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

Artículo Materias > Ingeniería Universidad Europea del Atlántico > Investigación > Producción Científica
Universidad Internacional Iberoamericana México > Investigación > Artículos y libros
Universidad Internacional Iberoamericana Puerto Rico > Investigación > Producción Científica
Universidad Internacional do Cuanza > Investigación > Producción Científica
Universidad de La Romana > Investigación > Producción Científica Abierto Inglés 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. metadata Rodríguez- Jiménez, Marcela; Martín-del-Campo-Becerra, Gustavo Daniel; Sumalla Cano, Sandra; Crespo-Álvarez, Jorge y Elío Pascual, Iñaki mail SIN ESPECIFICAR, SIN ESPECIFICAR, sandra.sumalla@uneatlantico.es, jorge.crespo@uneatlantico.es, inaki.elio@uneatlantico.es (2025) Image-Based Dietary Energy and Macronutrients Estimation with ChatGPT-5: Cross-Source Evaluation Across Escalating Context Scenarios. Nutrients, 17 (22). p. 3613. ISSN 2072-6643

Texto
nutrients-17-03613.pdf
Available under License Creative Commons Attribution.
Descargar (7MB)

URL Oficial: http://doi.org/10.3390/nu17223613

Resumen

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.

Tipo de Documento:	Artículo
Palabras Clave:	calorie and macronutrient estimation; image-based dietary assessment; validation metrics (MAE, MedAE, RMSE); vision-language models
Clasificación temática:	Materias > Ingeniería
Divisiones:	Universidad Europea del Atlántico > Investigación > Producción Científica Universidad Internacional Iberoamericana México > Investigación > Artículos y libros Universidad Internacional Iberoamericana Puerto Rico > Investigación > Producción Científica Universidad Internacional do Cuanza > Investigación > Producción Científica Universidad de La Romana > Investigación > Producción Científica
Depositado:	03 Dic 2025 23:32
Ultima Modificación:	03 Dic 2025 23:32
URI:	https://repositorio.unini.edu.mx/id/eprint/17880

Acciones (logins necesarios)

Ver Objeto

open

Infrared thermography to assess fatigue, injury risk factors and recovery in soccer: a systematic review of original studies

Background: Recovery after a training session or match is a key factor in injury prevention and sports performance. The purpose of this systematic review was to analyze and consolidate the available scientific evidence from the main databases on the use of infrared thermography in the assessment of fatigue, injury risk factors, and recovery in soccer players.Methods: The literature search was conducted following the PRISMA guidelines and the PICOS model until June 30, 2025, in the main scientific databases (ScienceDirect, EMBASE, Web of Science (WOS), Cochrane Library, SciELO, MEDLINE/PubMed, SPORTDiscus, and Scopus). The risk of bias and methodological quality were assessed using the Cochrane Handbook guidelines and the PEDro scale.”Results: The initial literature search yielded a total of 510 records. After applying the inclusion and exclusion criteria, the final sample consisted of 20 studies, which were of high methodological quality. The results showed the effects of infrared thermography in assessing fatigue, identifying injury risk factors, and monitoring recovery processes in soccer players. The studies also systematically reported the characterization of the population, the assessment methods used, the variables analyzed, the methodological design, the main results, and the effects of the intervention.Conclusions: Infrared thermography shows promise as a valid, reliable, and non-invasive tool for assessing skin temperature, reflecting temperature changes in response to physiological processes. It allows for the analysis of structural or metabolic fatigue and thermal asymmetries. Therefore, thermography could be used to design individualized recovery protocols.

