Dataset Information

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?ConclusionsThe 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.

SUBMITTER: Zhan J

PROVIDER: S-EPMC7923817 | biostudies-literature | 2021 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Zhan Jian J Wu Zhuo-Xi ZX Duan Zhen-Xin ZX Yang Gui-Ying GY Du Zhi-Yong ZY Bao Xiao-Hang XH Li Hong H

BMC anesthesiology 20210302 1

<h4>Background</h4>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.<h4>Methods</h4>A nove ...[more]

PMID: 33653263

Similar Datasets

Project description:Background: Performance of wrist actigraphy in assessing sleep not only depends on the sensor technology of the actigraph hardware but also on the attributes of the interpretative algorithm (IA). The objective of our research was to improve assessment of sleep quality, relative to existing IAs, through development of a novel IA using deep learning methods, utilizing as input activity count and heart rate variability (HRV) metrics of different window length (number of epochs of data). Methods: Simultaneously recorded polysomnography (PSG) and wrist actigraphy data of 222 participants were utilized. Classic deep learning models were applied to: (a) activity count alone (without HRV), (b) activity count + HRV (30-s window), (c) activity count + HRV (3-min window), and (d) activity count + HRV (5-min window) to ascertain the best set of inputs. A novel deep learning model (Haghayegh Algorithm, HA), founded on best set of inputs, was developed, and its sleep scoring performance was then compared with the most popular University of California San Diego (UCSD) and Actiwatch proprietary IAs. Results: Activity count combined with HRV metrics calculated per 5-min window produced highest agreement with PSG. HA showed 84.5% accuracy (5.3-6.2% higher than comparator IAs), 89.5% sensitivity (6.2% higher than UCSD IA and 6% lower than Actiwatch proprietary IA), 70.0% specificity (8.2-34.3% higher than comparator IAs), and 58.7% Kappa agreement (16-23% higher than comparator IAs) in detecting sleep epochs. HA did not differ significantly from PSG in deriving sleep parameters-sleep efficiency, total sleep time, sleep onset latency, and wake after sleep onset; moreover, bias and mean absolute error of the HA model in estimating them was less than the comparator IAs. HA showed, respectively, 40.9% and 54.0% Kappa agreement with PSG in detecting rapid and non-rapid eye movement (REM and NREM) epochs. Conclusions: The HA model simultaneously incorporating activity count and HRV metrics calculated per 5-min window demonstrates significantly better sleep scoring performance than existing popular IAs.

Project description:Background: Heart rate variability (HRV), defined as the variability between consecutive heartbeats, is a surrogate measure of cardiac vagal tone. It is widely accepted that a decreased HRV is associated to several risk factors and cardiovascular diseases. However, a possible association between HRV and altered cerebral hemodynamics is still debated, suffering from HRV short-term measures and the paucity of high-resolution deep cerebral data. We propose a computational approach to evaluate the deep cerebral and central hemodynamics subject to physiological alterations of HRV in an ideal young healthy patient at rest. Methods: The cardiovascular-cerebral model is composed by electrical components able to reproduce the response of the different cardiovascular regions and their features. The model was validated over more than thirty studies and recently exploited to understand the hemodynamic mechanisms between cardiac arrythmia and cognitive deficit. Three configurations (baseline, increased HRV, and decreased HRV) are built based on the standard deviation (SDNN) of RR beats. For each configuration, 5,000 RR beats are simulated to investigate the occurrence of extreme values, alteration of the regular hemodynamics pattern, and variation of mean perfusion/pressure levels. Results: In the cerebral circulation, our results show that HRV has overall a stronger impact on pressure than flow rate mean values but similarly alters pressure and flow rate in terms of extreme events. By comparing reduced and increased HRV, this latter induces a higher probability of altered mean and extreme values, and is therefore more detrimental at distal cerebral level. On the contrary, at central level a decreased HRV induces a higher cardiac effort without improving the mechano-contractile performance, thus overall reducing the heart efficiency. Conclusions: Present results suggest that: (i) the increase of HRV per se does not seem to be sufficient to trigger a better cerebral hemodynamic response; (ii) by accounting for both central and cerebral circulations, the optimal HRV configuration is found at baseline. Given the relation inversely linking HRV and HR, the presence of this optimal condition can contribute to explain why the mean HR of the general population settles around the baseline value (70 bpm).

Dataset Information

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

Background

Methods

Results

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets