{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T15:31:12Z","timestamp":1787844672491,"version":"build-2784847793"},"reference-count":41,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100014438","name":"Business Finland","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100014438","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100014438","name":"Business Finland","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100014438","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100014438","name":"Business Finland","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100014438","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>In recent years, numerous methods have been introduced to predict glucose levels using machine-learning techniques on patients\u2019 daily behavioral and continuous glucose data. Nevertheless, a definitive consensus remains elusive regarding modeling the combined effects of diet and exercise for optimal glucose prediction. A notable challenge is the propensity for observational patient datasets from uncontrolled environments to overfit due to skewed feature distributions of target behaviors; for instance, diabetic patients seldom engage in high-intensity exercise post-meal.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this study, we introduce a unique application of Bayesian transfer learning for postprandial glucose prediction using randomized controlled trial (RCT) data. The data comprises a time series of three key variables: continuous glucose levels, exercise expenditure, and carbohydrate intake. For building the optimal model to predict postprandial glucose levels we initially gathered balanced training data from RCTs on healthy participants by randomizing behavioral conditions. Subsequently, we pretrained the model\u2019s parameter distribution using RCT data from the healthy cohort. This pretrained distribution was then adjusted, transferred, and utilized to determine the model parameters for each patient.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The efficacy of the proposed method was appraised using data from 68 gestational diabetes mellitus (GDM) patients in uncontrolled settings. The evaluation underscored the enhanced performance attained through our method. Furthermore, when modeling the joint impact of diet and exercise, the synergetic model proved more precise than its additive counterpart.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>An innovative application of the transfer-learning utilizing randomized controlled trial data can improve the challenging modeling task of postprandial glucose prediction for GDM patients, integrating both dietary and exercise behaviors. For more accurate prediction, future research should focus on incorporating the long-term effects of exercise and other glycemic-related factors such as stress, sleep.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0298506","type":"journal-article","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T13:25:20Z","timestamp":1722518720000},"page":"e0298506","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":6,"title":["Optimizing postprandial glucose prediction through integration of diet and exercise: Leveraging transfer learning with imbalanced patient data"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6448-5184","authenticated-orcid":true,"given":"Shinji","family":"Hotta","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mikko","family":"Kyt\u00f6","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saila","family":"Koivusalo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seppo","family":"Heinonen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7078-7927","authenticated-orcid":true,"given":"Pekka","family":"Marttinen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,8,1]]},"reference":[{"issue":"5","key":"pone.0298506.ref001","doi-asserted-by":"crossref","first-page":"963","DOI":"10.2337\/dc17-1962","article-title":"Global Economic Burden of Diabetes in Adults: Projections From 2015 to 2030","volume":"41","author":"C Bommer","year":"2018","journal-title":"Diabetes Care"},{"issue":"1","key":"pone.0298506.ref002","doi-asserted-by":"crossref","first-page":"26","DOI":"10.3803\/EnM.2022.105","article-title":"Recent Updates to