{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T22:46:41Z","timestamp":1776379601222,"version":"3.51.2"},"reference-count":48,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T00:00:00Z","timestamp":1773446400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2306690"],"award-info":[{"award-number":["2306690"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000062","name":"National Institute of Diabetes and Digestive and Kidney Diseases","doi-asserted-by":"publisher","award":["R01DK113189"],"award-info":[{"award-number":["R01DK113189"]}],"id":[{"id":"10.13039\/100000062","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000092","name":"National Library of Medicine","doi-asserted-by":"publisher","award":["T15LM007079"],"award-info":[{"award-number":["T15LM007079"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003086","name":"Basque Government","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003086","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study examined the use of machine learning (ML) and domain-specific enrichment in patient-generated health data, in the form of free-text meal logs, to classify meals on alignment with different nutritional goals.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>We used a dataset of over 3000 meal records collected by 114 individuals from a diverse, low-income community in a major US city using a mobile app. Registered dietitians (RDs) provided expert judgment for meal-goal alignment, used as the \u201cgold-standard\u201d for evaluation. Using text embeddings (TF-IDF and BERT) and domain-specific enrichment information (ontologies, ingredient parsers, and macronutrient contents) as inputs, we evaluated the performance of logistic regression and multilayer perceptron classifiers using accuracy, precision, recall, and F1 score against the gold standard and the individual\u2019s self-assessment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>On average, individuals who logged meals achieved 0.576 accuracy of meal-goal alignment self-assessments. Even without enrichment, ML outperformed individual\u2019s self-assessments, with accuracies within 0.726-0.841 for different goals. The best-performing combination of ML classifier with enrichment achieved even higher accuracies (0.814-0.902). In general, ML classifiers with enrichment of parsed ingredients, food entities, and macronutrients information performed well across multiple nutritional goals, but there was variability in the impact of enrichment and classification algorithm on accuracy of classification for different nutritional goals.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>ML can utilize unstructured free-text meal logs and reliably classify whether meals align with specific nutritional goals, exceeding individuals\u2019 self-assessments, especially when incorporating nutrition domain knowledge. Our findings highlight the potential of ML analysis of patient-generated health data to support patient-centered nutrition guidance in precision healthcare.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamia\/ocaf200","type":"journal-article","created":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:51:54Z","timestamp":1763470314000},"page":"836-846","source":"Crossref","is-referenced-by-count":0,"title":["Exploring approaches to computational representation and classification of user-generated meal logs"],"prefix":"10.1093","volume":"33","author":[{"given":"Guanlan","family":"Hu","sequence":"first","affiliation":[{"name":"Department of Biomedical Informatics, Columbia University Irving Medical Center , New York, NY, 10032,","place":["United States"]},{"name":"The Data Science Institute, Columbia University , New York, NY, 10032,","place":["United States"]}]},{"given":"Adit","family":"Anand","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Columbia University Irving Medical Center , New York, NY, 10032,","place":["United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4510-4896","authenticated-orcid":false,"given":"Pooja M","family":"Desai","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Columbia University Irving Medical Center , New York, NY, 10032,","place":["United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3656-0037","authenticated-orcid":false,"given":"I\u00f1igo","family":"Urteaga","sequence":"additional","affiliation":[{"name":"BCAM\u2014Basque Center for Applied Mathematics & IKERBASQUE\u2014Basque Foundation for Science , Bilbao,","place":["Spain"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5203-274X","authenticated-orcid":false,"given":"Lena","family":"Mamykina","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Columbia University Irving Medical Center , New York, NY, 10032,","place":["United States"]},{"name":"The Data Science Institute, Columbia University , New York, NY, 10032,","place":["United States"]}]}],"member":"286","published-online":{"date-parts":[[2026,3,14]]},"reference":[{"key":"2026041617415900600_ocaf200-B1","doi-asserted-by":"publisher","first-page":"182","DOI":"10.3322\/caac.21608","article-title":"Innovations in research and clinical care using patient-generated health data","volume":"70","author":"Jim","year":"2020","journal-title":"CA Cancer J Clin"},{"key":"2026041617415900600_ocaf200-B2","doi-asserted-by":"crossref","first-page":"101153","DOI":"10.1016\/j.imu.2022.101153","article-title":"Patient generated health data and electronic health record integration, governance and socio-technical issues: a narrative review","volume":"37","author":"Kawu","year":"2023","journal-title":"Inform Med Unlocked"},{"key":"2026041617415900600_ocaf200-B3","doi-asserted-by":"crossref","first-page":"952","DOI":"10.1007\/s43441-023-00505-5","article-title":"Integrating patient-generated health data throughout the total product life cycle of medical devices","volume":"57","author":"Webber","year":"2023","journal-title":"Ther Innov Regul Sci"},{"key":"2026041617415900600_ocaf200-B4","author":"FDA_Workshop"},{"key":"2026041617415900600_ocaf200-B5","first-page":"101103","article-title":"Patient generated health data: benefits and challenges","volume":"51","author":"Omoloja","year":"2021","journal-title":"Curr Probl Pediatr Adolesc Health Care"},{"key":"2026041617415900600_ocaf200-B6","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/s11606-023-08461-4","article-title":"Unleashing the potential for patient-generated health data (PGHD)","volume":"39","author":"Nazi","year":"2024","journal-title":"J Gen Intern Med"},{"key":"2026041617415900600_ocaf200-B7","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1093\/jamiaopen\/ooz036","article-title":"Patient-generated health data management and quality challenges in remote patient monitoring","volume":"2","author":"Abdolkhani","year":"2019","journal-title":"JAMIA Open"},{"key":"2026041617415900600_ocaf200-B8","doi-asserted-by":"crossref","first-page":"2573","DOI":"10.3390\/nu16152573","article-title":"Evaluating the quality and comparative validity of manual food logging and artificial intelligence-enabled food image recognition in apps for nutrition care","volume":"16","author":"Li","year":"2024","journal-title":"Nutrients"},{"key":"2026041617415900600_ocaf200-B9","doi-asserted-by":"crossref","first-page":"1366","DOI":"10.1093\/jamia\/ocy054","article-title":"A visual analytics approach for pattern-recognition in patient-generated data","volume":"25","author":"Feller","year":"2018","journal-title":"J Am Med Inform Assoc"},{"key":"2026041617415900600_ocaf200-B10","doi-asserted-by":"crossref","first-page":"526","DOI":"10.1093\/jamia\/ocv187","article-title":"Data-driven health management: reasoning about personally generated data in diabetes with information technologies","volume":"23","author":"Mamykina","year":"2016","journal-title":"J Am Med Inform Assoc"},{"key":"2026041617415900600_ocaf200-B11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/ajcn\/nqx066","article-title":"Dietary assessment in the digital age: the ongoing quest for better methods","volume":"107","author":"McCullough","year":"2018","journal-title":"Am J Clin Nutr"},{"key":"2026041617415900600_ocaf200-B12","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1038\/s41538-018-0032-6","article-title":"FoodOn: a harmonized food ontology to increase global food traceability, quality control and data integration","volume":"2","author":"Dooley","year":"2018","journal-title":"NPJ Sci Food"},{"key":"2026041617415900600_ocaf200-B13","year":"2024"},{"key":"2026041617415900600_ocaf200-B14","doi-asserted-by":"crossref","first-page":"e3348","DOI":"10.1002\/dmrr.3348","article-title":"Improving blood glucose level predictability using machine learning","volume":"36","author":"Marcus","year":"2020","journal-title":"Diabetes Metab Res Rev"},{"key":"2026041617415900600_ocaf200-B15","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1016\/j.ajcnut.2022.11.022","article-title":"Natural language processing and machine learning approaches for food categorization and nutrition quality prediction compared with traditional