{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T10:14:45Z","timestamp":1776334485673,"version":"3.51.2"},"reference-count":52,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T00:00:00Z","timestamp":1710720000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Cleveland Clinic Center for Quantitative Metabolic Research"},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["1R61NS113258"],"award-info":[{"award-number":["1R61NS113258"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["4R33NS113258"],"award-info":[{"award-number":["4R33NS113258"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objectives<\/jats:title>\n                  <jats:p>Metabolic disease in children is increasing worldwide and predisposes a wide array of chronic comorbid conditions with severe impacts on quality of life. Tools for early detection are needed to promptly intervene to prevent or slow the development of these long-term complications.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>No clinically available tools are currently in widespread use that can predict the onset of metabolic diseases in pediatric patients. Here, we use interpretable deep learning, leveraging longitudinal clinical measurements, demographical data, and diagnosis codes from electronic health record data from a large integrated health system to predict the onset of prediabetes, type 2 diabetes (T2D), and metabolic syndrome in pediatric cohorts.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The cohort included 49\u00a0517 children with overweight or obesity aged 2-18 (54.9% male, 73% Caucasian), with a median follow-up time of 7.5 years and mean body mass index (BMI) percentile of 88.6%. Our model demonstrated area under receiver operating characteristic curve (AUC) accuracies up to 0.87, 0.79, and 0.79 for predicting T2D, metabolic syndrome, and prediabetes, respectively. Whereas most risk calculators use only recently available data, incorporating longitudinal data improved AUCs by 13.04%, 11.48%, and 11.67% for T2D, syndrome, and prediabetes, respectively, versus models using the most recent BMI (P\u2009&amp;lt;\u20092.2 \u00d7 10\u201316).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Discussion<\/jats:title>\n                  <jats:p>Despite most risk calculators using only the most recent data, incorporating longitudinal data improved the model accuracies because utilizing trajectories provides a more comprehensive characterization of the patient\u2019s health history. Our interpretable model indicated that BMI trajectories were consistently identified as one of the most influential features for prediction, highlighting the advantages of incorporating longitudinal data when available.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocae049","type":"journal-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T19:37:39Z","timestamp":1710790659000},"page":"1227-1238","source":"Crossref","is-referenced-by-count":5,"title":["An interpretable predictive deep learning platform for pediatric metabolic diseases"],"prefix":"10.1093","volume":"31","author":[{"given":"Hamed","family":"Javidi","sequence":"first","affiliation":[{"name":"Department of Quantitative Health Sciences, Lerner Research Institute, Cleveland Clinic , Cleveland, OH 44195, United States"},{"name":"Department of Electrical Engineering and Computer Science, Cleveland State University , Cleveland, OH 44115, United States"},{"name":"Center for Quantitative Metabolic Research, Cleveland Clinic , Cleveland, OH 44195, United States"}]},{"given":"Arshiya","family":"Mariam","sequence":"additional","affiliation":[{"name":"Department of Quantitative Health Sciences, Lerner Research Institute, Cleveland Clinic , Cleveland, OH 44195, United States"},{"name":"Center for Quantitative Metabolic Research, Cleveland Clinic , Cleveland, OH 44195, United States"}]},{"given":"Lina","family":"Alkhaled","sequence":"additional","affiliation":[{"name":"Center for Quantitative Metabolic Research, Cleveland Clinic , Cleveland, OH 44195, United States"},{"name":"Endocrinology and Metabolism Institute, Cleveland Clinic , Cleveland, OH 44195, United States"}]},{"given":"Kevin M","family":"Pantalone","sequence":"additional","affiliation":[{"name":"Center for Quantitative Metabolic Research, Cleveland Clinic , Cleveland, OH 44195, United States"},{"name":"Endocrinology and Metabolism Institute, Cleveland Clinic , Cleveland, OH 44195, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0553-3220","authenticated-orcid":false,"given":"Daniel M","family":"Rotroff","sequence":"additional","affiliation":[{"name":"Department of Quantitative Health Sciences, Lerner Research Institute, Cleveland Clinic , Cleveland, OH 44195, United States"},{"name":"Department of Electrical Engineering and Computer Science, Cleveland State University , Cleveland, OH 44115, United States"},{"name":"Center for Quantitative Metabolic Research, Cleveland Clinic , Cleveland, OH 44195, United States"},{"name":"Endocrinology and Metabolism Institute, Cleveland Clinic , Cleveland, OH 44195, United States"}]}],"member":"286","published-online":{"date-parts":[[2024,3,18]]},"reference":[{"issue":"4","key":"2024052019470501200_ocae049-B1","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1007\/s13679-019-00357-x","article-title":"Metabolic syndrome in children and adolescents: diagnostic criteria, therapeutic options and perspectives","volume":"8","author":"Weihe","year":"2019","journal-title":"Curr Obes Rep"},{"issue":"10113","key":"2024052019470501200_ocae049-B2","doi-asserted-by":"crossref","first-page":"2627","DOI":"10.1016\/S0140-6736(17)32129-3","article-title":"Worldwide trends in body-mass index, underweight, overweight, and obesity from 1975 to 2016: a pooled analysis of 2416 population-based measurement studies in 128\u00b79 million children, adolescents, and adults","volume":"390","author":"Bentham","year":"2017","journal-title":"Lancet"},{"issue":"7815","key":"2024052019470501200_ocae049-B3","doi-asserted-by":"crossref","first-page":"d4092","DOI":"10.1136\/bmj.d4092","article-title":"Factors associated with the presence of diabetic ketoacidosis at diagnosis of diabetes in children and young adults: a systematic review","volume":"343","author":"Usher-Smith","year":"2011","journal-title":"BMJ"},{"key":"2024052019470501200_ocae049-B4","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.metabol.2018.12.001","article-title":"Childhood obesity: increased risk for cardiometabolic disease and cancer in adulthood","volume":"92","author":"Weihrauch-Bl\u00fcher","year":"2019","journal-title":"Metabolism"},{"issue":"1","key":"2024052019470501200_ocae049-B5","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1038\/s41390-020-01192-w","article-title":"Pediatric obesity-related non-alcoholic fatty liver disease: waist-to-height ratio best anthropometrical predictor","volume":"90","author":"Umano","year":"2021","journal-title":"Pediatr Res"},{"issue":"6","key":"2024052019470501200_ocae049-B6","doi-asserted-by":"crossref","first-page":"870","DOI":"10.1111\/joim.13547","article-title":"Pediatric obesity-long-term consequences and effect of weight loss","volume":"292","author":"Marcus","year":"2022","journal-title":"J Intern Med"},{"issue":"1","key":"2024052019470501200_ocae049-B7","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1038\/s41366-018-0237-4","article-title":"Do adolescents with extreme obesity differ according to previous treatment seeking behavior? The Youth with Extreme obesity Study (YES) cohort","volume":"43","author":"Lennerz","year":"2018","journal-title":"Int J Obes (Lond)"},{"issue":"5","key":"2024052019470501200_ocae049-B8","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1177\/00034894211028489","article-title":"The relationship between obstructive sleep apnea and pediatric obesity: a nationwide analysis","volume":"131","author":"Bachrach","year":"2022","journal-title":"Ann Otol Rhinol Laryngol"},{"issue":"3","key":"2024052019470501200_ocae049-B9","first-page":"235","article-title":"Type 2 diabetes mellitus in children and adolescents: a relatively new clinical problem within pediatric practice","volume":"9","author":"Temneanu","year":"2016","journal-title":"J Med