Psychiatry Research: Neuroimaging最新文献

{"title":"Multimodal approach for early diagnosis of Parkinson’s disease using PET imaging, tremor detection, and machine learning","authors":"Nishu Chowdhury ,&nbsp;Utpol Kanti Das ,&nbsp;Sadia Sazzad ,&nbsp;Amit Chowdhury ,&nbsp;Panna Das","doi":"10.1016/j.pscychresns.2025.112063","DOIUrl":"10.1016/j.pscychresns.2025.112063","url":null,"abstract":"<div><div>Parkinson’s disease (PD) is a progressive neurodegenerative disorder that presents diagnostic challenges, particularly in its early stages. This study proposes a multimodal approach to PD classification that integrates neurological imaging, motor symptom analysis, and non-motor clinical features. Dopamine depletion, a core biomarker of PD, is assessed using PET imaging, where active brain regions are quantified through color segmentation and image processing. A reduction in the active area correlates with disease progression. Tremor detection is performed using the Hough Transform algorithm applied to line-drawing tests, effectively identifying motor irregularities. Non-motor features are analyzed using a publicly available dataset, and the XGBoost algorithm achieves a classification accuracy exceeding 95.42%. The combined approach demonstrates high potential for early, accurate, and interpretable PD diagnosis.</div></div>","PeriodicalId":20776,"journal":{"name":"Psychiatry Research: Neuroimaging","volume":"353 ","pages":"Article 112063"},"PeriodicalIF":2.1,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145099863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Real-time fMRI neurofeedback modulates auditory cortex activity and connectivity in schizophrenia patients with auditory hallucinations: A controlled study","authors":"Clemens C.C. Bauer ,&nbsp;Jiahe Zhang ,&nbsp;Francesca Morfini ,&nbsp;Oliver Hinds ,&nbsp;Paul Wighton ,&nbsp;Yoonji Lee ,&nbsp;Lena Stone ,&nbsp;Angelina Awad ,&nbsp;Kana Okano ,&nbsp;Melissa Hwang ,&nbsp;Jude Hammoud ,&nbsp;Paul Nestor ,&nbsp;Susan Whitfield-Gabrieli ,&nbsp;Ann K. Shinn ,&nbsp;Margaret A. Niznikiewicz","doi":"10.1016/j.pscychresns.2025.112050","DOIUrl":"10.1016/j.pscychresns.2025.112050","url":null,"abstract":"<div><h3>Background and Hypothesis</h3><div>Auditory hallucinations (AHs) affect 60–80 % of schizophrenia patients and often resist antipsychotic treatment. AHs involve superior temporal gyrus (STG) hyperactivity and disrupted auditory-cognitive control connectivity. Real-time fMRI neurofeedback (NFB) enables voluntary modulation of targeted brain regions. We previously showed STG-targeted NFB with mindfulness meditation reduced STG activation and AHs in one session. However, whether effects are specific to hallucination-related regions versus placebo, and whether NFB modulates broader networks, remained unclear.</div></div><div><h3>Study Design</h3><div>This randomized, sham-controlled trial examined NFB specificity and network effects. Twenty-three adults with schizophrenia/schizoaffective disorder and medication-resistant hallucinations practiced mindfulness meditation while receiving neurofeedback from either STG (<em>n</em> = 10, Real-NFB) or motor cortex (<em>n</em> = 13, Sham-NFB control). Sham participants subsequently received Real-NFB, providing within-subject comparison.</div></div><div><h3>Study Results</h3><div>Both groups showed reduced AHs post-NFB without group differences. However, compared to Sham-NFB, Real-NFB produced greater reductions in secondary auditory cortex activation and connectivity between auditory cortex and cognitive control regions (dorsolateral prefrontal cortex and anterior cingulate). These connectivity reductions persisted in the Real-after-Sham condition. Both groups showed reduced primary auditory cortex activation, suggesting mindfulness meditation independently regulates bottom-up hallucination processes.</div></div><div><h3>Conclusions</h3><div>Region-specific NFB targeting produces distinct neural changes beyond symptom reduction. STG-targeted NFB differentially modulates auditory-cognitive control networks, potentially restoring the disrupted balance between bottom-up sensory processing and top-down control in AHs. These findings highlight the importance of anatomically-informed NFB targets and provide mechanistic insights for developing precision interventions for treatment-resistant psychiatric symptoms.