A Comparative Study of Feature Selection Methods for the Discriminative Analysis of Temporal Lobe Epilepsy

Cortical morphometric vulnerability to generalised epilepsy reflects chromosome- and cell type-specific transcriptomic signatures

AIMS

Generalised epilepsy is thought to involve distributed brain networks. However, the molecular and cellular factors that render different brain regions more vulnerable to epileptogenesis remain largely unknown. We aimed to investigate epilepsy-related morphometric similarity network (MSN) abnormalities at the macroscale level and their relationships with microscale gene expressions at the microscale level.

METHODS

We compared the MSN of genetic generalised epilepsy with generalised tonic-clonic seizure patients (GGE-GTCS, n = 101) to demographically matched healthy controls (HC, n = 150). Cortical MSNs were estimated by combining seven morphometric features derived from structural magnetic resonance imaging for each individual. Regional gene expression profiles were derived from brain-wide microarray measurements provided by the Allen Human Brain Atlas.

RESULTS

GGE-GTCS patients exhibited decreased regional MSNs in primary motor, prefrontal and temporal regions and increases in occipital, insular and posterior cingulate cortices, when compared with the HC. These case-control neuroimaging differences were validated using split-half analyses and were not affected by medication or drug response effects. When assessing associations with gene expression, genes associated with GGE-GTCS-related MSN differences were enriched in several biological processes, including 'synapse organisation', 'neurotransmitter transport' pathways and excitatory/inhibitory neuronal cell types. Collectively, the GGE-GTCS-related cortical vulnerabilities were associated with chromosomes 4, 5, 11 and 16 and were dispersed bottom-up at the cellular, pathway and disease levels, which contributed to epileptogenesis, suggesting diverse neurobiologically relevant enrichments in GGE-GTCS.

CONCLUSIONS

By bridging the gaps between transcriptional signatures and in vivo neuroimaging, we highlighted the importance of using MSN abnormalities of the human brain in GGE-GTCS patients to investigate disease-relevant genes and biological processes.

Computerized application for epilepsy in China: Does the era of artificial intelligence comes?

Epilepsy, one of the most common neurological diseases in China, is notorious for its spontaneous, unprovoked and recurrent seizures. The etiology of epilepsy varies among individual patients, including congenital gene mutation, traumatic injury, infections, etc. This heterogeneity partly hampered the accurate diagnosis and choice of appropriate treatments. Encouragingly, great achievements have been achieved in computational science, making it become a key player in medical fields gradually and bringing new hope for rapid and accurate diagnosis as well as targeted therapies in epilepsy. Here, we historically review the advances of computerized applications in epilepsy-especially those tremendous findings achieved in China-for different purposes including seizure prediction, localization of epileptogenic zone, post-surgical prognosis, etc. Special attentions are paid to the great progress based on artificial intelligence (AI), which is more "sensitive", "smart" and "in-depth" than human capacities. At last, we give a comprehensive discussion about the disadvantages and limitations of current computerized applications for epilepsy and propose some future directions as further stepping stones to embrace "the era of AI" in epilepsy.

Using a recurrent neural network with S2 characteristics, efficient identification of localised cortical dysplasia

Focal cortical dysplasia (FCD) is an inborn anomaly in brain growth and morphological deformation in lesions of the brain which induces focal seizures. Neurosurgical therapies were performed for the detection of FCD. Furthermore, it can be overcome through the presurgical evaluation of epilepsy. The surgical result is attained basically through the output of the presurgical output. In preprocessing the process of increasing true positives with the decrease in false negatives occurs which results in an effective outcome. MRI (Magnetic Resonance Imaging) outputs are efficient to predict the FCD lesions through T1- MPRAGE and T2- FLAIR efficient output can be obtained. In our proposed work we extract the S2 features through the testing of T1, T2 images. Using RNN-LSTM (Recurrent neural network-Long short-term memory) test images were trained and the FCD lesions were segmented. The output of our work is compared with the proposed work yields better results compared to the existing system such as artificial neural network (ANN), support vector machine (SVM), and convolution neural network (CNN). This approach obtained an accuracy rate of 0.195% (ANN), 0.20% (SVM), 0.14% (CNN), specificity rate of 0.23% (ANN), 0.15% (SVM), 0.13% (CNN) and sensitivity rate of 0.22% (ANN), 0.14% (SVM), 0.08% (CNN) respectively in comparison with RNN-LSTM.

