Schizophrenia is a severe psychiatric disorder showing cognitive deficits among the early symptoms. Previous studies have reported that sex hormones are related to the cognitive dysfunction in schizophrenia. In this paper, we explore sex hormones as the potential biomarkers in differentiating first-episode schizophrenia patients from healthy controls, and investigate the most discriminative sex-hormone related biomarkers for the diagnosis of schizophrenia at the same time. Specifically, six sex hormones, which are follicle-stimulating hormone, luteinizing hormone, prolactin, estradiol, progesterone and testosterone, were examined as the basic features. Based on these sex hormones, the sex-hormone ratios and log-transformed sex-hormone ratios were computed for feature enhancement. T-test was further used for feature selection. In order to avoid the possible bias on sex hormones caused by female physiological factors, the classification experiment was performed on male participants using random forest. The effectiveness of different feature combination strategies was further studied. Among these strategies, the scheme fusing sex hormones, sex-hormone ratios and log-transformed sex-hormone ratios produced the best classification performance with an accuracy of 80.67%, which is comparable with the results obtained by complex neuroimaging data. Finally, the most discriminative features were further discussed according to the t-test results. Results show that the luteinizing hormone, prolactin, sex-hormone ratios and log-transformed sex-hormone ratios are the most significant features. This work supports the use of sex hormones as potential biomarkers for the diagnosis of schizophrenia. Given the convenient detection of these sex hormones in the routine examination, it could be a more straightforward and cost-saving way for the early diagnosis of schizophrenia patients.
Schizophrenia is associated with cognitive impairments. Exercise interventions including yoga and aerobic exercise have been shown to improve cognitive functioning in schizophrenic patients. Yet the underlying neural basis is not clear for this cognitive improvement. This work aimed to investigate the brain functional effect caused by exercise interventon in female patients with early psychosis. Resting-state fMRI was collected longitudinally from 71 patients who were randomized into three programs: yoga, aerobic exercise and waitlist control. Functional connectivity matrices of each individual at baseline and 12-week follow-up timepoint were estimated. Then the connectivity changes were calculated and used as potential predictors to classify the three groups. A machine learning method gcForest was used to train classification models on a subset and tested on the rest of the data. Classification performance was evaluated using multiple n-fold cross-validation to ensure a robust estimate of the accuracy. The classification accuracy ranges from 86.31 to 94.00. The most predictive features were examined in the brain, which include connectivity changes along several major pathways in high order functional networks including default mode and executive control networks. This is the first study showing that the connectivity alterations can successfully distinguish intervention from control groups, and also detect the two different types of intervention: yoga and aerobic exercise. Findings suggest that the altered functional connectivity may contribute to the cognitive improvement after intervention. Our work sheds light on the use of advanced neuroimaging and machine learning approaches to explore potential biomarkers for predicting outcomes of exercise intervention in psychosis.
Alzheimer's disease (AD) is an irreversible neurodegenerative disorder with progressive impairment of memory and cognitive functions. Its early diagnosis is crucial for development of future treatment. Magnetic resonance images (MRI) play important role to help understand the brain anatomical changes related to AD. Conventional methods extract the hand-crafted features such as gray matter volumes and cortical thickness and train a classifier to distinguish AD from other groups. Different from these methods, this paper proposes to construct multiple deep 3D convolutional neural networks (3D-CNNs) to learn the various features from local brain images which are combined to make the final classification for AD diagnosis. First, a number of local image patches are extracted from the whole brain image and a 3D-CNN is built upon each local patch to transform the local image into more compact high-level features. Then, the upper convolution and fully connected layers are fine-tuned to combine the multiple 3D-CNNs for image classification. The proposed method can automatically learn the generic features from imaging data for classification. Our method is evaluated using T1-weighted structural MR brain images on 428 subjects including 199 AD patients and 229 normal controls (NC) from Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Experimental results show that the proposed method achieves an accuracy of 87.15% and an AUC (area under the ROC curve) of 92.26% for AD classification, demonstrating the promising classification performances.