You are currently viewing a new version of our website. To view the old version click .

All Articles (35,949)

Image-Based Dietary Energy and Macronutrients Estimation with ChatGPT-5: Cross-Source Evaluation Across Escalating Context Scenarios

  • Marcela Rodríguez-Jiménez,
  • Gustavo Daniel Martín-del-Campo-Becerra and
  • Sandra Sumalla-Cano
  • + 2 authors

Background/Objectives: Estimating energy and macronutrients from food images is clinically relevant yet challenging, and rigorous evaluation requires transparent accuracy metrics with uncertainty and clear acknowledgement of reference data limitations across heterogeneous sources. This study assessed ChatGPT-5, a general-purpose vision-language model, across four scenarios differing in the amount and type of contextual information provided, using a composite dataset to quantify accuracy for calories and macronutrients. Methods: A total of 195 dishes were evaluated, sourced from Allrecipes.com, the SNAPMe dataset, and Home-prepared, weighed meals. Each dish was evaluated under Case 1 (image only), Case 2 (image plus standardized non-visual descriptors), Case 3 (image plus ingredient lists with amounts), and Case 4 (replicates Case 3 but excluding the image). The primary endpoint was kcal Mean Absolute Error (MAE); secondary endpoints included Median Absolute Error (MedAE) and Root Mean Square Error (RMSE) for kcal and macronutrients (protein, carbohydrates, and lipids), all reported with 95% Confidence Intervals (CIs) via dish-level bootstrap resampling and accompanied by absolute differences (Δ) between scenarios. Inference settings were standardized to support reproducibility and variance estimation. Source stratified analyses and quartile summaries were conducted to examine heterogeneity by curation level and nutrient ranges, with additional robustness checks for error complexity relationships. Results and Discussion: Accuracy improved from Case 1 to Case 2 and further in Case 3 for energy and all macronutrients when summarized by MAE, MedAE, and RMSE with 95% CIs, with absolute reductions (Δ) indicating material gains as contextual information increased. In contrast to Case 3, estimation accuracy declined in Case 4, underscoring the contribution of visual cues. Gains were largest in the Home-prepared dietitian-weighed subset and smaller yet consistent for Allrecipes.com and SNAPMe, reflecting differences in reference curation and measurement fidelity across sources. Scenario-level trends were concordant across sources, and stratified and quartile analyses showed coherent patterns of decreasing absolute errors with the provision of structured non-visual information and detailed ingredient data. Conclusions: ChatGPT-5 can deliver practically useful calorie and macronutrient estimates from food images, particularly when augmented with standardized nonvisual descriptors and detailed ingredients, as evidenced by reductions in MAE, MedAE, and RMSE with 95% CIs across scenarios. The decline in accuracy observed when the image was omitted, despite providing detailed ingredient information, indicates that visual cues contribute meaningfully to estimation performance and that improvements are not solely attributable to arithmetic from ingredient lists. Finally, to promote generalizability, it is recommended that future studies include repeated evaluations across diverse datasets, ensure public availability of prompts and outputs, and incorporate systematic comparisons with non-artificial-intelligence baselines.

19 November 2025

Scatter plots of estimated vs. reference values for calories and macronutrients by data source.

Background/Objectives: Skeletal muscle–derived myokines have emerged as pivotal mediators of the muscle–brain axis, linking peripheral metabolic regulation with central nervous system function. These molecules may influence skeletal muscle maintenance, neuroplasticity, neuroinflammation, and cognitive performance, and their dysregulation is increasingly associated with metabolic and cognitive impairment. In obesity (OB) and type 2 diabetes mellitus (T2DM), dysregulated myokine profiles characterized by reduced levels of irisin, brain-derived neurotrophic factor (BDNF), and cathepsin B (CTSB) have been reported and may contribute to the development of both sarcopenia and cognitive impairment. This review aims to summarize current evidence on myokine alterations in OB and T2DM and to evaluate how exercise- and nutrition-based interventions may modulate the muscle–brain axis to support metabolic and cognitive health. Methods: This narrative review synthesizes experimental, clinical, and translational studies examining (1) alterations in circulating myokines in OB and T2DM, (2) associations between myokines, skeletal muscle function, and neurocognitive outcomes, and (3) the modulatory effects of exercise and specific nutrients on myokine-mediated muscle–brain communication. Results: Available evidence indicates that OB and T2DM are frequently accompanied by reduced circulating levels of beneficial myokines such as irisin, BDNF, and CTSB, which may impair skeletal muscle integrity and contribute to cognitive decline. Restoring favorable myokine signaling through physical activity appears to enhance skeletal muscle maintenance, neuroplasticity, and metabolic homeostasis. Emerging data further suggest that selected nutrients can mimic or potentiate some exercise-induced myokine responses, thereby supporting both muscle and brain function. Collectively, these findings imply that combined exercise and nutrition strategies may exert synergistic or additive effects by reinforcing inter-organ communication along the muscle–brain axis. Conclusions: This review outlines current evidence on myokine alterations observed in OB and T2DM and discusses how exercise- and nutrition-based approaches may modulate the muscle–brain axis to mitigate metabolic dysfunction and preserve cognitive health. Targeting beneficial myokine pathways through tailored lifestyle interventions represents a promising avenue to support both skeletal muscle and neurocognitive function in individuals with metabolic disease.