</div></div>","PeriodicalId":20776,"journal":{"name":"Psychiatry Research: Neuroimaging","volume":"353 ","pages":"Article 112050"},"PeriodicalIF":2.1,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144920117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"fMRI features in recent suicide attempters performing the future imagination task","authors":"Milad Esmaeil-Zadeh ,&nbsp;Morteza Fattahi ,&nbsp;Nafee Rasouli ,&nbsp;Hamid Soltanian-Zadeh ,&nbsp;Majid Abbasi Sisara ,&nbsp;Ehsan Rajab ,&nbsp;Amirhossein Jafari ,&nbsp;Seyed Kazem Malakouti","doi":"10.1016/j.pscychresns.2025.112049","DOIUrl":"10.1016/j.pscychresns.2025.112049","url":null,"abstract":"<div><h3>Background</h3><div>A negative future outlook increases vulnerability to depression and suicide. Understanding neural mechanisms of future-oriented thinking may reveal insights into suicide risk. This study used fMRI to identify brain activation patterns during future imagination in individuals with recent suicide attempts.</div></div><div><h3>Methods</h3><div>Sixty-two participants were grouped as recent suicide attempters with major depressive disorder (SA+MDD), depressed individuals without suicide history (MDD), and healthy controls (HC). Diagnoses were confirmed via SCID-5-RV. Participants performed a block-designed future imagination task with positive and negative scenarios during fMRI.</div></div><div><h3>Results</h3><div>Compared to MDD, the SA+MDD group showed increased activation in the left orbitofrontal cortex, bilateral cingulate, insula, and inferior frontal gyrus, but decreased activity in the left parahippocampus and postcentral gyrus. During positive imagination, greater activation was observed in the right orbitofrontal cortex, supramarginal gyrus, and left superior temporal regions. Psychologically, SA+MDD individuals had lower “reasons for living” and higher suicidal ideation.</div></div><div><h3>Conclusion</h3><div>Recent suicide attempters exhibit heightened neural responses to negative future events, reflecting increased threat perception and emotion dysregulation. Hyperactivation in reward-related areas may facilitate suicidal behavior as escape from psychological pain, while reduced episodic memory engagement impairs adaptive planning. Targeting hemispheric imbalances offers potential for suicide prevention.</div></div>","PeriodicalId":20776,"journal":{"name":"Psychiatry Research: Neuroimaging","volume":"353 ","pages":"Article 112049"},"PeriodicalIF":2.1,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144926309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Altered neural reward activation predicts clinical depression improvement after a novel loving-kindness meditation: a multimodal neuroimaging study","authors":"Zhaohua Chen ,&nbsp;Chun Cui ,&nbsp;Xiaoxiao Sun ,&nbsp;Wenjun Xiang ,&nbsp;Fei Liang ,&nbsp;Qin Dai","doi":"10.1016/j.pscychresns.2025.112059","DOIUrl":"10.1016/j.pscychresns.2025.112059","url":null,"abstract":"<div><h3>Objective</h3><div>Major depressive disorder (MDD) has become the second largest risk factor affecting human health, with a progress in its treatment especially non-pharmacological therapies. The loving-kindness meditation (LKM) has been introduced to depression but is not popular due to requirement on awareness and concentration, and its utilization in clinical MDD is absent as well as exploration on neural mechanism. This study aims to develop a more feasible novel therapy—loving-kindness meditation integrating cognition and behavior (LKM-CB), examine its effect on clinical depression, and further explore its neural mechanism by multimodal neuroimaging.</div></div><div><h3>Method</h3><div>In study 1, the knowledge about love and the behavior of love were integrated into the LKM to form a LKM-CB, to better activate patients with cognitive and behavioral approach. It was further utilized to 30 MDD patients (31 controls). Study 2 further explored the neural mechanism behind the LKM-CB with 16 MDD patients, who underwent a structural MRI, resting-state fMRI, and reward card-guessing task fMRI before and after the LKM-CB.</div></div><div><h3>Results</h3><div>Study 1 developed a novel 8-week LKM-CB and found that compared with control group, LKM-CB significantly improved clinical depression in intervention group. Study 2 further showed that after LKM-CB intervention, patients showed lower activation in frontal-striatum especially middle orbito-frontal cortex (OFC) and anterior cingulate (AC) and insula for win and neutral outcome and anticipation following a loss feedback, while they showed higher activation in frontal-striatum including medial/middle-OFC and hippocampus for loss outcome and anticipation following a win feedback. Similar increased ALFF activation and grey matter in frontal cortex was also found. In contrast, patients showed higher activation in non-reward temporal-occipital cortex for loss and neutral outcome and anticipation following a loss feedback, while they showed decreased temporal-occipital ALFF activation and grey matter.