{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T18:42:08Z","timestamp":1785436928161,"version":"3.56.0"},"reference-count":45,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T00:00:00Z","timestamp":1780876800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002341","name":"Research Council of Finland","doi-asserted-by":"publisher","award":["369116"],"award-info":[{"award-number":["369116"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]},{"award":["369116"],"award-info":[{"award-number":["369116"]}],"id":[{"id":"https:\/\/ror.org\/05k73zm37","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Sepsis is life-threatening organ dysfunction caused by a dysregulated host response to infection, making early detection critical for improving outcomes in intensive care units (ICUs). This study presents a retrospective comparative evaluation of deep learning architectures for predicting sepsis up to 6 h before the PhysioNet\/Computing in Cardiology 2019 Challenge onset label using hourly structured electronic health record (EHR) variables, including vital signs, laboratory measurements, and demographics. Evaluated architectures include Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Bidirectional Long Short-Term Memory (Bi-LSTM), Temporal Convolutional Network (TCN), Transformer, and hybrid Convolutional Neural Network\u2013Vision Transformer (CNN-ViT) models. Median imputation and class-weighted loss were applied to address missing values and severe class imbalance, while Shapley Additive Explanations (SHAP) and attention analyses were used as complementary interpretability approaches. Among the evaluated models, CNN-ViT achieved the strongest overall minority-class performance, with 88.25% accuracy, 0.7480 recall, a 0.454 F1-score, and a 0.48 area under the precision\u2013recall curve (AUPRC), although the numerical gains over other advanced temporal and hybrid architectures were modest. Leave-one-unit-out evaluation further demonstrated relatively stable performance under internal distribution shifts. The results suggest that combining local feature extraction with temporal and attention-based modeling can improve early sepsis prediction from structured ICU data. However, the study represents a retrospective computational benchmark using a public dataset and does not constitute prospective clinical validation or real-world deployment assessment.<\/jats:p>","DOI":"10.3390\/s26123648","type":"journal-article","created":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T10:04:14Z","timestamp":1780913054000},"page":"3648","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Early Sepsis Detection Using Heterogeneous Structured ICU Data with Explainable Deep Learning"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5991-8858","authenticated-orcid":false,"given":"Attaphongse","family":"Taparugssanagorn","sequence":"first","affiliation":[{"name":"Faculty of Advanced Science and Technology, Asian Institute of Technology, Pathum Thani 12120, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6967-1908","authenticated-orcid":false,"given":"Mariella","family":"S\u00e4rest\u00f6niemi","sequence":"additional","affiliation":[{"name":"Health Science and Technology, Faculty of Medicine, University of Oulu, FI-90014 Oulu, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6115-5255","authenticated-orcid":false,"given":"Matti","family":"H\u00e4m\u00e4l\u00e4inen","sequence":"additional","affiliation":[{"name":"Centre for Wireless Communications, University of Oulu, FI-90014 Oulu, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6420-1547","authenticated-orcid":false,"given":"Jari","family":"Iinatti","sequence":"additional","affiliation":[{"name":"Centre for Wireless Communications, University of Oulu, FI-90014 Oulu, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Islam, K.R., Prithula, J., Kumar, J., Tan, T.L., Reaz, M.B.I., Sumon, M.S.I., and Chowdhury, M.E.H. (2023). Machine learning-based early prediction of sepsis using electronic health records: A systematic review. J. Clin. Med., 12.","DOI":"10.3390\/jcm12175658"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1016\/j.cmi.2020.02.022","article-title":"Interventions for rapid recognition and treatment of sepsis in the emergency department: A narrative review","volume":"27","author":"Uffen","year":"2021","journal-title":"Clin. Microbiol. Infect."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1016\/j.jelectrocard.2017.08.013","article-title":"Early sepsis detection in critical care patients using multiscale blood pressure and heart rate dynamics","volume":"50","author":"Shashikumar","year":"2017","journal-title":"J. Electrocardiol."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Yang, Z., Cui, X., and Song, Z. (2023). Predicting sepsis onset in ICU using machine learning models: A systematic review and meta-analysis. BMC Infect. Dis., 23.","DOI":"10.1186\/s12879-023-08614-0"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e28","DOI":"10.2196\/medinform.5909","article-title":"Prediction of sepsis in the intensive care unit with minimal electronic health record data: A machine learning approach","volume":"4","author":"Desautels","year":"2016","journal-title":"JMIR Med. Inform."