Jul 2026· Nutrition and Health· pp.
2601060261469016
· 0 citations· 30 references
Medicine
TL;DR
MyNetDiary, Fitatu, and HealthifyMe provided the broadest range of functionalities, while only five apps incorporated AI-based features, while only five apps incorporated AI-based features.
Abstract
Background: Mobile health (mHealth) applications are increasingly used for dietary assessment and self-monitoring, yet their validity and comprehensiveness remain uncertain. Aim: This study aimed to evaluate the quality, features, and nutritional accuracy of popular nutrition-related mobile applications available in Türkiye by comparing their outputs with standardized 3-day food records (3D-FRs). Methods: A total of 807 apps were identified in the App Store in Türkiye using the search terms 'diet' and 'food'. Seventeen applications meeting the inclusion criteria were systematically evaluated. App quality and functionality were evaluated using the Mobile Application Rating Scale (MARS). Features were categorized into dietary, tracking, insights, technical, educational, social, and artificial intelligence (AI) domains. Energy and macronutrient estimates from the apps were compared with 3D-FRs to determine validity. Summary: MyNetDiary, Fitatu, and HealthifyMe provided the broadest range of functionalities, while only five apps incorporated AI-based features. The mean MARS score for the 17 apps was 3.61/5, with the highest average in the 'functionality' domain (4.03) and the lowest in 'engagement' (3.27). Compared with 3D-FRs, 10 of the 13 apps overestimated energy intake (+327 kcal), 8 overestimated carbohydrate (+33 g), 12 overestimated protein (+23 g), and 12 overestimated fat (+19 g). The greatest discrepancies were observed in Cronometer, Diyet 7/24, Fitbit, Lifesum, and HealthifyMe, whereas MyNetDiary and FatSecret yielded estimates closest to reference records. Despite strong performance in usability and tracking features, most apps showed systematic overestimation with notable variability (≈+327 kcal; +19-33 g among overestimating apps), although findings are limited by the use of standardized menus.
This research describes the development of a tailored dietary feedback function within Intake24-NZ and its pilot testing with NZ registered nutrition professionals to identify improvements in accuracy, cultural safety and relevance for Māori and other ethnic groups, and appropriateness for public use.
Lucy Pakenham, B. Follong, C. N. Mhurchu et al.· Proceedings of the Nutrition...· 0 citations
Adequate dietary intake is essential for positive clinical outcomes of hospitalized patients, yet monitoring food intake is labor-intensive and often subjective. AI-based food recognition could automate monitoring and assessment, but evidence in real-world hospital settings is limited. This study evaluated an AI-powered food recognition system, FlavoriaFlex, to assess its detection performance, deployment feasibility, and acceptability among dietitians. Previously validated in restaurant (F1 0.75, weight MAE 23.6 g, energy MAE 235 kcal), the system was deployed in a hospital ward for six days. A total of 133 meals were recorded; 102 had paired leftover images (235 total images). Manual annotation of 483 food segments provided ground truth for evaluating food recognition and menu mapping. Semi-structured interviews with dietitians assessed usability, perceived benefits, and clinical value. FlavoriaFlex enabled automatic estimation of item- and meal-level consumption, including weights and energy- and macronutrient contents. Overall food recognition accuracy was 94% (F1 0.76), remaining high for served meals (96.5%, F1 0.85) and robust for visually complex leftovers (89.5%, F1 0.71). Unknown/non-food segments were minimal (2.4% of leftovers; 0.27% of weight). A web dashboard delivered real-time visualizations, including energy and nutrient intake. Dietitians reported reduced cognitive burden, more objective assessment, and improved observability into patient dietary intake, while emphasizing the need for further validation and integration for clinical use. These findings demonstrate that FlavoriaFlex could be integrated into hospital workflows to provide accurate, clinically meaningful intake estimates, with AI-assisted food recognition offering an efficient, reliable approach to improving nutritional monitoring at scale.
