{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:11:26Z","timestamp":1758672686398,"version":"3.44.0"},"reference-count":47,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:00:00Z","timestamp":1758585600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:00:00Z","timestamp":1758585600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"L\u2019Oreal-UNESCO UK and Ireland","award":["For Women in Science Rising Talent"],"award-info":[{"award-number":["For Women in Science Rising Talent"]}]},{"DOI":"10.13039\/501100000761","name":"Imperial College London","doi-asserted-by":"crossref","award":["President\u2019s PhD Scholarship"],"award-info":[{"award-number":["President\u2019s PhD Scholarship"]}],"id":[{"id":"10.13039\/501100000761","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100014013","name":"UK Research and Innovation","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000287","name":"Royal Academy of Engineering","doi-asserted-by":"crossref","award":["Research Fellowship"],"award-info":[{"award-number":["Research Fellowship"]}],"id":[{"id":"10.13039\/501100000287","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000833","name":"Rosetrees Trust","doi-asserted-by":"crossref","award":["Research Fellowship"],"award-info":[{"award-number":["Research Fellowship"]}],"id":[{"id":"10.13039\/501100000833","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000700","name":"Royal Commission for the Exhibition of 1851","doi-asserted-by":"crossref","award":["Research Fellowship"],"award-info":[{"award-number":["Research Fellowship"]}],"id":[{"id":"10.13039\/501100000700","id-type":"DOI","asserted-by":"crossref"}]},{"name":"ERC-EPSRC Frontier Research Guarantee","award":["EP\/X038645"],"award-info":[{"award-number":["EP\/X038645"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2025,9,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Accurately predicting blood glucose dynamics is crucial for understanding metabolic regulation and advancing bioelectronic medicine. The vagus nerve (VN) plays a key role in glucose homeostasis, yet its real-time relationship with blood glucose fluctuations remains underexplored. We introduce neural controlled differential equations (NCDEs) as a novel data-driven approach for modelling the complex interaction between VN activity and blood glucose levels in rats. We utilise data collected from 12 rats including high-frequency neural recordings from single-channel microwire electrodes implanted around the left cervical VN, alongside capillary blood glucose measurements taken every 5 min. We compare the performance of the NCDE against traditional machine learning models\u2013feed-forward neural networks (FFNNs), convolutional neural networks (CNNs) and gated recurrent units (GRUs)\u2014 for forecasting future blood glucose levels. The input features comprised the frequency and mean amplitude of detected VN spikes, combined with initial glucose concentration over the prediction window. Results demonstrate that NCDE significantly outperforms FFNNs, CNNs, and GRUs achieving a mean squared error (MSE) below 10%, compared to over 15% for the baseline models. Furthermore, replacing the real neural recordings with random noise led to a sharp increase in MSE (over 20%), confirming the ability of the NCDE in extracting meaningful neural signal information. These findings underscore the potential of NCDEs to enhance physiological time-series modelling, particularly for applications in bioelectronic medicine and precision neural signal decoding.<\/jats:p>","DOI":"10.1088\/2632-2153\/ae023f","type":"journal-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T23:48:32Z","timestamp":1756856912000},"page":"035062","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Data-driven prediction of blood glucose dynamics from vagus nerve recordings using neural controlled differential equations"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1583-481X","authenticated-orcid":true,"given":"Antonio","family":"Malpica-Morales","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9858-3504","authenticated-orcid":true,"given":"Serafim","family":"Kalliadasis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4582-8501","authenticated-orcid":true,"given":"George G","family":"Malliaras","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4206-6812","authenticated-orcid":true,"given":"Amparo","family":"G\u00fcemes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2025,9,23]]},"reference":[{"key":"mlstae023fbib1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.mpmed.2018.10.002","type":"journal-article","article-title":"What