{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T06:53:58Z","timestamp":1780469638534,"version":"3.54.1"},"reference-count":34,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2021,11,24]],"date-time":"2021-11-24T00:00:00Z","timestamp":1637712000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001869","name":"Academia Sinica","doi-asserted-by":"publisher","award":["3010 Research Center for Applied Sciences"],"award-info":[{"award-number":["3010 Research Center for Applied Sciences"]}],"id":[{"id":"10.13039\/501100001869","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Previously published photoplethysmography-(PPG) based non-invasive blood glucose (NIBG) measurements have not yet been validated over 500 subjects. As illustrated in this work, we increased the number subjects recruited to 2538 and found that the prediction accuracy (the ratio in zone A of Clarke\u2019s error grid) reduced to undesirable 60.6%. We suspect the low prediction accuracy induced by larger sample size might arise from the physiological diversity of subjects, and one possibility is that the diversity might originate from medication. Therefore, we split the subjects into two cohorts for deep learning: with and without medication (1682 and 856 recruited subjects, respectively). In comparison, the cohort training for subjects without any medication had approximately 30% higher prediction accuracy over the cohort training for those with medication. Furthermore, by adding quarterly (every 3 months) measured glycohemoglobin (HbA1c), we were able to significantly boost the prediction accuracy by approximately 10%. For subjects without medication, the best performing model with quarterly measured HbA1c achieved 94.3% prediction accuracy, RMSE of 12.4 mg\/dL, MAE of 8.9 mg\/dL, and MAPE of 0.08, which demonstrates a very promising solution for NIBG prediction via deep learning. Regarding subjects with medication, a personalized model could be a viable means of further investigation.<\/jats:p>","DOI":"10.3390\/s21237815","type":"journal-article","created":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T01:45:02Z","timestamp":1638323102000},"page":"7815","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["90% Accuracy for Photoplethysmography-Based Non-Invasive Blood Glucose Prediction by Deep Learning with Cohort Arrangement and Quarterly Measured HbA1c"],"prefix":"10.3390","volume":"21","author":[{"given":"Justin","family":"Chu","sequence":"first","affiliation":[{"name":"Research Center for Applied Sciences, Academia Sinica, 128 Academia Rd., Sec. 2, Nankang, Taipei City 11529, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen-Tse","family":"Yang","sequence":"additional","affiliation":[{"name":"Research Center for Applied Sciences, Academia Sinica, 128 Academia Rd., Sec. 2, Nankang, Taipei City 11529, Taiwan"},{"name":"Department of Biomechatronics Engineering, National Taiwan University, No. 1, Sec. 4, Roosevelt Rd., Taipei City 10607, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Ru","family":"Lu","sequence":"additional","affiliation":[{"name":"Research Center for Applied Sciences, Academia Sinica, 128 Academia Rd., Sec. 2, Nankang, Taipei City 11529, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao-Ting","family":"Chang","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Department of Internal Medicine, Taipei Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, No. 289, Jianguo Rd., Xindian Dist., New Taipei City 23142, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9439-9945","authenticated-orcid":false,"given":"Tung-Han","family":"Hsieh","sequence":"additional","affiliation":[{"name":"Research Center for Applied Sciences, Academia Sinica, 128 Academia Rd., Sec. 2, Nankang, Taipei City 11529, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2823-9692","authenticated-orcid":false,"given":"Fu-Liang","family":"Yang","sequence":"additional","affiliation":[{"name":"Research Center for Applied Sciences, Academia Sinica, 128 Academia Rd., Sec. 2, Nankang, Taipei City 11529, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,11,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Sarkar, K., Ahmad, D., Singha, S.K., and Ahmad, M. (2018, January 21\u201323). Design and implementation of a noninvasive blood glucose monitoring device. Proceedings of the 2018 21st International Conference of Computer and Information Technology (ICCIT), Dhaka, Bangladesh.","DOI":"10.1109\/ICCITECHN.2018.8631942"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"101923","DOI":"10.1016\/j.bspc.2020.101923","article-title":"Accurate prediction of glucose concentration and identification of major contributing features from hardly distinguishable near-infrared spectroscopy","volume":"59","author":"Mekonnen","year":"2020","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2062","DOI":"10.1364\/OL.19.002062","article-title":"Possible correlation between blood glucose concentration and the reduced scattering coefficient of tissues in the near infrared","volume":"19","author":"Maier","year":"1994","journal-title":"Opt. Lett."