Rehan Khalil, Sanna Koskimäki, Hanna Lähde et al.· AHFE International· 0 citations
Standardized dietary assessment tools are essential for evaluating population diets, eating patterns, and their relationships with health. Although digital dietary assessment tools can support more standardized and efficient dietary data collection, they require appropriate cultural adaptation to be applicable in different populations. In the United Arab Emirates (UAE), the lack of a culturally appropriate digital 24-h dietary recall tool limits standardized dietary assessment for nutrition research and population surveys.
To develop a culturally adapted digital 24-h dietary recall application for the UAE population’s eating practices.
Abu Dhabi Food Intake24 (ADINTAKE24) is a tablet-optimized, Android-based application. It collects survey questionnaires and 24-h dietary recall data, calculates nutrient intake, and compares the results with the recommendations. The ADINTAKE24 uses the multiple-pass method that integrates food composition data from the United States Department of Agriculture (USDA), regional, and local sources. UAE-specific food photographs aid in estimating food portion sizes. The application is available in Arabic and English and includes a web-based administrative interface. The system was iteratively developed and tested under field conditions during a large community-based nutrition survey. A pilot survey with families informed system refinement, followed by usability assessment among 35 trained interviewers using the System Usability Scale (SUS).
After initial development, the tool was piloted with 98 participants from 39 households using an interviewer-administered approach. Challenges identified during the pilot study included problems with saving and searching for food items in the food composition databases on the server during field data collection. Refinements were made based on the tool’s feedback to improve its functionality. The mean System Usability Scale (SUS) score was 69.9 (95% CI: 66.0–73.9; SD = 11.6).
Abu Dhabi Food Intake24 addresses a key gap in digital dietary assessment in the UAE. Further usability evaluation of the finalized application and validation for self-administered use are needed before wider implementation.
Habiba I. Ali, L. Akkad, Minat Allah T. Al Hassan et al.· Frontiers in Nutrition· 0 citations
OBJECTIVE
This study aimed to evaluate the validity and reliability of the Turkish version of the Short Questionnaire for the Evaluation of Adherence to the Mediterranean Diet and Nutritional Sustainability (MedQ-Sus), which excludes alcohol consumption and simultaneously assesses adherence to the Mediterranean diet and a sustainable diet, in adults.
METHODS
The study included 138 adults, of whom 39.9% were male and 60.1% were female, with a mean age of 34.3 ± 12.7 years. The MedQ-Sus is a brief questionnaire that generates a Mediterranean Diet score and a Sustainable Diet score from the same eight food-group consumption data using different scoring criteria. Dietary intake was assessed using 3-day food records. Validity was evaluated by comparing the MedQ-Sus scores with corresponding food-group and nutrient intakes derived from the food records and by examining construct validity using a modified alternate Mediterranean Diet score (aMED) and the Planetary Health Diet Index (PHDI). Associations and agreement were assessed using Spearman correlation coefficients, Bland-Altman analysis, and intraclass correlation coefficients (ICCs) based on absolute agreement, as appropriate. Test-retest reliability was evaluated in 71 randomly selected participants 4 weeks after the initial administration.
RESULTS
Statistically significant and positive correlations were found between the consumption levels of all food groups associated with the Mediterranean Diet score components. The Sustainable Diet score showed positive correlations with all food groups except legumes and fresh fruits (p < 0.05). The strongest relationship for both the Mediterranean Diet score (r = 0.490) and the Sustainable Diet score (r = 0.488) was observed in the consumption of fish and fish products (p < 0.001). Bland-Altman analysis indicated an acceptable level of agreement between the MedQ-Sus scores and the corresponding estimates derived from the food records. As adherence levels measured by the MedQ-Sus increased, intakes of fish, olive oil, dietary fibre, magnesium, zinc, monounsaturated fatty acids, and omega-3 fatty acids increased, whereas polyunsaturated fatty acid intake decreased. In the test-retest analysis, strong positive correlations were observed for the Mediterranean Diet score (r = 0.782) and the Sustainable Diet score (r = 0.813) (both p < 0.001).
