{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T19:45:59Z","timestamp":1781725559537,"version":"3.54.5"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"vor","delay-in-days":50,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100008949","name":"Uniscientia Stiftung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008949","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The LOOP Zurich"},{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008475","name":"Hartmann M\u00fcller-Stiftung f\u00fcr Medizinische Forschung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008475","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Artificial intelligence (AI) is transforming dietary assessment, yet few tools have been clinically validated against physiological reference methods. This cross-sectional observational validation study conducted under free-living conditions evaluated the validity of SNAQ, an AI-powered image-based dietary assessment app, against doubly labelled water (DLW) in females with obesity. Twenty participants completed a 7-day protocol, including DLW-based measurement of total daily energy expenditure (TDEE) and estimation of total daily energy intake using SNAQ and 24-h dietary recall (24HR). Compared with DLW-derived TDEE (3004\u2009\u00b1\u2009481\u2009kcal\/day), SNAQ underestimated energy intake by 25% (bias \u2212817\u2009kcal\/day; limits of agreement \u22123707 to 2073\u2009kcal\/day), while 24HR underestimated intake by 50%. Individual-level agreement had negligible within-subject reliability (ICC\u2009=\u20090.00). Despite advanced AI architecture, SNAQ showed systematic group-level underestimation and poor individual-level agreement, underscoring the translational gap between algorithmic performance and clinical feasibility and the need for standardised clinical validation before implementation.<\/jats:p>","DOI":"10.1038\/s41746-026-02536-2","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T21:02:41Z","timestamp":1773781361000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Limited validity of an AI-powered app for dietary assessment in females with obesity"],"prefix":"10.1038","volume":"9","author":[{"given":"Michele","family":"Serra","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniela","family":"Alceste","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicole","family":"Jucker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lotta","family":"Haupt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Elben","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samuel","family":"M\u00fcller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul J. M.","family":"Hulshof","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harro A. J.","family":"Meijer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Thalheimer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert E.","family":"Steinert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philipp A.","family":"Gerber","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alan C.","family":"Spector","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Gero","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Bueter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,17]]},"reference":[{"key":"2536_CR1","doi-asserted-by":"publisher","first-page":"e55","DOI":"10.1016\/S2589-7500(19)30027-5","volume":"1","author":"A Ferretti","year":"2019","unstructured":"Ferretti, A., Ronchi, E. & Vayena, E. From principles to practice: benchmarking government guidance on health apps. Lancet Digit. Health 1, e55\u2013e57 (2019).","journal-title":"Lancet Digit. Health"},{"key":"2536_CR2","doi-asserted-by":"crossref","unstructured":"Huckvale, K., Prieto, J. T., Tilney, M., Benghozi, P. J. & Car, J. Unaddressed privacy risks in accredited health and wellness apps: a cross-sectional systematic assessment. BMC Med. 13, (2015).","DOI":"10.1186\/s12916-015-0444-y"},{"key":"2536_CR3","doi-asserted-by":"publisher","first-page":"66","DOI":"10.2471\/BLT.17.197426","volume":"96","author":"E Vayena","year":"2018","unstructured":"Vayena, E., Dzenowagis, J., Brownstein, J. S. & Sheikh, A. Policy implications of big data in the health sector. Bull. World Health Organ. 96, 66\u201368 (2018).","journal-title":"Bull. World Health Organ."