Translational Psychiatry最新文献

{"title":"Associations between biomarkers of inflammation and depressive symptoms-potential differences between diabetes types and symptom clusters of depression.","authors":"Christian Herder, Anna Zhu, Andreas Schmitt, Maria C Spagnuolo, Bernhard Kulzer, Michael Roden, Norbert Hermanns, Dominic Ehrmann","doi":"10.1038/s41398-024-03209-y","DOIUrl":"10.1038/s41398-024-03209-y","url":null,"abstract":"<p><p>Inflammation is a probable biological pathway underlying the relationship between diabetes and depression, but data on differences between diabetes types and symptom clusters of depression are scarce. Therefore, this cross-sectional study aimed to compare associations of a multimarker panel of biomarkers of inflammation with depressive symptoms and its symptom clusters between people with type 1 diabetes (T1D) and type 2 diabetes (T2D). This cross-sectional study combined data from five studies including 1260 participants (n = 706 T1D, n = 454 T2D). Depressive symptoms were assessed using the Center for Epidemiological Studies-Depression Scale (CES-D). Serum levels of 92 biomarkers of inflammation were quantified with proximity extension assay technology. After quality control, 76 biomarkers of inflammation remained for statistical analysis. Associations between biomarkers and depressive symptom scores and clusters (cognitive-affective, somatic, anhedonia) were estimated with multivariable linear regression models. Nine biomarkers were positively associated with depressive symptoms in the total sample (CCL11/eotaxin, CCL25, CDCP1, FGF-21, IL-8, IL-10RB, IL-18, MMP-10, TNFRSF9; all p < 0.05) without interaction by diabetes type. Associations differed for eight biomarkers (p_interaction < 0.05). TNFβ was inversely associated with depressive symptoms in T1D, whereas three biomarkers (GDNF, IL-18R1, LIF-R) were positively associated with depressive symptoms in T2D. For the remaining four biomarkers (CD6, CD244, FGF-5, IFNγ) associations were not significant in either subgroup. Biomarker associations were more pronounced with somatic and anhedonia than with cognitive-affective symptoms. These results indicate that different proinflammatory pathways may contribute to depression in T1D and T2D and that there may be a symptom specificity in the link between subclinical inflammation and depression.</p>","PeriodicalId":23278,"journal":{"name":"Translational Psychiatry","volume":"15 1","pages":"9"},"PeriodicalIF":5.8,"publicationDate":"2025-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11724873/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142972273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of functional near-infrared spectroscopy and machine learning to predict treatment response after six months in major depressive disorder.","authors":"Cyrus Su Hui Ho, Jinyuan Wang, Gabrielle Wann Nii Tay, Roger Ho, Hai Lin, Zhifei Li, Nanguang Chen","doi":"10.1038/s41398-025-03224-7","DOIUrl":"10.1038/s41398-025-03224-7","url":null,"abstract":"<p><p>Depression treatment responses vary widely among individuals. Identifying objective biomarkers with predictive accuracy for therapeutic outcomes can enhance treatment efficiency and avoid ineffective therapies. This study investigates whether functional near-infrared spectroscopy (fNIRS) and clinical assessment information can predict treatment response in major depressive disorder (MDD) through machine-learning techniques. Seventy patients with MDD were included in this 6-month longitudinal study, with the primary treatment outcome measured by changes in the Hamilton Depression Rating Scale (HAM-D) scores. fNIRS and clinical information were strictly evaluated using nested cross-validation to predict responders and non-responders based on machine-learning models, including support vector machine, random forest, XGBoost, discriminant analysis, Naïve Bayes, and transformers. The task change of total haemoglobin (HbT), defined as the difference between pre-task and post-task average HbT concentrations, in the dorsolateral prefrontal cortex (dlPFC) is significantly correlated with treatment response (p < 0.005). Leveraging a Naïve Bayes model, inner cross-validation performance (bAcc = 70% [SD = 4], AUC = 0.77 [SD = 0.04]) and outer cross-validation results (bAcc = 73% [SD = 3], AUC = 0.77 [SD = 0.02]) were yielded for predicting response using solely fNIRS data. The bimodal model combining fNIRS and clinical data showed inferior performance in outer cross-validation (bAcc = 68%, AUC = 0.70) compared to the fNIRS-only model. Collectively, fNIRS holds potential as a scalable neuroimaging modality for predicting treatment response in MDD.