CONCLUSION
The MedQ-Sus demonstrated good validity and reliability as a practical screening tool for simultaneously assessing adherence to the Mediterranean diet and adherence to a sustainable diet among the adults included in this study, while its exclusion of alcohol consumption may support its use across different adult population groups.
N. Rakıcıoğlu, Rüveyda Esra Özkalaycı, Canan Altınsoy· Journal of human nutrition a...· 0 citations
Abstract In the context of the rapidly evolving modern food environment, there is a need for dietary assessment tools to accurately assess current food intake. The objective of this research was to develop and validate a new food frequency questionnaire (FFQ). A 265 item web-based, self-administered FFQ (PREDICT-FFQ-v1) was developed using information from two FFQs and US and UK cohort level data. Over a 1-month period, 68 participants completed the PREDICT-FFQ-v1 and six 24-h recalls (reference tool; Intake24). Relative validity was assessed using Bland–Altman plots, cross-classification food group analysis, and Spearman’s rank correlation for food groups and nutrients. From the Bland–Altman plots, the median bias between the PREDICT-FFQ-v1 and Intake24 were energy (414 kcal (95%CI 289 to 609) (1734 kj (95% CI 1208 to 2549)), carbohydrate (2.3 %EI, 95%CI 0.08 to 3.68), fat (2.5 %EI, 95%CI 0.23 to 3.52), protein (−1.14 %EI, 95% CI −1.64 to −0.23), and fibre (1.86 g/1000 kcal, 95% CI 1.05 to 2.65). Cross-classification by quartiles of diet quality (plant-based diet index) categorised >76% of participants into the same or adjacent quartiles. Correlation coefficients for food groups assessed using both tools ranged from 0.38 (legumes) to 0.78 (meat), and for energy-adjusted nutrients ranged from 0.28 (total fat) to 0.82 (alcohol). The PREDICT-FFQ-v1 captures intakes of foods that are commonly consumed in modern diets, with greater resolution at the food level than previous tools. The PREDICT-FFQ-v1 has acceptable relative validity in comparison to 24-h dietary recall and provides a valuable alternative for assessing dietary intake in nutritional epidemiology.
K. Bermingham, I. Linenberg, L. Francis et al.· Journal of Nutritional Scien...· 0 citations
Background Short-form video platforms are increasingly used as sources of health information. However, the accuracy and trustworthiness of cardiovascular disease (CVD)-related dietary guidance remains unclear. This study aimed to evaluate the quality, reliability, and content characteristics of CVD-related dietary guidance videos on Douyin, the Chinese version of TikTok. Methods A cross-sectional study was conducted on April 7, 2026, using Douyin as the data source. A total of 98 videos directly related to CVD dietary guidance were included after screening. Baseline characteristics, uploader types, and user engagement metrics were extracted. Video quality and reliability were independently assessed using the Global Quality Score (GQS), the Journal of the American Medical Association (JAMA) benchmark criteria, and the modified DISCERN (mDISCERN) instrument. Results Among the 98 included videos, 59.0% were uploaded by professional individuals and 11.2% by professional institutions. Fruits and vegetables (98.0%) and grains and tubers (87.0%) were the most frequently covered dietary categories, whereas oil and salt restriction was less frequently addressed (47.0%). Videos uploaded by professional institutions and medical professionals achieved higher GQS, mDISCERN, and JAMA scores than those from nonprofessional creators (all P < 0.001). Video quality showed weak positive correlations with engagement metrics, including followers and likes (Spearman r = 0.24–0.31, all P < 0.05). GQS, mDISCERN, and JAMA scores were positively correlated (Spearman r = 0.35–0.40, all P < 0.001). Conclusion Douyin videos provide accessible dietary guidance for CVD, but overall quality and comprehensiveness remain suboptimal. Professional involvement improves reliability and evidence-based content. Regulatory oversight, standardized quality criteria, and targeted education for content creators are needed to ensure accurate dietary information dissemination.
Rui-Xue Song, Mingjie Wang, Shuzhen Yu et al.· Frontiers in Cardiovascular...· 0 citations
