{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:44:18Z","timestamp":1785545058751,"version":"3.56.0"},"reference-count":30,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Real-time prediction of sepsis is a critical yet highly challenging task. Existing studies face 2 major limitations. First, they often rely on laboratory test results that are not readily available in real time, making timely diagnosis difficult. Second, the patient\u2019s condition evolves as a typical time series, but current methods often adopt coarse modeling strategies, with model architectures that are inefficient to train and deploy effectively.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to develop a prediction model for online sepsis detection using only easily obtainable vital signs, such as heart rate and temperature, with variable-length input sequences while maintaining high predictive performance through the multiscale temporal representation learning.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We propose a deep learning model, Multi-Scale Temporal-aware Contrastive Learning (MSTCL), for efficient sepsis prediction based on the intensive care unit data derived from publicly available databases. We propose a multiscale temporal model to capture both short- and long-term dependencies in variable-length physiological time series. To enhance the robustness of our model, we used contrastive learning techniques that differentiate between positive and negative sepsis progression trajectories. Input features were limited to 6 vital signs, without reliance on laboratory tests or clinical notes.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n The model was evaluated on more than 400 patients with and without sepsis. It achieved an area under the receiver operating characteristic curve of 88.34%, a sensitivity of 89.29%, and a specificity of 73% for predicting sepsis onset based on variable-length vital-sign histories. The normalized mean absolute error for the predicted sepsis onset was 0.11%.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Our proposed model\u2019s low complexity and rapid inference make it suitable for deployment in real-time monitoring systems and low-resource environments. The ability to learn from variable-length historical data enhances the clinical applicability of our model. Furthermore, the methodology of temporal-aware contrastive learning offers a robust and efficient solution for online sepsis detection in diverse clinical settings.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/82762","type":"journal-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T21:12:14Z","timestamp":1781903534000},"page":"e82762-e82762","source":"Crossref","is-referenced-by-count":0,"title":["Online Sepsis Prediction Using Vital Signs and Multiscale Temporal-Aware Contrastive Learning: Model Development and Validation Study"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1006-0423","authenticated-orcid":false,"given":"Xiaoqiong","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0207-8998","authenticated-orcid":false,"given":"Zezhong","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1877-232X","authenticated-orcid":false,"given":"Hanming","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4014-8595","authenticated-orcid":false,"given":"Qianyi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9847-8820","authenticated-orcid":false,"given":"Wei","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4675-2880","authenticated-orcid":false,"given":"Ziqun","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4025-8369","authenticated-orcid":false,"given":"Wenjie","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,6,19]]},"reference":[{"issue":"8","key":"R1","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1001\/jama.2016.0287","article-title":"The third international consensus definitions for sepsis and septic shock (sepsis-3)","volume":"315","author":"Singer","journal-title":"JAMA"},{"issue":"13","key":"R2","doi-asserted-by":"publisher","first-page":"1241","DOI":"10.1001\/jama.2017.13836","article-title":"Incidence and trends of sepsis in US hospitals using clinical vs claims data, 2009-2014","volume":"318","author":"Rhee","journal-title":"JAMA"},{"issue":"1","key":"R3","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.annemergmed.2014.02.023","article-title":"Many emergency department patients with severe sepsis and septic shock do not meet diagnostic criteria within 3 hours of arrival","volume":"64","author":"Villar","journal-title":"Ann Emerg Med"},{"key":"R4","doi-asserted-by":"crossref","unstructured":"Alexandropoulou CA Panagiotopoulos I Kleanthous S et al. AI-enabled solutions, explainability and ethical concerns for predicting sepsis in ICUs: a systematic review. Presented at: 2023 IEEE 19th International Conference on e-Science (e-Science); Oct 9-13, 2023; Limassol, Cyprus. [doi: 10.1109\/e-Science58273.2023.10254863]","DOI":"10.1109\/e-Science58273.2023.10254863"},{"issue":"1","key":"R5","doi-asserted-by":"publisher","first-page":"6","DOI":"10.3390\/make7010006","article-title":"AI advances in ICU with an emphasis on sepsis prediction: an overview","volume":"7","author":"Stylianides","journal-title":"Mach Learn Knowl Extr"},{"issue":"8","key":"R6","doi-asserted-by":"publisher","first-page":"762","DOI":"10.1001\/jama.2016.0288","article-title":"Assessment of clinical criteria for sepsis: for the third international consensus definitions for sepsis and septic shock (sepsis-3)","volume":"315","author":"Seymour","journal-title":"JAMA"},{"issue":"4","key":"R7","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1080\/10903127.2016.1274348","article-title":"qSOFA has poor sensitivity for prehospital identification of severe sepsis and septic shock","volume":"21","author":"Dorsett","journal-title":"Prehosp Emerg Care"},{"issue":"8","key":"R8","doi-asserted-by":"publisher","first-page":"1490","DOI":"10.1016\/j.ajem.2018.10.058","article-title":"Comparison of