is diabetes?","volume":"47","author":"Egan","year":"2019","journal-title":"Medicine"},{"key":"mlstae023fbib2","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1016\/S0140-6736(23)01301-6","type":"journal-article","article-title":"Global, regional and national burden of diabetes from 1990 to 2021, with projections of prevalence to 2050: a systematic analysis for the global burden of disease study 2021","volume":"402","author":"Ong","year":"2023","journal-title":"Lancet"},{"key":"mlstae023fbib3","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0253125","type":"journal-article","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":"mlstae023fbib4","doi-asserted-by":"publisher","first-page":"4191","DOI":"10.1007\/s00521-020-05248-0","type":"journal-article","article-title":"Long short-term memory neural network for glucose prediction","volume":"33","author":"Carrillo-Moreno","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"mlstae023fbib5","first-page":"pp 77","type":"conference-proceedings","article-title":"Glucose prediction based on the recurrent neural network model","author":"Zhang","year":"2023"},{"key":"mlstae023fbib6","doi-asserted-by":"publisher","first-page":"1251","DOI":"10.1109\/JBHI.2018.2840690","type":"journal-article","article-title":"An ARIMA model with adaptive orders for predicting blood glucose concentrations and hypoglycemia","volume":"23","author":"Yang","year":"2019","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"mlstae023fbib7","first-page":"pp 135","type":"conference-proceedings","article-title":"Blood glucose level prediction using physiological models and support vector regression","author":"Bunescu","year":"2013"},{"key":"mlstae023fbib8","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899X\/803\/1\/012012","type":"journal-article","article-title":"Blood glucose prediction model for type 1 diabetes based on extreme gradient boosting","volume":"803","author":"Alfian","year":"2020","journal-title":"IOP Conf. Ser.: Mater. Sci. Eng."},{"key":"mlstae023fbib9","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ad861d","type":"journal-article","article-title":"Machine-learning-based diabetes classification method using blood flow oscillations and pearson correlation analysis of feature importance","volume":"5","author":"Jung","year":"2024","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstae023fbib10","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1089\/dia.2009.0076","type":"journal-article","article-title":"Artificial neural network algorithm for online glucose prediction from continuous glucose monitoring","volume":"12","author":"P\u00e9rez-Gand\u00eda","year":"2010","journal-title":"Diabetes Technol. Ther."},{"key":"mlstae023fbib11","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1109\/JBHI.2019.2931842","type":"journal-article","article-title":"Glunet: a deep learning framework for accurate glucose forecasting","volume":"24","author":"Li","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"mlstae023fbib12","first-page":"pp 1124","type":"conference-proceedings","article-title":"Glucose prediction for type 1 diabetes using KLMS algorithm","author":"Sun","year":"2017"},{"key":"mlstae023fbib13","doi-asserted-by":"publisher","first-page":"905","DOI":"10.1088\/0967-3334\/25\/4\/010","type":"journal-article","article-title":"Nonlinear model predictive control of glucose concentration in subjects with type 1 diabetes","volume":"25","author":"Hovorka","year":"2004","journal-title":"Physiol. Meas."},{"key":"mlstae023fbib14","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1109\/JBHI.2019.2908488","type":"journal-article","article-title":"Convolutional recurrent neural networks for glucose prediction","volume":"24","author":"Li","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"mlstae023fbib15","first-page":"pp 188","type":"conference-proceedings","article-title":"Glucose prediction data analytics for diabetic patients monitoring","author":"Huzooree","year":"2017"},{"key":"mlstae023fbib16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s42234-019-0025-z","type":"journal-article","article-title":"Identification of hypoglycemia-specific neural signals by decoding murine vagus nerve activity","volume":"5","author":"Masi","year":"2019","journal-title":"Bioelectron. Med."},{"key":"mlstae023fbib17","doi-asserted-by":"publisher","first-page":"114","DOI":"10.3390\/bios12020114","type":"journal-article","article-title":"Decoding vagus-nerve activity with carbon nanotube sensors in freely moving rodents","volume":"12","author":"Marmerstein","year":"2022","journal-title":"Biosensors"},{"key":"mlstae023fbib18","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/acfdcd","type":"journal-article","article-title":"A multivariate physiological model of vagus nerve signalling during metabolic challenges in anaesthetised rats for diabetes treatment","volume":"20","author":"G\u00fcemes Gonzalez","year":"2023","journal-title":"J. Neural Eng."},{"key":"mlstae023fbib19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-72512-7","type":"journal-article","article-title":"Multi-channel intraneural vagus nerve recordings with a novel high-density carbon fiber microelectrode array","volume":"10","author":"Jiman","year":"2020","journal-title":"Sci. Rep."},{"key":"mlstae023fbib20","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/ac84ab","type":"journal-article","article-title":"A lightweight learning-based decoding algorithm for intraneural vagus nerve activity classification in pigs","volume":"19","author":"Pollina","year":"2022","journal-title":"J. Neural Eng."},{"key":"mlstae023fbib21","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-89624-3","type":"journal-article","article-title":"Classification of directionally specific vagus nerve activity using an upper airway obstruction model in anesthetized rodents","volume":"11","author":"Sabetian","year":"2021","journal-title":"Sci. Rep."},{"key":"mlstae023fbib22","doi-asserted-by":"publisher","first-page":"0460a2","DOI":"10.1088\/1741-2552\/ac0d42","type":"journal-article","article-title":"Simultaneous decoding of cardiovascular and respiratory functional changes from pig intraneural vagus nerve signals","volume":"18","author":"Vallone","year":"2021","journal-title":"J. Neural Eng."},{"key":"mlstae023fbib23","first-page":"pp 27","type":"book","article-title":"Canonical correlation analysis of time series and the use of an information criterion","volume":"vol 126","author":"Akaike","year":"1976"},{"key":"mlstae023fbib24","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1103\/PhysRevLett.85.461","type":"journal-article","article-title":"Measuring information transfer","volume":"85","author":"Schreiber","year":"2000","journal-title":"Phys. Rev. Lett."},{"key":"mlstae023fbib25","doi-asserted-by":"publisher","first-page":"3\u20131-3","DOI":"10.1029\/2000RG000092","type":"journal-article","article-title":"Advanced spectral methods for climatic time series","volume":"40","author":"Ghil","year":"2002","journal-title":"Rev. Geophys."},{"key":"mlstae023fbib26","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac3de0","type":"journal-article","article-title":"Deeptime: a python library for machine learning dynamical models from time series data","volume":"3","author":"Hoffmann","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstae023fbib27","doi-asserted-by":"publisher","first-page":"215","DOI":"10.4171\/rmi\/240","type":"journal-article","article-title":"Differential equations driven by rough signals","volume":"14","author":"Lyons","year":"1998","journal-title":"Rev. Mat. Iberoam"},{"key":"mlstae023fbib28","doi-asserted-by":"publisher","first-page":"12227","DOI":"10.1073\/pnas.1101777108","type":"journal-article","article-title":"Aerosol-cloud-precipitation system as a predator-prey problem","volume":"108","author":"Koren","year":"2011","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstae023fbib29","doi-asserted-by":"publisher","first-page":"6531","DOI":"10.1109\/TNNLS.2022.3210695","type":"journal-article","article-title":"Machine learning memory kernels as closure for non-Markovian stochastic processes","volume":"35","author":"Russo","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"mlstae023fbib30","doi-asserted-by":"publisher","DOI":"10.1063\/5.0189402","type":"journal-article","article-title":"Forecasting with an N-dimensional Langevin equation and a neural-ordinary differential equation","volume":"34","author":"Malpica-Morales","year":"2024","journal-title":"Chaos"},{"key":"mlstae023fbib31","first-page":"pp 6696","type":"conference-proceedings","article-title":"Neural controlled differential equations for irregular time series","volume":"vol 33","author":"Kidger","year":"2020"},{"key":"mlstae023fbib32","doi-asserted-by":"crossref","DOI":"10.1109\/ICDM51629.2021.00035","type":"preprint","article-title":"Attentive neural controlled differential equations for time-series classification and forecasting","author":"Jhin","year":"2021"},{"article-title":"Neural controlled differential equations for online prediction tasks","year":"2021","author":"Morrill","key":"mlstae023fbib33","type":"preprint"},{"key":"mlstae023fbib34","first-page":"pp 385","type":"book","article-title":"Chapter 27\u2014anatomy of the vagus nerve","author":"Camara","year":"2015"},{"key":"mlstae023fbib35","doi-asserted-by":"publisher","DOI":"10.1016\/j.biopsycho.2022.108378","type":"journal-article","article-title":"The multibranched nerve: vagal function beyond heart rate variability","volume":"172","author":"Karemaker","year":"2022","journal-title":"Biol. Psychol."