Producción Científica

Yehinson Barajas Ramón mail , Julio Calleja-González mail , José Luaces-Carreño mail , Álvaro Velarde-Sotres mail alvaro.velarde@uneatlantico.es,

Barajas Ramón

open

Association between socioeconomic and health variables and community-acquired pneumonia mortality rates in Chile from 1990 to 2021

Objectives To describe long-term trends in mortality attributed to community-acquired pneumonia (CAP) in Chile from 1990 to 2021, stratified by age group, and to evaluate associations with selected socioeconomic and demographic indicators. Study design Ecological, observational, longitudinal study using national secondary data. Methods CAP mortality rates were analyzed for the total population and by age group. Associations with the Human Development Index (HDI), poverty rate, aging index, and life expectancy at birth were examined using a hierarchical analytical approach. This included Spearman's rank correlation for initial exploration, multivariable linear regression to assess adjusted associations, and Prais–Winsten generalized least squares regression to account for first-order autocorrelation and shared temporal trends. Stationarity was evaluated using augmented Dickey–Fuller tests, with supplementary analyses using first-differenced variables. Missing data were imputed using time-based regression or interpolation, with sensitivity analyses performed. Results CAP mortality declined substantially across all age groups over the study period. Strong bivariate correlations were observed between mortality and all socioeconomic indicators; however, these associations were attenuated after adjustment for confounding and temporal autocorrelation. In multivariable and time-series models, HDI and the aging index remained significantly associated with CAP mortality in children (0–9 years) and older adults (≥65 years), whereas associations in intermediate age groups were not robust after accounting for shared secular trends. Poverty and life expectancy did not demonstrate independent associations in adjusted models. Conclusions CAP mortality in Chile has decreased markedly over the past three decades. Associations with socioeconomic indicators are strongest at the extremes of age and persist after accounting for temporal structure, although the ecological design precludes causal inference. These findings highlight the importance of considering demographic and socioeconomic context in population-level analyses of infectious disease outcomes.

Artículos y libros

Italo Salvador López Muñoz mail italo.lopez@doctorado.unini.edu.mx, Maria Loreto Romero Ladrón de Guevara mail , Christian R. Mejia mail , Shyla Del-Aguila-Arcentales mail , Aldo Alvarez-Risco mail , Neal M. Davies mail , Jaime A. Yáñez mail ,

López Muñoz

open

An Integrated Machine Learning and Genomic Framework for Precise Detection of Gastric Cancer

This study presents a novel integrative approach for the analysis of high-dimensional gene expression data, leveraging the complementary strengths of unsupervised clustering and supervised classification. Using K-means clustering, the dataset is stratified into three distinct clusters, revealing intrinsic biological patterns and relationships. The resulting cluster assignments are subsequently employed as pseudo-labels to train machine learning models, including support vector machines, random forest, and a stacking ensemble classifier. To validate and enhance the robustness of clustering, complementary methodologies such as hierarchical clustering and DBSCAN are employed, with results visualized through PCA-driven dimensionality reduction. The high predictive accuracy achieved by the classifiers underscores the separability and reliability of the identified clusters. Furthermore, feature importance analysis highlighted key genetic determinants within each cluster, offering actionable insights into potential biomarkers and critical genomic features. This framework bridges the gap between exploratory unsupervised learning and predictive supervised modeling, providing a scalable and interpretable methodology for analyzing complex genomic datasets. Its applicability extends to biomarker discovery, patient stratification, and other precision medicine applications, emphasizing its utility in advancing genomic research and clinical practice.

Producción Científica

Eshmal Iman mail , Sohail Jabbar mail , Shabana Ramzan mail , Ali Raza mail , Farwa Raoof mail , Stefanía Carvajal-Altamiranda mail stefania.carvajal@uneatlantico.es, Vivian Lipari mail vivian.lipari@uneatlantico.es, Imran Ashraf mail ,

Iman

open

Efecto de la suplementación con L-leucina, L-arginina y Lcarnitina sobre la composición corporal en hemodiálisis

