A deep learning approach for diagnosis of schizophrenia disorder via data augmentation based on convolutional neural network and long short-term memory.

Schizophrenia (SZ) is a severe, chronic mental disorder without specific treatment. Due to the increasing prevalence of SZ in societies and the similarity of the characteristics of this disease with other mental illnesses such as bipolar disorder, most people are not aware of having it in their daily lives. Therefore, early detection of this disease will allow the sufferer to seek treatment or at least control it. Previous SZ detection studies through machine learning methods, require the extraction and selection of features before the classification process. This study attempts to develop a novel, end-to-end approach based on a 15-layers convolutional neural network (CNN) and a 16-layers CNN- long short-term memory (LSTM) to help psychiatrists automatically diagnose SZ from electroencephalogram (EEG) signals. The deep model uses CNN layers to learn the temporal properties of the signals, while LSTM layers provide the sequence learning mechanism. Also, data augmentation method based on generative adversarial networks is employed over the training set to increase the diversity of the data. Results on a large EEG dataset show the high diagnostic potential of both proposed methods, achieving remarkable accuracy of 98% and 99%. This study shows that the proposed framework is able to accurately discriminate SZ from healthy subject and is potentially useful for developing diagnostic tools for SZ disorder.

Deceptive intensities: An exploratory strategy for overcoming early central fatigue in resistance training.

Neuropsychological stress induced by misleading information can limit human performance, possibly by early central fatigue mechanisms. In this study, we investigated the impact caused by prescribing misleading intensities of resistance exercise on acute electroencephalogram (EEG) and electromyogram (EMG) responses and the total number of repetitions to exhaustion. Collegiate female students performed three sets of biceps curls to exhaustion. The actual intensity for all sets was set at 65% 1-Repetition Maximum (1-RM). However, participants were deceptively informed that the intensities were 60%, 65%, or 70% 1-RM. The number of repetitions to fatigue and the magnitude of EEG and EMG signals were analyzed. The number of repetitions to exhaustion was significantly lower in greater announced intensities (18.11 ± 8.44) compared to lower (29.76 ± 16.28; p = 0.017) and correctly (27.82 ± 11.01; p = 0.001) announced intensity. The correlation between frontal and motor-cortex signals was significant in lower (r = 0.72, p = 0.001) and higher (r = 0.64, p = 0.005) announced intensities. The median and mean frequencies of EMG signal and Root Mean Square (RMS) did not show any significant difference between sets, but the peak-to-peak range (PPR) of biceps EMG signals was significantly higher in lower intensity (0.145 ± 0.042) when compared with higher (0.104 ± 0.044; p = 0.028) or correctly (0.126 ± 0.048; p = 0.037) announced intensity. It seems that deceptive information regarding the mass of an object could affect the number of repetitions to exhaustion and PPR to cover muscle capacity in endurance-type strength training.

Source separation from single-channel abdominal phonocardiographic signals based on independent component analysis.

Purpose: Continuous monitoring of fetal heart rate (FHR) is essential to diagnose heart abnormalities. Therefore, FHR measurement is considered as the most important parameter to evaluate heart function. One method of FHR extraction is done by using fetal phonocardiogram (fPCG) signal, which is obtained directly from the mother abdominal surface with a medical stethoscope. A variety of high-amplitude interference such as maternal heart sound and environmental noise cause a low SNR fPCG signal. In addition, the signal is nonstationary because of changes in features that are highly dependent on pregnancy age, fetal position, maternal obesity, bandwidth of the recording system and nonlinear transmission environment. Methods: In this paper, a sources separation process from the recorded fPCG signal is proposed. Independent component analysis (ICA) has always been one of the most efficient methods for extracting background noise from multichannel data. In order to extract the source signals from the single-channel fPCG data using ICA algorithm, it is necessary to first decompose the signal into multivariate data using a proper decomposition technique. In this paper, we implemented three combined methods of SSA-ICA, Wavelet-ICA and EEMD-ICA. Results: In order to validate the performance of the methods, we used simulated and real fPCG signals. The results indicated that SSA-ICA recovers sources of single-channel signals with different SNRs. Conclusion: The performance criteria such as power spectral density (PSD) peak and cross correlation value show that the SSA-ICA method has been more successful in extracting independent sources.

