{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T20:56:23Z","timestamp":1790801783469,"version":"4.1.0"},"reference-count":42,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Mhealth Uhealth"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Continuous glucose monitoring (CGM) can facilitate weight management and lower the risk of metabolic diseases by providing real-time feedback on glycemic responses, thereby enabling more informed lifestyle decisions. However, current CGM systems remain constrained by invasiveness, cost, and short sensor lifespan, limiting their practicality for guiding individualized postprandial low-glycemic diets.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n Extending earlier proof-of-concept findings, this study aimed to validate an interstitial glucose (IG) machine learning algorithm in real-world environments using multimodal, continuous data collected from wearable sensors and smartwatches. In the long term, we aim to embed a noninvasive, sensor-based algorithm for estimating tissue glucose within mobile health apps and postprandial low-glycemic diet frameworks to enable scalable, personalized prevention strategies.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We conducted a 2-week study phase during which participants continuously wore 2 noninvasive sensor devices: a scientific sensor wristband (Empatica EmbracePlus) and a commercially available smartwatch (Fitbit Sense 2). As a reference measurement, an invasive CGM sensor (Abbott FreeStyle Libre 3) measured IG levels. For metabolic characterization, 1-point fasting blood and urine samples were collected, and deep phenotyping using state-of-the-art nuclear magnetic resonance spectroscopy and bioelectrical impedance analysis was performed. For participants with overweight and obesity, clinical standard parameters focusing on glucose metabolism were analyzed.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n A total of 74 participants, 34 (46%) healthy controls and 40 (54%) metabolically at-risk (MR) individuals, simultaneously used an invasive CGM device together with 2 noninvasive wristbands over 2 weeks. Healthy controls were characterized by a mean age of 24.53 (SD 3.68) years and a mean BMI of 22.36 (SD 2.16) kg\/m\u00b2. In contrast, the MR cohort had a mean age of 55.38 (SD 15.08) years and a mean BMI of 35.38 (SD 4.91) kg\/m\u00b2. Furthermore, the MR cohort showed elevated fasting glucose levels (mean 107.56, SD 19.26 mg\/dL), hemoglobin A\n 1c<\/jats:sub>\n levels (mean 5.67%, SD 0.63%), and an increased homeostatic model assessment of insulin resistance index (mean 4.34, SD 3.49), indicating a disturbed glucose metabolism. The proposed long short-term memory network based on feature vectors obtained the best IG prediction performance, with an average root-mean-squared error of 21.04 (SD 8.32) mg\/dL and 98.3% of predictions in zones A and B of the Clarke error grid analysis, representing a high level of predictive accuracy. In addition, based on data from a smartwatch, we achieved a comparable average root-mean-squared error of 23.49 (SD 11.46) mg\/dL for the overall cohort.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This study demonstrates that IG levels can be predicted from multimodal, noninvasive wearable sensor data using a machine learning approach under real-world conditions. While further validation in larger and more diverse cohorts is warranted, this approach represents a promising step toward accessible, personalized glycemic monitoring and dietary guidance as a preventive tool in mobile health apps.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/91724","type":"journal-article","created":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T19:55:21Z","timestamp":1790798121000},"page":"e91724-e91724","source":"Crossref","is-referenced-by-count":0,"title":["Noninvasive Interstitial Glucose Estimation Using Wearables and Machine Learning in Healthy Individuals and Individuals With Obesity: Observational Cohort Study"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0649-675X","authenticated-orcid":false,"given":"Franziska","family":"Schmelter","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3210-3891","authenticated-orcid":false,"given":"Xinyu","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0458-4519","authenticated-orcid":false,"given":"Annika","family":"Heidmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2677-0641","authenticated-orcid":false,"given":"Paul","family":"Beier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7093-619X","authenticated-orcid":false,"given":"Friederike