Psychiatry Research: Neuroimaging最新文献

{"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":"2025-07-18","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}

{"title":"Understanding episodic memory in schizophrenia: a functional neuroimaging meta-analysis","authors":"Nada Hannaoui ,&nbsp;Mélanie Boisvert ,&nbsp;Stéphane Potvin","doi":"10.1016/j.pscychresns.2025.112022","DOIUrl":"10.1016/j.pscychresns.2025.112022","url":null,"abstract":"<div><h3>Background</h3><div>In schizophrenia, episodic memory deficits are observed across verbal and visual memory tasks, as well as during free recall and recognition. Functional neuroimaging studies have revealed abnormalities in several brain regions, though findings have often been inconsistent. To resolve these discrepancies, we conducted a meta-analysis to provide an updated understanding of the neural mechanisms involved in episodic memory deficits in schizophrenia.</div></div><div><h3>Methods</h3><div>The meta-analysis included 59 functional neuroimaging studies using episodic memory tasks in schizophrenia.</div></div><div><h3>Results</h3><div>The analysis revealed reduced brain activity, during encoding, in the left para-hippocampal gyrus, the left inferior frontal gyrus, the left fusiform gyrus and the left striatum. During retrieval, reduced activations were observed in schizophrenia in the left dorsal anterior cingulate cortex and medial superior frontal gyrus, the right angular gyrus and the left supplementary motor are.</div></div><div><h3>Conclusion</h3><div>We found reduced activations in the memory-relevant para-hippocampal gyrus, as well as in brain regions involved in semantic processing, cognitive control and visual processing. This study fills critical gaps in understanding the neural correlates of episodic memory deficits in schizophrenia, offering insights into how cognitive functions are affected in this disorder.</div></div>","PeriodicalId":20776,"journal":{"name":"Psychiatry Research: Neuroimaging","volume":"352 ","pages":"Article 112022"},"PeriodicalIF":2.1,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144679677","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":"Morphometric brain MRI findings in hair-pulling and skin-picking disorders in youth","authors":"Joseph O’Neill ,&nbsp;Tara S. Peris ,&nbsp;Emily J. Ricketts ,&nbsp;Jon E. Grant ,&nbsp;Christine Lochner ,&nbsp;Dan J. Stein ,&nbsp;Darin D. Dougherty ,&nbsp;Douglas W. Woods ,&nbsp;Matthew J. Kempton ,&nbsp;Nancy J. Keuthen ,&nbsp;John C. Piacentini","doi":"10.1016/j.pscychresns.2025.112031","DOIUrl":"10.1016/j.pscychresns.2025.112031","url":null,"abstract":"<div><div>Pediatric hair-pulling disorder (HPD) and skin-picking disorder (SPD) are treatment-resistant conditions understudied with neuroimaging. We report cross-sectional morphometric MRI results from the adolescent-early adult subsample of the Body-Focused Precision Medicine Initiative (BPMI), a major HPD-SPD MRI database. Participants aged 11–21 years comprised 30 with HPD, 13 with SPD, 16 with both HPD and SPD, and 29 typically developing (TD). Whole-brain MRI was parcellated into cortical and subcortical regions with FreeSurfer. Volume and (for cortex) thickness and surface area of each region were analyzed for effects of HPD and SPD, controlling for psychotropic medication, age, total intracranial volume, and scanning site. Morphometry of four regions most reflected diagnosis and severity of HPD: 1) left inferior frontal cortex (larger and thicker for more severe HPD); 2) corpus callosum (larger for more severe HPD); 3) lingual gyrus (smaller right cortical surface area and white-matter volume); and 4) fusiform gyrus (smaller right cortical and white-matter volumes for more severe HPD). For SPD, there were three regions: 1) parahippocampal gyrus (larger left white matter volume and larger bilateral cortical volume and surface area for more severe SPD); 2) fusiform cortex (thicker left cortex for more severe skin-picking urgency); and 3) entorhinal cortex (thicker right cortex for more severe urgency). Variations in regional morphometry may result from or predispose to HPD and SPD. Left inferior frontal and callosal findings suggest lateralized dysfunction in HPD similar to language disorders; in SPD parahippocampal findings may indicate dysfunction in emotion regulation and/or contextual association.