Single Trial EEG Patterns for the Prediction of Individual Differences in Fluid Intelligence

The value of linear and non-linear quantitative EEG analysis in paediatric epilepsy surgery: a machine learning approach

Epilepsy surgery is effective for patients with medication-resistant seizures, however 20-40% of them are not seizure free after surgery. Aim of this study is to evaluate the role of linear and non-linear EEG features to predict post-surgical outcome. We included 123 paediatric patients who underwent epilepsy surgery at Bambino Gesù Children Hospital (January 2009-April 2020). All patients had long term video-EEG monitoring. We analysed 1-min scalp interictal EEG (wakefulness and sleep) and extracted 13 linear and non-linear EEG features (power spectral density (PSD), Hjorth, approximate entropy, permutation entropy, Lyapunov and Hurst value). We used a logistic regression (LR) as feature selection process. To quantify the correlation between EEG features and surgical outcome we used an artificial neural network (ANN) model with 18 architectures. LR revealed a significant correlation between PSD of alpha band (sleep), Mobility index (sleep) and the Hurst value (sleep and awake) with outcome. The fifty-four ANN models gave a range of accuracy (46-65%) in predicting outcome. Within the fifty-four ANN models, we found a higher accuracy (64.8% ± 7.6%) in seizure outcome prediction, using features selected by LR. The combination of PSD of alpha band, mobility and the Hurst value positively correlate with good surgical outcome.

Single-trial extraction of event-related potentials (ERPs) and classification of visual stimuli by ensemble use of discrete wavelet transform with Huffman coding and machine learning techniques

BACKGROUND

Presentation of visual stimuli can induce changes in EEG signals that are typically detectable by averaging together data from multiple trials for individual participant analysis as well as for groups or conditions analysis of multiple participants. This study proposes a new method based on the discrete wavelet transform with Huffman coding and machine learning for single-trial analysis of evenal (ERPs) and classification of different visual events in the visual object detection task.

METHODS

EEG single trials are decomposed with discrete wavelet transform (DWT) up to the [Formula: see text] level of decomposition using a biorthogonal B-spline wavelet. The coefficients of DWT in each trial are thresholded to discard sparse wavelet coefficients, while the quality of the signal is well maintained. The remaining optimum coefficients in each trial are encoded into bitstreams using Huffman coding, and the codewords are represented as a feature of the ERP signal. The performance of this method is tested with real visual ERPs of sixty-eight subjects.

RESULTS

The proposed method significantly discards the spontaneous EEG activity, extracts the single-trial visual ERPs, represents the ERP waveform into a compact bitstream as a feature, and achieves promising results in classifying the visual objects with classification performance metrics: accuracies 93.60[Formula: see text], sensitivities 93.55[Formula: see text], specificities 94.85[Formula: see text], precisions 92.50[Formula: see text], and area under the curve (AUC) 0.93[Formula: see text] using SVM and k-NN machine learning classifiers.

CONCLUSION

The proposed method suggests that the joint use of discrete wavelet transform (DWT) with Huffman coding has the potential to efficiently extract ERPs from background EEG for studying evoked responses in single-trial ERPs and classifying visual stimuli. The proposed approach has O(N) time complexity and could be implemented in real-time systems, such as the brain-computer interface (BCI), where fast detection of mental events is desired to smoothly operate a machine with minds.

Neuro-Cognitive Profile of Morning and Evening Chronotypes at Different Times of Day

BACKGROUND

Chronotype is the circadian time preference for sleep-wake timings. However, its impact on cognitive performance is least explored.

OBJECTIVE

The present study investigated the effect of chronotype (morning "M" vs. evening "E") on cognitive measures as a function of time of the day. In addition, the correlation between electroencephalogram (EEG) waves and subjective/objective cognitive measures were investigated.

METHOD

Cognitive status of 28 adult male subjects (15 "M" and 13 "E") was assessed objectively through event-related potential (ERP) by administering visual odd ball paradigm test and subjectively through Montreal Cognitive Assessment questionnaire. In addition, 20 to 30 min of resting EEG was recorded. Recordings were done from 8 to 10 am and from 4 to 6 pm on a single day. Power spectral analysis of EEG for alpha and beta waves at PZ and FZ cortical sites was done after subjecting selected epochs to fast Fourier transformation. Also, latency and amplitude of P300 potential from event-related potential record were measured. Appropriate statistical tests were applied for analysis.

RESULTS

Higher alpha and beta power was observed in "E" at PZ in the evening. "M" showed increased P300 latency and amplitude during evening session for frequent and rare stimuli and vice versa in "E."' Significant negative correlation was seen between latency of rare stimuli and alpha and beta power at FZ site during evening in "E" chronotype only.

CONCLUSION

Result indicates better attention and alertness during evening hours in evening chronotypes and vice versa in morning chronotypes. The findings could be implemented to schedule the mental performance/cognitive load according to individual chronotype.

Can Working Memory Task-Related EEG Biomarkers Measure Fluid Intelligence and Predict Academic Achievement in Healthy Children?

Background

Educational psychology research has linked fluid intelligence (Gf) with working memory (WM), but it is still dubious whether electroencephalography (EEG) markers robustly indicate Gf. This study addresses this issue and notes the relationship between WM task-related EEG markers with Gf and academic performance.

Method

A sample of 62 healthy children between the ages of 9 and 12 years was selected to perform three tasks: (1) Raven’s Standard Progressive Matrices (RSPM) test to assess Gf; (2) 2-back task to assess central executive system (CES); and (3) delayed match-to-sample task to assess short-term storage. These subjects were divided into high ability (HA) and low ability (LA) groups based on their RSPM scores. Support vector machine and logistic regression were used to train the EEG candidate indicators. A multiple regression was used to predict children’s academic performance using P3 amplitude, P2 latency, and θ-ERS.

Results

Behavioral results demonstrated that the correct rate of the HA group is higher than that of the LA group. The event-related potential results of the 2-back task showed that the P3 amplitude of the HA group was relatively larger and that the P2 latency was shorter than that observed in the LA group. For the delayed matching to sample task, the θ-ERS of the LA group was higher than that of the HA group. However, the area under the curve of these three indicators for Gf was < 0.75 for each and < 0.85 for the combined indicators. In predicting academic performance, only P3 amplitude showed a significant effect.

Conclusion

These results challenge previous findings, which reported that P3, P2, or theta power might be used in standard psychometric tests to assess an individual’s intelligence.