Electroencephalogram-based machine learning models to predict neurologic outcome after cardiac arrest: A systematic review.

AIM OF THE REVIEW: The primary aim of this systematic review was to investigate the most common electroencephalogram (EEG)-based machine learning (ML) model with the highest Area Under Receiver Operating Characteristic Curve (AUC) in two ML categories, conventional ML and Deep Neural Network (DNN), to predict the neurologic outcomes after cardiac arrest; the secondary aim was to investigate common EEG features applied to ML models. METHODS: Systematic search of medical literature from PubMed and engineering literature from Compendex up to June 2, 2023. One reviewer screened studies that used EEG-based ML models to predict the neurologic outcomes after cardiac arrest. Four reviewers validated that the studies met selection criteria. Nine variables were manually extracted. The top-five common EEG features were calculated. We evaluated each study's risk of bias using the Quality in Prognosis Studies guideline. RESULTS: Out of 351 identified studies, 17 studies met the inclusion criteria. Random Forest (RF) (n = 7) was the most common ML model in the conventional ML category (n = 11), followed by Convolutional Neural Network (CNN) (n = 4) in the DNN category (n = 6). The AUCs for RF ranged between 0.8 and 0.97, while CNN had AUCs between 0.7 and 0.92. The top-three commonly used EEG features were band power (n = 12), Shannon's Entropy (n = 11), burst-suppression ratio (n = 9). CONCLUSIONS: RF and CNN were the two most common ML models with the highest AUCs for predicting the neurologic outcomes after cardiac arrest. Using a multimodal model that combines EEG features and electronic health record data may further improve prognostic performance.

Comparing different wavelet transforms on removing electrocardiogram baseline wanders and special trends.

BACKGROUND: Electrocardiogram (ECG) signal, an important indicator for heart problems, is commonly corrupted by a low-frequency baseline wander (BW) artifact, which may cause interpretation difficulty or inaccurate analysis. Unlike current state-of-the-art approach using band-pass filters, wavelet transforms can accurately capture both time and frequency information of a signal. However, extant literature is limited in applying wavelet transforms (WTs) for baseline wander removal. In this study, we aimed to evaluate 5 wavelet families with a total of 14 wavelets for removing ECG baseline wanders from a semi-synthetic dataset. METHODS: We created a semi-synthetic ECG dataset based on a public QT Database on Physionet repository with ECG data from 105 patients. The semi-synthetic ECG dataset comprised ECG excerpts from the QT database superimposed with artificial baseline wanders. We extracted one ECG excerpt from each of 105 patients, and the ECG excerpt comprised 14 s of randomly selected ECG data. Twelve baseline wanders were manually generated, including sinusoidal waves, spikes and step functions. We implemented and evaluated 14 commonly used wavelets up to 12 WT levels. The evaluation metric was mean-square-error (MSE) between the original ECG excerpt and the processed signal with artificial BW removed. RESULTS: Among the 14 wavelets, Daubechies-3 wavelet and Symlets-3 wavelet with 7 levels of WT had best performance, MSE = 0.0044. The average MSEs for sinusoidal waves, step, and spike functions were 0.0271, 0.0304, 0.0199 respectively. For artificial baseline wanders with spikes or step functions, wavelet transforms in general had lower performance in removing the BW; however, WTs accurately located the temporal position of an impulse edge. CONCLUSIONS: We found wavelet transforms in general accurately removed various baseline wanders. Daubechies-3 and Symlets-3 wavelets performed best. The study could facilitate future real-time processing of streaming ECG signals for clinical decision support systems.

Noxious and innocuous cold discrimination in humans: evidence for separate afferent channels.

The present study evaluated the ability of humans to discriminate temperature decreases in the noxious and innocuous cold range. Two groups of five subjects detected changes in cold stimuli applied to the maxillary face. For five subjects, adapting temperatures of 22 degrees, 16 degrees, 6 degrees and 0 degrees C were used, and thresholds for detecting temperature decreases were determined using an adaptive psychophysical paradigm. Visual analogue scale (VAS) ratings of cold and pain sensation were also recorded at 5-min intervals throughout each session. A second group of five subjects performed a similar detection task, but in this case using classical psychophysical techniques (method of constant stimuli) and adapting temperatures of 22 degrees, 16 degrees, 10 degrees and 6 degrees C. These subjects described the quality of the detected change in sensation, in addition to rating overall cold and pain sensation throughout the session. Detection thresholds were 0.27 degrees, 0.48 degrees, 4.8 degrees, 8.0 degrees and >10.0 degrees C for baselines of 22 degrees, 16 degrees, 10 degrees, 6 degrees and 0 degrees C, respectively, indicating that discrimination was better in the innocuous cool (22 degrees and 16 degrees C) than in the noxious and near-noxious cold (10-0 degrees C) range (P < 0.05). Tonic adapting temperatures of 22 degrees and 16 degrees C were always rated as cool but not painful, whereas adapting temperatures of 10 degrees and 6 degrees were sometimes and 0 degrees C usually rated as painful. Phasic temperature decreases from 22 degrees and 16 degrees C always produced cooling sensations, whereas decreases from baselines of 10 degrees and 6 degrees C produced primarily sensations of painful and non-painful prickle. These data suggest that different afferent channels mediate cool and noxious cold perception and add support to the hypothesis that noxious cold sensation is mediated by subdermal nociceptors.