Miriam","family":"Rundfeldt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1909-1967","authenticated-orcid":false,"given":"Christina","family":"Pl\u00f6ger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2137-8363","authenticated-orcid":false,"given":"Artur","family":"Piet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0240-1708","authenticated-orcid":false,"given":"Md Abid","family":"Hasan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7056-9476","authenticated-orcid":false,"given":"Yuanheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6185-3146","authenticated-orcid":false,"given":"Lennart","family":"Jablonski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8665-9137","authenticated-orcid":false,"given":"Oliver","family":"Witt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4897-1481","authenticated-orcid":false,"given":"Torsten","family":"Schr\u00f6der","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6142-5577","authenticated-orcid":false,"given":"Stefanie","family":"Derer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3602-7841","authenticated-orcid":false,"given":"Chris","family":"Easthope Awai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4877-8287","authenticated-orcid":false,"given":"Marcin","family":"Grzegorzek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7640-1220","authenticated-orcid":false,"given":"Christian","family":"Sina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,9,30]]},"reference":[{"issue":"2","key":"R1","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1038\/nri2925","article-title":"Type 2 diabetes as an inflammatory disease","volume":"11","author":"Donath","journal-title":"Nat Rev Immunol"},{"issue":"10","key":"R2","doi-asserted-by":"publisher","first-page":"3330","DOI":"10.1038\/s41591-025-03944-9","article-title":"Prevention of type 2 diabetes through prediabetes remission without weight loss","volume":"31","author":"Sandforth","journal-title":"Nat Med"},{"key":"R3","doi-asserted-by":"publisher","DOI":"10.1016\/j.metabol.2023.155640","article-title":"Continuous glucose monitoring in a healthy population: understanding the post-prandial glycemic response in individuals without diabetes mellitus","volume":"146","author":"Jarvis","journal-title":"Metabolism"},{"issue":"10","key":"R4","doi-asserted-by":"publisher","first-page":"923","DOI":"10.1111\/j.1467-789X.2012.01011.x","article-title":"Impact of postprandial glycaemia on health and prevention of disease","volume":"13","author":"Blaak","journal-title":"Obes Rev"},{"issue":"5","key":"R5","doi-asserted-by":"publisher","first-page":"1079","DOI":"10.1016\/j.cell.2015.11.001","article-title":"Personalized nutrition by prediction of glycemic responses","volume":"163","author":"Zeevi","journal-title":"Cell"},{"issue":"6","key":"R6","doi-asserted-by":"publisher","first-page":"964","DOI":"10.1038\/s41591-020-0934-0","article-title":"Human postprandial responses to food and potential for precision nutrition","volume":"26","author":"Berry","journal-title":"Nat Med"},{"issue":"14","key":"R7","doi-asserted-by":"publisher","first-page":"2927","DOI":"10.3390\/nu14142927","article-title":"A digital therapeutic allowing a personalized low-glycemic nutrition for the prophylaxis of migraine: real world data from two prospective studies","volume":"14","author":"Lelleck","journal-title":"Nutrients"},{"issue":"1","key":"R8","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1177\/19322968241266821","article-title":"Unlocking potential: personalized lifestyle therapy for type 2 diabetes through a predictive algorithm-driven digital therapeutic","volume":"20","author":"Kannenberg","journal-title":"J Diabetes Sci Technol"},{"issue":"S3","key":"R9","doi-asserted-by":"publisher","first-page":"S25","DOI":"10.1089\/dia.2017.0035","article-title":"Continuous glucose monitoring: a review of recent studies demonstrating improved glycemic outcomes","volume":"19","author":"Rodbard","journal-title":"Diabetes Technol Ther"},{"issue":"7","key":"R10","doi-asserted-by":"publisher","DOI":"10.1007\/s11892-021-01389-1","article-title":"Advances, challenges, and cost associated with continuous glucose monitor use in adolescents and young adults with type 1 diabetes","volume":"21","author":"Datye","journal-title":"Curr Diab Rep"},{"issue":"5","key":"R11","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.1093\/ajcn\/61.5.1013","article-title":"Thermic effect of food in humans: methods and results from use of a respiratory chamber","volume":"61","author":"Tataranni","journal-title":"Am J Clin Nutr"},{"issue":"4","key":"R12","doi-asserted-by":"publisher","first-page":"678","DOI":"10.1038\/s42255-024-01016-9","article-title":"Non-invasive