loading page

Intraoperative Hypotension Prediction Based on Features Automatically Generated Within an Interpretable Deep Learning Model
  • +3
  • Eugene Hwang ,
  • Yong-Seok Park ,
  • Jin-Young Kim ,
  • Sung-Hyuk Park ,
  • Junetae Kim ,
  • Sung-Hoon Kim
Eugene Hwang
Author Profile
Yong-Seok Park
Author Profile
Jin-Young Kim
Author Profile
Sung-Hyuk Park
Author Profile
Junetae Kim
National Cancer Center Korea, National Cancer Center Korea, National Cancer Center Korea

Corresponding Author:[email protected]

Author Profile
Sung-Hoon Kim
Author Profile


Monitoring arterial blood pressure (ABP) in anesthetized patients is crucial for preventing hypotension, which can lead to adverse clinical outcomes. Thus, several efforts have been made to develop an artificial intelligence-based hypotension prediction index. Nevertheless, the use of these indices is limited because they may not provide a convincing interpretation of the association between predictors and hypotension. Herein, we developed an interpretable deep learning model that forecasts hypotension occurrences 10 min before a given 90 s ABP record. Internal and external validations of model performance reported the area under the receiver operating characteristic curve (AUC) as 0.9145 and 0.9035, respectively. Furthermore, the hypotension prediction mechanism can be physiologically interpreted by using predictors representing ABP trends that are automatically generated in the proposed model. Ultimately, we demonstrate high-applicability of a deep learning model that has a high accuracy performance and provides an interpretation of the association between ABP trends and hypotension in clinical practices.
2023Published in IEEE Transactions on Neural Networks and Learning Systems on pages 1-15. 10.1109/TNNLS.2023.3273187