Evaluation of Feature Selection Methods for Classification of Epileptic Seizure EEG Signals

Epilepsy is a disease that decreases the quality of life of patients; it is also among the most common neurological diseases. Several studies have approached the classification and prediction of seizures by using electroencephalographic data and machine learning techniques. A large diversity of features has been extracted from electroencephalograms to perform classification tasks; therefore, it is important to use feature selection methods to select those that leverage pattern recognition. In this study, the performance of a set of feature selection methods was compared across different classification models; the classification task consisted of the detection of ictal activity from the CHB-MIT and Siena Scalp EEG databases. The comparison was implemented for different feature sets and the number of features. Furthermore, the similarity between selected feature subsets across classification models was evaluated. The best F1-score (0.90) was reported by the K-nearest neighbor along with the CHB-MIT dataset. Results showed that none of the feature selection methods clearly outperformed the rest of the methods, as the performance was notably affected by the classifier, dataset, and feature set. Two of the combinations (classifier/feature selection method) reporting the best results were K-nearest neighbor/support vector machine and random forest/embedded random forest.

EBST: An Evolutionary Multi-Objective Optimization Based Tool for Discovering Potential Biomarkers in Ovarian Cancer

Ovarian cancer is the deadliest gynecologic malignancy, mainly due to limitations in early diagnosis. With advances in high-throughput technologies, research interest in identifying novel and customized tumor biomarkers for early detection and diagnosis is rapidly growing. Here we introduce a new tool called EBST to select microRNAs with biomarker potency in ovarian cancer. This tool has pre-processing options and Its core is the use of Modified Multi Objective Imperialist Competitive Algorithm and six objective functions based on the classifier performance/structure evaluation, clustering error and mRMR filter. In this paper, we used the FDR filter in the pre-processing stage and considered five objective functions, four of which relate to the l₁-SVM classifier performance and one to the average mRMR ranking. The proposed method has identified 11 microRNAs including hsa-miR-6784-5p, hsa-miR-1228-5p, hsa-miR-8073, hsa-miR-6756-5p, hsa-miR-1307-3p, hsa-miR-4697-5p, hsa-miR-3663-3p, hsa-miR-328-5p, hsa-miR-1228-3p, hsa-miR-6821-5p, hsa-miR-1268a. Data classification by the proposed model showed 100 percent sensitivity, 99.38 percent specificity, 99.69 percent accuracy and 99.39 percent positive predictive value. In comparison with routine state-of-the-art methods, superiority of our method was confirmed. The biological evaluation of selected microRNAs using bioinformatics tools and published articles confirms their role in cancer signaling pathways. The tool and its MATLAB code are freely available at https://github.com/hanif-y.

CB2R induces a protective response against epileptic seizures through ERK and p38 signaling pathways

BACKGROUND AND PURPOSE

Epilepsy is a pivotal neurological disorder characterized by the synchronous discharging of neurons to induce momentary brain dysfunction. Temporal lobe epilepsy is the most common type of epilepsy, with seizures originating from the mesial temporal lobe. The hippocampus forms part of the mesial temporal lobe and plays a significant role in epileptogenesis; it also has a vital influence on the mental development of children. In this study, we aimed to explore the effects of CB2 receptor (CB2R) activation on ERK and p38 signaling in nerve cells of a rat epilepsy model.

MATERIALS AND METHODS

We treated Sprague-Dawley rats with pilocarpine to induce an epilepsy model and treated such animals with a CB2R agonist (JWH133) alone or with a CB2R antagonist (AM630). Nissl's stain showed the neuron conditon in different groups. Western blot analyzed the level of p-ERK and p-p38.

RESULTS

JWH133 can increase the latent period of first seizure attack and decrease the Grades IV-V magnitude ratio after the termination of SE. Nissl's stain showed JWH133 protected neurons in the hippocampus while AM630 inhibited the functioning of CB2R in neurons. Western blot analysis showed that JWH133 decreased levels of p-ERK and p-p38, which is found at increased levels in the hippocampus of our epilepsy model. In contrast, AM630 inhibited the protective function of JWH133 and also enhanced levels of p-ERK and p-p38.

CONCLUSIONS

CB2R activation can induce neurons proliferation and survival through activation of ERK and p38 signaling pathways.

Analysing wideband absorbance immittance in normal and ears with otitis media with effusion using machine learning

Wideband Absorbance Immittance (WAI) has been available for more than a decade, however its clinical use still faces the challenges of limited understanding and poor interpretation of WAI results. This study aimed to develop Machine Learning (ML) tools to identify the WAI absorbance characteristics across different frequency-pressure regions in the normal middle ear and ears with otitis media with effusion (OME) to enable diagnosis of middle ear conditions automatically. Data analysis included pre-processing of the WAI data, statistical analysis and classification model development, and key regions extraction from the 2D frequency-pressure WAI images. The experimental results show that ML tools appear to hold great potential for the automated diagnosis of middle ear diseases from WAI data. The identified key regions in the WAI provide guidance to practitioners to better understand and interpret WAI data and offer the prospect of quick and accurate diagnostic decisions.