Introducción: los pacientes con enfermedad renal crónica (ERC) en hemodiálisis presentan una elevada prevalencia de deterioro nutricional, caracterizado por pérdida de masa y función muscular, lo que se asocia con peor pronóstico clínico. La suplementación nutricional oral (SNO) es una estrategia frecuente en esta población; sin embargo, la evidencia comparativa entre distintos suplementos es limitada. Objetivo: evaluar el efecto de SNO con L-arginina, L-leucina o L-carnitina sobre la composición corporal y la fuerza muscular en pacientes con ERC en hemodiálisis. Materiales y métodos: ensayo clínico aleatorizado, abierto y controlado, con tres grupos paralelos, en pacientes adultos con ERC en estadio 5 en hemodiálisis crónica. Se administró SNO durante 90 días. Se evaluaron parámetros antropométricos, de fuerza y bioimpedancia. La ingesta dietética se estimó mediante recordatorio de 24 horas. El análisis longitudinal se realizó mediante modelos mixtos de efectos lineales. Se incluyeron 158 pacientes en el análisis final. Resultados: la ingesta energética y proteica fue insuficiente en más del 80 % de los pacientes. Se observaron mejorías significativas intragrupo en peso corporal, masa muscular y fuerza de prensión manual (p < 0,05), sin diferencias estadísticamente significativas entre los tipos de suplemento (p > 0,05). Se observaron correlaciones positivas moderadas entre masa muscular, fuerza de prensión y ángulo de fase. Conclusión: la SNO se asoció con mejorías en parámetros antropométricos y funcionales en pacientes con ERC en hemodiálisis, independientemente del tipo de suplemento utilizado. La evaluación funcional resulta clave para la detección temprana del deterioro nutricional en esta población.

Artículos y libros

Mónica del Carmen Montenegro Cedeno mail , Mercedes Briones Urbano mail mercedes.briones@uneatlantico.es, Israel Barria mail , Rossana Broce mail , Adilia Gómez mail , Ruth Ávila mail , Mayte Batista mail , Eyleen Montero mail , Victoria Rodríguez mail , Alieth Sáez mail , María Vergara mail , Otilda Mercedes Valderrama Vergara mail ,

Montenegro Cedeno

open

A novel approach for disease and pests detection in potato production system based on deep learning

Vulnerability of potato crops to diseases and pest infestation can affect its quality and lead to significant yield losses. Timely detection of such diseases can help take effective decisions. For this purpose, a deep learning-based object detection framework is designed in this study to identify and classify major potato diseases and pests under real-world field conditions. A total of 2,688 field images were collected from two research farms in Punjab, Pakistan, across multiple growth stages in various seasonal conditions. Excluding 285 symptoms-free images from the earliest collection led to 2,403 images which were annotated into four biotic-stress classes: blight disease (n = 630), leaf spot disease (n = 370), leafroll virus (viral symptom complex; n = 888), and Colorado potato beetle (larvae/adults; n = 515), indicating class imbalance. Several state-of-the-art models were used including YOLOv8 variants (n/s/m), YOLOv7, YOLOv5, and Faster R-CNN, and the results are discussed in relation to recent potato disease classification studies involving cropped leaf images. Stratified splitting (70% training, 20% validation, 10% testing) was applied to preserve class distribution across all subsets. YOLOv8-medium achieve the best performance with mean average precision (mAP)@0.5 of 98% on the held-out test images. Results for stable 5-fold cross-validation show a mean mAP@0.5 of 97.8%, which offers a balance between accuracy and inference time. Model robustness was evaluated using 5-fold cross-validation and repeated training with different random seeds, showing a low variance of ±0.4% mAP. Results demonstrate promising outcomes under the real-world field conditions, while, broader cross-region and cross-season validation is intended for the future.

Producción Científica

Ahmed Abbas mail , Saif Ur Rehman mail , Khalid Mahmood mail , Santos Gracia Villar mail santos.gracia@uneatlantico.es, Luis Alonso Dzul López mail luis.dzul@uneatlantico.es, Aseel Smerat mail , Imran Ashraf mail ,

Abbas

Enlaces de interés

Enlaces de interés

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

Resumen

Acciones (logins necesarios)

TEMÁTICA

ACCESO

IDIOMA

Filtros