Multimodal spatio-temporal-spectral fusion for deep learning applications in physiological time series processing: A case study in monitoring the depth of anesthesia

Bahador, Nooshin; Jokelainen, Jarno; Mustola, Seppo; Kortelainen, Jukka

doi:10.1016/j.inffus.2021.03.001

Cited by 11 publications

(4 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A weight matrix can be formed based on pairwise correlation coefficient of channels according to equation (1):…”

Section: Methodsmentioning

confidence: 99%

“…HEN it comes to electroencephalography (EEG) recordings as one of the major modalities, widely used for neural systems and rehabilitation applications, there are many sources of variabilities including impedance change, shifts in electrode position, electrode popping and electrode shortcuts [1][2][3]. These faulty recordings lead to missing channels.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Reconstruction of missing channel in electroencephalogram using spatiotemporal correlation-based averaging

et al. 2021

Self Cite

View full text Add to dashboard Cite

Objective. Electroencephalogram (EEG) recordings often contain large segments with missing signals due to poor electrode contact or other artifact contamination. Recovering missing values, contaminated segments and lost channels could be highly beneficial, especially for automatic classification algorithms, such as machine/deep learning models, whose performance relies heavily on high-quality data. The current study proposes a new method for recovering missing segments in EEG. Approach. In the proposed method, the reconstructed segment is estimated by substitution of the missing part of the signal with the normalized weighted sum of other channels. The weighting process is based on inter-channel correlation of the non-missing preceding and proceeding temporal windows. The algorithm was designed to be computationally efficient. Experimental data from patients (N = 20) undergoing general anesthesia due to elective surgery were used for the validation of the algorithm. The data were recorded using a portable EEG device with ten channels and a self-adhesive frontal electrode during induction of anesthesia with propofol from waking state until burst suppression level, containing lots of variation in both amplitude and frequency properties. The proposed imputation technique was compared with another simple-structure technique. Distance correlation (DC) was used as a measure of comparison evaluation. Main results.:The proposed method with average distance correlation of 82.48±10.01 (µ ± σ)% outperformed its competitor with average distance correlation of 67.89±14.12 (µ ± σ)% . This algorithm also showed better performance for an increasing number of missing channels. Significance. the proposed technique provides an easy-to-implement and computationally efficient approach for the reliable reconstruction of missing or contaminated EEG segments.

show abstract

“…A weight matrix can be formed based on pairwise correlation coefficient of channels according to equation (1):…”

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Reconstruction of missing channel in electroencephalogram using spatiotemporal correlation-based averaging

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Artificial intelligence techniques have been employed to analyze EEG signals to assess DOA [17][18][19][20][21][22][23][24][25][26]. DOA estimation involves two primary tasks.…”

Section: Introductionmentioning

confidence: 99%

“…Anes-MetaNet achieved an accuracy of 81.8% for the classifications of three anaesthesia states: light, moderate, and deep anaesthesia. Bahador et al [25] proposed a neural network using fused information from joint EEG-electrocardiogram (ECG) recordings to track transitions between different anesthesia states, and the model achieved an accuracy of 94.14%. Most of the studies used multi-channel EEG as input to the model and by fusing multi-channel EEG data, the model can capture brain activity from various regions, thereby enhancing overall accuracy [23,25].…”

Section: Introductionmentioning

confidence: 99%

SQI-DOANet: electroencephalogram-based deep neural network for estimating signal quality index and depth of anaesthesia

Yu,

Zhou,

et al. 2024

J. Neural Eng.

View full text Add to dashboard Cite

Objective:Monitoring the depth of anaesthesia (DOA) during surgery is of critical importance. However, accurate and real-time estimation of DOA remains a challenging task. In this paper, we proposed a signal quality index (SQI) network (SQINet) for assessing the electroencephalogram (EEG) signal quality and a DOA network (DOANet) for analyzing EEG signals to precisely estimate DOA. The two networks are termed SQI-DOANet.Approach:The SQINet contained a shallow convolutional neural network to quickly determine the quality of the EEG signal. The DOANet comprised a feature extraction module for extracting features, a dual attention module for fusing multi-channel and multi-scale information, and a gated multilayer perceptron module for extracting temporal information. The performance of the SQI-DOANet model was validated by training and testing the model on the large VitalDB database, with the bispectral index (BIS) as the reference standard.Main results:The proposed DOANet yielded a Pearson correlation coefficient with the BIS score of 0.88 in the 5-fold cross-validation, with a mean absolute error (MAE) of 4.81. The mean Pearson correlation coefficient of SQI-DOANet with the BIS score in the 5-fold cross-validation was 0.82, with an MAE of 5.66.Significance:The SQI-DOANet model outperformed three compared methods. The proposed SQI-DOANet may be used as a new deep learning method for DOA estimation. The code of the SQI-DOANet will be made available publicly at https://github.com/YuRui8879/SQI-DOANet.

show abstract

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

Keim,

Bolwin,

Feldmann,

et al. 2024

J Clin Monit Comput

View full text Add to dashboard Cite

The aim of the proof-of-concept study is to investigate the level of concordance between the heart rate variability (HRV), the EEG-based Narcotrend Index as a surrogate marker for the depth of hypnosis, and the minimal alveolar concentration (MAC) of the inhalation anesthetic sevoflurane across the entire course of a surgical procedure. This non-blinded cross-sectional study recorded intraoperative HRV, Narcotrend Index, and MAC in 31 male patients during radical prostatectomy using the Da-Vinci robotic-assisted surgical system at Mannheim University Medical Center. The degree of concordance was calculated using repeated measures correlation with the R package (rmcorr) and presented using the rmcorr coefficient (rrm). The Narcotrend Index correlates significantly across all measures with the time-dependent parameter of HRV, the standard deviation of the means of RR intervals (SDNN) (rrm = 0.2; p < 0.001), the frequency-dependent parameters low frequency (LF) (rrm = 0.09; p = 0.04) and the low frequency/high frequency ratio (LF/HF ratio) (rrm = 0.11; p = 0.002). MAC correlated significantly negatively with the time-dependent parameter of heart rate variability, SDNN (rrm = -0.28; p < 0.001), the frequency-dependent parameter LF (rrm = -0.06; p < 0.001) and the LF/HF ratio (rrm = -0.18; p < 0.001) and the Narcotrend Index (rrm = -0.49; p < 0.001) across all measures. HRV mirrors the trend of the Narcotrend Index used to monitor depth of hypnosis and the inhibitory influence of the anesthetic sevoflurane on the autonomic nervous system. Therefore, HRV can provide essential information about the homeostasis of the autonomic nervous system during general anesthesia. DRKS00024696, March 9th, 2021.

show abstract

Multimodal spatio-temporal-spectral fusion for deep learning applications in physiological time series processing: A case study in monitoring the depth of anesthesia

Cited by 11 publications

References 61 publications

Reconstruction of missing channel in electroencephalogram using spatiotemporal correlation-based averaging

Reconstruction of missing channel in electroencephalogram using spatiotemporal correlation-based averaging

SQI-DOANet: electroencephalogram-based deep neural network for estimating signal quality index and depth of anaesthesia

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

Contact Info

Product

Resources

About