},{"key":"mlstae023fbib36","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/S0169-7439(97)00061-0","type":"journal-article","article-title":"Introduction to multi-layer feed-forward neural networks","volume":"39","author":"Svozil","year":"1997","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"mlstae023fbib37","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1016\/j.patcog.2017.10.013","type":"journal-article","article-title":"Recent advances in convolutional neural networks","volume":"77","author":"Gu","year":"2018","journal-title":"Pattern Recognit."},{"article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling NIPS","year":"2014","author":"Chung","key":"mlstae023fbib38","type":"conference-proceedings"},{"key":"mlstae023fbib39","doi-asserted-by":"publisher","DOI":"10.1016\/j.biopsycho.2023.108626","type":"journal-article","article-title":"Signal processing in the vagus nerve: hypotheses based on new genetic and anatomical evidence","volume":"182","author":"Shaffer","year":"2023","journal-title":"Biol. Psychol."},{"year":"2013","author":"ISO 15197:2013","key":"mlstae023fbib40","type":"other"},{"article-title":"Self-monitoring blood glucose test systems for over-the-counter use: guidance for industry and Food and Drug Administration staff","year":"2016","author":"U S Department of Health and Human Services, U S Food and Drug Administration","key":"mlstae023fbib41","type":"other"},{"key":"mlstae023fbib42","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1186\/s42234-020-00046-4","type":"journal-article","article-title":"Closed-loop bioelectronic medicine for diabetes management","volume":"6","author":"G\u00fcemes Gonzalez","year":"2020","journal-title":"Bioelectron. Med."},{"edition":"2nd edn","year":"1996","author":"Risken","key":"mlstae023fbib43","type":"book"},{"key":"mlstae023fbib44","doi-asserted-by":"publisher","DOI":"10.1063\/5.0071629","type":"journal-article","article-title":"Physics-constrained Bayesian inference of state functions in classical density-functional theory","volume":"156","author":"Yatsyshin","year":"2022","journal-title":"J. Chem. Phys."},{"key":"mlstae023fbib45","doi-asserted-by":"publisher","DOI":"10.1063\/5.0146920","type":"journal-article","article-title":"Physics-informed Bayesian inference of external potentials in classical density-functional theory","volume":"159","author":"Malpica-Morales","year":"2023","journal-title":"J. Chem. Phys."},{"key":"mlstae023fbib46","first-page":"pp 5140","type":"journal-article","article-title":"Short term blood glucose prediction based on continuous glucose monitoring data","author":"Mohebbi","year":"2020"},{"key":"mlstae023fbib47","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.16965885","type":"journal-article","article-title":"Vagus nerve recordings and blood-glucose levels from 12 adult anaesthetised rats","author":"Guemes Gonzalez","year":"2025","journal-title":"Zenodo"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae023f","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae023f\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae023f","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae023f\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae023f\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae023f\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae023f\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae023f\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T08:56:46Z","timestamp":1758617806000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae023f"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,23]]},"references-count":47,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,9,23]]},"published-print":{"date-parts":[[2025,9,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ae023f","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2025,9,23]]},"assertion":[{"value":"Data-driven prediction of blood glucose dynamics from vagus nerve recordings using neural controlled differential equations","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-03-21","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-09-01","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-09-23","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}