Development of a Machine Learning Model for Diagnosing Schizophrenia and Bipolar Disorder Based on Diffusion Tensor Imaging: A Preliminary Study / 생물치료정신의학

Objectives@#This study aimed to develop a machine learning model for diagnosing schizophrenia (SZ) and bipolar disorder (BD) based on diffusion tensor imaging (DTI) data. @*Methods@#We used 3T-magnetic resonance imaging to examine SZ, BD, healthy control (HC) subjects (aged 20-50 years, n=65 in each group). Applying Support Vector Machine (SVM) to fractional anisotropy (FA) values, we built classification models of SZ and HC, BD and HC, and SZ and BD. Features of white matter (WM) tracts were selected through recursive feature elimination, and 5-fold cross validation was performed. @*Results@#The SVM models classified SZ and BD from HC with a mean accuracy of 83.5% and 75.4%, respectively. The SZ-BD classification model archived 75.0% accuracy. These classification models used FA values in 15-18 WM tracts as features, including the retrolenticular part of the internal capsule, superior corona radiata, cingulum, and superior fronto-occipital fasciculus. @*Conclusions@#This study presented a preliminary machine learning model to diagnose SZ and BD based on DTI data. Our findings also suggest that there might be a specific pattern of abnormalities in WM integrity that can differentiate the two psychotic disorders.

Cortical Volumetric Correlates of Childhood Trauma, Anxiety, and Impulsivity in Bipolar Disorder

Objective@#More recently, attention has turned to the linkage between childhood trauma and emotional dysregulation, but the evidence in bipolar disorder (BD) is limited. To determine neurobiological relationships between childhood trauma, current anxiety, and impulsivity, we investigated cortical volumetric correlates of these clinical factors in BD. @*Methods@#We studied 36 patients with DSM-5 BD and 29 healthy controls. Childhood trauma, coexisting anxiety, and impulsivity were evaluated with the Korean version-Childhood Trauma Questionnaire (CTQ), the Korean version-Beck Anxiety Inventory (BAI), and the Korean version-Barratt Impulsiveness Scale (BIS). Voxel-based morphometry (VBM) was used to assess gray matter volume (GMV) alterations on the brain magnetic resonance imaging (MRI). Partial correlation analyses were conducted to examine associations between the GMV and each scale in the BD group. @*Results@#Childhood trauma, anxiety, and impulsivity were interrelated in BD. BD patients revealed significant inverse correlations between the GMV in the right precentral gyrus and CTQ scores (r=-0.609, p<0.0003); between the GMV in the left middle frontal gyrus and BAI scores (r=-0.363, p=0.044). Moreover, patients showed similar tendency of negative correlations between the GMV in the right precentral gyrus and BIS scores; between the GMV in the left middle frontal gyrus and CTQ scores. @*Conclusion@#The present study provides evidence for a neural basis between childhood trauma and affect regulations in BD. The GMV alterations in multiple frontal lobe areas may represent neurobiological markers for anticipating the course of BD.

Network Structures of Social Functioning Domains in Schizophrenia and Bipolar Disorder: A Preliminary Study

Objective@#This study used network analyses to examine network structures reflecting interactions between specific domains of social functioning in schizophrenia (SZ) and bipolar disorder (BD). @*Methods@#We used the World Health Organization Disability Assessment Schedule 2.0 (WHODAS 2.0) to assess six domains of social functioning (‘cognition’, ‘mobility’, ‘self-care’, ‘getting along’, ‘life activities’, and ‘participation’) in 143 patients with SZ, 81 patients with BD, and 106 healthy subjects. We constructed regularized partial correlation networks, estimated network centrality and edge strength, tested network stability, and compared SZ and BD network structures. @*Results@#Patients with SZ showed a significantly higher level of functional disability than patients with BD. In the networks we constructed, ‘cognition’ was the most central domain of social functioning in both SZ and BD. The ‘cognition’ domain was primarily associated with the ‘getting along’ domain in the SZ network and the ‘life activities’ domain in the BD network. We found no significant group-level differences in network structures for SZ vs. BD. @*Conclusion@#Our results suggest that cognition may play a pivotal role in social functioning in both SZ and BD. In addition, domains of social functioning in SZ and BD have similar network structures despite the higher level of disability in SZ compared to BD.

Suicidality and Related Psychopathology across Different Stages of Schizophrenia / 대한정신분열병학회지

Objectives@#This study aimed to investigate suicidal behaviors and the related psychopathology across the different stages of schizophrenia. @*Methods@#We recruited 131 patients with schizophrenia and categorized them into two groups, according to the duration of illness (DI) as follows: ≤10 years (n=39) and >10 years (n=92). Psychopathology and suicidality were assessed using the 18-item Brief Psychiatric Rating Scale (BPRS-18) and the suicidality module from the Mini-International Neuropsychiatric Interview, respectively. @*Results@#One-quarter of the patients with a DI ≤10 years and nearly one-sixth of the patients with a DI >10 years experienced suicidal behaviors in the previous month. Suicidality scores were significantly associated with the “affect” factor scores of the BPRS-18 in patients with a DI ≤10 years (β=0.55, p=0.003) and with the “resistance” factor scores in patients with a DI of >10 years (β=0.29, p=0.006). @*Conclusion@#The present study demonstrated that psychopathological factors were differentially associated with suicidality in patients with schizophrenia according to the illness stage. Our findings suggest that for effective suicide prevention, different approaches are required for the management of each stage of schizophrenia.