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1839","DOI":"10.1001\/jama.282.19.1839","article-title":"Cygnus Research Team; Cygnus Research Team. Noninvasive glucose monitoring: Comprehensive clinical results","volume":"282","author":"Tamada","year":"1999","journal-title":"JAMA"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"433","DOI":"10.2337\/diacare.20.3.433","article-title":"Noninvasive blood glucose monitoring","volume":"20","author":"Klonoff","year":"1997","journal-title":"Diabetes Care"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2263","DOI":"10.2337\/diacare.25.12.2263","article-title":"Noninvasive blood glucose monitoring with optical coherence tomography: A pilot study in human subjects","volume":"25","author":"Larin","year":"2002","journal-title":"Diabetes Care"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1016\/j.bspc.2015.01.005","article-title":"Prospects and limitations of non-invasive blood glucose monitoring using near-infrared spectroscopy","volume":"18","author":"Yadav","year":"2015","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_8","first-page":"59","article-title":"The evolution of non-invasive blood glucose monitoring system for personal application","volume":"8","author":"Manap","year":"2016","journal-title":"J. Telecommun. Electron. Comput. Eng."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.artmed.2011.05.001","article-title":"Non-invasive estimate of blood glucose and blood pressure from a photoplethysmograph by means of machine learning techniques","volume":"53","year":"2011","journal-title":"Artif. Intell. Med."},{"key":"ref_10","unstructured":"Blank, T.B., Ruchti, T.L., Lorenz, A.D., Monfre, S.L., Makarewicz, M.R., Mattu, M., and Hazen, K. (2002, January 23). Clinical results from a noninvasive blood glucose monitor. Proceedings of the Optical Diagnostics and Sensing of Biological Fluids and Glucose and Cholesterol Monitoring II, San Jose, CA, USA."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Paul, B., Manuel, M.P., and Alex, Z.C. (2012, January 6). Design and development of non invasive glucose measurement system. Proceedings of the 2012 1st International Symposium on Physics and Technology of Sensors (ISPTS-1), Pune, India.","DOI":"10.1109\/ISPTS.2012.6260873"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ramasahayam, S., Arora, L., Chowdhury, S.R., and Anumukonda, M. (2015, January 8\u201310). FPGA based system for blood glucose sensing using photoplethysmography and online motion artifact correction using adaline. Proceedings of the 2015 9th International Conference on Sensing Technology (ICST), Auckland, New Zealand.","DOI":"10.1109\/ICSensT.2015.7438358"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1016\/j.snb.2019.01.121","article-title":"Wearable-band type visible-near infrared optical biosensor for non-invasive blood glucose monitoring","volume":"286","author":"Rachim","year":"2019","journal-title":"Sens. Actuators B Chem."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1366\/000370206776593780","article-title":"New methodology to obtain a calibration model for noninvasive near-infrared blood glucose monitoring","volume":"60","author":"Maruo","year":"2006","journal-title":"Appl. Spectrosc."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1016\/j.bpa.2014.08.006","article-title":"Photoplethysmography","volume":"28","author":"Alian","year":"2014","journal-title":"Best Prac. Res. Clin. Anaesthesiol."},{"key":"ref_16","unstructured":"Jain, P., Joshi, A.M., and Mohanty, S.P. (2019). iGLU 1.0: An Accurate Non-Invasive Near-Infrared Dual Short Wavelengths Spectroscopy based Glucometer for Smart Healthcare. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Bunescu, R., Struble, N., Marling, C., Shubrook, J., and Schwartz, F. (2013, January 4\u20137). Blood glucose level prediction using physiological models and support vector regression. Proceedings of the 2013 12th International Conference on Machine Learning and Applications, Miami, FL, USA.","DOI":"10.1109\/ICMLA.2013.30"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Georga, E.I., Protopappas, V.C., Polyzos, D., and Fotiadis, D.I. (December, January 28). A predictive model of subcutaneous glucose concentration in type 1 diabetes based on random forests. Proceedings of the 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, San Diego, CA, USA.","DOI":"10.1109\/EMBC.2012.6346567"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1080\/00031305.1992.10475879","article-title":"An introduction to kernel and nearest-neighbor nonparametric regression","volume":"46","author":"Altman","year":"1992","journal-title":"Am. Stat."