{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T05:13:45Z","timestamp":1761801225432,"version":"build-2065373602"},"reference-count":30,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Centro Universitario de Ciencias Exactas e Ingenier\u00edas (CUCEI) of Universidad de Guadalajara"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>One of the main challenges when working with time series captured online using sensors is the appearance of noise or null values, generally caused by sensor failures or temporary disconnections. These errors compromise data reliability and can lead to incorrect decisions. Particularly in the treatment of diabetes mellitus, where medical decisions depend on continuous glucose monitoring (CGM) systems provided by modern sensors, the presence of corrupted data can pose a significant risk to patient health. This work presents an approach that encompasses online detection and imputation of anomalous data using physiological inputs (insulin and carbohydrate intake), which enables decision-making in automatic glucose monitoring systems or for glucose control purposes. Four deep neural network architectures are proposed: CNN-LSTM, GRU, 1D-CNN, and Transformer-LSTM, under a controlled fault injection protocol and compared with the ARIMA model and the Temporal Convolutional Network (TCN). The obtained performance is compared using regression (MAE, RMSE, MARD) and classification (accuracy, precision, recall, F1-score, AUC) metrics. Results show that the CNN-LSTM network is the most effective for fault detection, achieving an F1-score of 0.876 and an accuracy of 0.979. Regarding data imputation, the 1D-CNN network obtained the best performance, with an MAE of 2.96 mg\/dL and an RMSE of 3.75 mg\/dL. Then, validation on the OhioT1DM dataset, containing real CGM data with natural sensor disconnections, showed that the CNN\u2013LSTM model accurately detected anomalies and reliably imputed missing glucose segments under real-world conditions.<\/jats:p>","DOI":"10.3390\/a18110688","type":"journal-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T03:44:39Z","timestamp":1761795879000},"page":"688","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Online Imputation of Corrupted Glucose Sensor Data Using Deep Neural Networks and Physiological Inputs"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8215-6348","authenticated-orcid":false,"given":"Oscar D.","family":"Sanchez","sequence":"first","affiliation":[{"name":"Departamento Acad\u00e9mico de Computaci\u00f3n e Industrial, Universidad Aut\u00f3noma de Guadalajara, Av. Patria 1201, Zapopan 45129, Mexico"}]},{"given":"Eduardo","family":"Mendez-Palos","sequence":"additional","affiliation":[{"name":"Centro Universitario de Ciencias Exactas e Ingenier\u00edas, Universidad de Guadalajara, Blvd. Marcelino Garc\u00eda Barrag\u00e1n 1421, Guadalajara 44430, Mexico"}]},{"given":"Daniel A.","family":"Pascoe","sequence":"additional","affiliation":[{"name":"Centro Universitario de Ciencias Exactas e Ingenier\u00edas, Universidad de Guadalajara, Blvd. Marcelino Garc\u00eda Barrag\u00e1n 1421, Guadalajara 44430, Mexico"}]},{"given":"Hannia M.","family":"Hernandez","sequence":"additional","affiliation":[{"name":"Centro Universitario de Ciencias Exactas e Ingenier\u00edas, Universidad de Guadalajara, Blvd. Marcelino Garc\u00eda Barrag\u00e1n 1421, Guadalajara 44430, Mexico"}]},{"given":"Jesus G.","family":"Alvarez","sequence":"additional","affiliation":[{"name":"Centro Universitario de Ciencias Exactas e Ingenier\u00edas, Universidad de Guadalajara, Blvd. Marcelino Garc\u00eda Barrag\u00e1n 1421, Guadalajara 44430, Mexico"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9600-779X","authenticated-orcid":false,"given":"Alma Y.","family":"Alanis","sequence":"additional","affiliation":[{"name":"Centro Universitario de Ciencias Exactas e Ingenier\u00edas, Universidad de Guadalajara, Blvd. Marcelino Garc\u00eda Barrag\u00e1n 1421, Guadalajara 44430, Mexico"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1109\/RBME.2009.2036073","article-title":"Diabetes: Models, Signals, and