Functional Disabilities Evaluated using World Health Organization Disability Assessment Schedule 2.0 in Patients with Chronic Schizophrenia and Its Related Factors / 신경정신의학

OBJECTIVES: This study examined the functional disabilities of patients with chronic schizophrenia using WHO Disability Assessment Schedule 2.0 (WHODAS 2.0) and its related factors. METHODS: The subjects consisted of 86 patients with schizophrenia with more than 10 years' duration of illness and 40 healthy volunteers. The functional disabilities and psychopathology were evaluated using the WHODAS 2.0 and 18-items Brief Psychiatric Rating Scale (BPRS-18), respectively. This study analyzed the six sub-domains ('cognition', 'mobility', 'self-care', 'getting along', 'life activities', and 'participation') of WHODAS 2.0 and the four sub-scales ('positive symptoms', 'negative symptoms', 'affect', and 'resistance') of BPRS-18. RESULTS: Patients with chronic schizophrenia experienced severe functional disabilities across all six sub-domains of WHODAS 2.0 compared to healthy people. Hierarchical regression showed that 'negative symptoms' explained the disabilities in the WHODAS 2.0 sub-domains of 'cognition' (p<0.05), 'self-care' (p<0.05), 'getting along' (p<0.01), and 'life activities' (p<0.05). 'Positive symptoms' and 'affect' explained the disabilities in 'cognition' (p<0.01 and p<0.05, respectively) and 'participation' (p<0.05 and p<0.01, respectively). 'Resistance' was found to be a predictor of 'getting along' disabilities (p<0.01). CONCLUSION: Negative symptoms mainly accounted for the multiple domains of functional disabilities in the WHODAS 2.0 but residual positive and affective symptoms could also deteriorate the cognition and social participation of patients with chronic schizophrenia.

Detection of Suicide Attempters among Suicide Ideators Using Machine Learning

OBJECTIVE: We aimed to develop predictive models to identify suicide attempters among individuals with suicide ideation using a machine learning algorithm. METHODS: Among 35,116 individuals aged over 19 years from the Korea National Health & Nutrition Examination Survey, we selected 5,773 subjects who reported experiencing suicide ideation and had answered a survey question about suicide attempts. Then, we performed resampling with the Synthetic Minority Over-sampling TEchnique (SMOTE) to obtain data corresponding to 1,324 suicide attempters and 1,330 non-suicide attempters. We randomly assigned the samples to a training set (n=1,858) and a test set (n=796). In the training set, random forest models were trained with features selected through recursive feature elimination with 10-fold cross validation. Subsequently, the fitted model was used to predict suicide attempters in the test set. RESULTS: In the test set, the prediction model achieved very good performance [area under receiver operating characteristic curve (AUC)=0.947] with an accuracy of 88.9%. CONCLUSION: Our results suggest that a machine learning approach can enable the prediction of individuals at high risk of suicide through the integrated analysis of various suicide risk factors.

Use of a Machine Learning Algorithm to Predict Individuals with Suicide Ideation in the General Population

OBJECTIVE: In this study, we aimed to develop a model predicting individuals with suicide ideation within a general population using a machine learning algorithm. METHODS: Among 35,116 individuals aged over 19 years from the Korea National Health & Nutrition Examination Survey, we selected 11,628 individuals via random down-sampling. This included 5,814 suicide ideators and the same number of non-suicide ideators. We randomly assigned the subjects to a training set (n=10,466) and a test set (n=1,162). In the training set, a random forest model was trained with 15 features selected with recursive feature elimination via 10-fold cross validation. Subsequently, the fitted model was used to predict suicide ideators in the test set and among the total of 35,116 subjects. All analyses were conducted in R. RESULTS: The prediction model achieved a good performance [area under receiver operating characteristic curve (AUC)=0.85] in the test set and predicted suicide ideators among the total samples with an accuracy of 0.821, sensitivity of 0.836, and specificity of 0.807. CONCLUSION: This study shows the possibility that a machine learning approach can enable screening for suicide risk in the general population. Further work is warranted to increase the accuracy of prediction.

Characteristics of Telepresence by Multisensory Feedback and Related Neural Mechanism in Patients with Schizophrenia : A Functional MRI Study

OBJECTIVES: The multimodal telepresence systems have been adopted in a variety of applications, such as telemedicine, space or underwater teleoperation and videoconference. Multimedia, one of the telepresence systems, has been used in various fields including entertainment, education and communication. The degree of subjective telepresence is defined as the probability that a person perceives to be physically in the remote place when he/she experiences a multisensory feedback from the multimedia. The current study aimed to explore the neural mechanism of telepresence related to multisensory feedback in patients with schizophrenia. METHODS: Brain activity was measured using functional magnetic resonance imaging while fifteen healthy controls and fifteen patients with schizophrenia were experiencing filmed referential conversation at various distances (1 m, 5 m and 10 m). Correlations between the image contrast values and the telepresence scores were analyzed. RESULTS: Subjective telepresence was not significantly different between the two groups. Some significant correlations of brain activities with the telepresence scores were found in the left postcentral gyrus, bilateral inferior frontal gyri, right fusiform gyrus, and left superior temporal sulcus. There were no main effects of group and distance. CONCLUSION: These results suggest that patients with schizophrenia experience telepresence as appropriately as healthy people do when exposed to multimedia. Therefore, patients with schizophrenia would have no difficulty in immersing themselves in multimedia which may be used in clinical training therapies.