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Tomczak, J.M. (2017). Gaussian process regression with categorical inputs for predicting the blood glucose level. Advances in Systems Science, Springer International Publishing.","DOI":"10.1007\/978-3-319-48944-5_10"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Yadav, J., Rani, A., Singh, V., and Mohan Murari, B. (2017). Investigations on multisensor-based noninvasive blood glucose measurement system. J. Med. Devices, 11.","DOI":"10.1115\/1.4036580"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2436","DOI":"10.1093\/eurheartj\/eht149","article-title":"Diabetes and vascular disease: Pathophysiology, clinical consequences, and medical therapy: Part I","volume":"34","author":"Paneni","year":"2013","journal-title":"Eur. Heart J."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Benichou, T., Pereira, B., Mermillod, M., Tauveron, I., Pfabigan, D., Maqdasy, S., and Dutheil, F. (2018). Heart rate variability in type 2 diabetes mellitus: A systematic review and meta-analysis. PLoS ONE, 13.","DOI":"10.1371\/journal.pone.0195166"},{"key":"ref_24","unstructured":"World Health Organization (2011). Use of glycated haemoglobin (HbA1c) in the diagnosis of diabetes mellitus: Abbreviated report of a WHO consultation. WHO Guidelines Approved by the Guidelines Review Committee, World Health Organization."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"8","DOI":"10.11648\/j.bsi.20210601.12","article-title":"One-minute finger pulsation measurement for diabetes rapid screening with 1.3% to 13% false-negative prediction rate","volume":"6","author":"Chu","year":"2021","journal-title":"Biomed. Stat. Inform."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"662","DOI":"10.1109\/TBME.2002.1010849","article-title":"A real-time algorithm for the quantification of blood pressure waveforms","volume":"49","author":"Navakatikyan","year":"2002","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1109\/TPAMI.2007.56","article-title":"Robust object recognition with cortex-like mechanisms","volume":"29","author":"Serre","year":"2007","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7\u201312). Going deeper with convolutions. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.1038\/14819","article-title":"Hierarchical models of object recognition in cortex","volume":"2","author":"Riesenhuber","year":"1999","journal-title":"Nat. Neurosci."},{"key":"ref_30","unstructured":"Serre, T., Kouh, M., Cadieu, C., Knoblich, U., Kreiman, G., and Poggio, T. (2021, November 17). A Theory of Object Recognition: Computations and Circuits in the Feedforward Path of the Ventral Stream in Primate Visual Cortex. MIT-CSAIL-TR-2005-082. Available online: https:\/\/dspace.mit.edu\/handle\/1721.1\/36407."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"107398","DOI":"10.1016\/j.ymssp.2020.107398","article-title":"1D convolutional neural networks and applications: A survey","volume":"151","author":"Kiranyaz","year":"2021","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_32","doi-asserted-by":"crossref","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","year":"1987","journal-title":"Diabetes Care"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3130919","article-title":"SugarMate: Non-intrusive blood glucose monitoring with smartphones","volume":"1","author":"Gu","year":"2017","journal-title":"Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"733810","DOI":"10.3389\/fbioe.2021.733810","article-title":"Advances in biosensors for continuous glucose monitoring towards wearables","volume":"9","author":"Johnston","year":"2021","journal-title":"Front. Bioeng. Biotechnol."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/23\/7815\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:35:11Z","timestamp":1760168111000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/23\/7815"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,24]]},"references-count":34,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["s21237815"],"URL":"https:\/\/doi.org\/10.3390\/s21237815","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,24]]}}}