SIRS, qSOFA, and NEWS for the early identification of sepsis in the emergency department","volume":"37","author":"Usman","journal-title":"Am J Emerg Med"},{"issue":"4","key":"R9","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1097\/CCM.0000000000002936","article-title":"An interpretable machine learning model for accurate prediction of sepsis in the ICU","volume":"46","author":"Nemati","journal-title":"Crit Care Med"},{"key":"R10","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.104110","article-title":"SSP: early prediction of sepsis using fully connected LSTM-CNN model","volume":"128","author":"Rafiei","journal-title":"Comput Biol Med"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2022.964667","article-title":"Machine learning models for predicting in-hospital mortality in patient with sepsis: analysis of vital sign dynamics","volume":"9","author":"Cheng","journal-title":"Front Med (Lausanne)"},{"key":"R12","unstructured":"Vaswani A Shazeer N Parmar N et al. Attention is all you need. In: von Luxburg U Guyon I Bengio S Wallach H Fergus R , editors. NIPS\u201917: Proceedings of the 31st International Conference on Neural Information Processing Systems. Curran Associates Inc; 2017. ISBN: 9781510860964"},{"issue":"1","key":"R13","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-023-02138-6","article-title":"A time series driven model for early sepsis prediction based on transformer module","volume":"24","author":"Tang","journal-title":"BMC Med Res Methodol"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2024.108060","article-title":"A transformer-based diffusion probabilistic model for heart rate and blood pressure forecasting in intensive care unit","volume":"246","author":"Chang","journal-title":"Comput Methods Programs Biomed"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","journal-title":"Sci Data"},{"issue":"2","key":"R16","doi-asserted-by":"publisher","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","journal-title":"Crit Care Med"},{"key":"R17","unstructured":"Kingma DP Ba J . Adam: a method for stochastic optimization. arXiv. Preprint posted online on Dec 22, 2014. [doi: 10.48550\/arXiv.1412.6980]"},{"key":"R18","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103957","article-title":"Automated prediction of sepsis using temporal convolutional network","volume":"127","author":"Kok","journal-title":"Comput Biol Med"},{"key":"R19","doi-asserted-by":"crossref","unstructured":"Li X Andr\u00e9 Ng G Schlindwein F . Convolutional and recurrent neural networks for early detection of sepsis using hourly physiological data from patients in intensive care unit. Presented at: 2019 Computing in Cardiology Conference; Sep 8-11, 2019; Singapore, Singapore. [doi: 10.22489\/CinC.2019.054]","DOI":"10.22489\/CinC.2019.054"},{"issue":"1","key":"R20","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-021-01529-3","article-title":"Kinematics approach with neural networks for early detection of sepsis (KANNEDS)","volume":"21","author":"Cruz","journal-title":"BMC Med Inform Decis Mak"},{"key":"R21","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/6522633","article-title":"Early prediction of sepsis based on machine learning algorithm","volume":"2021","author":"Zhao","journal-title":"Comput Intell Neurosci"},{"key":"R22","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2024.1386760","article-title":"Predictive modeling of biomedical temporal data in healthcare applications: review and future directions","volume":"15","author":"Patharkar","journal-title":"Front Physiol"},{"key":"R23","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2018.09.033","article-title":"Life model: a novel representation of life-long temporal sequences in health predictive analytics","volume":"92","author":"Manashty","journal-title":"Future Gener Comput Syst"},{"key":"R24","doi-asserted-by":"crossref","unstructured":"Liu Y Zhang Z Qin S Salim FD Yepes AJ . Contrastive learning-based imputation-prediction networks for in-hospital mortality risk modeling using EHRs. In: Machine Learning and Knowledge Discovery in Databases: Applied Data Science and Demo Track. Springer Nature; 2023.","DOI":"10.1007\/978-3-031-43427-3_26"},{"issue":"12","key":"R25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2021.100389","article-title":"Contrastive learning improves critical event prediction in COVID-19 patients","volume":"2","author":"Wanyan","journal-title":"Patterns (N Y)"},{"issue":"9","key":"R26","doi-asserted-by":"publisher","first-page":"4221","DOI":"10.3390\/s23094221","article-title":"Self-supervised contrastive learning for medical time series: a systematic review","volume":"23","author":"Liu","journal-title":"Sensors (Basel)"},{"key":"R27","volume":"139","author":"Y\u00e8che","journal-title":"Proc Mach Learn Res"},{"issue":"1","key":"R28","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2017-017833","article-title":"Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU","volume":"8","author":"Mao","journal-title":"BMJ Open"},{"issue":"5","key":"R29","doi-asserted-by":"publisher","first-page":"7858","DOI":"10.1109\/JSEN.2024.3424655","article-title":"SepAl: sepsis alerts on low-power wearables with digital biomarkers and on-device tiny machine learning","volume":"25","author":"Giordano","journal-title":"IEEE Sensors J"},{"key":"R30","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1485","article-title":"Remote patient monitoring using artificial intelligence: current state, applications, and challenges","author":"Shaik","journal-title":"WIREs Data Mining Knowl Discov"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e82762","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:26:18Z","timestamp":1785536778000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e82762"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,19]]},"references-count":30,"URL":"https:\/\/doi.org\/10.2196\/82762","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,19]]},"article-number":"v14i8e82762"}}