Neuroimaging technologies have been applied to the diagnosis of schizophrenia. In order to improve the performance of the single-modal neuroimaging-based computer-aided diagnosis (CAD) for schizophrenia, an ensemble learning algorithm based on learning using privileged information (LUPI) was proposed in this work. Specifically, the extreme learning machine based auto-encoder (ELM-AE) was first adopted to learn new feature representation for the single-modal neuroimaging data. Random project algorithm was then performed on the learned high-dimensional features to generate several new feature subspaces. After that, multiple feature pairs were built among these subspaces to work as source domain and target domain, respectively, which were used to train multiple support vector machine plus (SVM+) classifier. Finally, a strong classifier is learned by combining these SVM+ classifiers for classification. The proposed algorithm was evaluated on a public schizophrenia neuroimaging dataset, including the data of structural magnetic resonance imaging (sMRI) and functional MRI (fMRI). The results showed that the proposed algorithm achieved the best diagnosis performance. In particular, the classification accuracy, sensitivity and specificity of the proposed algorithm were 72.12% ± 8.20%, 73.50% ± 15.44% and 70.93% ± 12.93%, respectively, on the sMRI data, and it also achieved the classification accuracy of 72.33% ± 8.95%, sensitivity of 68.50% ± 16.58% and specificity of 75.73% ± 16.10% on the fMRI data. The proposed algorithm overcomes the problem that the traditional LUPI methods need the additional privileged information modality as source domain. It can be directly applied to the single-modal data for classification, and also can improve the classification performance. Therefore, it suggests that the proposed algorithm will have wider applications.
The aim of the present study was to investigate the alternations of brain functional networks at resting state in the schizophrenia (SCH) patients using voxel-wise degree centrality (DC) method. The resting-state functional magnetic resonance imaging (rfMRI) data were collected from 41 SCH patients and 41 matched healthy control subjects and then analyzed by voxel-wise DC method. The DC maps between the patient group and the control group were compared using by two sample t test. The correlation analysis was also performed between DC values and clinical symptom and illness duration in SCH group. Results showed that compared with the control group, SCH patients exhibited significantly decreased DC value in primary sensorimotor network, and increased DC value in executive control network. In addition, DC value of the regions with obvious differences between the two groups significantly correlated to Positive and Negative Syndrome Scale (PANSS) scores and illness duration of SCH patients. The study showed the abnormal functional integration in primary sensorimotor network and executive control network in SCH patients.
A great number of studies have demonstrated the structural and functional abnormalities in chronic schizophrenia (SZ) patients. However, few studies analyzed the differences between first-episode, drug-naive SZ (FESZ) patients and normal controls (NCs). In this study, we recruited 44 FESZ patients and 56 NCs, and acquired their multi-modal magnetic resonance imaging (MRI) data, including structural and resting-state functional MRI data. We calculated gray matter volume (GMV), regional homogeneity (ReHo), amplitude of low frequency fluctuation (ALFF), and degree centrality (DC) of 90 brain regions, basing on an automated anatomical labeling (AAL) atlas. We then applied these features into support vector machine (SVM) combined with recursive feature elimination (RFE) to discriminate FESZ patients from NCs. Our results showed that the classifier using the combination of ReHo and ALFF as input features achieved the best performance (an accuracy of 96.97%). Moreover, the most discriminative features for classification were predominantly located in the frontal lobe. Our findings may provide potential information for understanding the neuropathological mechanism of SZ and facilitate the development of biomarkers for computer-aided diagnosis of SZ patients.
Cognitive impairment is one of the three primary symptoms of schizophrenic patients and shows important value in early detection and warning for high-risk individuals. To study the specifics of electroencephalogram (EEG) in patients with schizophrenia under the cognitive load, we collected EEG signals from 17 schizophrenic patients and 19 healthy controls, extracted signals of each band based on wavelet transform, calculated the characteristics of nonlinear dynamic and functional brain networks, and automatically classified the two groups of people by using a machine learning algorithm. Experimental results indicated that the correlation dimension and sample entropy showed significant differences in α, β, θ, and γ rhythm of the Fp1 and Fp2 electrodes between groups under the cognitive load. These results implied that the functional disruptions in the frontal lobe might be the important factors of cognitive impairments in schizophrenic patients. Further results of the automatic classification analysis indicated that the combination of nonlinear dynamics and functional brain network properties as the input characteristics of the classifier showed the best performance, with the accuracy of 76.77%, sensitivity of 72.09%, and specificity of 80.36%. The results of this study demonstrated that the combination of nonlinear dynamics and function brain network properties may be potential biomarkers for early screening and auxiliary diagnosis of schizophrenia.
ObjectAimed to describe the clinical characteristics of the patients with interictal schizophrenia-like psychoses of epilepsy (SLPE), so as to improve the identification, diagnosis and treatment.MethodsWe collected the cases from January 2017 to December 2019 that diagnosed as "epileptic psychosis/organic mental disorders/brain damage and functional disorders and somatic diseases caused by other mental disorders/organic delusions (schizophrenia-like) disorders" in the medical record system of the Sixth Hospital of Changchun. The discharge records were re-diagnosed by two experienced epilepsy specialists and psychiatrists respectively. Retrospective statistical analysis was performed on the cases identified as SLPE.ResultsA total of 45 patients were diagnosed as SLPE (male: female=1:1.4). The onset age of epilepsy and mental symptoms was (16.4±12.5) years and (35.3±13.4) years respectively. The duration of mental symptoms after first seizure was (18.9±13.4) years. 7 patients (15.6%) were not treated with AEDs, and 26 patients (57.8%) were treated with first generation AEDs. 8 patients (17.8%) had no seizures within 1 year before the onset of mental symptoms, and 28 patients (62.2%) had frequent seizures, even status epilepticus or clustered seizures. 2 patients (4.4%) had generalized tonic-clonic seizure, only 4 patients (8.9%) showed focal impaired awareness seizure, and 39 patients (86.7%) had focal to bilateral tonic-clonic seizure.The PANSS positive symptom score, PANSS negative symptom score and BPRS score were (15.1±4.4), (17.7±4.6) and (44.7±8.4) respectively.ConclusionThere were some features of epilepsy in SLPE, such as early onset age, frequent seizure (some patients were seizure-free), focal epilepsy, and poor AEDs treatment compliance. The onset age of mental symptoms in SLPE was later than Schizophrenia and long duration after first seizure. The PANSS scale showed that the mental symptoms of patients with SLPE were similar to those of patients with schizophrenia, and both positive and negative symptoms existed.
Objective To explore the effectiveness and safety of ziprasidone in the treatment of female patients with schizophrenia. Methods A before-after study design with prospective consecutive data collection was adopted. From June 2006 to May 2007, 30 female patients with schizophrenia discharged from the Second Veterans Hospital of Shanxi Province were included. Ziprasidone 60-120 mg/d was orally administered for 6 weeks. Positive and Negative Syndrome Scale (PANSS) and Treatment Emergent Symptom Scale (TESS) were measured before the treatment and at the end of Week 2, 4 and 6 after the treatment, respectively.Results At Week 6, the significant improvement rate and the total improvement rate were 86.67% and 93.33%, respectively; the incidence of side effects was 86.67%. Conclusion Ziprasidone is safe and effective in the treatment of schizophrenia. Since it will not increase body weight or the level of prolactin, it can be especially applied to female schizophrenic patients.