An MRI-Based Machine Learning Prediction Framework to Lateralize Hippocampal Sclerosis in Patients With Temporal Lobe Epilepsy

Objective.MRI fails to reveal hippocampal pathology in 30-50% of temporal lobe epilepsy (TLE) surgical candidates. To address this clinical challenge, we developed an automated MRI-based classifier that lateralizes the side of covert hippocampal pathology in TLE.Methods.We trained a surface-based linear discriminant classifier that uses T1-weighted (morphology) and T2-weighted as well as FLAIR/T1 (intensity) features. The classifier was trained on 60 TLE patients (mean age: 35.6; 58% female) with histologically-verified hippocampal sclerosis (HS). Images were deemed as MRI-negative in 42% of cases based on neuroradiological reading (40% based on hippocampal volumetry). The predictive model automatically labelled patients as left or right TLE. Lateralization accuracy was compared to electro-clinical data, including side of surgery. Accuracy of the classifier was further assessed in two independent TLE cohorts with similar demographics and electro-clinical characteristics (n=57; 58% MRI-negative).Results.The overall lateralization accuracy was 93% (95%; CI 92% - 94%), regardless of HS visibility. In MRI-negative TLE, the combination of T2 and FLAIR/T1 intensities provided the highest accuracy both in the training (84%, area-under-the-curve (AUC): 0.95±0.02) and the validation cohorts (Cohort 1: 90%, AUC: 0.99; Cohort 2: 76%, AUC: 0.94).Conclusion.This prediction model for TLE lateralization operates on readily available conventional MRI contrasts and offers gain in accuracy over visual radiological assessment. The combined contribution of decreased T1- and increased T2-weighted intensities makes the synthetic FLAIR/T1 contrast particularly effective in MRI-negative HS, setting the basis for broad clinical translation.

Non-Intrusive Load Disaggregation by Linear Classifier Group Considering Multi-Feature Integration

Non-intrusive load monitoring (NILM) is a core technology for demand response (DR) and energy conservation services. Traditional NILM methods are rarely combined with practical applications, and most studies aim to disaggregate the whole loads in a household, which leads to low identification accuracy. In this method, the event detection method is used to obtain the switching event sets of all loads, and the power consumption curves of independent unknown electrical appliances in a period are disaggregated by utilizing comprehensive features. A linear discriminant classifier group based on multi-feature global similarity is used for load identification. The uniqueness of our algorithm is that it designs an event detector based on steady-state segmentation and a linear discriminant classifier group based on multi-feature global similarity. The simulation is carried out on an open source data set. The results demonstrate the effectiveness and high accuracy of the multi-feature integrated classification (MFIC) algorithm by using the state-of-the-art NILM methods as benchmarks.

Non-Intrusive Load Disaggregation by Linear Classifier Group Considering Multi-Feature Integration

Non-intrusive load monitoring (NILM) is a core technology for demand response (DR) and energy conservation services. Traditional NILM methods are rarely combined with practical applications, and most studies aim to decompose the whole loads in a household, which leads to low identification accuracy. In this paper, an NILM approach based on multi-feature integrated classification (MFIC) is explored, which combines some non-electrical features such as ON/OFF duration, usage frequency of appliances, and usage period to improve load differentiability. The implementation of MFIC algorithm is consistent with traditional event-based method. The uniqueness of our algorithm is that it designs an event detector based on steady-state segmentation and a linear discriminant classifier group based on multi-feature global similarity. Simulation results using an open-access dataset demonstrate the effectiveness and high accuracy of MFIC algorithm, with the state-of-the-art NILM methods as benchmarks.

EEG correlation at a distance: A re-analysis of two studies using a machine learning approach

Background: In this paper, data from two studies relative to the relationship between the electroencephalogram (EEG) activities of two isolated and physically separated subjects were re-analyzed using machine-learning algorithms. The first dataset comprises the data of 25 pairs of participants where one member of each pair was stimulated with a visual and an auditory 500 Hz signals of 1 second duration. The second dataset consisted of the data of 20 pairs of participants where one member of each pair received visual and auditory stimulation lasting 1 second duration with on-off modulation at 10, 12, and 14 Hz. Methods and Results: Applying a ‘linear discriminant classifier’ to the first dataset, it was possible to correctly classify 50.74% of the EEG activity of non-stimulated participants, correlated to the remote sensorial stimulation of the distant partner. In the second dataset, the percentage of correctly classified EEG activity in the non-stimulated partners was 51.17%, 50.45% and 51.91%, respectively, for the 10, 12, and 14 Hz stimulations, with respect the condition of no stimulation in the distant partner. Conclusions: The analysis of EEG activity using machine-learning algorithms has produced advances in the study of the connection between the EEG activities of the stimulated partner and the isolated distant partner, opening new insight into the possibility to devise practical application for non-conventional “mental telecommunications” between physically and sensorially separated participants.

EEG correlation at a distance: A re-analysis of two studies using a machine learning approach

Background: In this paper, data from two studies relative to the relationship between the electroencephalogram (EEG) activities of two isolated and physically separated subjects were re-analyzed using machine-learning algorithms. The first dataset comprises the data of 25 pairs of participants where one member of each pair was stimulated with a visual and an auditory 500 Hz signals of 1 second duration. The second dataset consisted of the data of 20 pairs of participants where one member of each pair received visual and auditory stimulation lasting 1 second duration with on-off modulation at 10, 12, and 14 Hz. Methods and Results: Applying a ‘linear discriminant classifier’ to the first dataset, it was possible to correctly classify 50.74% of the EEG activity of non-stimulated participants, correlated to the remote sensorial stimulation of the distant partner. In the second dataset, the percentage of correctly classified EEG activity in the non-stimulated partners was 51.17%, 50.45% and 51.91%, respectively, for the 10, 12, and 14 Hz stimulations, with respect the condition of no stimulation in the distant partner. Conclusions: The analysis of EEG activity using machine-learning algorithms has produced advances in the study of the connection between the EEG activities of the stimulated partner and the isolated distant partner, opening new insight into the possibility to devise practical application for non-conventional “mental telecommunications” between physically and sensorially separated participants.

Stress Emotion Recognition Based on RSP and EMG Signals

To recognize the stress emotion, a subject was put alternately in periods of high and low stress by configuring the speed and difficulty of a game named Tetris. The respiration (RSP) signal and the electromyogram (EMG) signal with different stress level were then acquired. After preprocessing, the mathematical features were calculated and automatic detection of stress level based on Fisher linear discriminant classifier was realized. The results show that the average correct detection rate of stress level based on the EMG signal can reach 97.8%. That of the RSP signal is only 86.7%. The EMG signal is more effective than the RSP signal in detection of stress level. Union of multiple physiological signals can effectively improve the correct detection rate.