},{"key":"2536_CR4","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nbt.3826","volume":"35","author":"Y-FY Chan","year":"2017","unstructured":"Chan, Y.-F. Y. et al. The Asthma Mobile Health Study, a large-scale clinical observational study using ResearchKit. Nat. Biotechnol. 35, 354\u2013362 (2017).","journal-title":"Nat. Biotechnol."},{"key":"2536_CR5","doi-asserted-by":"publisher","first-page":"e344","DOI":"10.1016\/S2589-7500(19)30129-3","volume":"1","author":"A Shcherbina","year":"2019","unstructured":"Shcherbina, A. et al. The effect of digital physical activity interventions on daily step count: a randomised controlled crossover substudy of the MyHeart Counts Cardiovascular Health Study. Lancet Digit. Health 1, e344\u2013e352 (2019).","journal-title":"Lancet Digit. Health"},{"key":"2536_CR6","doi-asserted-by":"publisher","first-page":"e322","DOI":"10.1016\/S2589-7500(19)30154-2","volume":"1","author":"GH Tison","year":"2019","unstructured":"Tison, G. H. & Marcus, G. M. Will the smartphone become a useful tool to promote physical activity? Lancet Digit. Health 1, e322\u2013e323 (2019).","journal-title":"Lancet Digit. Health"},{"key":"2536_CR7","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1038\/s41746-020-0268-9","volume":"3","author":"DM Levine","year":"2020","unstructured":"Levine, D. M. et al. Design and testing of a mobile health application rating tool. NPJ Digit. Med. 3, 74 (2020).","journal-title":"NPJ Digit. Med."},{"key":"2536_CR8","doi-asserted-by":"publisher","first-page":"1155","DOI":"10.1001\/jama.2014.9002","volume":"312","author":"SR Chan","year":"2014","unstructured":"Chan, S. R. & Misra, S. Certification of mobile apps for health care. JAMA 312, 1155\u20131156 (2014).","journal-title":"JAMA"},{"key":"2536_CR9","doi-asserted-by":"publisher","first-page":"90","DOI":"10.3389\/fnut.2020.00090","volume":"7","author":"MN Ravelli","year":"2020","unstructured":"Ravelli, M. N. & Schoeller, D. A. Traditional self-reported dietary instruments are prone to inaccuracies and new approaches are needed. Front. Nutr. 7, 90 (2020).","journal-title":"Front. Nutr."},{"key":"2536_CR10","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1017\/S0007114514003602","volume":"113","author":"L Gemming","year":"2015","unstructured":"Gemming, L. et al. Wearable cameras can reduce dietary under-reporting: doubly labelled water validation of a camera-assisted 24\u2009h recall. Br. J. Nutr. 113, 284\u2013291 (2015).","journal-title":"Br. J. Nutr."},{"key":"2536_CR11","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1038\/s41366-021-00738-0","volume":"45","author":"MN Ravelli","year":"2021","unstructured":"Ravelli, M. N. & Schoeller, D. A. An objective measure of energy intake using the principle of energy balance. Int. J. Obes. 45, 725\u2013732 (2021).","journal-title":"Int. J. Obes."},{"key":"2536_CR12","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.1093\/ije\/dys105","volume":"41","author":"AK Illner","year":"2012","unstructured":"Illner, A. K. et al. Review and evaluation of innovative technologies for measuring diet in nutritional epidemiology. Int. J. Epidemiol. 41, 1187\u20131203 (2012).","journal-title":"Int. J. Epidemiol."},{"key":"2536_CR13","doi-asserted-by":"crossref","unstructured":"Williams, L. T. Advances in assessing dietary intake: lessons from technology and nutritional epidemiology. Nutr. Diet. 78, 117\u2013120 (2021).","DOI":"10.1111\/1747-0080.12669"},{"key":"2536_CR14","doi-asserted-by":"publisher","first-page":"658","DOI":"10.1093\/jn\/nxy009","volume":"148","author":"J Most","year":"2018","unstructured":"Most, J. et al. Food photography is not an accurate measure of energy intake in obese, pregnant women. J. Nutr. 148, 658\u2013663 (2018).","journal-title":"J. Nutr."},{"key":"2536_CR15","doi-asserted-by":"publisher","first-page":"e15294","DOI":"10.2196\/15294","volume":"8","author":"D Herzig","year":"2020","unstructured":"Herzig, D. et al. Volumetric food quantification using computer vision on a depth-sensing smartphone: preclinical study. JMIR Mhealth Uhealth 8, e15294 (2020).","journal-title":"JMIR Mhealth Uhealth"},{"key":"2536_CR16","doi-asserted-by":"publisher","first-page":"1255499","DOI":"10.3389\/fnut.2023.1255499","volume":"10","author":"M Serra","year":"2023","unstructured":"Serra, M. et al. Assessing daily energy intake in adult women: validity of a food-recognition mobile application compared to doubly labelled water. Front. Nutr. 10, 1255499 (2023).","journal-title":"Front. Nutr."