Clinical Practice Guidelines for Diabetes Mellitus","volume":"37","author":"J Yu","year":"2022","journal-title":"Endocrinol Metab (Seoul)"},{"issue":"4","key":"pone.0298506.ref003","doi-asserted-by":"crossref","first-page":"e36987","DOI":"10.2196\/36987","article-title":"Behavior Change App for Self-management of Gestational Diabetes: Design and Evaluation of Desirable Features","volume":"9","author":"M Kyt\u00f6","year":"2022","journal-title":"JMIR Hum Factors"},{"issue":"12","key":"pone.0298506.ref004","doi-asserted-by":"crossref","first-page":"2089","DOI":"10.1080\/03007995.2021.1976737","article-title":"Changing face of healthcare: digital therapeutics in the management of diabetes","volume":"37","author":"P Ramakrishnan","year":"2021","journal-title":"Curr Med Res Opin"},{"issue":"11","key":"pone.0298506.ref005","doi-asserted-by":"crossref","first-page":"e066292","DOI":"10.1136\/bmjopen-2022-066292","article-title":"Comprehensive self-tracking of blood glucose and lifestyle with a mobile application in the management of gestational diabetes: a study protocol for a randomised controlled trial (eMOM GDM study)","volume":"12","author":"M Kyt\u00f6","year":"2022","journal-title":"BMJ Open"},{"issue":"6","key":"pone.0298506.ref006","doi-asserted-by":"crossref","DOI":"10.1002\/cnm.2833","article-title":"A review of personalized blood glucose prediction strategies for T1DM patients","volume":"33","author":"S Oviedo","year":"2017","journal-title":"Int J Numer Method Biomed Eng"},{"key":"pone.0298506.ref007","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.artmed.2019.07.007","article-title":"Data-driven modeling and prediction of blood glucose dynamics: Machine learning applications in type 1 diabetes","volume":"98","author":"AZ Woldaregay","year":"2019","journal-title":"Artif Intell Med"},{"key":"pone.0298506.ref008","doi-asserted-by":"crossref","unstructured":"Jankovic MV, Mosimann S, Bally L, Stettler C, Mougiakakou S. Deep prediction model: The case of online adaptive prediction of subcutaneous glucose. 2016 13th Symposium on Neural Networks and Applications (NEUREL), Belgrade, Serbia, 2016.","DOI":"10.1109\/NEUREL.2016.7800095"},{"issue":"11","key":"pone.0298506.ref009","doi-asserted-by":"crossref","first-page":"e14452","DOI":"10.2196\/14452","article-title":"Development of a Deep Learning Model for Dynamic Forecasting of Blood Glucose Level for Type 2 Diabetes Mellitus: Secondary Analysis of a Randomized Controlled Trial","volume":"7","author":"SHA Faruqui","year":"2019","journal-title":"JMIR Mhealth Uhealth"},{"issue":"11","key":"pone.0298506.ref010","first-page":"CD010443","article-title":"Combined diet and exercise interventions for preventing gestational diabetes mellitus","volume":"11","author":"E Shepherd","year":"2017","journal-title":"Cochrane Database Syst Rev"},{"issue":"4","key":"pone.0298506.ref011","doi-asserted-by":"crossref","first-page":"2775","DOI":"10.1016\/j.dsx.2019.07.040","article-title":"Dietary and exercise interventions and glycemic control and maternal and newborn outcomes in women diagnosed with gestational diabetes: Systematic review","volume":"13","author":"SS Allehdan","year":"2019","journal-title":"Diabetes Metab Syndr"},{"issue":"5","key":"pone.0298506.ref012","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1139\/apnm-2017-0494","article-title":"Postprandial walking reduces glucose levels in women with gestational diabetes mellitus","volume":"43","author":"DP Coe","year":"2018","journal-title":"Appl Physiol Nutr Metab"},{"issue":"12","key":"pone.0298506.ref013","doi-asserted-by":"crossref","first-page":"2493","DOI":"10.2337\/dc11-2381","article-title":"The effect of walking on postprandial glycemic excursion in patients with type 1 diabetes and healthy people","volume":"35","author":"C Manohar","year":"2012","journal-title":"Diabetes Care"},{"issue":"6","key":"pone.0298506.ref014","doi-asserted-by":"crossref","first-page":"1479","DOI":"10.1007\/s40279-018-0864-x","article-title":"The Effects of Postprandial Exercise on Glucose Control in Individuals with Type 2 Diabetes: A Systematic Review","volume":"48","author":"A Borror","year":"2018","journal-title":"Sports Med"},{"issue":"6","key":"pone.0298506.ref015","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0066385","article-title":"Reducing