</div></div><div><h3>Conclusions</h3><div>This study develops a novel LKM-CB, which is effective in improving clinical depression. After the LKM-CB, there is dissociation in the neural reward activation pattern between reward anticipation (hyperactivation) and reward outcome (hypoactivation), and a hypoactivation in non-reward temporal-occipital cortex. This study provides a new feasible LKM-CB for non-pharmacological therapy of MDD, and to our knowledge, this is the first study to explore the neural mechanism behind the efficacy of LKM in depression therapy.</div></div>","PeriodicalId":20776,"journal":{"name":"Psychiatry Research: Neuroimaging","volume":"353 ","pages":"Article 112059"},"PeriodicalIF":2.1,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144920218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Incarcerated adolescents scoring high on the Brown Attention-Deficit Disorder Scale are characterized by impairments within brain regions associated with executive control: A source-based morphometry study","authors":"J. Michael Maurer ,&nbsp;Corey H. Allen ,&nbsp;Samantha N. Rodriguez ,&nbsp;Keith A. Harenski ,&nbsp;David D. Stephenson ,&nbsp;Bethany G. Edwards ,&nbsp;Nathaniel E. Anderson ,&nbsp;Carla L. Harenski ,&nbsp;Vince D. Calhoun ,&nbsp;Kent A. Kiehl","doi":"10.1016/j.pscychresns.2025.112065","DOIUrl":"10.1016/j.pscychresns.2025.112065","url":null,"abstract":"<div><div>Initially designed to assess executive control deficits for individuals meeting criteria for attention-deficit/hyperactivity disorder (ADHD), the Brown Attention-Deficit Disorder Scale (BADDS) is now frequently used to assess such deficits more broadly. However, no existing studies have investigated whether individuals scoring high on the BADDS are characterized by impairments within higher-order brain regions associated with executive control. Here, we investigated this association among incarcerated adolescents (205 boys and 35 girls). We incorporated the use of source-based morphometry (SBM), a data-driven, multivariate approach to identify large-scale structural brain networks. In separate analyses performed with incarcerated boys and girls, we observed that higher BADDS total scores were related to reduced loading coefficients in SBM components comprised of brain regions associated with executive control (e.g., superior/middle frontal gyrus, superior/inferior parietal lobule, and middle temporal gyrus). These structural impairments suggest participants scoring high on the BADDS are characterized by executive control deficits, including domains such as self-regulation, working memory, and sustained attention. Our results add to a growing body of literature suggesting that the BADDS serves as a reliable measure of executive control deficits. Further, our results support the use of the BADDS in samples beyond individuals strictly meeting criteria for ADHD.</div></div>","PeriodicalId":20776,"journal":{"name":"Psychiatry Research: Neuroimaging","volume":"353 ","pages":"Article 112065"},"PeriodicalIF":2.1,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145150607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Neurophysiological impact of childhood sexual abuse in men: A diffusion tensor imaging study","authors":"Michel Vezarov ,&nbsp;Carley Fall ,&nbsp;Jessie Moorman ,&nbsp;Zhuo Fang ,&nbsp;Elisa Romano ,&nbsp;Andra Smith","doi":"10.1016/j.pscychresns.2025.112061","DOIUrl":"10.1016/j.pscychresns.2025.112061","url":null,"abstract":"<div><h3>Background</h3><div>Childhood sexual abuse (CSA) can cause lasting neurodevelopmental changes, posing significant challenges for survivors. Its specific impact on men remains heavily stigmatized and under-researched. This study examined neurophysiological correlates of CSA in men using diffusion tensor imaging (DTI).</div></div><div><h3>Methods</h3><div>A community-based sample of men with CSA histories (<em>n</em> = 15) and controls (<em>n</em> = 13) were recruited from urban centers across Canada. All participants underwent DTI, which measures white matter integrity through fractional anisotropy (FA) values. Group comparisons were conducted using whole-brain voxel-wise and post-hoc region-of-interest (ROI) analyses with Bonferroni correction. Effect sizes (Cohen’s d) and power were reported.</div></div><div><h3>Results</h3><div>Compared to controls, the CSA group showed significantly lower FA values in the right posterior cingulum (<em>d</em> = 1.28, <em>p</em> = 0.002), superior frontal gyrus (<em>d</em> = 1.13, <em>p</em> = 0.006), anterior thalamic radiation (<em>d</em> = 1.19, <em>p</em> = 0.004), and superior longitudinal fasciculus (<em>d</em> = 1.90, <em>p</em> &lt; 0.001). These differences remained significant after Bonferroni adjustment. Lower FA values were also observed in the left anterior cingulum and right forceps minor, though these did not meet adjusted significance thresholds.