19 November 2025

Background: Obesity is a risk factor for several non-communicable diseases and premature death. The Western-type diet, rich in calories and diverse in tastes, smells, and textures, promotes the onset and progression of obesity. We compared the effects of two Western-style palatable obesogenic diets—the cafeteria (CAF) diet, which allows for self-selection of calorie-dense food items consumed by humans, and the fast-food diet (FFD)—composed of a fixed combination of cheeseburgers and fries—on the manifestation of obesity-related complications. Methods: 3-month-old female rats consumed either the control (CTRL), FFD, or CAF diet for 12 months. Body weight was monitored weekly. At the end of the experiment, rats underwent metabolic and behavioral testing. Cardiometabolic markers and those characterizing glycoxidative and carbonyl stress, inflammatory status, and tryptophan metabolism were determined. Results: The CAF rats gain most weight (CTRL: +111 ± 40 g; FFD: +211 ± 77 g; CAF: 316 ± 87 g). CAF feeding produced a classical metabolic syndrome–like profile with severe obesity, insulin resistance, dyslipidemia, and liver steatosis, whereas the FFD model led to moderate obesity with preserved insulin sensitivity but elevated blood pressure and hepatic cholesterol accumulation. Thus, the CAF group developed a severe metabolic syndrome-like pathology assessed as continuous metabolic syndrome z-core (CTRL: −2.3 ± 1.0; FFD: −0.4 ± 1.9; CAF: 3.0 ± 2.4). Despite these differences, both diets promoted neuroinflammation and social deficits, likely mediated through gut microbiota–derived metabolites such as 5-HIAA and indoxyl sulfate. Conclusions: In female rats, self-selected CAF diet drives more severe and distinct pattern of metabolic syndrome-like pathology than a fixed FFD.

19 November 2025

Background/Objectives: As high salt intake may increase obstructive sleep apnea (OSA) risk through fluid retention and upper airway narrowing during sleep, we aimed to determine whether dietary salt intake modified the association between menopausal transition and the risk of OSA. Methods: Between 2014 and 2018, we conducted a longitudinal study of 2572 women aged 42–52 years at the Kangbuk Samsung Hospital Total Healthcare Center. The participants were followed up until the end of 2024. OSA risk was evaluated using the STOP-Bang questionnaire, with a body mass index threshold adjusted to ≥30 kg/m2 in accordance with a Korean validation study. Dietary salt intake was categorized into tertiles, with tertile 3 representing the highest salt intake. Generalized estimating equations with time-dependent covariates were used to account for repeated measurements over time. Results: OSA risk increased during menopausal transition. Compared with the pre-menopausal stage, both late transition (β = 0.41, 95% confidence interval [CI] 0.05–0.78) and post-menopause (β = 0.61, 95% CI 0.20–1.02) were significantly associated with an increased risk of OSA, independent of potential confounders. A high salt intake (tertile 3) was also significantly associated with OSA. A significant interaction was observed between menopausal transition and salt intake (p = 0.040), with a stronger association between menopausal transition and OSA during the early transition stage in women with higher salt intake. Conclusions: Menopausal transition and high dietary salt intake appear to act synergistically to increase the risk of OSA in middle-aged women. Our results suggest that implementing targeted screening and reducing dietary salt intake may mitigate the risk of OSA during menopausal transition.

19 November 2025

News & Conferences

Issues

Open for Submission

Editor's Choice

Reprints of Collections

Nutrition and Growth of Preterm Neonates during Hospitalization
Reprint

Nutrition and Growth of Preterm Neonates during Hospitalization

Impact on Childhood Outcomes
Editors: Antonios K. Gounaris, Rozeta Sokou

Get Alerted

Add your email address to receive forthcoming issues of this journal.

XFacebookLinkedIn
Nutrients - ISSN 2072-6643