the Decline in Physical Activity during Pregnancy: A Systematic Review of Behaviour Change Interventions","volume":"8","author":"S Currie","year":"2013","journal-title":"PLoS One"},{"key":"pone.0298506.ref016","doi-asserted-by":"crossref","first-page":"105874","DOI":"10.1016\/j.cmpb.2020.105874","article-title":"Adversarial multi-source transfer learning in healthcare: Application to glucose prediction for diabetic people","volume":"199","author":"M De Bois","year":"2021","journal-title":"Comput Methods Programs Biomed"},{"key":"pone.0298506.ref017","doi-asserted-by":"crossref","first-page":"1875","DOI":"10.1007\/s40747-021-00360-7","article-title":"Deep transfer learning: a novel glucose prediction framework for new subjects with type 2 diabetes","volume":"8","author":"X Yu","year":"2022","journal-title":"Complex Intell. Syst"},{"issue":"1","key":"pone.0298506.ref018","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1038\/s41746-021-00480-x","article-title":"Deep transfer learning and data augmentation improve glucose levels prediction in type 2 diabetes patients","volume":"4","author":"Y Deng","year":"2021","journal-title":"NPJ Digit Med"},{"issue":"1","key":"pone.0298506.ref019","article-title":"A Data-Driven Personalized Model of Glucose Dynamics Taking Account of the Effects of Physical Activity for Type 1 Diabetes: An In Silico Study","volume":"141","author":"J Xie","year":"2019","journal-title":"J Biomech Eng"},{"issue":"1","key":"pone.0298506.ref020","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1109\/TITB.2012.2219876","article-title":"Multivariate prediction of subcutaneous glucose concentration in type 1 diabetes patients based on support vector regression","volume":"17","author":"EI Georga","year":"2013","journal-title":"IEEE J Biomed Health Inform"},{"key":"pone.0298506.ref021","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.jtbi.2014.04.038","article-title":"Personalized mechanistic models for exercise, meal and insulin interventions in children and adolescents with type 1 diabetes","volume":"357","author":"NP Balakrishnan","year":"2014","journal-title":"J Theor Biol"},{"key":"pone.0298506.ref022","unstructured":"Xuan J, Lu J, Zhang G. Bayesian transfer learning: An overview of probabilistic graphical models for transfer learning. 2021. arXiv preprint arXiv:2109.13233."},{"key":"pone.0298506.ref023","unstructured":"Piotr M. Suder, Jason Xu, David B. Dunson. Bayesian Transfer Learning. 2023. arXiv preprint arXiv:2312.13484"},{"issue":"1","key":"pone.0298506.ref024","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1109\/JBHI.2021.3100558","article-title":"A Multitask Learning Approach to Personalized Blood Glucose Prediction","volume":"26","author":"J Daniels","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"issue":"Suppl 2","key":"pone.0298506.ref025","doi-asserted-by":"crossref","first-page":"S322","DOI":"10.2337\/dc09-S331","article-title":"Implications of postprandial glucose and weight control in people with type 2 diabetes: understanding and implementing the International Diabetes Federation guidelines","volume":"32","author":"B. Gallwitz","year":"2009","journal-title":"Diabetes Care"},{"key":"pone.0298506.ref026","doi-asserted-by":"crossref","first-page":"219308","DOI":"10.1109\/ACCESS.2020.3042483","article-title":"Machine Learning Approach for Postprandial Blood Glucose Prediction in Gestational Diabetes Mellitus","volume":"8","author":"EA Pustozerov","year":"2020","journal-title":"IEEE Access"},{"issue":"1","key":"pone.0298506.ref027","doi-asserted-by":"crossref","first-page":"1885","DOI":"10.1080\/07853890.2021.1964035","article-title":"Computational modelling of self-reported dietary carbohydrate intake on glucose concentrations in patients undergoing Roux-en-Y gastric bypass versus one-anastomosis gastric bypass","volume":"53","author":"RA Ashrafi","year":"2021","journal-title":"Ann Med"},{"issue":"1","key":"pone.0298506.ref028","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1109\/JBHI.2020.2987323","article-title":"Errors-in-Variables Modeling of Personalized Treatment-Response Trajectories","volume":"25","author":"G Zhang","year":"2021","journal-title":"IEEE J Biomed Health