Control","volume":"2","author":"Cobelli","year":"2009","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Bian, Q., As\u2019arry, A., Cong, X., Rezali, K.A.b.M., and Raja Ahmad, R.M.K.b. (2024). A hybrid Transformer-LSTM model apply to glucose prediction. PLoS ONE, 19.","DOI":"10.1371\/journal.pone.0310084"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Alanis, A.Y., Alvarez, J.G., Sanchez, O.D., Hernandez, H.M., and Valdivia-G, A. (2024). Fault-Tolerant Closed-Loop Controller Using Online Fault Detection by Neural Networks. Machines, 12.","DOI":"10.3390\/machines12120844"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"van Doorn, W.P.T.M., Foreman, Y.D., Schaper, N.C., Savelberg, H.H.C.M., Koster, A., van der Kallen, C.J.H., Wesselius, A., Schram, M.T., Henry, R.M.A., and Dagnelie, P.C. (2021). Machine learning-based glucose prediction with use of continuous glucose and physical activity monitoring data: The Maastricht Study. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0253125"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"100275","DOI":"10.1016\/j.imu.2019.100275","article-title":"MICE vs PPCA: Missing data imputation in healthcare","volume":"17","author":"Hegde","year":"2019","journal-title":"Inform. Med. Unlocked"},{"key":"ref_6","first-page":"30","article-title":"Multiple imputation with multivariate imputation by chained equation (MICE) package","volume":"4","author":"Zhang","year":"2016","journal-title":"Ann. Transl. Med."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"120201","DOI":"10.1016\/j.eswa.2023.120201","article-title":"Deep learning versus conventional methods for missing data imputation: A review and comparative study","volume":"227","author":"Sun","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.chemolab.2015.04.001","article-title":"Statistical analysis based online sensor failure detection for continuous glucose monitoring in type I diabetes","volume":"144","author":"Zhao","year":"2015","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1109\/JBHI.2019.2908488","article-title":"Convolutional Recurrent Neural Networks for Glucose Prediction","volume":"24","author":"Li","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Alkanhel, R.I., Saleh, H., Elaraby, A., Alharbi, S., Elmannai, H., Alaklabi, S., Alsamhi, S.H., and Mostafa, S. (2024). Hybrid CNN-GRU Model for Real-Time Blood Glucose Forecasting: Enhancing IoT-Based Diabetes Management with AI. Sensors, 24.","DOI":"10.3390\/s24237670"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Dey, R., and Salem, F.M. (2017, January 6\u20139). Gate-Variants of Gated Recurrent Unit (GRU) Neural Networks. Proceedings of the 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS), Boston, MA, USA.","DOI":"10.1109\/MWSCAS.2017.8053243"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Alshehri, O.S., Alshehri, O.M., and Samma, H. (2024, January 27\u201329). Blood Glucose Prediction Using RNN, LSTM, and GRU: A Comparative Study. Proceedings of the 2024 IEEE International Conference on Advanced Systems and Emergent Technologies (IC_ASET), Hammamet, Tunisia.","DOI":"10.1109\/IC_ASET61847.2024.10596176"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Acuna, E., Aparicio, R., and Palomino, V. (2023). Analyzing the Performance of Transformers for the Prediction of the Blood Glucose Level Considering Imputation and Smoothing. Big Data Cogn. Comput., 7.","DOI":"10.3390\/bdcc7010041"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Shi, J., Wang, S., Qu, P., and Shao, J. (2024). Time series prediction model using LSTM-Transformer neural network for mine water inflow. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-69418-z"},{"key":"ref_15","first-page":"110","article-title":"Parametric identification of Sorensen model for glucose-insulin-carbohydrates dynamics using evolutive algorithms","volume":"54","author":"Quiroz","year":"2018","journal-title":"Kybernetika"},{"key":"ref_16","first-page":"e5102","article-title":"Auto Imputation Enabled Deep Temporal Convolutional Network (TCN) Model for PM2.5 Forecasting","volume":"12","author":"Samal","year":"2025","journal-title":"EAI Endorsed Trans. Scalable Inf. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Mu\u00f1oz-Organero, M., Queipo-\u00c1lvarez, P., and Garc\u00eda Guti\u00e9rrez, B. (2021). Learning Carbohydrate Digestion and Insulin Absorption Curves Using Blood Glucose Level Prediction and Deep Learning Models. Sensors, 21.","DOI":"10.3390\/s21144926"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"17104","DOI":"10.1109\/ACCESS.2023.3244712","article-title":"Impact of Nutritional Factors in Blood Glucose Prediction in Type 1 Diabetes Through Machine Learning","volume":"11","author":"Annuzzi","year":"2023","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2447","DOI":"10.1093\/bioinformatics\/bth270","article-title":"Metabolite fingerprinting: Detecting biological features by independent component analysis","volume":"20","author":"Scholz","year":"2004","journal-title":"Bioinformatics"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"19657","DOI":"10.1109\/ACCESS.2023.3246379","article-title":"Real-Time Neural Classifiers for Sensor Faults in Three Phase Induction Motors","volume":"11","author":"Sanchez","year":"2023","journal-title":"IEEE Access"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"470","DOI":"10.1007\/s12020-022-03216-3","article-title":"Accuracy of the intermittently scanned continuous glucose monitoring system in critically ill patients: A prospective, multicenter, observational study","volume":"78","author":"Huang","year":"2022","journal-title":"Endocrine"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Siami-Namini, S., Tavakoli, N., and Siami Namin, A. (2019, January 9\u201312). The Performance of LSTM and BiLSTM in Forecasting Time Series. Proceedings of the 2019 IEEE International Conference on Big Data (Big Data), Los Angeles, CA, USA.","DOI":"10.1109\/BigData47090.2019.9005997"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"650","DOI":"10.1016\/j.procir.2021.03.088","article-title":"A survey on long short-term memory networks for time series prediction","volume":"99","author":"Lindemann","year":"2021","journal-title":"Procedia CIRP"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Shenfield, A., and Howarth, M. (2020). A Novel Deep Learning Model for the Detection and Identification of Rolling Element-Bearing Faults. Sensors, 20.","DOI":"10.3390\/s20185112"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e2022WR033214","DOI":"10.1029\/2022WR033214","article-title":"Deep Learning-Based Rapid Flood Inundation Modeling for Flat Floodplains With Complex Flow Paths","volume":"58","author":"Zhou","year":"2022","journal-title":"Water Resour. Res."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Wen, Q., Zhou, T., Zhang, C., Chen, W., Ma, Z., Yan, J., and Sun, L. (2023). Transformers in Time Series: A Survey. arXiv.","DOI":"10.24963\/ijcai.2023\/759"},{"key":"ref_27","unstructured":"International Organization for Standardization (2013). In Vitro Diagnostic Test Systems\u2014Requirements for Blood-Glucose Monitoring Systems for Self-Testing in Managing Diabetes Mellitus, ISO. Available online: https:\/\/www.iso.org\/standard\/54976.html."},{"key":"ref_28","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_29","unstructured":"Sorensen, J.T. (1985). A Physiologic Model of Glucose Metabolism in Man and Its Use to Design and Assess Improved Insulin Therapies for Diabetes. [Ph.D. Thesis, Massachusetts Institute of Technology]."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"E992","DOI":"10.1152\/ajpendo.00304.2001","article-title":"Partitioning glucose distribution\/transport, disposal, and endogenous production during IVGTT","volume":"282","author":"Hovorka","year":"2002","journal-title":"Am. J. Physiol. Endocrinol. Metab."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/11\/688\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T05:10:15Z","timestamp":1761801015000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/11\/688"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,29]]},"references-count":30,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["a18110688"],"URL":"https:\/\/doi.org\/10.3390\/a18110688","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2025,10,29]]}}}