measurements of blood glucose levels by time-gating mid-infrared optoacoustic signals","volume":"6","author":"Ulu\u00e7","journal-title":"Nat Metab"},{"issue":"September","key":"R13","doi-asserted-by":"publisher","first-page":"115668","DOI":"10.1016\/j.bios.2023.115668","article-title":"In-human testing of a non-invasive continuous low-energy microwave glucose sensor with advanced machine learning capabilities","volume":"241","author":"Kazemi","journal-title":"Biosens Bioelectron"},{"issue":"17","key":"R14","doi-asserted-by":"publisher","first-page":"18742","DOI":"10.1109\/JSEN.2021.3090050","article-title":"Noninvasive glucose sensing in aqueous solutions using an active split-ring resonator","volume":"21","author":"Abdolrazzaghi","journal-title":"IEEE Sensors J"},{"issue":"9","key":"R15","doi-asserted-by":"publisher","first-page":"3121","DOI":"10.1038\/s41591-025-03849-7","article-title":"Multimodal AI correlates of glucose spikes in people with normal glucose regulation, pre-diabetes and type 2 diabetes","volume":"31","author":"Carletti","journal-title":"Nat Med"},{"issue":"21","key":"R16","doi-asserted-by":"publisher","DOI":"10.3390\/nu14214465","article-title":"Digital biomarkers for personalized nutrition: predicting meal moments and interstitial glucose with non-invasive, wearable technologies","volume":"14","author":"van den Brink","journal-title":"Nutrients"},{"issue":"1","key":"R17","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00465-w","article-title":"Engineering digital biomarkers of interstitial glucose from noninvasive smartwatches","volume":"4","author":"Bent","journal-title":"NPJ Digit Med"},{"issue":"1","key":"R18","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00956-y","article-title":"Digital health application integrating wearable data and behavioral patterns improves metabolic health","volume":"6","author":"Zahedani","journal-title":"NPJ Digit Med"},{"issue":"1","key":"R19","doi-asserted-by":"publisher","first-page":"30164","DOI":"10.1038\/s41598-025-14172-z","article-title":"Digital biomarkers for interstitial glucose prediction in healthy individuals using wearables and machine learning","volume":"15","author":"Huang","journal-title":"Sci Rep"},{"issue":"4","key":"R20","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1007\/s13300-023-01385-6","article-title":"Accuracy of the third generation of a 14-day continuous glucose monitoring system","volume":"14","author":"Alva","journal-title":"Diabetes Ther"},{"issue":"19","key":"R21","doi-asserted-by":"publisher","first-page":"9887","DOI":"10.1021\/ac5025039","article-title":"Precision high-throughput proton NMR spectroscopy of human urine, serum, and plasma for large-scale metabolic phenotyping","volume":"86","author":"Dona","journal-title":"Anal Chem"},{"key":"R22","doi-asserted-by":"publisher","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":"Woldaregay","journal-title":"Artif Intell Med"},{"issue":"9","key":"R23","doi-asserted-by":"publisher","first-page":"35591223","DOI":"10.3390\/s22093534","article-title":"Selection of noninvasive features in wrist-based wearable sensors to predict blood glucose concentrations using machine learning algorithms","volume":"22","author":"Bogue-Jimenez","journal-title":"Sensors (Basel)"},{"issue":"Supplement_1","key":"R24","doi-asserted-by":"publisher","first-page":"979","DOI":"10.2337\/db25-979-P","article-title":"979-P: leveraging machine learning and demographic insights to optimize blood glucose management on a digital health platform","volume":"74","author":"Fundoiano-hershcovitz","journal-title":"Diabetes"},{"key":"R25","doi-asserted-by":"crossref","unstructured":"Fulcher BD . Feature-based time-series analysis. In: Feature Engineering for Machine Learning and Data Analytics. CRC Press; 2017:87-116. [doi: 10.1201\/9781315181080-4]","DOI":"10.1201\/9781315181080-4"},{"key":"R26","doi-asserted-by":"crossref","unstructured":"Alshehri OS Alshehri OM Samma H . Blood glucose prediction using RNN, LSTM, and GRU: a comparative study. Presented at: 2024 IEEE International Conference on Advanced Systems and Emergent Technologies (IC_ASET); 1-5; Hammamet, Tunisia. Jul 23, 2024.[doi: 10.1109\/IC_ASET61847.2024.10596176]","DOI":"10.1109\/IC_ASET61847.2024.10596176"},{"issue":"3","key":"R27","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1093\/biomet\/93.3.491","article-title":"Adaptive linear step-up procedures that control the false discovery rate","volume":"93","author":"Benjamini","journal-title":"Biometrika"},{"key":"R28","unstructured":"Liu Y Hu T Zhang H Wu H Wang S Ma L et al. iTransformer: inverted transformers are effective for time series forecasting. Presented at: 12th International Conference on Learning Representations (ICLR 2024); May 7-11, 2024; Vienna, Austria. 