Surgical Hand Gesture Recognition Utilizing Electroencephalogram as Input to the Machine Learning and Network Neuroscience Algorithms

Shafiei, Somayeh B.; Durrani, Mohammad; Jing, Zhe; Mostowy, Michael; Doherty, Philippa; Hussein, Ahmed A.; Elsayed, Ahmed S.; Iqbal, Umar

doi:10.3390/s21051733

Cited by 3 publications

(2 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several prospective studies ( 22 – 24 ) have investigated the prediction of PODs in patients undergoing cardiovascular surgeries using a substantial array of preoperative clinical parameters. These studies reported an area under the curve (AUC) values ranging from 0.74 to 0.83, which were marginally lower than the findings in this study.…”

Section: Discussionmentioning

confidence: 99%

Predicting postoperative delirium after cardiovascular surgeries from preoperative portable electroencephalography oscillations

Hata,

Miyazaki,

Nagata

et al. 2023

Front. Psychiatry

View full text Add to dashboard Cite

IntroductionPostoperative delirium (POD) is common and life-threatening, however, with intensive interventions, a potentially preventable clinical syndrome. Although electroencephalography (EEG) is a promising biomarker of delirium, standard 20-leads EEG holds difficulties for screening usage in clinical practice.ObjectiveWe aimed to develop an accurate algorithm to predict POD using EEG data obtained from portable device.MethodsWe recruited 128 patients who underwent scheduled cardiovascular surgery. Cognitive function assessments were conducted, and portable EEG recordings were obtained prior to surgery.ResultsAmong the patients, 47 (36.7%) patients with POD were identified and they did not significantly differ from patients without POD in sex ratio, age, cognitive function, or treatment duration of intensive care unit. However, significant differences were observed in the preoperative EEG power spectrum densities at various frequencies, especially gamma activity, between patients with and without POD. POD was successfully predicted using preoperative EEG data with a machine learning algorithm, yielding accuracy of 86% and area under the receiver operating characteristic curve of 0.93.DiscussionThis study provides new insights into the objective and biological vulnerability to delirium. The developed algorithm can be applied in general hospitals without advanced equipment and expertise, thereby enabling the reduction of POD occurrences with intensive interventions for high-risk patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Predicting postoperative delirium after cardiovascular surgeries from preoperative portable electroencephalography oscillations

Hata,

Miyazaki,

Nagata

et al. 2023

Front. Psychiatry

View full text Add to dashboard Cite

show abstract

“…The Pearson filter is the simplest form of ranking that is performed by computing the correlation of every pair of features for all features [47]. ANOVA calculates the parametric statistical hypothesis score, F-value by comparing two or more samples of data (typically three samples) [48]. Chi-square scores calculate the dependencies between features by calculating the error between the observed and expected values [49].…”

Section: First Layer Feature Selectionmentioning

confidence: 99%

Dual-Layer Ranking Feature Selection Method Based on Statistical Formula for Driver Fatigue Detection of EMG Signals

Naim¹,

Mustafa²,

Sulaiman³

et al. 2022

View full text Add to dashboard Cite

Electromyography (EMG) signals are one of the most studied inputs for driver drowsiness detection systems. As the number of EMG features available can be daunting, finding the most significant and minimal subset features is desirable. Hence, a simplified feature selection method is necessary. This work proposed a dual-layer ranking feature selection algorithm based on statistical formula f EMG signals for driver fatigue detection. In the beginning, in the first layer, 21 filter algorithms were calculated to rank 47 sets of EMG features (25 time-domain and 9 frequency-domain) and applied to six classifiers. Then, in the second layer, all the ranks were re-ranked based on the statistical formula (average, median, mode and variance). The classification performance of all rankings was compared along with the number of features. The highest classification accuracy achieved was 95% for 12 features using the Average Statistical Rank (ASR) and LDA classifier. It is conclusive that a combination of features from the time domain and frequency domain can deliver better performance compared to a single domain feature. Concurrently, the statistical rank ASR performed better than the single filter rank by reducing the number of features. The proposed model can be a benchmark for the enhanced feature selection method for EMG driver fatigue signal.

show abstract

Magnetoencephalogram-based brain–computer interface for hand-gesture decoding using deep learning

Bu,

Harrington,

Lee

et al. 2023

Cerebral Cortex

View full text Add to dashboard Cite

Advancements in deep learning algorithms over the past decade have led to extensive developments in brain–computer interfaces (BCI). A promising imaging modality for BCI is magnetoencephalography (MEG), which is a non-invasive functional imaging technique. The present study developed a MEG sensor-based BCI neural network to decode Rock-Paper-scissors gestures (MEG-RPSnet). Unique preprocessing pipelines in tandem with convolutional neural network deep-learning models accurately classified gestures. On a single-trial basis, we found an average of 85.56% classification accuracy in 12 subjects. Our MEG-RPSnet model outperformed two state-of-the-art neural network architectures for electroencephalogram-based BCI as well as a traditional machine learning method, and demonstrated equivalent and/or better performance than machine learning methods that have employed invasive, electrocorticography-based BCI using the same task. In addition, MEG-RPSnet classification performance using an intra-subject approach outperformed a model that used a cross-subject approach. Remarkably, we also found that when using only central-parietal-occipital regional sensors or occipitotemporal regional sensors, the deep learning model achieved classification performances that were similar to the whole-brain sensor model. The MEG-RSPnet model also distinguished neuronal features of individual hand gestures with very good accuracy. Altogether, these results show that noninvasive MEG-based BCI applications hold promise for future BCI developments in hand-gesture decoding.

show abstract

Surgical Hand Gesture Recognition Utilizing Electroencephalogram as Input to the Machine Learning and Network Neuroscience Algorithms

Cited by 3 publications

References 57 publications

Predicting postoperative delirium after cardiovascular surgeries from preoperative portable electroencephalography oscillations

Predicting postoperative delirium after cardiovascular surgeries from preoperative portable electroencephalography oscillations

Dual-Layer Ranking Feature Selection Method Based on Statistical Formula for Driver Fatigue Detection of EMG Signals

Magnetoencephalogram-based brain–computer interface for hand-gesture decoding using deep learning

Contact Info

Product

Resources

About