Automated EEG-based screening of depression using deep convolutional neural network

EMPIRICAL MODE DECOMPOSITION-BASED PROCESSING FOR AUTOMATED DETECTION OF EPILEPSY

Epilepsy is a chronic illness of the brain characterized by recurring seizure attacks. Electroencephalogram (EEG) can record the electrical activity of the brain and is extensively used to analyze and diagnose epileptic seizures. However, the EEG signals are highly non-linear and chaotic and are difficult to analyze due to their small magnitude. Hence, empirical mode decomposition (EMD), a non-linear technique, has been widely adopted to capture the subtle changes present in the EEG signals. Hence, it is an added advantage to develop an automated computer-aided diagnostic (CAD) system to detect the different brain activities from the EEG signals using machine learning approaches. In this paper, we focus on the previous works which have used the EMD technique in the automated detection of normal or epileptic EEG signals.

Deep learning for electroencephalogram (EEG) classification tasks: a review

OBJECTIVE

Electroencephalography (EEG) analysis has been an important tool in neuroscience with applications in neuroscience, neural engineering (e.g. Brain-computer interfaces, BCI's), and even commercial applications. Many of the analytical tools used in EEG studies have used machine learning to uncover relevant information for neural classification and neuroimaging. Recently, the availability of large EEG data sets and advances in machine learning have both led to the deployment of deep learning architectures, especially in the analysis of EEG signals and in understanding the information it may contain for brain functionality. The robust automatic classification of these signals is an important step towards making the use of EEG more practical in many applications and less reliant on trained professionals. Towards this goal, a systematic review of the literature on deep learning applications to EEG classification was performed to address the following critical questions: (1) Which EEG classification tasks have been explored with deep learning? (2) What input formulations have been used for training the deep networks? (3) Are there specific deep learning network structures suitable for specific types of tasks?

APPROACH

A systematic literature review of EEG classification using deep learning was performed on Web of Science and PubMed databases, resulting in 90 identified studies. Those studies were analyzed based on type of task, EEG preprocessing methods, input type, and deep learning architecture.

MAIN RESULTS

For EEG classification tasks, convolutional neural networks, recurrent neural networks, deep belief networks outperform stacked auto-encoders and multi-layer perceptron neural networks in classification accuracy. The tasks that used deep learning fell into five general groups: emotion recognition, motor imagery, mental workload, seizure detection, event related potential detection, and sleep scoring. For each type of task, we describe the specific input formulation, major characteristics, and end classifier recommendations found through this review.

SIGNIFICANCE

This review summarizes the current practices and performance outcomes in the use of deep learning for EEG classification. Practical suggestions on the selection of many hyperparameters are provided in the hope that they will promote or guide the deployment of deep learning to EEG datasets in future research.

Computer Aided Diagnosis System for multiple sclerosis disease based on phase to amplitude coupling in covert visual attention

BACKGROUND AND OBJECTIVE

Computer Aided Diagnosis (CAD) techniques have widely been used in research to detect the neurological abnormalities and improve the consistency of diagnosis and treatment in medicine. In this study, a new CAD system based on EEG signals was developed. The motivation for the development of the CAD system was to diagnose multiple sclerosis (MS) disease during covert visual attention tasks. It is worth noting that research of this kind on the efficacy of attention tasks is limited in scope for MS patients; therefore, it is vital to develop a feature of EEG to characterize the patient's state with high sensitivity and specificity.

METHODS

We evaluated the use of phase-amplitude coupling (PAC) of EEG signals to diagnose MS. It is assumed that the role of PAC for information encoding during visual attention in MS is greatly unknown; therefore, we made an attempt to investigate it via CAD systems. The EEG signals were recorded from healthy and MS patients while performing new visual attention tasks. Machine learning algorithms were also used to identify the EEG signals as to whether the disease existed or not. The challenge regarding the dimensionality of the extracted features was addressed through selecting the relevant and efficient features using T-test and Bhattacharyya distance criteria, and the validity of the system was assessed through leave-one-subject-out cross-validation method.