methods","volume":"117","author":"Hu","year":"2023","journal-title":"Am J Clin Nutr"},{"key":"2026041617415900600_ocaf200-B16","doi-asserted-by":"crossref","first-page":"2312","DOI":"10.1038\/s41467-023-37457-1","article-title":"Machine learning prediction of the degree of food processing","volume":"14","author":"Menichetti","year":"2023","journal-title":"Nat Commun"},{"key":"2026041617415900600_ocaf200-B17","doi-asserted-by":"crossref","first-page":"4167","DOI":"10.3390\/nu15194167","article-title":"Accelerating the classification of NOVA food processing levels using a fine-tuned language model: a multi-country study","volume":"15","author":"Hu","year":"2023","journal-title":"Nutrients"},{"key":"2026041617415900600_ocaf200-B18","doi-asserted-by":"crossref","first-page":"667","DOI":"10.3390\/foods13050667","article-title":"Development of a machine learning model for classifying cooking recipes according to dietary styles","volume":"13","author":"Yamaguchi","year":"2024","journal-title":"Foods"},{"key":"2026041617415900600_ocaf200-B19","year":"2020"},{"key":"2026041617415900600_ocaf200-B20","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1016\/j.datak.2018.04.004","article-title":"What you use, not what you do: Automatic classification and similarity detection of recipes","volume":"117","author":"Kicherer","year":"2018","journal-title":"Data Knowledge Eng"},{"key":"2026041617415900600_ocaf200-B21","doi-asserted-by":"crossref","first-page":"e0253125","DOI":"10.1371\/journal.pone.0253125","article-title":"Machine learning-based glucose prediction with use of continuous glucose and physical activity monitoring data: The Maastricht Study","volume":"16","author":"van Doorn","year":"2021","journal-title":"PLoS One"},{"key":"2026041617415900600_ocaf200-B22","doi-asserted-by":"crossref","first-page":"e0304389","DOI":"10.1371\/journal.pone.0304389","article-title":"Machine learning prediction of nutritional status among pregnant women in Bangladesh: evidence from Bangladesh demographic and health survey 2017-18","volume":"19","author":"Begum","year":"2024","journal-title":"PLoS ONE"},{"key":"2026041617415900600_ocaf200-B23","doi-asserted-by":"crossref","first-page":"1079","DOI":"10.1016\/j.cell.2015.11.001","article-title":"Personalized nutrition by prediction of glycemic responses","volume":"163","author":"Zeevi","year":"2015","journal-title":"Cell"},{"key":"2026041617415900600_ocaf200-B24","doi-asserted-by":"crossref","first-page":"4364","DOI":"10.3390\/s20164364","article-title":"Machine learning models for classifying physical activity in free-living preschool children","volume":"20","author":"Ahmadi","year":"2020","journal-title":"Sensors"},{"key":"2026041617415900600_ocaf200-B25","doi-asserted-by":"crossref","first-page":"e11030","DOI":"10.2196\/11030","article-title":"Data-driven blood glucose pattern classification and anomalies detection: machine-learning applications in type 1 diabetes","volume":"21","author":"Woldaregay","year":"2019","journal-title":"J Med Internet Res"},{"key":"2026041617415900600_ocaf200-B26","doi-asserted-by":"crossref","first-page":"e1005232","DOI":"10.1371\/journal.pcbi.1005232","article-title":"Personalized glucose forecasting for type 2 diabetes using data assimilation","volume":"13","author":"Albers","year":"2017","journal-title":"PLoS Comput Biol"},{"key":"2026041617415900600_ocaf200-B27","year":"2019"},{"key":"2026041617415900600_ocaf200-B28","doi-asserted-by":"crossref","first-page":"e210","DOI":"10.2196\/jmir.9410","article-title":"Identifying objective physiological markers and modifiable behaviors for self-reported stress and mental health status using wearable sensors and mobile phones: observational study","volume":"20","author":"Sano","year":"2018","journal-title":"J Med Internet Res"},{"key":"2026041617415900600_ocaf200-B29","doi-asserted-by":"crossref","first-page":"4653923","DOI":"10.1155\/2022\/4653923","article-title":"Machine learning for healthcare wearable devices: the big picture","volume":"2022","author":"Sabry","year":"2022","journal-title":"J Healthc Eng"},{"key":"2026041617415900600_ocaf200-B30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3449173","article-title":"Automated vs human health coaching: exploring participant and practitioner experiences","volume":"5","author":"Mitchell","year":"2021","journal-title":"Proc ACM Hum-Comput Interact"},{"key":"2026041617415900600_ocaf200-B31","doi-asserted-by":"crossref","DOI":"10.1093\/cdn\/nzz050.P16-051-19","article-title":"Personal informatics technology for engagement in community health (PI-TECH): mixed methods study of platano, a motivationally tailored app for dietary diabetes management (P16-051-19)","volume":"3","author":"Burgermaster","year":"2019","journal-title":"Curr Dev Nutr."