},{"key":"2536_CR17","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-10377-8","volume":"12","author":"X Wang","year":"2022","unstructured":"Wang, X., Kong, D., van Dijk, G. & Meijer, H. A. J. First use of triply labelled water analysis for energy expenditure measurements in mice. Sci. Rep. 12, 6351 (2022).","journal-title":"Sci. Rep."},{"key":"2536_CR18","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1016\/S0022-5193(87)80103-0","volume":"126","author":"JR Speakman","year":"1987","unstructured":"Speakman, J. R. Calculation of CO2 production in doubly-labelled water studies. J. Theor. Biol. 126, 101\u2013104 (1987).","journal-title":"J. Theor. Biol."},{"key":"2536_CR19","doi-asserted-by":"publisher","first-page":"E402","DOI":"10.1152\/ajpendo.1991.261.3.E402","volume":"261","author":"E Ravussin","year":"1991","unstructured":"Ravussin, E., Harper, I. T., Rising, R. & Bogardus, C. Energy expenditure by doubly labeled water: validation in lean and obese subjects. Am. J. Physiol. -Endocrinol. Metab. 261, E402\u2013E409 (1991).","journal-title":"Am. J. Physiol. -Endocrinol. Metab."},{"key":"2536_CR20","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/0022-5193(66)90185-8","volume":"12","author":"N Lifson","year":"1966","unstructured":"Lifson, N. & McClintock, R. Theory of use of the turnover rates of body water for measuring energy and material balance. J. Theor. Biol. 12, 46\u201374 (1966).","journal-title":"J. Theor. Biol."},{"key":"2536_CR21","doi-asserted-by":"publisher","first-page":"R496","DOI":"10.1152\/ajpregu.1996.270.3.R496","volume":"270","author":"M Rosenbaum","year":"1996","unstructured":"Rosenbaum, M. et al. A comparative study of different means of assessing long-term energy expenditure in humans. Am. J. Physiol.-Regul. Integr. Comp. Physiol. 270, R496\u2013R504 (1996).","journal-title":"Am. J. Physiol.-Regul. Integr. Comp. Physiol."},{"key":"2536_CR22","doi-asserted-by":"publisher","first-page":"1253","DOI":"10.1093\/ajcn\/nqz156","volume":"110","author":"DS Ludwig","year":"2019","unstructured":"Ludwig, D. S., Ebbeling, C. B., Wong, J. M. W., Wolfe, R. R. & Wong, W. W. Methodological error in measurement of energy expenditure by the doubly labeled water method: much ado about nothing? Am. J. Clin. Nutr. 110, 1253\u20131254 (2019).","journal-title":"Am. J. Clin. Nutr."},{"key":"2536_CR23","doi-asserted-by":"publisher","first-page":"R823","DOI":"10.1152\/ajpregu.1986.250.5.R823","volume":"250","author":"DA Schoeller","year":"1986","unstructured":"Schoeller, D. A. et al. Energy expenditure by doubly labeled water: validation in humans and proposed calculation. Am. J. Physiol.-Regul. Integr. Comp. Physiol. 250, R823\u2013R830 (1986).","journal-title":"Am. J. Physiol.-Regul. Integr. Comp. Physiol."},{"key":"2536_CR24","doi-asserted-by":"publisher","first-page":"1119","DOI":"10.1038\/sj.ijo.0801376","volume":"24","author":"AE Black","year":"2000","unstructured":"Black, A. E. Critical evaluation of energy intake using the Goldberg cut-off for energy intake: basal metabolic rate. A practical guide to its calculation, use and limitations. Int. J. Obes. 24, 1119\u20131130 (2000).","journal-title":"Int. J. Obes."},{"key":"2536_CR25","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.jand.2014.09.015","volume":"115","author":"L Gemming","year":"2015","unstructured":"Gemming, L., Utter, J. & Mhurchu, C. N. Image-assisted dietary assessment: a systematic review of the evidence. J. Acad. Nutr. Diet. 115, 64\u201377 (2015).","journal-title":"J. Acad. Nutr. Diet."},{"key":"2536_CR26","doi-asserted-by":"publisher","first-page":"2430965","DOI":"10.1080\/21642850.2024.2430965","volume":"12","author":"Z van der Heijden","year":"2024","unstructured":"van der Heijden, Z. et al. Digital behavioral dietary interventions to promote a healthy diet among children and adolescents: a scoping review of technologies, design, behavioral theory, and assessed outcomes. Health Psychol. Behav. Med. 12, 2430965 (2024).","journal-title":"Health Psychol. Behav. Med."