A hybrid 1D CNN-BiLSTM model for epileptic seizure detection using multichannel EEG feature fusion.

Epilepsy, a chronic non-communicable disease is characterized by repeated unprovoked seizures, which are transient episodes of abnormal electrical activity in the brain. While Electroencephalography (EEG) is considered as the gold standard for diagnosis in current clinical practice, manual inspection of EEG is time consuming and biased. This paper presents a novel hybrid 1D CNN-Bi LSTM feature fusion model for automatically detecting seizures. The proposed model leverages spatial features extracted by one dimensional convolutional neural network and temporal features extracted by bi directional long short-term memory network. Ictal and inter ictal data is first acquired from the long multichannel EEG record. The acquired data is segmented and labelled using small fixed windows. Signal features are then extracted from the segments concurrently by the parallel combination of CNN and Bi-LSTM. The spatial and temporal features thus captured are then fused to enhance classification accuracy of model. The approach is validated using benchmark CHB-MIT dataset and 5-fold cross validation which resulted in an average accuracy of 95.90%, with precision 94.78%, F1 score 95.95%. Notably model achieved average sensitivity of 97.18% with false positivity rate at 0.05/hr. The significantly lower false positivity and false negativity rates indicate that the proposed model is a promising tool for detecting seizures in epilepsy patients. The employed parallel path network benefits from memory function of Bi-LSTM and strong feature extraction capabilities of CNN. Moreover, eliminating the need for any domain transformation or additional preprocessing steps, model effectively reduces complexity and enhances efficiency, making it suitable for use by clinicians during the epilepsy diagnostic process.

How does "locus of control" affect persons with epilepsy?

PURPOSE: Locus of control (LOC) is the degree to which people believe that they have control over the outcome of events in their lives. A person's locus can be internal, external, or chance. A person with internal locus of control believes that one can control one's own life. A person with external locus of control believes that his life is controlled by external factors or people over which he has no influence. A person with chance locus of control believes that fate, chance, or luck controls his own life. The aim of the current study was to determine the health locus of control, anxiety, and depression levels in persons with epilepsy (PWE) and to assess whether locus of control has relation to anxiety, depression, and seizure control. METHODS: Patients aged 18 years or older with a history of epilepsy for at least 1 year were recruited from the outpatient epilepsy clinic or from the inpatient epilepsy monitoring unit at SCTIMST, Trivandrum from January 2019 to May 2020. Patients filled the questionnaire form consisting of demographic data, age of onset of seizures, present seizure control, and the current antiepileptic drugs. The Hospital Anxiety and Depression (HAD) scale was used to estimate the level of anxiety and depression in these patients. The Form-C of the Multidimensional Health Locus of Control (MHLC) scale was used to evaluate the health locus of control. Healthy controls aged 18 years or older and free of any chronic disease or psychiatric illness were also recruited. They were asked to fill the questionnaire forms with basic demographic data. HAD scale was used to estimate the level of anxiety and depression and form-C of MHLC was used to evaluate the health locus of control in the healthy controls. The mean scores of anxiety, depression, and locus of control were compared between the two groups. RESULTS: A total of 170 participants were recruited which consisted of 100 PWE and 70 healthy controls. The mean anxiety and depression scores were 8.13(SD = 4.23) and 5.85(SD = 3.66) in the PWE group and 6.75(SD = 3.39) and 4.14(SD = 2.96) in the control group, respectively. The mean internal, external, and chance LOC scores were 24.95(SD = 10.92), 26.94(SD = 4.96), and 24.41(SD = 6.46) in the PWE group; and 29.44(SD = 5.62), 26.53(SD = 5.79), and 19.9(SD = 7.13) in the control group, respectively. Persons with epilepsy had higher chance LOC scores and lower internal LOC scores compared to controls (p = 0.00003, p < 0.00001 respectively). There were no differences in the external LOC scores between the two groups (p = 0.620). Persons with epilepsy with some level of anxiety had lower internal LOC scores compared to patients with no anxiety (p = 0.04). PWE with poor seizure control had higher external LOC score and lower internal LOC scores which however did not reach statistical significance. Persons with epilepsy with poor seizure control had higher anxiety and depression scores. CONCLUSIONS: Persons with epilepsy had low perceptions of internal and strong perceptions of chance health locus of control. This means that PWE feel that luck plays an important role in their disease control. This information is important in the counseling of persons with epilepsy.