Automated fusion of multimodal imaging data for identifying epileptogenic lesions in patients with inconclusive magnetic resonance imaging

Many methods applied to data acquired by various imaging modalities have been evaluated for their benefit in localizing lesions in magnetic resonance (MR) negative epilepsy patients. No approach has proven to be a stand-alone method with sufficiently high sensitivity and specificity. The presented study addresses the potential benefit of the automated fusion of results of individual methods in presurgical evaluation. We collected electrophysiological, MR, and nuclear imaging data from 137 patients with pharmacoresistant MR-negative/inconclusive focal epilepsy. A subgroup of 32 patients underwent surgical treatment with known postsurgical outcomes and histopathology. We employed a Gaussian mixture model to reveal several classes of gray matter tissue. Classes specific to epileptogenic tissue were identified and validated using the surgery subgroup divided into two disjoint sets. We evaluated the classification accuracy of the proposed method at a voxel-wise level and assessed the effect of individual methods. The training of the classifier resulted in six classes of gray matter tissue. We found a subset of two classes specific to tissue located in resected areas. The average classification accuracy (i.e., the probability of correct classification) was significantly higher than the level of chance in the training group (0.73) and even better in the validation surgery subgroup (0.82). Nuclear imaging, diffusion-weighted imaging, and source localization of interictal epileptic discharges were the strongest methods for classification accuracy. We showed that the automatic fusion of results can identify brain areas that show epileptogenic gray matter tissue features. The method might enhance the presurgical evaluations of MR-negative epilepsy patients.

Prediction of Nephrotoxicity Associated With Cisplatin-Based Chemotherapy in Testicular Cancer Patients

Background

Cisplatin-based chemotherapy may induce nephrotoxicity. This study presents a random forest predictive model that identifies testicular cancer patients at risk of nephrotoxicity before treatment.

Methods

Clinical data and DNA from saliva samples were collected for 433 patients. These were genotyped on Illumina HumanOmniExpressExome-8 v1.2 (964 193 markers). Clinical and genomics-based random forest models generated a risk score for each individual to develop nephrotoxicity defined as a 20% drop in isotopic glomerular filtration rate during chemotherapy. The area under the receiver operating characteristic curve was the primary measure to evaluate models. Sensitivity, specificity, and positive and negative predictive values were used to discuss model clinical utility.

Results

Of 433 patients assessed in this study, 26.8% developed nephrotoxicity after bleomycin-etoposide-cisplatin treatment. Genomic markers found to be associated with nephrotoxicity were located at NAT1, NAT2, and the intergenic region of CNTN6 and CNTN4. These, in addition to previously associated markers located at ERCC1, ERCC2, and SLC22A2, were found to improve predictions in a clinical feature–trained random forest model. Using only clinical data for training the model, an area under the receiver operating characteristic curve of 0.635 (95% confidence interval [CI] = 0.629 to 0.640) was obtained. Retraining the classifier by adding genomics markers increased performance to 0.731 (95% CI = 0.726 to 0.736) and 0.692 (95% CI = 0.688 to 0.696) on the holdout set.

Conclusions

A clinical and genomics-based machine learning algorithm improved the ability to identify patients at risk of nephrotoxicity compared with using clinical variables alone. Novel genetics associations with cisplatin-induced nephrotoxicity were found for NAT1, NAT2, CNTN6, and CNTN4 that require replication in larger studies before application to clinical practice.

Detecting Abnormal Brain Regions in Schizophrenia Using Structural MRI via Machine Learning

Utilizing neuroimaging and machine learning (ML) to differentiate schizophrenia (SZ) patients from normal controls (NCs) and for detecting abnormal brain regions in schizophrenia has several benefits and can provide a reference for the clinical diagnosis of schizophrenia. In this study, structural magnetic resonance images (sMRIs) from SZ patients and NCs were used for discriminative analysis. This study proposed an ML framework based on coarse-to-fine feature selection. The proposed framework used two-sample t-tests to extract the differences between groups first, then further eliminated the nonrelevant and redundant features with recursive feature elimination (RFE), and finally utilized the support vector machine (SVM) to learn the decision models with selected gray matter (GM) and white matter (WM) features. Previous studies have tended to report differences at the group level instead of at the individual level and cannot be widely applied. The method proposed in this study extends the diagnosis to the individual level and has a higher recognition rate than previous methods. The experimental results of this study demonstrate that the proposed framework distinguishes SZ patients from NCs, with the highest classification accuracy reaching over 85%. The identified biomarkers are also consistent with previous literature findings. As a universal method, the proposed framework can be extended to diagnose other diseases.