Inform"},{"issue":"5","key":"pone.0298506.ref029","doi-asserted-by":"crossref","first-page":"1080","DOI":"10.3390\/nu14051080","article-title":"The Effects of Postprandial Walking on the Glucose Response after Meals with Different Characteristics","volume":"14","author":"A Bellini","year":"2022","journal-title":"Nutrients"},{"key":"pone.0298506.ref030","doi-asserted-by":"crossref","first-page":"228","DOI":"10.3389\/fendo.2017.00228","article-title":"Exercise after You Eat: Hitting the Postprandial Glucose Target","volume":"8","author":"ML Erickson","year":"2017","journal-title":"Front Endocrinol (Lausanne)"},{"key":"pone.0298506.ref031","unstructured":"Shwartz-Ziv R, Goldblum M, Souri H, Kapoor S, Zhu C, LeCun Y, et al. Pre-train your loss: Easy bayesian transfer learning with informative priors. In Advances in Neural Information Processing Systems. 42."},{"issue":"6","key":"pone.0298506.ref032","first-page":"667","article-title":"Lilly lecture 1987. The triumvirate: beta-cell, muscle, liver. A collusion responsible for NIDDM","volume":"37","author":"RA DeFronzo","year":"1988","journal-title":"Diabetes"},{"key":"pone.0298506.ref033","unstructured":"Stan Development Team (2023). \u201cRStan: the R interface to Stan.\u201d R package version 2.21.8, https:\/\/mc-stan.org\/."},{"issue":"2","key":"pone.0298506.ref034","doi-asserted-by":"crossref","first-page":"89","DOI":"10.5830\/CVJA-2016-021","article-title":"Physiological changes in pregnancy","volume":"27","author":"P Soma-Pillay","year":"2016","journal-title":"Cardiovasc J Afr"},{"issue":"6","key":"pone.0298506.ref035","doi-asserted-by":"crossref","first-page":"100440","DOI":"10.1016\/j.ajogmf.2021.100440","article-title":"Postprandial interval walking-effect on blood glucose in pregnant women with gestational diabetes","volume":"3","author":"MB Andersen","year":"2021","journal-title":"Am J Obstet Gynecol MFM"},{"key":"pone.0298506.ref036","doi-asserted-by":"crossref","DOI":"10.1201\/b16018","volume-title":"Bayesian Data Analysis","author":"A Gelman","year":"2013"},{"issue":"S2","key":"pone.0298506.ref037","doi-asserted-by":"crossref","first-page":"S25","DOI":"10.1089\/dia.2018.0092","article-title":"Glucose Variability: A Review of Clinical Applications and Research Developments","volume":"20","author":"D. Rodbard","year":"2018","journal-title":"Diabetes Technol Ther"},{"issue":"6","key":"pone.0298506.ref038","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1007\/s12160-016-9830-8","article-title":"Just-in-Time Adaptive Interventions (JITAIs) in Mobile Health: Key Components and Design Principles for Ongoing Health Behavior Support","volume":"52","author":"I Nahum-Shani","year":"2018","journal-title":"Ann Behav Med"},{"issue":"8","key":"pone.0298506.ref039","doi-asserted-by":"crossref","first-page":"856","DOI":"10.1139\/apnm-2021-0168","article-title":"Exercise-nutrient interactions for improved postprandial glycemic control and insulin sensitivity","volume":"46","author":"JB Gillen","year":"2021","journal-title":"Appl Physiol Nutr Metab"},{"issue":"1","key":"pone.0298506.ref040","doi-asserted-by":"crossref","first-page":"e6","DOI":"10.2196\/mhealth.9236","article-title":"Development and Evaluation of a Mobile Personalized Blood Glucose Prediction System for Patients With Gestational Diabetes Mellitus","volume":"6","author":"E Pustozerov","year":"2018","journal-title":"JMIR Mhealth Uhealth"},{"issue":"2","key":"pone.0298506.ref041","doi-asserted-by":"crossref","first-page":"e0000014","DOI":"10.1371\/journal.pdig.0000014","article-title":"Transfer learning for non-image data in clinical research: A scoping review","volume":"1","author":"A Ebbehoj","year":"2022","journal-title":"PLOS Digit Health"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0298506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T13:26:17Z","timestamp":1722518777000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0298506"}},"subtitle":[],"editor":[{"given":"Everson","family":"Nunes","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,8,1]]},"references-count":41,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2024,8,1]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0298506","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.01.28.24301902","asserted-by":"object"}]},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,1]]}}}