronger adherence to the Mediterranean diet in patients with ulcerative colitis can help improve quality of life and modulate disease activity. However, further prospective studies are needed to investigate the potential use of the Mediterranean diet in inflammatory bowel disease management.
Background: This randomized controlled study sought to determine the effect of intermittent fasting on anthropometric measurements, fibroblast growth factor (FGF)-21, and autophagy markers, as well as on hepatic steatosis and fibrosis levels in overweight or obese patients with metabolic dysfunction-associated fatty liver disease (MAFLD). Methods: Patients were randomly assigned into two groups: received a dietary treatment involving 22–25 kcal/kg/day of energy for 8 weeks and followed the same dietary intervention and a 16:8 pattern. The extent of hepatic steatosis and fibrosis was determined using transient elastography on a FibroScan® device. The controlled attenuation parameter (CAP) and liver stiffness measurement (LSM), determined by transient elastography, reflect hepatic steatosis and fibrosis, respectively. In duplicate, serum levels of FGF-21, Beclin-1, and ATG-5 were determined using enzyme-linked immunosorbent assay. Results: The study included 48 patients with a mean age of 48.2 ± 1.4 years (27 female and 21 male). Improvements in anthropometric measurement and CAP and LSM levels and a decrease in serum FGF-21 levels were found in both groups (p < 0.05). Changes in the CAP and FGF-21 levels were higher in the energy + time-restricted diet group (p < 0.05). Autophagy-related protein (ATG)-5 levels increased only in the energy + time-restricted diet group [(0.74 (0.46–1.29) ng/mL vs. 0.95 (0.73–1.32) ng/mL, p = 0.03]. Conclusions: Intermittent fasting was potentially practical in the management of MAFLD. In particular, changes in FGF-21 and ATG-5 levels indicate the potential of intermittent fasting to regulate metabolic processes and autophagy. However, methodological limitations should be taken into consideration when interpreting the study results.
Background: We evaluated diet plans generated by ChatGPT for hypertension and dyslipidaemia. Methods: In October 2024, ChatGPT was used to generate meal plans for 24 simulated patients with different cardiovascular health problems. Data were used from men (n=12) and women (n=12), aged 56 yr, with mean heights of 176 cm and 161 cm respectively. Weight categories were based on BMI: normal, overweight, and obese, using weights of 56, 71, and 84 kg for women and 67, 85, and 101 kg for men. Four health conditions were assessed: hypertension stages 1 and 2 (systolic BP 130-139 mm Hg and ≥140 mm Hg; diastolic BP 80-89 mm Hg and ≥90 mm Hg), and elevated LDL levels (≥130 mg/dL and ≥160 mg/dL). Menus were evaluated for adherence to Mediterranean and DASH diets, including recommendations. Results: Adherence to the Mediterranean and DASH diets was low across all groups, with median scores below 9 and 4.5, respectively. Common recommendations included weight loss, physical activity, reduced salt intake, stress management, and omega-3s for both hypertension and LDL reduction. Plant sterols/stanols were suggested only for LDL. No advice was given on smoking or alcohol use. Nutrient content did not differ significantly between hypertension and LDL menus (P>0.05). Conclusion: This pioneering study found that AI-generated dietary models had low adherence to DASH and Mediterranean diets, though most recommendations were generally appropriate. Since the prompts only requested basic nutrition plans, future research should use more specific, personalized prompts to better assess AI's role in managing chronic diseases.