</div></div><div><h3>Conclusions</h3><div>This study provides empirical evidence of the long-lasting neurophysiological impact of CSA in men. The observed white matter differences may underlie the behavioral, emotional, and cognitive difficulties often experienced by this population. These results are discussed in the context of destigmatizing male CSA and helping clinicians better understand the neurophysiological factors affecting their patients.</div></div>","PeriodicalId":20776,"journal":{"name":"Psychiatry Research: Neuroimaging","volume":"353 ","pages":"Article 112061"},"PeriodicalIF":2.1,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145007773","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Neuroanatomical subtyping for schizophrenia with machine learning","authors":"Ibrahim Sungur ,&nbsp;Simay Selek ,&nbsp;Kaan Keskin ,&nbsp;Asli Ceren Hinc ,&nbsp;Furkan Yazici ,&nbsp;Elif Ozge Aktas ,&nbsp;Yigit Erdogan ,&nbsp;Ali Saffet Gonul","doi":"10.1016/j.pscychresns.2025.112058","DOIUrl":"10.1016/j.pscychresns.2025.112058","url":null,"abstract":"<div><div>Schizophrenia is a heterogeneous disorder with significant variability in neurobiological and clinical presentations. In this study, we aimed to investigate neuroanatomical subtypes of schizophrenia using a data-driven machine-learning algorithm. Structural MRI data from 222 participants (136 schizophrenia patients and 86 healthy controls) were analyzed. Subtypes were identified using HYDRA (Heterogeneity Through Discriminative Analysis), a semi-supervised machine learning algorithm designed to reveal disease-related patterns while minimizing the influence of normal anatomical variation followed by voxel-based morphometry (VBM) analysis to compare these subtypes with healthy controls. The study identified two subtypes among schizophrenia patients. Subtype 1 showed widespread lower grey matter volumes in several cortical regions, mainly in the insula, cingulate, frontal, and temporal regions. Subtype 2 demonstrated increased subcortical volumes, pallidal volumes relative to controls and thalamus, hippocampus relative to subtype 1. Despite significant neuroanatomical differences, the subtypes did not differ in demographic or clinical characteristics. These findings highlight the potential of machine learning to disentangle structural heterogeneity in schizophrenia, offering a refined framework for neuroanatomical subtyping. Identifying distinct subtypes may contribute to personalized treatment approaches and enhance the precision of future clinical and research efforts.</div></div>","PeriodicalId":20776,"journal":{"name":"Psychiatry Research: Neuroimaging","volume":"353 ","pages":"Article 112058"},"PeriodicalIF":2.1,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144989247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of anorexia nervosa on structural morphometry of the brain in adolescents and adults after weight recovery: A systematic review","authors":"Shelby D. Leverett ,&nbsp;Sinaida Cherubin ,&nbsp;Maria Roche-Dean (Assistant Professor) ,&nbsp;Bridget E. Weller (Professor)","doi":"10.1016/j.pscychresns.2025.112043","DOIUrl":"10.1016/j.pscychresns.2025.112043","url":null,"abstract":"<div><h3>Purpose</h3><div>To systematically review the evidence for 1) the effect of acute anorexia nervosa and weight recovery on aspects of structural morphometry of the brain, and 2) how these effects may differ between adolescents and adults.</div></div><div><h3>Method</h3><div>We used the PRISMA guidelines for systematic reviews. We searched online databases (Web of Knowledge, PubMed, and PsychINFO) and identified relevant studies. Eligible studies were longitudinal and included a healthy control group.</div></div><div><h3>Results</h3><div>Thirteen articles met the inclusion criteria. Studies often demonstrated global and regional grey matter volumes among individuals with acute anorexia nervosa compared to healthy controls, which increased following weight recovery. Grey matter volumes normalized in adolescents following weight recovery but remained smaller in recovered adults relative to their healthy controls. White matter volumes (globally and regionally) were largely unaffected by either phase of anorexia nervosa (e.g., acute and recovered). Cerebrospinal fluid (CSF) volumes were elevated in individuals with anorexia compared to healthy counterparts, but volumes normalized following weight recovery. However, the decrease in CSF volume was only found for adolescents.</div></div><div><h3>Conclusion</h3><div>The structural morphometry of the brains of adults and adolescents with anorexia appears to be differentially affected by weight restoration. Future longitudinal research is needed that uses a consistent definition of recovery, and more diverse participants.