Show simple item record

dc.contributor.authorChang, Ping
dc.contributor.authorLi, Huayu
dc.contributor.authorQuan, Stuart F
dc.contributor.authorLu, Shuyang
dc.contributor.authorWung, Shu-Fen
dc.contributor.authorRoveda, Janet
dc.contributor.authorLi, Ao
dc.date.accessioned2024-05-08T16:01:41Z
dc.date.available2024-05-08T16:01:41Z
dc.date.issued2024-02-08
dc.identifier.citationChang, P., Li, H., Quan, S. F., Lu, S., Wung, S. F., Roveda, J., & Li, A. (2024). A Transformer-based Diffusion Probabilistic Model for Heart Rate and Blood Pressure Forecasting in Intensive Care Unit. Computer Methods and Programs in Biomedicine, 108060.en_US
dc.identifier.pmid38350189
dc.identifier.doi10.1016/j.cmpb.2024.108060
dc.identifier.urihttp://hdl.handle.net/10150/672321
dc.description.abstractBackground and Objective: Vital sign monitoring in the Intensive Care Unit (ICU) is crucial for enabling prompt interventions for patients. This underscores the need for an accurate predictive system. Therefore, this study proposes a novel deep learning approach for forecasting Heart Rate (HR), Systolic Blood Pressure (SBP), and Diastolic Blood Pressure (DBP) in the ICU. Methods: We extracted 24,886 ICU stays from the MIMIC-III database which contains data from over 46 thousand patients, to train and test the model. The model proposed in this study, Transformer-based Diffusion Probabilistic Model for Sparse Time Series Forecasting (TDSTF), merges Transformer and diffusion models to forecast vital signs. The TDSTF model showed state-of-the-art performance in predicting vital signs in the ICU, outperforming other models' ability to predict distributions of vital signs and being more computationally efficient. The code is available at https://github.com/PingChang818/TDSTF. Results: The results of the study showed that TDSTF achieved a Standardized Average Continuous Ranked Probability Score (SACRPS) of 0.4438 and a Mean Squared Error (MSE) of 0.4168, an improvement of 18.9% and 34.3% over the best baseline model, respectively. The inference speed of TDSTF is more than 17 times faster than the best baseline model. Conclusion: TDSTF is an effective and efficient solution for forecasting vital signs in the ICU, and it shows a significant improvement compared to other models in the field.en_US
dc.language.isoenen_US
dc.publisherElsevier Ireland Ltden_US
dc.rights© 2024 Elsevier B.V. All rights reserved.en_US
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en_US
dc.subjectDeep Learningen_US
dc.subjectICUen_US
dc.subjectSparse dataen_US
dc.subjectTime series forecastingen_US
dc.subjectVital signsen_US
dc.titleA transformer-based diffusion probabilistic model for heart rate and blood pressure forecasting in Intensive Care Uniten_US
dc.typeArticleen_US
dc.identifier.eissn1872-7565
dc.contributor.departmentDepartment of Electrical & Computer Engineering, The University of Arizonaen_US
dc.contributor.departmentAsthma and Airway Disease Research Center, College of Medicine, The University of Arizonaen_US
dc.contributor.departmentBio5 Institute, The University of Arizonaen_US
dc.contributor.departmentCollege of Nursing, The University of Arizonaen_US
dc.identifier.journalComputer methods and programs in biomedicineen_US
dc.description.note12 month embargo; first published 8 February 2024en_US
dc.description.collectioninformationThis item from the UA Faculty Publications collection is made available by the University of Arizona with support from the University of Arizona Libraries. If you have questions, please contact us at repository@u.library.arizona.edu.en_US
dc.eprint.versionFinal accepted manuscripten_US
dc.source.journaltitleComputer methods and programs in biomedicine
dc.source.volume246
dc.source.beginpage108060
dc.source.endpage
dc.source.countryUnited States
dc.source.countryIreland


Files in this item

Thumbnail
Name:
TDSTF_clean.pdf
Embargo:
2025-02-08
Size:
3.649Mb
Format:
PDF
Description:
Final Accepted Manuscript

This item appears in the following Collection(s)

Show simple item record