Life"},{"issue":"8","key":"2024052019470501200_ocae049-B10","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1001\/jama.2021.11165","article-title":"Trends in prevalence of type 1 and type 2 diabetes in children and adolescents in the US, 2001-2017","volume":"326","author":"Lawrence","year":"2021","journal-title":"JAMA"},{"issue":"1175","key":"2024052019470501200_ocae049-B11","doi-asserted-by":"crossref","first-page":"985","DOI":"10.1093\/postmj\/qgad008","article-title":"Prevalence of metabolic syndrome in the United States National Health and Nutrition Examination Survey 2011\u201318","volume":"99","author":"Liang","year":"2023","journal-title":"Postgrad Med J"},{"key":"2024052019470501200_ocae049-B12","author":"National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK)"},{"key":"2024052019470501200_ocae049-B13","author":"Centers for Disease Control and Prevention"},{"key":"2024052019470501200_ocae049-B14","doi-asserted-by":"crossref","first-page":"2042018819863022","DOI":"10.1177\/2042018819863022","article-title":"Precision medicine in adult and pediatric obesity: a clinical perspective","volume":"10","author":"Bomberg","year":"2019","journal-title":"Ther Adv Endocrinol Metab"},{"key":"2024052019470501200_ocae049-B15","first-page":"S6","article-title":"The accumulating data to optimally predict obesity treatment (ADOPT) core measures project: rationale and approach","volume":"26(Suppl 2)","author":"MacLean","year":"2018","journal-title":"Obesity (Silver Spring)"},{"issue":"1","key":"2024052019470501200_ocae049-B16","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1038\/s41746-022-00651-4","article-title":"Identification of robust deep neural network models of longitudinal clinical measurements","volume":"5","author":"Javidi","year":"2022","journal-title":"NPJ Digit Med"},{"issue":"8","key":"2024052019470501200_ocae049-B17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3390\/nu12082466","article-title":"Machine learning models to predict childhood and adolescent obesity: a review","volume":"12","author":"Colmenarejo","year":"2020","journal-title":"Nutrients"},{"issue":"1","key":"2024052019470501200_ocae049-B18","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1038\/s41598-018-36745-x","article-title":"Learning from longitudinal data in electronic health record and genetic data to improve cardiovascular event prediction","volume":"9","author":"Zhao","year":"2019","journal-title":"Sci Rep"},{"issue":"10","key":"2024052019470501200_ocae049-B19","doi-asserted-by":"crossref","first-page":"1419","DOI":"10.1093\/jamia\/ocy068","article-title":"Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review","volume":"25","author":"Xiao","year":"2018","journal-title":"J Am Med Inform Assoc"},{"issue":"1","key":"2024052019470501200_ocae049-B20","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1093\/jamia\/ocw042","article-title":"Opportunities and challenges in developing risk prediction models with electronic health records data: a systematic review","volume":"24","author":"Goldstein","year":"2017","journal-title":"J Am Med Informatics Assoc"},{"issue":"1","key":"2024052019470501200_ocae049-B21","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1038\/s41746-020-00372-6","article-title":"Machine learning-based prediction of COVID-19 diagnosis based on symptoms","volume":"4","author":"Zoabi","year":"2021","journal-title":"NPJ Digit Med"},{"issue":"1","key":"2024052019470501200_ocae049-B22","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1186\/s12874-019-0681-4","article-title":"Machine learning in medicine: a practical introduction","volume":"19","author":"Sidey-Gibbons","year":"2019","journal-title":"BMC Med Res Methodol"},{"key":"2024052019470501200_ocae049-B23","first-page":"432","author":"Cheng","year":"2016"},{"issue":"7553","key":"2024052019470501200_ocae049-B24","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Lecun","year":"2015","journal-title":"Nature"},{"key":"2024052019470501200_ocae049-B25","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":"2014","journal-title":"Neural Networks"},{"issue":"11","key":"2024052019470501200_ocae049-B26","first-page":"1","article-title":"Deep