{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T04:30:48Z","timestamp":1786681848343,"version":"build-2736575974"},"reference-count":23,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T00:00:00Z","timestamp":1786665600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Physiol."],"abstract":"<jats:p>During flight, pilots are exposed to unique environmental factors such as low air pressure, acceleration, and psychological stress, which can lead to altered glucose metabolism that poses a threat to flight safety. Traditional fingerstick blood glucose monitoring has drawbacks such as the need for intermittent readings, time-consuming procedures, and passive monitoring. Conventional continuous glucose monitoring (CGM) can only display historical and real-time glucose data and lacks predictive capabilities. In the present study, an artificial intelligence (AI)-driven blood glucose prediction system for pilots based on CGM and a multimodal transformer was developed with the aim of achieving proactive early warning of blood glucose risks among pilots. Sixty healthy male volunteers aged 25\u201350 years were recruited. Subjects completed 180 simulated flight experiments, during which multimodal data such as CGM glucose level, heart rate, blood oxygen saturation, and physical activity levels, were simultaneously collected to establish a scenario-specific dataset in aviation. A multimodal transformer model was developed to predict future blood glucose levels at 15, 30, and 60\u00a0min, and its performance was compared with baseline models such as linear extrapolation, long short-term memory (LSTM), and gated recurrent unit (GRU).The results showed that the mean absolute percentage error (MAPE) of the model for the prediction of blood glucose at 30\u00a0min was 7.2%, and the root mean square error (RMSE) was 9.4 mg\/dL, which indicated a significantly superior prediction performance compared with the baseline models. For hypoglycemia event prediction, sensitivity was 92.5%, specificity was 89.7%, and the area under the receiver operating characteristic (ROC) curve was 0.94.\u00a0A Clarke error grid analysis revealed that 98.7% of the predicted points fell within the clinically accurate region, which could potentially provide pilots with approximately 32\u00a0min of lead time for intervention. This system proved capable of accurately predicting blood glucose fluctuations during flight. Therefore, it may aid in shifting the metabolic health management of pilots from passive monitoring to proactive prevention, and serve as a novel tool for assuring aviation medical safety.<\/jats:p>","DOI":"10.3389\/fphys.2026.1902975","type":"journal-article","created":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T04:22:47Z","timestamp":1786681367000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and validation of an AI-driven blood glucose prediction system for pilots based on continuous glucose monitoring"],"prefix":"10.3389","volume":"17","author":[{"given":"Dalong","family":"Guo","sequence":"first","affiliation":[{"name":"Air Force Medical Center, Air Force Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangyun","family":"Wang","sequence":"additional","affiliation":[{"name":"Air Force Medical Center, Air Force Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dexin","family":"Kong","sequence":"additional","affiliation":[{"name":"Guangzhou Institute of Technology, Xidian University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Tian","sequence":"additional","affiliation":[{"name":"Air Force Medical Center, Air Force Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baosen","family":"Tan","sequence":"additional","affiliation":[{"name":"Air Force Medical Center, Air Force Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufei","family":"Qin","sequence":"additional","affiliation":[{"name":"Air Force Medical Center, Air Force Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoting","family":"Yang","sequence":"additional","affiliation":[{"name":"Air Force Medical Center, Air Force Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yubin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Air Force Medical Center, Air Force Medical University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haocheng","family":"Yin","sequence":"additional","affiliation":[{"name":"Guangzhou Institute of Technology, Xidian University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yimeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Key Laboratory of Wide Band-Gap Semiconductor Materials and Devices, Xidian University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,14]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2025.101033","article-title":"Cyber\u2013physical\u2013human systems in precision medicine: advances in artificial pancreas for treatment of diabetes","volume":"60","author":"Ahmadasas","year":"2025","journal-title":"Annu. Rev. Control"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1456","DOI":"10.1177\/19322968231204884","article-title":"Multivariable automated insulin delivery system for handling planned and spontaneous physical activities","volume":"17","author":"Askari","year":"2023","journal-title":"J. Diabetes Sci. Technol."},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2024.1342744","article-title":"Exploratory insights into prefrontal cortex activity in continuous glucose monitoring: findings from a portable wearable functional near-infrared spectroscopy system","volume":"18","author":"Chen","year":"2024","journal-title":"Front. Neurosci."