Heart rate variability-derived features based on deep neural network for distinguishing different anaesthesia states

Abstract

Background Estimating the depth of anaesthesia (DoA) is critical in modern anaesthetic practice. Multiple DoA monitors based on electroencephalograms (EEGs) have been widely used for DoA monitoring; however, these monitors may be inaccurate under certain conditions. In this work, we hypothesize that heart rate variability (HRV)-derived features based on a deep neural network can distinguish different anaesthesia states, providing a secondary tool for DoA assessment. Methods A novel method of distinguishing different anaesthesia states was developed based on four HRV-derived features in the time and frequency domain combined with a deep neural network. Four features were extracted from an electrocardiogram, including the HRV high-frequency power, low-frequency power, high-to-low-frequency power ratio, and sample entropy. Next, these features were used as inputs for the deep neural network, which utilized the expert assessment of consciousness level as the reference output. Finally, the deep neural network was compared with the logistic regression, support vector machine, and decision tree models. The datasets of 23 anaesthesia patients were used to assess the proposed method. Results The accuracies of the four models, in distinguishing the anaesthesia states, were 86.2% (logistic regression), 87.5% (support vector machine), 87.2% (decision tree), and 90.1% (deep neural network). The accuracy of deep neural network was higher than those of the logistic regression (p < 0.05), support vector machine (p < 0.05), and decision tree (p < 0.05) approaches. Our method outperformed the logistic regression, support vector machine, and decision tree methods. Conclusions The incorporation of four HRV-derived features in the time and frequency domain and a deep neural network could accurately distinguish between different anaesthesia states; however, this study is a pilot feasibility study. The proposed method—with other evaluation methods, such as EEG—is expected to assist anaesthesiologists in the accurate evaluation of the DoA.

Heart rate variability as a predictor of intraoperative autonomic nervous system homeostasis

“…This is consistent with previous studies which have demonstrated a sharp decrease of HRV during induction of general anesthesia. [17,18] Furthermore the clinical data acquisition in this study, supports the advantages in assessing HRV-based depth of anesthesia described by Zhan, et al [5] and facilitates validation of the HRV parameters by measuring them perioperatively in the context of the established methods. Consequently, standard monitoring ECG recordings might be used for a software-based rating of anesthesia depth without the need for additional hardware.…”

“…[17] Recent studies on the impact of anesthesia on the ANS validated HRV as a suitable method for assessing the depth of anesthesia. [18,32] In a pilot study, Zhan, et al [5] showed that the time and frequency parameters of HRV facilitate the assessment of anesthesia across a wide ranges of levels. So far, the level of concordance of EEG and HRV has been tested on awake patients [19][20][21], under experimental conditions [22] or performed during the induction of general anesthesia.…”

“…[3,4] However, EEG analysis cannot be utilized under all circumstances. [5] Furthermore, monitoring surrogate markers for the effects of general anesthesia on the CNS by EEG remains incomplete, since the inhaled agents exert a strong inhibitory in uence on the autonomic nervous system (ANS) as well. [6] Of particular note, perioperative mortality and morbidity are directly associated with the activity level of the patient's ANS in terms of the exaggerated stress response of the postaggression metabolism.…”

Heart rate variability in anaesthesiology – narrative review

“…Another implementation of HRV analysis during general anaesthesia is its use as a complementary tool to monitor the depth of anaesthesia. The idea behind such a monitor would be to rely on cardiorespiratory interactions and autonomic nervous system activity [68][69][70].…”

Application of Decision Tree Intelligent Algorithm in Data Analysis of Physical Health Test

“…In the algorithm, the actual application of the quality and complexity evaluation of theoretical association is combined with examples, and the discrete characteristics of the algorithm are verified [ 9 ]. Liu et al applied the intelligent evaluation algorithm to the anesthesia depth detection system and obtained the actual parameter changes of each patient during the anesthesia period from the physical health test gap after the combination of the system, so as to verify the feasibility of the algorithm [ 10 ]. PAAP et al comprehensively tested the performance of computer adaptive testing, so as to carry out model analysis and data integration for multidimensional projects.…”