</div></div>","PeriodicalId":20776,"journal":{"name":"Psychiatry Research: Neuroimaging","volume":"352 ","pages":"Article 112031"},"PeriodicalIF":2.1,"publicationDate":"2025-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144679678","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":"Exploring retinal thickness variations in adolescents with first episode psychosis and schizophrenia: A comparative study with healthy siblings and controls","authors":"Kardelen Akbal Bağcı ,&nbsp;Pınar Nalçacıoğlu Memiş ,&nbsp;Mustafa Akhoroz ,&nbsp;Beyza Nur Top Karakılınç ,&nbsp;Esra Çöp","doi":"10.1016/j.pscychresns.2025.112020","DOIUrl":"10.1016/j.pscychresns.2025.112020","url":null,"abstract":"<div><h3>Background</h3><div>The retina offers a way to indirectly evaluate inflammation and degeneration in the brain. Recently, scientists are focusing on the retina as a valuable tool to understand brain structure and function. This study aims to compare retinal layer thicknesses of adolescents by using Optical coherence tomography (OCT), between first episode psychosis and schizophrenia patients, healthy siblings of schizophrenia patients and healthy control groups.</div></div><div><h3>Methods</h3><div>The study included 18 first episode psychosis (FEP) and 22 schizophrenia patients, 29 healthy siblings of schizophrenia patients and 31 healthy controls.The sociodemographic data form, Scale for the Assesment of Negative Symptoms(SANS), Scale for the Assessment of Positive Symptoms (SAPS), Clinical Global Impression (CGI) scale were completed by the clinician. The total macular thickness, macular retinal nerve fiber layer (RNFL), inner retinal layers including, ganglion cell layer (GCL), inner plexiform layer (IPL) were automatically measured by using OCT and compared between the four groups.</div></div><div><h3>Results</h3><div>The inner süperior and inner inferior subsegments of IPL and inner temporal subsegments of GCL were found thinner in schizophrenia patients and healthy siblings than healthy controls. Also, average GCL, inner süperior, inner nasal of RNFL thickness was greater in FEP patients than in healthy siblings and controls.</div></div><div><h3>Conclusion</h3><div>Retinal thinning in schizophrenia patients and healthy siblings might be the result of the neurodegeneration seen at schizophrenia. Also thinning in healthy siblings might be an endophenotype candidate. And the thickening in the FEP group could be due to neuroinflammation and edema occurring in the acute phase of the illness.</div></div>","PeriodicalId":20776,"journal":{"name":"Psychiatry Research: Neuroimaging","volume":"352 ","pages":"Article 112020"},"PeriodicalIF":2.1,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144580892","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":"Comparison of overnight trends in relative power for specific frequency bands, sleep stages, and brain regions between patients with depressive disorder and matched control subjects","authors":"Leping Li ,&nbsp;Amlan Talukder ,&nbsp;Deryck Yeung ,&nbsp;Yuanyuan Li ,&nbsp;David M. Umbach ,&nbsp;John H. Gilmore ,&nbsp;Zheng Fan","doi":"10.1016/j.pscychresns.2025.112021","DOIUrl":"10.1016/j.pscychresns.2025.112021","url":null,"abstract":"<div><div>Most EEG studies of MDD examined mean differences in frequency-band-specific power between MDD patients and control subjects; however, a few studies looked for differences in temporal trends in power. We focused on overnight time trends in relative power using polysomnography studies of 544 patients with MDD and 1662 age- and sex-matched controls. We sought to replicate our finding on MDD with an additional 653 patients with depressive disorder (DD) and 1959 age- and sex-matched controls. For each subject, we estimated trends as regression slopes separately for 180 features defined by six frequency bands, five sleep stages, and six brain regions. Relative theta power during stage 2 (N2) non-rapid eye movement (NREM) sleep in the frontal and central regions of the brain increased more rapidly through time in MDD patients than in controls. Similar upward trends of relative theta power were also statistically significant in DD patients. If validated in a longitudinal study, the time trend in relative theta power in the N2 stage of the NREM sleep could potentially serve as a surrogate biomarker for monitoring the responses of patients with depressive disorders to treatment.