learning for clustering of multivariate clinical patient trajectories with missing values","volume":"8","author":"de Jong","year":"2019","journal-title":"Gigascience"},{"issue":"4","key":"2024052019470501200_ocae049-B27","doi-asserted-by":"crossref","first-page":"e0215571","DOI":"10.1371\/journal.pone.0215571","article-title":"Predicting childhood obesity using electronic health records and publicly available data","volume":"14","author":"Hammond","year":"2019","journal-title":"PLoS One"},{"key":"2024052019470501200_ocae049-B28","first-page":"787","author":"Che","year":"2017"},{"issue":"2","key":"2024052019470501200_ocae049-B29","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1093\/jamia\/ocw112","article-title":"Using recurrent neural network models for early detection of heart failure onset","volume":"24","author":"Choi","year":"2017","journal-title":"J Am Med Inform Assoc"},{"issue":"1","key":"2024052019470501200_ocae049-B30","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1186\/s12933-020-01082-9","article-title":"Comparative predictive ability of visit-to-visit HbA1c variability measures for microvascular disease risk in type 2 diabetes","volume":"19","author":"Yang","year":"2020","journal-title":"Cardiovasc Diabetol"},{"issue":"1","key":"2024052019470501200_ocae049-B31","doi-asserted-by":"crossref","first-page":"4731","DOI":"10.1038\/s41598-021-84150-8","article-title":"Long-term HbA1c variability and the development and progression of diabetic retinopathy in subjects with type 2 diabetes","volume":"11","author":"Kim","year":"2021","journal-title":"Sci Rep"},{"key":"2024052019470501200_ocae049-B32","author":"Holzinger","year":"2017"},{"key":"2024052019470501200_ocae049-B33","first-page":"1","article-title":"2000 CDC growth charts for the United States: methods and development","author":"Kuczmarski","year":"2002"},{"issue":"2","key":"2024052019470501200_ocae049-B34","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1136\/amiajnl-2011-000439","article-title":"Use of diverse electronic medical record systems to identify genetic risk for type 2 diabetes within a genome-wide association study","volume":"19","author":"Kho","year":"2012","journal-title":"J Am Med Informatics Assoc"},{"issue":"5","key":"2024052019470501200_ocae049-B35","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1111\/j.1399-5448.2007.00271.x","article-title":"The metabolic syndrome in children and adolescents\u2014an IDF consensus report","volume":"8","author":"Zimmet","year":"2007","journal-title":"Pediatr Diabetes"},{"key":"2024052019470501200_ocae049-B36","year":"2023"},{"issue":"3","key":"2024052019470501200_ocae049-B37","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1093\/bioinformatics\/btg419","article-title":"Is cross-validation valid for small-sample microarray classification?","volume":"20","author":"Braga-Neto","year":"2004","journal-title":"Bioinformatics"},{"key":"2024052019470501200_ocae049-B38","first-page":"7","author":"Cheng"},{"key":"2024052019470501200_ocae049-B39","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511528446","volume-title":"The Shapley Value: Essays in Honor of Lloyd S. Shapley","author":"Roth","year":"1988"},{"issue":"1","key":"2024052019470501200_ocae049-B40","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1159\/000348625","article-title":"Predicting metabolic syndrome in obese children and adolescents: look, measure and ask","volume":"6","author":"Santoro","year":"2013","journal-title":"Obes Facts"},{"key":"2024052019470501200_ocae049-B41","doi-asserted-by":"crossref","first-page":"S3","DOI":"10.1016\/S2214-109X(23)00088-8","article-title":"Association between childhood BMI trajectories and cardiometabolic risk and mental health problems at the age of 13 years: the cohort STudy of Adolescence Resilience and Stress (STARS)","volume":"11(Suppl 1)","author":"Chen","year":"2023","journal-title":"Lancet Glob Heal"},{"issue":"3","key":"2024052019470501200_ocae049-B42","doi-asserted-by":"crossref","first-page":"e290","DOI":"10.1542\/peds.2004-1808","article-title":"Metabolic