},{"key":"2536_CR27","doi-asserted-by":"publisher","first-page":"20172","DOI":"10.1038\/s41746-017-0002-4","volume":"1","author":"B Noah","year":"2018","unstructured":"Noah, B. et al. Impact of remote patient monitoring on clinical outcomes: an updated meta-analysis of randomized controlled trials. NPJ Digit. Med. 1, 20172 (2018).","journal-title":"NPJ Digit. Med."},{"key":"2536_CR28","doi-asserted-by":"publisher","first-page":"1065","DOI":"10.1001\/jamainternmed.2021.2626","volume":"181","author":"A Wong","year":"2021","unstructured":"Wong, A. et al. External validation of a widely implemented proprietary sepsis prediction model in hospitalized patients. JAMA Intern. Med. 181, 1065\u20131070 (2021).","journal-title":"JAMA Intern. Med."},{"key":"2536_CR29","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1038\/sj.ijo.0802526","volume":"28","author":"A Bosy-Westphal","year":"2004","unstructured":"Bosy-Westphal, A. et al. Effect of organ and tissue masses on resting energy expenditure in underweight, normal weight and obese adults. Int. J. Obes. 28, 72\u201379 (2004).","journal-title":"Int. J. Obes."},{"key":"2536_CR30","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1080\/21551197.2022.2070320","volume":"41","author":"R Griffith","year":"2022","unstructured":"Griffith, R. et al. Validation of resting energy expenditure equations in older adults with obesity. J. Nutr. Gerontol. Geriatr. 41, 126\u2013139 (2022).","journal-title":"J. Nutr. Gerontol. Geriatr."},{"key":"2536_CR31","doi-asserted-by":"publisher","first-page":"E340","DOI":"10.1017\/S0029665124005780","volume":"83","author":"C Innih","year":"2024","unstructured":"Innih, C. et al. Nutritics GB23 database: an enhancement of the McCance Widdowson\u2019s The Composition of Foods Integrated Dataset (CoFID) database. Proc. Nutr. Soc. 83, E340 (2024).","journal-title":"Proc. Nutr. Soc."},{"key":"2536_CR32","doi-asserted-by":"publisher","first-page":"104070","DOI":"10.1016\/j.jfca.2021.104070","volume":"102","author":"M Silva","year":"2021","unstructured":"Silva, M. et al. Exploring two food composition databases to estimate nutritional components of whole meals. J. Food Compos. Anal. 102, 104070 (2021).","journal-title":"J. Food Compos. Anal."},{"key":"2536_CR33","unstructured":"Speakman, J. R. et al. A standard calculation methodology for human doubly labeled water studies. Cell Rep. Med. 2, (2021)."},{"key":"2536_CR34","first-page":"1","volume":"109","author":"V De","year":"1949","unstructured":"De, V. & Weir, J. B. New methods for calculating metabolic rate with special reference to protein metabolism. J. Physiol. 109, 1 (1949).","journal-title":"J. Physiol."},{"key":"2536_CR35","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1093\/ajcn\/51.2.241","volume":"51","author":"MD Mifflin","year":"1990","unstructured":"Mifflin, M. D. et al. A new predictive equation for resting energy expenditure in healthy individuals. Am. J. Clin. Nutr. 51, 241\u2013247 (1990).","journal-title":"Am. J. Clin. Nutr."},{"key":"2536_CR36","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.1345\/aph.19381","volume":"34","author":"MP Pai","year":"2000","unstructured":"Pai, M. P. & Paloucek, F. P. The origin of the \u201cideal\u201d body weight equations. Ann. Pharmacother. 34, 1066\u20131069 (2000).","journal-title":"Ann. Pharmacother."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02536-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02536-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02536-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T23:20:28Z","timestamp":1778023228000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02536-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,17]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2536"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02536-2","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7946611\/v1","asserted-by":"object"}]},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,17]]},"assertion":[{"value":"25 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests. SNAQ AG developed the customised version of the app, SNAQ Study, in exchange for financial compensation. R.E.S. is employed by DSM Nutritional Products. A.C.S. is a member of the scientific advisory board of Gila Therapeutics.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"357"}}