Academic Journal
Domain-Dependent Performance of Human Experts and AI Systems in Pediatric Menu Evaluation.
| Τίτλος: | Domain-Dependent Performance of Human Experts and AI Systems in Pediatric Menu Evaluation. |
|---|---|
| Συγγραφείς: | Martin-Hadmaș RM; Department of Community Nutrition and Food Safety, 'George Emil Palade' University of Medicine, Pharmacy, Science and Technology of Târgu Mures, Gheorghe Marinescu 38, 540139 Targu Mures, Romania., Sovea R; Department of Community Nutrition and Food Safety, 'George Emil Palade' University of Medicine, Pharmacy, Science and Technology of Târgu Mures, Gheorghe Marinescu 38, 540139 Targu Mures, Romania., Pol D; Department of Community Nutrition and Food Safety, 'George Emil Palade' University of Medicine, Pharmacy, Science and Technology of Târgu Mures, Gheorghe Marinescu 38, 540139 Targu Mures, Romania., Gavra GM; Center for Advanced Medical and Pharmaceutical Research, George Emil Palade University of Medicine, Pharmacy, Science, and Technology of Targu Mures, 540139 Targu Mures, Romania., Tarcea M; Department of Community Nutrition and Food Safety, 'George Emil Palade' University of Medicine, Pharmacy, Science and Technology of Târgu Mures, Gheorghe Marinescu 38, 540139 Targu Mures, Romania., Neghirlă A; Mures School Medicine Association, 540233 Targu Mures, Romania., Martin ȘA; Center for Advanced Medical and Pharmaceutical Research, George Emil Palade University of Medicine, Pharmacy, Science, and Technology of Targu Mures, 540139 Targu Mures, Romania. |
| Πηγή: | Nutrients [Nutrients] 2026 Sep 21; Vol. 18 (18). Date of Electronic Publication: 2026 Sep 21. |
| Τύπος έκδοσης: | Journal Article; Observational Study |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: MDPI Publishing Country of Publication: Switzerland NLM ID: 101521595 Publication Model: Electronic Cited Medium: Internet ISSN: 2072-6643 (Electronic) Linking ISSN: 20726643 NLM ISO Abbreviation: Nutrients Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: Basel, Switzerland : MDPI Publishing |
| Ιατρικοί όροι (MeSH): | Artificial Intelligence* , Nutrition Assessment* , Menu Planning*, Humans ; Cross-Sectional Studies ; Child ; Female ; Reproducibility of Results ; Energy Intake ; Male ; Pediatrics ; Nutritionists |
| Περίληψη: | Background/objectives: Artificial intelligence (AI) tools are increasingly used for dietary assessment, but their reliability in pediatric nutrition remains uncertain. This study compared AI systems and human evaluators in pediatric menu assessment against expert-defined reference ratings. Methods: This observational cross-sectional study used anonymized dietary and clinical information from three healthy pediatric cases. A multidisciplinary panel of pediatric nutrition specialists established standard evaluations. Assessments were completed by 84 AI evaluations, 116 nutrition specialists, 56 pediatric-focused physicians, and 88 physicians from other specialties. Outcomes included absolute error in total energy estimation, deviations in portion and qualitative ratings, standardized scores, and binary adequacy accuracy. Groups were compared using ANOVA or Kruskal-Wallis tests with post hoc analyses. Results: A total of 344 assessments were included. Energy-estimation error differed between groups (Kruskal-Wallis = 12.85, p = 0.0016), but this analysis was based on a limited and highly unbalanced subset of 77 assessments. AI had the largest mean absolute error (260.3 ± 194.3 kcal), followed by nutrition specialists (148.4 ± 81.5 kcal); physicians with other specialties had the lowest error (60.4 ± 53.3 kcal); these subgroup comparisons should be interpreted cautiously because of the small and unequal numbers of available energy estimates. AI showed greater portion-rating deviation (0.488; 95% CI: 0.38-0.60) than nutrition specialists (0.310; 95% CI: 0.20-0.42; p = 0.0019, q = 0.0059) and pediatric-focused physicians (0.286; 95% CI: 0.16-0.41; p = 0.0181, q = 0.019). Conversely, AI showed the lowest deviations for variety (0.37 ± 0.49) and processing (0.33 ± 0.47), compared with 1.15-1.36 and 1.22-1.57, respectively, among human groups (both p = 0.0001). Conclusions: AI may support structured pediatric menu screening for descriptive qualitative features; however, lower precision for energy and portion assessment supports, under these specific conditions, its use as an adjunct, for qualified nutrition professionals. |
| References: | J Med Internet Res. 2023 May 4;25:e44030. (PMID: 37140973) J Nutr Sci. 2023 Apr 11;12:e43. (PMID: 37123397) J Med Internet Res. 2024 Nov 28;26:e54557. (PMID: 39608003) Front Nutr. 2025 Jan 23;12:1518466. (PMID: 39917741) J Hum Nutr Diet. 2025 Oct;38(5):e70135. (PMID: 41054023) Front Nutr. 2026 Mar 12;13:1765598. (PMID: 41909033) Healthcare (Basel). 2025 Oct 14;13(20):. (PMID: 41154258) Nutrients. 2024 Jun 28;16(13):. (PMID: 38999814) Mhealth. 2026 Feb 27;12:17. (PMID: 42170225) J Med Internet Res. 2024 Nov 15;26:e51432. (PMID: 39546777) Indian J Otolaryngol Head Neck Surg. 2025 May;77(5):2078-2087. (PMID: 40321382) Front Nutr. 2025 Aug 07;12:1635682. (PMID: 40851903) Nutrients. 2025 Jan 05;17(1):. (PMID: 39796624) Nutrients. 2024 Jun 19;16(12):. (PMID: 38931294) Front Public Health. 2025 Aug 20;13:1654482. (PMID: 40910043) Gut Microbes. 2022 Jan-Dec;14(1):2138672. (PMID: 36318623) Nutrients. 2025 Feb 07;17(4):. (PMID: 40004936) Nutrients. 2025 Dec 20;18(1):. (PMID: 41515141) JAMA Pediatr. 2024 Jun 1;178(6):632. (PMID: 38683650) Nutrients. 2024 Aug 05;16(15):. (PMID: 39125452) |
| Contributed Indexing: | Keywords: artificial intelligence; clinical decision support; dietary assessment; energy estimation; large language models; menu evaluation; nutrition professionals; pediatric nutrition |
| Entry Date(s): | Date Created: 20260926 Date Completed: 20260926 Latest Revision: 20260929 |
| Update Code: | 20260929 |
| PubMed Central ID: | PMC13610824 |
| DOI: | 10.3390/nu18183106 |
| PMID: | 42797089 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 2072-6643 |
|---|---|
| DOI: | 10.3390/nu18183106 |