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1186\/s40635-025-00765-5","article-title":"Explainable machine learning models for mortality prediction in patients with sepsis in tertiary care hospital ICU in low- to middle-income countries","volume":"13","author":"Diwan","year":"2025","journal-title":"Intensive Care Med. Exp."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"104504","DOI":"10.1016\/j.jbi.2023.104504","article-title":"Prognostic models of in-hospital mortality of intensive care patients using neural representation of unstructured text: A systematic review and critical appraisal","volume":"146","author":"Vagliano","year":"2023","journal-title":"J. Biomed. Inform."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1097\/CCM.0000000000004145","article-title":"Early prediction of sepsis from clinical data: The PhysioNet\/Computing in Cardiology Challenge 2019","volume":"48","author":"Reyna","year":"2020","journal-title":"Crit. Care Med."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"15132","DOI":"10.1038\/s41598-019-51219-4","article-title":"LiSep LSTM: A machine learning algorithm for early detection of septic shock","volume":"9","author":"Wilhelms","year":"2019","journal-title":"Sci. Rep."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1038\/s41467-021-20910-4","article-title":"Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare","volume":"12","author":"Goh","year":"2021","journal-title":"Nat. Commun."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Umezuruike, C., Olaniyan, D., Olaniyan, J., Adeniyi, A.E., Oyebade, A., and Abaneme, D. (2024, January 26\u201328). Comparative analysis of long short-term memory (LSTM), gated recurrent unit (GRU) and transformer models in predicting stock prices. Proceedings of the 2024 IEEE 5th International Conference on Electro-Computing Technologies for Humanity (NIGERCON), Ado Ekiti, Nigeria.","DOI":"10.1109\/NIGERCON62786.2024.10927198"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"13705","DOI":"10.1007\/s00521-021-06007-5","article-title":"Dilated causal convolution with multi-head self-attention for human activity recognition","volume":"33","author":"Hamad","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","article-title":"A survey of vision transformers","volume":"45","author":"Han","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_15","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021, January 3\u20137). An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale. Proceedings of the International Conference on Learning Representations (ICLR), Virtual Event."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., and Zhang, L. (2021). CvT: Introducing convolutions to vision transformers. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref_17","first-page":"2286","article-title":"ConViT: Improving vision transformers with soft convolutional inductive biases","volume":"Volume 139","author":"Touvron","year":"2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning (ICML)"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"110491","DOI":"10.1016\/j.patcog.2024.110491","article-title":"UCTNet: Uncertainty-guided CNN-Transformer hybrid networks for medical image segmentation","volume":"152","author":"Guo","year":"2024","journal-title":"Pattern Recognit."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"110057","DOI":"10.1016\/j.engappai.2025.110057","article-title":"Exploring the synergies of hybrid convolutional neural network and vision transformer architectures for computer vision: A survey","volume":"144","author":"Haruna","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1186\/s12967-025-06862-z","article-title":"Multi-stream feature fusion of vision transformer and CNN for precise epileptic seizure detection from EEG signals","volume":"23","author":"Li","year":"2025","journal-title":"J. Transl. Med."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1748","DOI":"10.1016\/j.ijforecast.2021.03.012","article-title":"Temporal fusion transformers for interpretable multi-horizon time series forecasting","volume":"37","author":"Lim","year":"2021","journal-title":"Int. J. Forecast."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"7155","DOI":"10.1038\/s41598-020-62922-y","article-title":"BEHRT: Transformer for electronic health records","volume":"10","author":"Li","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1038\/s41746-021-00504-6","article-title":"Artificial intelligence sepsis prediction algorithm learns to say \u2018I don\u2019t know\u2019","volume":"4","author":"Shashikumar","year":"2021","journal-title":"npj Digit. Med."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1038\/s41746-023-00986-6","article-title":"Impact of a deep learning sepsis prediction model on quality of care and survival","volume":"7","author":"Boussina","year":"2024","journal-title":"npj Digit. Med."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1007\/s00371-018-1582-y","article-title":"Learning a convolutional neural network for propagation-based stereo image segmentation","volume":"36","author":"Li","year":"2020","journal-title":"Vis. Comput."