2024.[doi: 10.48550\/arXiv.2310.06625]"},{"issue":"5","key":"R29","doi-asserted-by":"publisher","first-page":"622","DOI":"10.2337\/diacare.10.5.622","article-title":"Evaluating clinical accuracy of systems for self-monitoring of blood glucose","volume":"10","author":"Clarke","journal-title":"Diabetes Care"},{"issue":"Dl","key":"R30","doi-asserted-by":"publisher","first-page":"283","DOI":"10.3233\/SHTI230484","article-title":"Estimating blood glucose levels using machine learning models with non-invasive wearable device data","volume":"305","author":"Aziz","journal-title":"Stud Health Technol Inform"},{"issue":"1","key":"R31","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-84265-8","article-title":"Non-invasive blood glucose monitoring using PPG signals with various deep learning models and implementation using TinyML","volume":"15","author":"Zeynali","journal-title":"Sci Rep"},{"issue":"1","key":"R32","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-13018-7","article-title":"Noninvasive continuous glucose monitoring using a multisensor-based glucometer and time series analysis","volume":"7","author":"Geng","journal-title":"Sci Rep"},{"issue":"1","key":"R33","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1016\/j.numecd.2021.09.024","article-title":"Serum metabolites associated with increased insulin resistance and low cardiorespiratory fitness in overweight adolescents","volume":"32","author":"Duft","journal-title":"Nutr Metab Cardiovasc Dis"},{"issue":"1009","key":"R34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1259\/bjr\/38447238","article-title":"The clinical importance of visceral adiposity: a critical review of methods for visceral adipose tissue analysis","volume":"85","author":"Shuster","journal-title":"Br J Radiol"},{"issue":"1","key":"R35","doi-asserted-by":"publisher","first-page":"7010","DOI":"10.1038\/s41598-019-43431-z","article-title":"Serum amino acid profiles and risk of type 2 diabetes among Japanese adults in the Hitachi Health Study","volume":"9","author":"Chen","journal-title":"Sci Rep"},{"issue":"1","key":"R36","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1038\/s41392-024-01951-9","article-title":"Type 2 diabetes mellitus in adults: pathogenesis, prevention and therapy","volume":"9","author":"Lu","journal-title":"Sig Transduct Target Ther"},{"issue":"5","key":"R37","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1111\/j.1365-2796.2006.01643.x","article-title":"The apoB\/apoA-I ratio: a strong, new risk factor for cardiovascular disease and a target for lipid-lowering therapy--a review of the evidence","volume":"259","author":"Walldius","journal-title":"J Intern Med"},{"key":"R38","doi-asserted-by":"publisher","DOI":"10.7573\/dic.212525","article-title":"High-density lipoprotein (HDL) functionality and its relevance to atherosclerotic cardiovascular disease","volume":"7","author":"Kosmas","journal-title":"DIC"},{"key":"R39","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-0260-4","article-title":"Verification, analytical validation, and clinical validation (V3): the foundation of determining fit-for-purpose for Biometric Monitoring Technologies (BioMeTs)","volume":"3","author":"Goldsack","journal-title":"NPJ Digit Med"},{"issue":"6","key":"R40","doi-asserted-by":"publisher","first-page":"6989","DOI":"10.1609\/aaai.v37i6.25854","article-title":"NHITS: Neural Hierarchical Interpolation for Time Series Forecasting","volume":"37","author":"Challu","journal-title":"AAAI"},{"key":"R41","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107489","article-title":"Wearable-based human flow experience recognition enhanced by transfer learning methods using emotion data","volume":"166","author":"Irshad","journal-title":"Comput Biol Med"},{"issue":"3","key":"R42","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/MSP.2020.2975749","article-title":"Federated learning: challenges, methods, and future directions","volume":"37","author":"Li","journal-title":"IEEE Signal Process Mag"}],"container-title":["JMIR mHealth and uHealth"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T19:55:23Z","timestamp":1790798123000},"score":1,"resource":{"primary":{"URL":"https:\/\/mhealth.jmir.org\/2026\/1\/e91724"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,30]]},"references-count":42,"URL":"https:\/\/doi.org\/10.2196\/91724","relation":{},"ISSN":["2291-5222"],"issn-type":[{"value":"2291-5222","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,30]]},"article-number":"v14i2e91724"}}