},{"key":"2026041617415900600_ocaf200-B32","author":"Nutrition5k: Towards automatic nutritional understanding of generic food","year":"2021"},{"key":"2026041617415900600_ocaf200-B33","author":"USDA"},{"key":"2026041617415900600_ocaf200-B34","year":"2006"},{"key":"2026041617415900600_ocaf200-B35","author":"Nutritionix","year":"2025"},{"key":"2026041617415900600_ocaf200-B36","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1108\/eb026526","article-title":"K. A statistical interpretation of term specificity and its application in retrieval","volume":"28","author":"Jones","year":"1972","journal-title":"J Document"},{"key":"2026041617415900600_ocaf200-B37","year":"2019"},{"key":"2026041617415900600_ocaf200-B38","doi-asserted-by":"crossref","DOI":"10.1002\/9781118548387","volume-title":"Applied Logistic Regression","author":"Hosmer","year":"2013"},{"key":"2026041617415900600_ocaf200-B39","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep learning in neural networks: an overview","volume":"61","author":"Schmidhuber","year":"2015","journal-title":"Neural Netw"},{"key":"2026041617415900600_ocaf200-B40","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1038\/s41746-020-0292-9","article-title":"Learning endometriosis phenotypes from patient-generated data","volume":"3","author":"Urteaga","year":"2020","journal-title":"NPJ Digit Med"},{"key":"2026041617415900600_ocaf200-B41","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1055\/s-0040-1702214","article-title":"Detecting social and behavioral determinants of health with structured and free-text clinical data","volume":"11","author":"Feller","year":"2020","journal-title":"Appl Clin Inform"},{"key":"2026041617415900600_ocaf200-B42","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1038\/s41746-020-0233-7","article-title":"Methods in predictive techniques for mental health status on social media: a critical review","volume":"3","author":"Chancellor","year":"2020","journal-title":"NPJ Digit Med"},{"key":"2026041617415900600_ocaf200-B43","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.cobeha.2017.07.005","article-title":"Detecting depression and mental illness on social media: an integrative review","volume":"18","author":"Guntuku","year":"2017","journal-title":"Curr Opin Behav Sci"},{"key":"2026041617415900600_ocaf200-B44","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1016\/B978-0-12-802928-2.00001-1","article-title":"Dietary assessment methodology","author":"Thompson","year":"2017","journal-title":"Nutr Prev Treat Dis"},{"key":"2026041617415900600_ocaf200-B45","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1016\/S0022-3182(97)70245-0","article-title":"Misconceptions of fruit and vegetable consumption: differences between objective and subjective estimation of intake","volume":"29","author":"Lechner","year":"1997","journal-title":"J Nutr Educ"},{"key":"2026041617415900600_ocaf200-B46","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1016\/j.amepre.2008.11.012","article-title":"Literacy, numeracy, and portion-size estimation skills","volume":"36","author":"Huizinga","year":"2009","journal-title":"Am J Prev Med"},{"key":"2026041617415900600_ocaf200-B47","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1016\/j.nut.2018.05.003","article-title":"The use of a food logging app in the naturalistic setting fails to provide accurate measurements of nutrients and poses usability challenges","volume":"57","author":"Chen","year":"2019","journal-title":"Nutrition"},{"key":"2026041617415900600_ocaf200-B48","first-page":"1371","article-title":"Pre-trained large language models\u2019 utility for food concept normalization","author":"Anand","year":"2024","journal-title":"AMIA Ann Symp"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/4\/836\/67357772\/ocaf200.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/4\/836\/67357772\/ocaf200.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T21:43:30Z","timestamp":1776375810000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/33\/4\/836\/8524035"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":48,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,3,14]]},"published-print":{"date-parts":[[2026,4,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocaf200","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,4]]},"published":{"date-parts":[[2026,3,14]]}}}