Presurgical epilepsy evaluation and epilepsy surgery

With a prevalence of 0.8 to 1.2%, epilepsy represents one of the most frequent chronic neurological disorders; 30 to 40% of patients suffer from drug-resistant epilepsy (that is, seizures cannot be controlled adequately with antiepileptic drugs). Epilepsy surgery represents a valuable treatment option for 10 to 50% of these patients. Epilepsy surgery aims to control seizures by resection of the epileptogenic tissue while avoiding neuropsychological and other neurological deficits by sparing essential brain areas. The most common histopathological findings in epilepsy surgery specimens are hippocampal sclerosis in adults and focal cortical dysplasia in children. Whereas presurgical evaluations and surgeries in patients with mesial temporal sclerosis and benign tumors recently decreased in most centers, non-lesional patients, patients requiring intracranial recordings, and neocortical resections increased. Recent developments in neurophysiological techniques (high-density electroencephalography [EEG], magnetoencephalography, electrical and magnetic source imaging, EEG-functional magnetic resonance imaging [EEG-fMRI], and recording of pathological high-frequency oscillations), structural magnetic resonance imaging (MRI) (ultra-high-field imaging at 7 Tesla, novel imaging acquisition protocols, and advanced image analysis [post-processing] techniques), functional imaging (positron emission tomography and single-photon emission computed tomography co-registered to MRI), and fMRI significantly improved non-invasive presurgical evaluation and have opened the option of epilepsy surgery to patients previously not considered surgical candidates. Technical improvements of resective surgery techniques facilitate successful and safe operations in highly delicate brain areas like the perisylvian area in operculoinsular epilepsy. Novel less-invasive surgical techniques include stereotactic radiosurgery, MR-guided laser interstitial thermal therapy, and stereotactic intracerebral EEG-guided radiofrequency thermocoagulation.

A MACHINE LEARNING MODEL TO PREDICT SEIZURE SUSCEPTIBILITY FROM RESTING-STATE FMRI CONNECTIVITY

Traumatic brain injury (TBI) is a leading cause of disability globally. Many patients develop post-traumatic epilepsy, or recurrent seizures following TBI. In recent years, significant efforts have been made to identify biomarkers of epileptogenesis that may assist in preventing seizure occurrence by identifying high-risk patients. We present a novel method of assessing seizure susceptibility using data from 49 patients enrolled in the Epilepsy Bioinformatics Study for Antiepileptogenic Therapy (EpiBioS4Rx). We employ a machine learning paradigm that utilizes a Random Forest classifier trained with resting-state functional magnetic resonance imaging (fMRI) data to predict seizure outcomes. Following 100 rounds of stratified cross-validation with 70% of resting state fMRI scans as the training set and 30% as the testing set, our model was found to assess seizure outcome in the testing set with 69% accuracy. To validate the method, we compared our results with classification by Support Vector Machines and Neural Network classifiers.

A Novel Feature Optimization for Wearable Human-Computer Interfaces Using Surface Electromyography Sensors

The novel human-computer interface (HCI) using bioelectrical signals as input is a valuable tool to improve the lives of people with disabilities. In this paper, surface electromyography (sEMG) signals induced by four classes of wrist movements were acquired from four sites on the lower arm with our designed system. Forty-two features were extracted from the time, frequency and time-frequency domains. Optimal channels were determined from single-channel classification performance rank. The optimal-feature selection was according to a modified entropy criteria (EC) and Fisher discrimination (FD) criteria. The feature selection results were evaluated by four different classifiers, and compared with other conventional feature subsets. In online tests, the wearable system acquired real-time sEMG signals. The selected features and trained classifier model were used to control a telecar through four different paradigms in a designed environment with simple obstacles. Performance was evaluated based on travel time (TT) and recognition rate (RR). The results of hardware evaluation verified the feasibility of our acquisition systems, and ensured signal quality. Single-channel analysis results indicated that the channel located on the extensor carpi ulnaris (ECU) performed best with mean classification accuracy of 97.45% for all movement’s pairs. Channels placed on ECU and the extensor carpi radialis (ECR) were selected according to the accuracy rank. Experimental results showed that the proposed FD method was better than other feature selection methods and single-type features. The combination of FD and random forest (RF) performed best in offline analysis, with 96.77% multi-class RR. Online results illustrated that the state-machine paradigm with a 125 ms window had the highest maneuverability and was closest to real-life control. Subjects could accomplish online sessions by three sEMG-based paradigms, with average times of 46.02, 49.06 and 48.08 s, respectively. These experiments validate the feasibility of proposed real-time wearable HCI system and algorithms, providing a potential assistive device interface for persons with disabilities.