A transformer-based diffusion probabilistic model for heart rate and blood pressure forecasting in Intensive Care Unit
Computer Methods and Programs in Biomedicine · 2024-04 · 246 · 108060
DOI: 10.1016/j.cmpb.2024.108060 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Methods and Programs in Biomedicine, 2024-04. Verfasst von Ping Chang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical & Computer Engineering, The University of Arizona, Tucson, AZ, USA. Hauptthemen laut MEDLINE: Intensive Care Units, Vital Signs. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NHLBI NIH HHS, National Science Foundation, National Heart Lung and Blood Institute.
Themen: Intensivpflege
Abstract (Originalsprache)
BACKGROUND 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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electrical & Computer Engineering, The University of Arizona, Tucson, AZ, USA.
- Division of Sleep and Circadian Disorders, Departments of Medicine and Neurology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA; Asthma and Airway Disease Research Center, College of Medicine, Th…
- Department of Cardiovascular Surgery, Zhongshan Hospital, Fudan University, Shanghai, PR China; The Shanghai Institute of Cardiovascular Diseases, Shanghai, PR China.
- Bio5 Institute, The University of Arizona, Tucson, AZ, USA; College of Nursing, The University of Arizona, Tucson, AZ, USA.
- Department of Electrical & Computer Engineering, The University of Arizona, Tucson, AZ, USA; Bio5 Institute, The University of Arizona, Tucson, AZ, USA; Department of Biomedical Engineering, The University of Arizona, T…
- Department of Electrical & Computer Engineering, The University of Arizona, Tucson, AZ, USA; Bio5 Institute, The University of Arizona, Tucson, AZ, USA. Electronic address: aoli1@arizona.edu.
Förderung
- NHLBI NIH HHS
- National Science Foundation
- National Heart Lung and Blood Institute
Zitieren
APA
Chang, 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, 246, 108060. https://doi.org/10.1016/j.cmpb.2024.108060
Vancouver
Chang P, Li H, Quan SF, Lu S, Wung SF, Roveda J, et al. A transformer-based diffusion probabilistic model for heart rate and blood pressure forecasting in Intensive Care Unit. Computer Methods and Programs in Biomedicine. 2024;246:108060. doi:10.1016/j.cmpb.2024.108060
BibTeX
@article{Chang2024,
author = {Chang, Ping and Li, Huayu and Quan, Stuart F and Lu, Shuyang and Wung, Shu-Fen and Roveda, Janet and Li, Ao},
title = {A transformer-based diffusion probabilistic model for heart rate and blood pressure forecasting in Intensive Care Unit},
journal = {Computer Methods and Programs in Biomedicine},
year = {2024},
volume = {246},
pages = {108060},
doi = {10.1016/j.cmpb.2024.108060}
}
EUVIMED