</div></div>","PeriodicalId":20776,"journal":{"name":"Psychiatry Research: Neuroimaging","volume":"352 ","pages":"Article 112043"},"PeriodicalIF":2.1,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144864524","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing schizophrenia diagnosis efficiency with EEGNet: a simplified recognition model based on γ band features","authors":"Shuai Hao ,&nbsp;Zhi-jie Zhang ,&nbsp;Xu Wang ,&nbsp;Pan Zhang ,&nbsp;Hui-peng Ren ,&nbsp;Wei-cong Ren","doi":"10.1016/j.pscychresns.2025.112047","DOIUrl":"10.1016/j.pscychresns.2025.112047","url":null,"abstract":"<div><h3>Objective</h3><div>This study aims to develop an objective and efficient diagnostic model for schizophrenia (SCZ) by integrating electroencephalogram (EEG) signals with deep learning techniques. Building on previous research, γ wave activity is selected as a potential biomarker to achieve high recognition accuracy while significantly reducing model complexity and enhancing training efficiency.</div></div><div><h3>Methods</h3><div>We implemented an EEGNet architecture optimized for simplified feature engineering, targeting γ band features extracted from resting-state EEG recordings. The model was trained and evaluated using Leave-One-Subject-Out Cross-Validation (LOSOCV) to ensure robustness in distinguishing SCZ patients from healthy controls (HC).</div></div><div><h3>Results</h3><div>The γ band feature model achieved average recognition accuracies of 98.19 % for the SCZ group and 97.24 % for the HC group. Additionally, the model significantly reduced training time, indicating an efficient classification process that is more conducive to training on large datasets.</div></div><div><h3>Conclusion</h3><div>The findings highlight the effectiveness of γ band features for EEG-based SCZ diagnostics, with the proposed model offering both high accuracy and improved training efficiency. This study underscores the potential clinical utility of γ band-focused EEG analysis as an objective diagnostic tool for SCZ.</div></div>","PeriodicalId":20776,"journal":{"name":"Psychiatry Research: Neuroimaging","volume":"352 ","pages":"Article 112047"},"PeriodicalIF":2.1,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144830340","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-modal predictive modeling of schizophrenia severity: Leveraging liver function indicators and cognitive scores with random forest and SVM","authors":"Sayed Sayem ,&nbsp;Sayed Sumsul Islam Sanny ,&nbsp;Rupali Hossain ,&nbsp;Tanjila Hossen ,&nbsp;Md Tauhidur Rahman Sakib ,&nbsp;Md Abu Talha","doi":"10.1016/j.pscychresns.2025.112032","DOIUrl":"10.1016/j.pscychresns.2025.112032","url":null,"abstract":"<div><div>Schizophrenia is a complex neuropsychiatric disorder with cognitive deficits and systemic physiological disturbances, including emerging links to hepatic dysfunction via the gut-liver-brain axis. Despite growing evidence, the integration of liver function biomarkers into predictive models for schizophrenia severity remains largely unexplored. This study proposes a multimodal machine learning framework combining hepatic indicators—Alanine Aminotransferase (ALT), Aspartate Aminotransferase (AST), Bilirubin, Albumin, and International Normalized Ratio (INR)—with cognitive assessment scores to enhance severity prediction. A synthetic dataset of 500 patient profiles was programmatically generated using MATLAB R2023a, simulating realistic clinical variability across demographics and biomarker distributions. Controlled missingness was introduced and imputed using moving mean methods, followed by Min-Max normalization to standardize features. Two machine learning models were developed: Random Forest for continuous severity regression and Support Vector Machine (SVM) with Error-Correcting Output Codes (ECOC) and Radial Basis Function (RBF) kernel for multiclass classification. The Random Forest regressor achieved an RMSE of 21.85, Mean Absolute Error of 17.26, and an R² of 0.70, capturing 72 % of variance. The SVM classifier attained 86.4 % accuracy, with macro-averaged precision, recall, and F1-score of 0.86, and an AUC of 0.91. Feature importance analysis revealed cognitive score, ALT, and AST as dominant predictors. Residual and confusion matrix analyses further confirmed model reliability. This integrative approach demonstrates the technical feasibility and clinical relevance of leveraging hepatic biomarkers alongside cognitive scores for schizophrenia severity assessment, offering a robust data-driven methodology for complex psychiatric evaluation.</div></div>","PeriodicalId":20776,"journal":{"name":"Psychiatry Research: Neuroimaging","volume":"352 ","pages":"Article 112032"},"PeriodicalIF":2.1,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144712843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}