Medullary Thyroid Carcinoma--Circulating Status of Vaspin and Retinol Binding Protein-4 in Iranian Patients.

BACKGROUND: Vaspin and Retinol binding protein-4 (RBP4) are new adipokines mainly produced by adipose tissue. Considering that medullary thyroid carcinoma (MTC) is a malignant neuroendocrine tumor, and to date the relationship between serum levels of vaspin and RBP4 with MTC has not been studied, in this matched case-control study we evaluated their possible significance to this tumor type. MATERIALS AND METHODS: A total of 45 patients with MTC (21 males and 24 females) and 45 healthy persons as a control group (24 males and 21 females) were selected. The two groups were matched for age, sex and body mass index. Serum Vaspin and RBP4 levels were measured by enzyme-linked immunosorbent assay (ELISA) methods in both groups. Also, weight and height were measured and body mass index was calculated too. RESULTS: In total, patients with MTC had significantly higher serum vaspin levels compared to the controls (0.52 ng/ml vs. 0.45 ng/ml, P=0.0241). However, no significant difference was found in serum RBP4 concentrations between the patients with MTC and the controls (15.2±2.55 µg/ml versus 15.1±3.34 µg/ml, p>0.05). CONCLUSIONS: The results of this study demonstrated that serum RBP4 levels in MTC patients are not significantly different from those found in healthy individuals and did not correlate with MTC. On the other hand, higher levels of serum vaspin are associated with an increased risk of MTC. Thus Vaspin may be a novel and promising biomarker for diagnosis or confirmation of MTC in conjunction other specific tumor markers.

Modeling of heart systolic murmurs based on multivariate matching pursuit for diagnosis of valvular disorders.

Heart murmurs are pathological sounds produced by turbulent blood flow due to certain cardiac defects such as valves disorders. Detection of murmurs via auscultation is a task that depends on the proficiency of physician. There are many cases in which the accuracy of detection is questionable. The purpose of this study is development of a new mathematical model of systolic murmurs to extract their crucial features for identifying the heart diseases. A high resolution algorithm, multivariate matching pursuit, was used to model the murmurs by decomposing them into a series of parametric time-frequency atoms. Then, a novel model-based feature extraction method which uses the model parameters was performed to identify the cardiac sound signals. The proposed framework was applied to a database of 70 heart sound signals containing 35 normal and 35 abnormal samples. We achieved 92.5% accuracy in distinguishing subjects with valvular diseases using a MLP classifier, as compared to the matching pursuit-based features with an accuracy of 77.5%.

Nutrigenomics and cancer.

Cancer incidence is projected to increase in the future and an effectual preventive strategy is required to face this challenge. Alteration of dietary habits is potentially an effective approach for reducing cancer risk. Assessment of biological effects of a specific food or bioactive component that is linked to cancer and prediction of individual susceptibility as a function of nutrient-nutrient interactions and genetics is an essential element to evaluate the beneficiaries of dietary interventions. In general, the use of biomarkers to evaluate individuals susceptibilities to cancer must be easily accessible and reliable. However, the response of individuals to bioactive food components depends not only on the effective concentration of the bioactive food components, but also on the target tissues. This fact makes the response of individuals to food components vary from one individual to another. Nutrigenomics focuses on the understanding of interactions between genes and diet in an individual and how the response to bioactive food components is influenced by an individual's genes. Nutrients have shown to affect gene expression and to induce changes in DNA and protein molecules. Nutrigenomic approaches provide an opportunity to study how gene expression is regulated by nutrients and how nutrition affects gene variations and epigenetic events. Finding the components involved in interactions between genes and diet in an individual can potentially help identify target molecules important in preventing and/or reducing the symptoms of cancer.