RESULTS

Our findings indicated that online sequential extreme learning machine (OS-ELM) classifier with T-test feature selection method yielded peak accuracy, sensitivity and specificity in both color and direction tasks. These values were 91%, 83% and 96% for color task, and 90%, 82% and 96% for the direction task.

CONCLUSIONS

Based on the results, it can be concluded that this procedure can be used for the automatic diagnosis of early MS, and can also facilitate the treatment assessment in patients.

Drug-Drug Interaction Extraction via Recurrent Hybrid Convolutional Neural Networks with an Improved Focal Loss

Drug-drug interactions (DDIs) may bring huge health risks and dangerous effects to a patient’s body when taking two or more drugs at the same time or within a certain period of time. Therefore, the automatic extraction of unknown DDIs has great potential for the development of pharmaceutical agents and the safety of drug use. In this article, we propose a novel recurrent hybrid convolutional neural network (RHCNN) for DDI extraction from biomedical literature. In the embedding layer, the texts mentioning two entities are represented as a sequence of semantic embeddings and position embeddings. In particular, the complete semantic embedding is obtained by the information fusion between a word embedding and its contextual information which is learnt by recurrent structure. After that, the hybrid convolutional neural network is employed to learn the sentence-level features which consist of the local context features from consecutive words and the dependency features between separated words for DDI extraction. Lastly but most significantly, in order to make up for the defects of the traditional cross-entropy loss function when dealing with class imbalanced data, we apply an improved focal loss function to mitigate against this problem when using the DDIExtraction 2013 dataset. In our experiments, we achieve DDI automatic extraction with a micro F-score of 75.48% on the DDIExtraction 2013 dataset, outperforming the state-of-the-art approach by 2.49%.

Machine Learning and Primary Total Knee Arthroplasty: Patient Forecasting for a Patient-Specific Payment Model

BACKGROUND

Value-based and patient-specific care represent 2 critical areas of focus that have yet to be fully reconciled by today's bundled care model. Using a predictive naïve Bayesian model, the objectives of this study were (1) to develop a machine-learning algorithm using preoperative big data to predict length of stay (LOS) and inpatient costs after primary total knee arthroplasty (TKA) and (2) to propose a tiered patient-specific payment model that reflects patient complexity for reimbursement.

METHODS

Using 141,446 patients undergoing primary TKA from an administrative database from 2009 to 2016, a Bayesian model was created and trained to forecast LOS and cost. Algorithm performance was determined using the area under the receiver operating characteristic curve and the percent accuracy. A proposed risk-based patient-specific payment model was derived based on outputs.

RESULTS

The machine-learning algorithm required age, race, gender, and comorbidity scores ("risk of illness" and "risk of morbidity") to demonstrate a high degree of validity with an area under the receiver operating characteristic curve of 0.7822 and 0.7382 for LOS and cost. As patient complexity increased, cost add-ons increased in tiers of 3%, 10%, and 15% for moderate, major, and extreme mortality risks, respectively.

CONCLUSION

Our machine-learning algorithm derived from an administrative database demonstrated excellent validity in predicting LOS and costs before primary TKA and has broad value-based applications, including a risk-based patient-specific payment model.

Parkinson's disease: Cause factors, measurable indicators, and early diagnosis

Parkinson's disease (PD) is a neurodegenerative disease of the central nervous system caused due to the loss of dopaminergic neurons. It is classified under movement disorder as patients with PD present with tremor, rigidity, postural changes, and a decrease in spontaneous movements. Comorbidities including anxiety, depression, fatigue, and sleep disorders are observed prior to the diagnosis of PD. Gene mutations, exposure to toxic substances, and aging are considered as the causative factors of PD even though its genesis is unknown. This paper reviews PD etiologies, progression, and in particular measurable indicators of PD such as neuroimaging and electrophysiology modalities. In addition to gene therapy, neuroprotective, pharmacological, and neural transplantation treatments, researchers are actively aiming at identifying biological markers of PD with the goal of early diagnosis. Neuroimaging modalities used together with advanced machine learning techniques offer a promising path for the early detection and intervention in PD patients.