</div></div>","PeriodicalId":20776,"journal":{"name":"Psychiatry Research: Neuroimaging","volume":"351 ","pages":"Article 112021"},"PeriodicalIF":2.1,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144523007","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":"Differential precuneus and frontal activity associated with facial emotion processing in adolescent depression","authors":"Nazia Jassim ,&nbsp;Cindy Hagan ,&nbsp;Rosemary Holt ,&nbsp;Ian Goodyer ,&nbsp;John Suckling","doi":"10.1016/j.pscychresns.2025.112019","DOIUrl":"10.1016/j.pscychresns.2025.112019","url":null,"abstract":"<div><div>Adolescence is a critical period of vulnerability to mental health issues, yet emotion processing in adolescent depression remains understudied. This task-based functional Magnetic Resonance Imaging (fMRI) study examines emotion processing in depressed adolescents and the effects of Cognitive Behavioural Therapy (CBT). fMRI data were collected during an emotional face processing task from 94 depressed adolescents and 34 healthy controls at baseline. As part of a feasibility study, a longitudinal sub-cohort of 14 depressed adolescents and 33 controls underwent follow-up scans after 24 weeks of CBT. Whole-brain analyses estimated: (a) neural responses to overall facial emotions, and (b) a dynamic range of responses to varying emotion intensities. At baseline, depressed adolescents exhibited greater precuneus activity for positive emotions and hypoactivity in the frontal pole for negative emotions, both correlating with trait anxiety. Although CBT did not significantly alter neural responses in the smaller follow-up sample, behavioural data indicated that depressed adolescents rated high-intensity sad faces as less sad post-treatment. These findings underscore the importance of early interventions targeting emotional biases in adolescent depression. Future studies with larger samples are needed to clarify neural mechanisms of treatment effects.</div></div>","PeriodicalId":20776,"journal":{"name":"Psychiatry Research: Neuroimaging","volume":"351 ","pages":"Article 112019"},"PeriodicalIF":2.1,"publicationDate":"2025-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144563425","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":"Understanding caffeine’s impact on sustained attention in early phase psychosis: Unveiling cognitive insights through the use of EEG","authors":"Ashley M. Francis ,&nbsp;T-Jay Anderson ,&nbsp;Katelyn J. McKearney ,&nbsp;Bronwen Schryver ,&nbsp;Philip G. Tibbo ,&nbsp;Derek J. Fisher","doi":"10.1016/j.pscychresns.2025.112006","DOIUrl":"10.1016/j.pscychresns.2025.112006","url":null,"abstract":"<div><div>Cognitive impairment, particularly in attention and working memory, is a notable feature of schizophrenia (SZ). Individuals with SZ frequently consume high levels of caffeine, often exceeding 550 mg daily, yet the cognitive effects of this excessive intake – especially in the early stages of the illness – remain unexplored. This study is the first to investigate the acute effects of caffeine on cognition in SZ using a rigorous double-blind, placebo-controlled design. Utilizing electroencephalography (EEG)-derived event-related potentials (ERPs) and the AX-continuous performance task (AX-CPT), we examined behavioural and neurophysiological markers of sustained attention, including P300 amplitude and latency.</div><div>Our sample included individuals within the first five years of their SZ diagnosis (<em>n</em> = 11) and healthy controls (<em>n</em> = 14) aged 20 – 38 (HC: <em>M</em> = 22.5, SZ: <em>M</em> = 28.2).