},{"key":"B4","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","year":"1987","journal-title":"Diabetes Care"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2147\/jmdh.s572696","article-title":"Type 2 diabetes-related complications among commercial pilots: aeromedical considerations from a retrospective cohort","volume":"19","author":"Demir","year":"2026","journal-title":"J. Multidiscip. Healthc."},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1007\/s00125-025-06364-z","article-title":"Comparison of continuous glucose monitoring with self-monitoring of blood glucose in type 1 diabetes in the changing atmospheric pressures in aviation: a hypobaric flight simulation","volume":"68","author":"Fan","year":"2025","journal-title":"Diabetologia"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1111\/dme.15472","article-title":"The practical operation and consequences of glucose measurement by pilots with diabetes","volume":"42","author":"Fan","year":"2024","journal-title":"Diabet. Med."},{"key":"B8","first-page":"1","article-title":"Attengluco: multimodal transformer-based blood glucose forecasting on ai-readi dataset","author":"Farahmand","year":"2025"},{"key":"B9","doi-asserted-by":"publisher","first-page":"612","DOI":"10.1038\/s41746-025-01994-4","article-title":"Generalized multi task learning framework for glucose forecasting and hypoglycemia detection using simulation to reality","volume":"8","author":"Hwang","year":"2025","journal-title":"NPJ Digit. Med."},{"key":"B10","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1893\/0005-3155(2007)78[95:eolbgo]2.0.co;2","article-title":"Research article: effects of low blood glucose on pilot performance","volume":"78","author":"Johnson","year":"2007","journal-title":"BIOS"},{"key":"B11","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/j.metabol.2009.07.014","article-title":"Acute altitude-induced hypoxia suppresses plasma glucose and leptin in healthy humans","volume":"59","author":"Kelly","year":"2010","journal-title":"Metabolism"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics14070740","article-title":"Machine learning and deep learning models for nocturnal high- and low-glucose prediction in adults with type 1 diabetes","volume":"14","author":"Kozinetz","year":"2024","journal-title":"Diagnostics"},{"key":"B13","doi-asserted-by":"crossref","DOI":"10.1152\/japplphysiol.91523.2008","article-title":"Effects of acute intermittent hypoxia on glucose metabolism in awake healthy volunteers","volume-title":"J. Appl. Physiol","author":"Louis","year":"2009"},{"key":"B14","first-page":"2412.09727","article-title":"Let Curves Speak: A Continuous Glucose Monitor based Large Sensor Foundation Model for Diabetes Management","volume-title":"arXiv preprint","author":"Luo","year":"2024"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09925-9","article-title":"A foundation model for continuous glucose monitoring data","volume":"650","author":"Lutsker","year":"2026","journal-title":"Nature"},{"key":"B16","doi-asserted-by":"publisher","first-page":"613","DOI":"10.3934\/bioeng.2025028","article-title":"Translational design and clinical validation of a non-invasive glucose monitor based on oxygen saturation and heart rate signals","volume":"12","author":"Mahmood","year":"2025","journal-title":"AIMS Bioeng."},{"key":"B17","doi-asserted-by":"publisher","first-page":"2245","DOI":"10.1111\/dom.70418","article-title":"Performance of continuous glucose monitoring systems (cgms) during commercial flights in t1dm: a within\u2010subject comparative pilot study","volume":"28","author":"Me\u00e7ani","year":"2026","journal-title":"Diabetes Obes. Metab."},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.3390\/s25154647","article-title":"Incorporating uncertainty estimation and interpretability in personalized glucose prediction using the temporal fusion transformer","volume":"25","author":"Rodriguez-Almeida","year":"2025","journal-title":"Sensors"},{"key":"B19","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1186\/s12911-025-03224-z","article-title":"Gpt-4o and the quest for machine learning interpretability in icu risk of death prediction","volume":"25","author":"Samadi","year":"2025","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"B20","doi-asserted-by":"publisher","first-page":"1642","DOI":"10.1001\/jamainternmed.2019.3806","article-title":"Patient perceptions of diabetes guideline frameworks for individualizing glycemic targets","volume":"179","author":"Schoenborn","year":"2019","journal-title":"JAMA Intern. Med."},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2021.665821","article-title":"Hypoxic hypoxia and brain function in military aviation: basic physiology and applied perspectives","volume":"12","author":"Shaw","year":"2021","journal-title":"Front. Physiol."},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1101\/2025.07.12.25331188","article-title":"Empowering digital health management with on-device large language models for glucose prediction","volume":"129","author":"Zhu","year":"2025","journal-title":"medRxiv"},{"key":"B23","doi-asserted-by":"publisher","first-page":"2744","DOI":"10.1109\/jbhi.2020.3040225","article-title":"Deep learning for diabetes: a systematic review","volume":"25","author":"Zhu","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1902975\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T04:22:48Z","timestamp":1786681368000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1902975\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,14]]},"references-count":23,"alternative-id":["10.3389\/fphys.2026.1902975"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2026.1902975","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,14]]},"article-number":"1902975"}}