syndrome in childhood: association with birth weight, maternal obesity, and gestational diabetes mellitus","volume":"115","author":"Boney","year":"2005","journal-title":"Pediatrics"},{"issue":"20","key":"2024052019470501200_ocae049-B43","doi-asserted-by":"crossref","first-page":"1876","DOI":"10.1056\/NEJMoa1010112","article-title":"Childhood adiposity, adult adiposity, and cardiovascular risk factors","volume":"365","author":"Juonala","year":"2011","journal-title":"N Engl J Med"},{"issue":"2","key":"2024052019470501200_ocae049-B44","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1016\/j.jpeds.2007.09.010","article-title":"Metabolic syndrome in childhood predicts adult metabolic syndrome and type 2 diabetes mellitus 25 to 30 years later","volume":"152","author":"Morrison","year":"2008","journal-title":"J Pediatr"},{"issue":"10","key":"2024052019470501200_ocae049-B45","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1001\/jama.290.10.1345","article-title":"National surveillance for type 2 diabetes mellitus in Taiwanese children","volume":"290","author":"Wei","year":"2003","journal-title":"JAMA"},{"issue":"1","key":"2024052019470501200_ocae049-B46","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1186\/s12933-022-01735-x","article-title":"Weight variability and cardiovascular outcomes: a systematic review and meta-analysis","volume":"22","author":"Massey","year":"2023","journal-title":"Cardiovasc Diabetol"},{"issue":"3","key":"2024052019470501200_ocae049-B47","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1007\/s10900-004-1955-1","article-title":"The association between weight fluctuation and mortality: results from a population-based cohort study","volume":"30","author":"Diaz","year":"2005","journal-title":"J Community Health"},{"issue":"14","key":"2024052019470501200_ocae049-B48","doi-asserted-by":"crossref","first-page":"1332","DOI":"10.1056\/NEJMoa1606148","article-title":"Body-weight fluctuations and outcomes in coronary disease","volume":"376","author":"Bangalore","year":"2017","journal-title":"N Engl J Med"},{"issue":"26","key":"2024052019470501200_ocae049-B49","doi-asserted-by":"crossref","first-page":"1839","DOI":"10.1056\/NEJM199106273242602","article-title":"Variability of body weight and health outcomes in the Framingham population","volume":"324","author":"Lissner","year":"1991","journal-title":"N Engl J Med"},{"issue":"12","key":"2024052019470501200_ocae049-B50","doi-asserted-by":"crossref","first-page":"2804","DOI":"10.1111\/dom.14538","article-title":"Associations of weight loss with obesity-related comorbidities in a large integrated health system","volume":"23","author":"Mariam","year":"2021","journal-title":"Diabetes, Obes Metab"},{"key":"2024052019470501200_ocae049-B51","doi-asserted-by":"crossref","first-page":"636","DOI":"10.1542\/peds.146.1MA7.636","article-title":"Pediatric dyslipidemia screening by pediatricians and family medicine physicians: current practices and future directions","volume":"146(1_MeetingAbstract)","author":"Sleeth","year":"2020","journal-title":"Pediatrics"},{"issue":"6","key":"2024052019470501200_ocae049-B52","first-page":"e415\u201325","article-title":"Recurrent neural network models (CovRNN) for predicting outcomes of patients with COVID-19 on admission to hospital: model development and validation using electronic health record data","volume":"4","author":"Rasmy","year":"2022","journal-title":"Lancet Digit Heal"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/31\/6\/1227\/57769051\/ocae049.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/31\/6\/1227\/57769051\/ocae049.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T19:48:24Z","timestamp":1716234504000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/31\/6\/1227\/7630960"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,18]]},"references-count":52,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,3,18]]},"published-print":{"date-parts":[[2024,5,20]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocae049","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,6,1]]},"published":{"date-parts":[[2024,3,18]]}}}