</div><div>Findings revealed that within the caffeine condition, individuals with SZ exhibited enhanced P300 amplitudes and shorter latencies for the priming stimulus compared to controls. Behavioural performance, however, did not support this and found individuals with SZ performed worse than controls, suggesting the enhancement of cognitive resources during the caffeine condition does not significantly improve performance in individuals with SZ. Correlational findings suggest a potential interaction between symptomology and caffeine’s cognitive effects, whereby increased positive symptoms were associated with increased amplitudes, while, negative symptoms were associated with latency findings.</div><div>These findings challenge the assumptions that caffeine consumption enhances cognitive function in SZ, at least at the doses tested. Future research should explore caffeine’s effects at intake levels that are more representative of each individual’s habitual consumption to better determine whether chronic high doses exert differential effects on cognition in this population.</div></div>","PeriodicalId":20776,"journal":{"name":"Psychiatry Research: Neuroimaging","volume":"351 ","pages":"Article 112006"},"PeriodicalIF":2.1,"publicationDate":"2025-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144549508","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":"Comparison of retinal neural network parameters of children and adolescents diagnosed with obsessive compulsive disorder with the healthy controls: A cross-sectional study","authors":"Rukiye Çolak Sivri ,&nbsp;Umay Güvenç ,&nbsp;Güner Üney ,&nbsp;Ayşe Nihal Eraslan ,&nbsp;Arzu Yılmaz ,&nbsp;Firdevs Örnek ,&nbsp;Burçin Çolak","doi":"10.1016/j.pscychresns.2025.112017","DOIUrl":"10.1016/j.pscychresns.2025.112017","url":null,"abstract":"<div><div>Obsessive Compulsive Disorder (OCD) is a chronic psychiatric disorder that often begins in childhood or adolescence and is associated with functional abnormalities in cortico-striato-thalamo-cortical circuits. Given the neurodevelopmental basis of OCD and the anatomical and physiological relationship between the retina and the central nervous system, recent studies have focused on investigating retinal changes in neuropsychiatric disorders using Optical Coherence Tomography (OCT). However, data on retinal structural changes in pediatric OCD populations are scant. The aim of this study was to investigate possible retinal structural differences in children and adolescents diagnosed with OCD by comparing OCT-derived measurements with healthy controls. This study compares the Peripapillary Retinal Nerve Fiber Layer (RNFL) thickness, Ganglion Cell Layer (GCL) volume, GCL thickness, Ganglion Cell Complex (GCC) thickness, and Central Macular Thickness (CMT) in pediatric 33 OCD patients and 45 healthy controls. A sociodemographic data form, Maudsley Obsessive Compulsive Questionnaire (MOCI) and Screen for Child Anxiety and Related Disorders (SCARED) were applied. OCT imaging was performed to measure RNFL, GCL volume, GCL thickness, GCC thickness, and CMT. Results showed that the CMT was significantly lower in the OCD group compared to the healthy controls, while the GCC value was lower but not significantly different. No correlation was found between OCT measurements and scale scores. This study is the first to investigate these retinal measurements in pediatric OCD, suggesting a potential relationship that future studies should explore further.</div></div>","PeriodicalId":20776,"journal":{"name":"Psychiatry Research: Neuroimaging","volume":"351 ","pages":"Article 112017"},"PeriodicalIF":2.1,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144365673","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":"Does hyperventilation alter the prefrontal hemodynamics of panic disorder during cognitive task? A functional near-infrared spectroscopy (fNIRS) based study","authors":"Pavithra Jayasankar ,&nbsp;Sonika Nichenmetla ,&nbsp;Vanteemar S Sreeraj ,&nbsp;Vijay Kumar ,&nbsp;Harleen Chhabra ,&nbsp;Narayana Manjunatha ,&nbsp;Ganesan Venkatasubramanian ,&nbsp;Y C Janardhan Reddy","doi":"10.1016/j.pscychresns.2025.112018","DOIUrl":"10.1016/j.pscychresns.2025.112018","url":null,"abstract":"<div><h3>Background</h3><div>Cerebral hypofrontality has been implicated in the pathophysiology of panic disorder, (PD). This study examined the effect of symptom provocation on prefrontal cortex activity during a cognitive task in PD patients and healthy controls (HC) using functional near-infrared spectroscopy (fNIRS).