A Deep Learning Framework for Anesthesia Depth Prediction from Drug Infusion History
In the target-controlled infusion (TCI) of propofol and remifentanil intravenous anesthesia, accurate prediction of the depth of anesthesia (DOA) is very challenging. Patients with different physiological characteristics have inconsistent pharmacodynamic responses during different stages of anesthes...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-11-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/21/8994 |
_version_ | 1797631276638797824 |
---|---|
author | Mingjin Chen Yongkang He Zhijing Yang |
author_facet | Mingjin Chen Yongkang He Zhijing Yang |
author_sort | Mingjin Chen |
collection | DOAJ |
description | In the target-controlled infusion (TCI) of propofol and remifentanil intravenous anesthesia, accurate prediction of the depth of anesthesia (DOA) is very challenging. Patients with different physiological characteristics have inconsistent pharmacodynamic responses during different stages of anesthesia. For example, in TCI, older adults transition smoothly from the induction period to the maintenance period, while younger adults are more prone to anesthetic awareness, resulting in different DOA data distributions among patients. To address these problems, a deep learning framework that incorporates domain adaptation and knowledge distillation and uses propofol and remifentanil doses at historical moments to continuously predict the bispectral index (BIS) is proposed in this paper. Specifically, a modified adaptive recurrent neural network (AdaRNN) is adopted to address data distribution differences among patients. Moreover, a knowledge distillation pipeline is developed to train the prediction network by enabling it to learn intermediate feature representations of the teacher network. The experimental results show that our method exhibits better performance than existing approaches during all anesthetic phases in the TCI of propofol and remifentanil intravenous anesthesia. In particular, our method outperforms some state-of-the-art methods in terms of root mean square error and mean absolute error by 1 and 0.8, respectively, in the internal dataset as well as in the publicly available dataset. |
first_indexed | 2024-03-11T11:20:35Z |
format | Article |
id | doaj.art-96c9c615dca54845bb1ca8da22e521ce |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-11T11:20:35Z |
publishDate | 2023-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-96c9c615dca54845bb1ca8da22e521ce2023-11-10T15:13:04ZengMDPI AGSensors1424-82202023-11-012321899410.3390/s23218994A Deep Learning Framework for Anesthesia Depth Prediction from Drug Infusion HistoryMingjin Chen0Yongkang He1Zhijing Yang2School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Information Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Information Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaIn the target-controlled infusion (TCI) of propofol and remifentanil intravenous anesthesia, accurate prediction of the depth of anesthesia (DOA) is very challenging. Patients with different physiological characteristics have inconsistent pharmacodynamic responses during different stages of anesthesia. For example, in TCI, older adults transition smoothly from the induction period to the maintenance period, while younger adults are more prone to anesthetic awareness, resulting in different DOA data distributions among patients. To address these problems, a deep learning framework that incorporates domain adaptation and knowledge distillation and uses propofol and remifentanil doses at historical moments to continuously predict the bispectral index (BIS) is proposed in this paper. Specifically, a modified adaptive recurrent neural network (AdaRNN) is adopted to address data distribution differences among patients. Moreover, a knowledge distillation pipeline is developed to train the prediction network by enabling it to learn intermediate feature representations of the teacher network. The experimental results show that our method exhibits better performance than existing approaches during all anesthetic phases in the TCI of propofol and remifentanil intravenous anesthesia. In particular, our method outperforms some state-of-the-art methods in terms of root mean square error and mean absolute error by 1 and 0.8, respectively, in the internal dataset as well as in the publicly available dataset.https://www.mdpi.com/1424-8220/23/21/8994depth of anesthesiadomain adaptationknowledge distillationtarget-controlled infusion |
spellingShingle | Mingjin Chen Yongkang He Zhijing Yang A Deep Learning Framework for Anesthesia Depth Prediction from Drug Infusion History Sensors depth of anesthesia domain adaptation knowledge distillation target-controlled infusion |
title | A Deep Learning Framework for Anesthesia Depth Prediction from Drug Infusion History |
title_full | A Deep Learning Framework for Anesthesia Depth Prediction from Drug Infusion History |
title_fullStr | A Deep Learning Framework for Anesthesia Depth Prediction from Drug Infusion History |
title_full_unstemmed | A Deep Learning Framework for Anesthesia Depth Prediction from Drug Infusion History |
title_short | A Deep Learning Framework for Anesthesia Depth Prediction from Drug Infusion History |
title_sort | deep learning framework for anesthesia depth prediction from drug infusion history |
topic | depth of anesthesia domain adaptation knowledge distillation target-controlled infusion |
url | https://www.mdpi.com/1424-8220/23/21/8994 |
work_keys_str_mv | AT mingjinchen adeeplearningframeworkforanesthesiadepthpredictionfromdruginfusionhistory AT yongkanghe adeeplearningframeworkforanesthesiadepthpredictionfromdruginfusionhistory AT zhijingyang adeeplearningframeworkforanesthesiadepthpredictionfromdruginfusionhistory AT mingjinchen deeplearningframeworkforanesthesiadepthpredictionfromdruginfusionhistory AT yongkanghe deeplearningframeworkforanesthesiadepthpredictionfromdruginfusionhistory AT zhijingyang deeplearningframeworkforanesthesiadepthpredictionfromdruginfusionhistory |