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"119363","DOI":"10.1016\/j.ins.2023.119363","article-title":"Multi-view computable online learner modeling by heterogeneous network: An AI-enabled perspective","volume":"645","author":"Zhao","year":"2023","journal-title":"Inf. Sci."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention (MICCAI), Springer. LNCS 9351.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Siddiquee, M.M.R., Tajbakhsh, N., and Liang, J. (2018). UNet++: A nested U-Net architecture for medical image segmentation. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Springer. LNCS 11045.","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"103280","DOI":"10.1016\/j.media.2024.103280","article-title":"TransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformers","volume":"97","author":"Chen","year":"2024","journal-title":"Med. Image Anal."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Cao, H., Wang, Y., Chen, J., Jiang, D., Zhang, X., Tian, Q., and Wang, M. (2023). Swin-Unet: Unet-like pure transformer for medical image segmentation. Computer Vision\u2014ECCV 2022 Workshops, Springer. LNCS 13803.","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Roy, S., Koehler, G., Ulrich, C., Baumgartner, M., Petersen, J., Isensee, F., J\u00e4ger, P.F., and Maier-Hein, K.H. (2023). MedNeXt: Transformer-driven scaling of ConvNets for medical image segmentation. Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2023, Springer. LNCS 14223.","DOI":"10.1007\/978-3-031-43901-8_39"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"108559","DOI":"10.1016\/j.compbiomed.2024.108559","article-title":"ConvMedSegNet: A multi-receptive field depthwise convolutional neural network for medical image segmentation","volume":"174","author":"Peng","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"107936","DOI":"10.1016\/j.patcog.2021.107936","article-title":"A survey on heterogeneous network representation learning","volume":"116","author":"Xie","year":"2021","journal-title":"Pattern Recognit."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1773","DOI":"10.1038\/s41591-022-01981-2","article-title":"Multimodal biomedical AI","volume":"28","author":"Acosta","year":"2022","journal-title":"Nat. Med."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"101805","DOI":"10.1016\/j.inffus.2023.101805","article-title":"Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence","volume":"99","author":"Ali","year":"2023","journal-title":"Inf. Fusion"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1007\/s10462-024-10852-w","article-title":"A review of evaluation approaches for explainable AI with applications in cardiology","volume":"57","author":"Salih","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1038\/s41746-024-01166-w","article-title":"A multi-center study on the adaptability of a shared foundation model for electronic health records","volume":"7","author":"Guo","year":"2024","journal-title":"npj Digit. Med."},{"key":"ref_38","unstructured":"Gu, A., and Dao, T. (2024, January 7\u20139). Mamba: Linear-time sequence modeling with selective state spaces. Proceedings of the First Conference on Language Modeling (COLM), Philadelphia, PA, USA."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1186\/s40537-024-01001-9","article-title":"CMMamba: Channel mixing Mamba for time series forecasting","volume":"11","author":"Li","year":"2024","journal-title":"J. Big Data"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/s10462-024-10884-2","article-title":"Handling imbalanced medical datasets: Review of a decade of research","volume":"57","author":"Salmi","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"6086","DOI":"10.1038\/s41598-024-56706-x","article-title":"Evaluation metrics and statistical tests for machine learning","volume":"14","author":"Rainio","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic analysis of performance measures for classification tasks","volume":"45","author":"Sokolova","year":"2009","journal-title":"Inf. Process. Manag."},{"key":"ref_43","first-page":"73","article-title":"A review of the F-measure: Its history, properties, criticism, and alternatives","volume":"56","author":"Christen","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Mu\u015fat, F., P\u0103duraru, D.N., Bolocan, A., Palc\u0103u, C.A., Cop\u0103ceanu, A.-M., Ion, D., Jinga, V., and Andronic, O. (2024). Machine learning models in sepsis outcome prediction for ICU patients: Integrating routine laboratory tests\u2014A systematic review. Biomedicines, 12.","DOI":"10.3390\/biomedicines12122892"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"16245","DOI":"10.1038\/s41598-023-43380-8","article-title":"A study of dealing class imbalance problem with machine learning methods for code smell severity detection using PCA-based feature selection technique","volume":"13","author":"Rao","year":"2023","journal-title":"Sci. Rep."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/12\/3648\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T10:08:59Z","timestamp":1780913339000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/12\/3648"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,8]]},"references-count":45,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["s26123648"],"URL":"https:\/\/doi.org\/10.3390\/s26123648","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,8]]}}}