</div></div><div><h3>Methods</h3><div>We included 20 drug-naïve PD patients and 20 HC. Participants performed the N-back task before and after hyperventilation, while prefrontal activation was recorded using fNIRS. Two-way repeated-measures ANOVA was used to analyze changes in task performance and brain activation.</div></div><div><h3>Results</h3><div>There was a significant group effect for two-back D′, F(1, 32) = 4.93, <em>p</em> = 0.03, η² = 0.13, indicating that PD participants performed worse than HC. A significant time × group interaction was observed during the zero-back task in LBA8 and right prefrontal regions: RBA10, RBA8, and RBA46 (all <em>p</em> &lt; 0.05), suggesting that the HC group showed greater activation changes after hyperventilation.</div></div><div><h3>Conclusion</h3><div>Our findings highlight working memory deficits and prefrontal hypofunction in PD. The absence of right prefrontal deactivation after hyperventilation in the PD group, compared to HC, suggests altered right-hemisphere involvement in PD pathophysiology.</div></div>","PeriodicalId":20776,"journal":{"name":"Psychiatry Research: Neuroimaging","volume":"351 ","pages":"Article 112018"},"PeriodicalIF":2.1,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144480898","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":"Redefining parameter-efficiency in ADHD diagnosis: A lightweight attention-driven kolmogorov-arnold network with reduced parameter complexity and a novel activation function","authors":"Deepika,&nbsp;Meghna Sharma,&nbsp;Shaveta Arora","doi":"10.1016/j.pscychresns.2025.112016","DOIUrl":"10.1016/j.pscychresns.2025.112016","url":null,"abstract":"<div><div>As deep learning continues to advance in medical analysis, the increasing complexity of models, particularly Convolutional Neural Networks (CNNs), presents significant challenges related to interpretability, computational costs, and real-world applicability. These issues are critical in the medical domain, e.g., Attention Deficit Hyperactivity Disorder (ADHD) diagnosis, where model efficiency and interpretability are paramount. This paper proposes a novel parameter-efficient framework based on the Kolmogorov-Arnold Network (KAN) to overcome these challenges. Unlike CNNs, KAN restructures feature transformations, significantly reducing parameter overhead while preserving high classification accuracy. An attention-driven feature selection mechanism dynamically prioritizes the most significant features, minimizing irrelevant features and unnecessary computational load. Recognizing the complex and diverse nature of ADHD- related brain connectivity features, a novel activation function with learnable coefficients is introduced, enabling adaptive transformation based on specific data patterns. To further enhance model generalization, an advanced sliding window-based data augmentation technique is incorporated to meet substantial data requirements for training. Extensive experimentation on the benchmark ADHD-200 dataset demonstrates the model's superiority, achieving an accuracy of 79.25 %, an F1-score of 78. 75 % and a precision of 78.23 %, surpassing many state-of-the-art ADHD studies. Remarkably, these results are achieved using only a few thousand parameters compared to the millions required by many existing approaches, making it valuable for various resource-constrained researchers and organizations. The proposed framework, seamlessly fusing KAN, attention-driven feature selection, adaptive activation, and robust data augmentation, achieves substantial parameter reduction with enhanced performance. This lightweight architecture, combined with superior performance and interpretability, makes the proposed model highly promising for ADHD diagnosis and other complex medical applications.</div></div>","PeriodicalId":20776,"journal":{"name":"Psychiatry Research: Neuroimaging","volume":"351 ","pages":"Article 112016"},"PeriodicalIF":2.1,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144514215","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}