</p>","PeriodicalId":23278,"journal":{"name":"Translational Psychiatry","volume":"15 1","pages":"7"},"PeriodicalIF":5.8,"publicationDate":"2025-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11724951/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142972272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Remote photobiomodulation ameliorates behavioral and neuropathological outcomes in a rat model of repeated closed head injury.","authors":"Chongyun Wu, Meng Li, Zhe Chen, Shu Feng, Qianting Deng, Rui Duan, Timon Cheng-Yi Liu, Luodan Yang","doi":"10.1038/s41398-025-03228-3","DOIUrl":"10.1038/s41398-025-03228-3","url":null,"abstract":"<p><p>Repeated closed-head injuries (rCHI) from activities like contact sports, falls, military combat, and traffic accidents pose a serious risk due to their cumulative impact on the brain. Often, rCHI is not diagnosed until symptoms of irreversible brain damage appear, highlighting the need for preventive measures. This study assessed the prophylactic efficacy of remote photobiomodulation (PBM) targeted at the lungs against rCHI-induced brain injury and associated behavioral deficits. Utilizing the \"Marmarou\" weight-drop model, rCHI was induced in rats on days 0, 5, and 10. Remote PBM, employing an 808 nm continuous wave laser, was administered daily in 2-min sessions per lung side over 20 days. Behavioral deficits were assessed through three-chamber social interaction, forced swim, grip strength, open field, elevated plus maze, and Barnes maze tests. Immunofluorescence staining and 3D reconstruction evaluated neuronal damage, apoptosis, degeneration, and the morphology of microglia and astrocytes, as well as astrocyte and microglia-mediated excessive synapse elimination. Additionally, 16S rDNA amplicon sequencing analyzed changes in the lung microbiome following remote PBM treatment. Results demonstrated that remote PBM significantly improved depressive-like behaviors, motor dysfunction, and social interaction impairment while enhancing grip strength and reducing neuronal damage, apoptosis, and degeneration induced by rCHI. Analysis of lung microbiome changes revealed an enrichment of lipopolysaccharide (LPS) biosynthesis pathways, suggesting a potential link to neuroprotection. Furthermore, remote PBM mitigated hyperactivation of cortical microglia and astrocytes and significantly reduced excessive synaptic phagocytosis by these cells, highlighting its potential as a preventive strategy for rCHI with neuroprotective effects.</p>","PeriodicalId":23278,"journal":{"name":"Translational Psychiatry","volume":"15 1","pages":"8"},"PeriodicalIF":5.8,"publicationDate":"2025-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11724958/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142972274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Electrophysiology-based screening identifies neuronal HtrA serine peptidase 2 (HTRA2) as a synaptic plasticity regulator participating in tauopathy.","authors":"Naizhen Zheng, Kun Li, Jing Cao, Zijie Wang, Liang Zhang, Zihao Zhao, Jiawei He, Yong Wang, Xiang Zhu, Yiqing Chen, Jian Meng, Dongdong Zhao, Mengxi Niu, Hong Luo, Xian Zhang, Hao Sun, Yun-Wu Zhang","doi":"10.1038/s41398-025-03227-4","DOIUrl":"10.1038/s41398-025-03227-4","url":null,"abstract":"<p><p>Long-term potentiation (LTP) and long-term depression (LTD) are widely used to study synaptic plasticity. However, whether proteins regulating LTP and LTD are altered in cognitive disorders and contribute to disease onset remains to be determined. Herein, we induced LTP and LTD in the hippocampal CA3-CA1 Schaffer collateral pathway, respectively, and then performed proteomic analysis of the CA1 region. We identified 20 differentially expressed proteins (DEPs) shared by the LTP and the LTD processes. Among them, we found that HtrA serine peptidase 2 (HTRA2) was mainly expressed in neurons and that HTRA2 levels were increased in both the LTP and the LTD processes in C57BL/6 mice. HTRA2 downregulation impaired synapses and reduced ATP production in cultured primary neurons. Furthermore, adeno-associated virus (AAV)-mediated HTRA2 downregulation in the hippocampus impaired synaptic plasticity and cognitive function in C57BL/6 mice. Moreover, we found that HTRA2 expression decreased in the brains of Alzheimer's disease patients, frontotemporal lobar degeneration with ubiquitin inclusions patients, and tauopathy model mice. Finally, we showed that lentivirus-mediated HTRA2 overexpression in the hippocampus rescued PP2B reduction, alleviated tau hyperphosphorylation, and partially attenuated synaptic plasticity and cognitive deficits in the PS19 tauopathy model mice. Our study not only indicates that HTRA2 in neurons plays an important role in regulating synaptic plasticity under both physiological and pathological conditions, but also provides a novel, electrophysiology-based strategy to identify proteins regulating synaptic plasticity systematically.</p>","PeriodicalId":23278,"journal":{"name":"Translational Psychiatry","volume":"15 1","pages":"5"},"PeriodicalIF":5.8,"publicationDate":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11724108/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142966676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Targeting Shp2 as a therapeutic strategy for neurodegenerative diseases.","authors":"Jiao Pang, Changqian Cen, Yuan Tian, Xingrui Cao, Liang Hao, Xueshu Tao, Zhipeng Cao","doi":"10.1038/s41398-024-03222-1","DOIUrl":"10.1038/s41398-024-03222-1","url":null,"abstract":"<p><p>The incidence of neurodegenerative diseases (NDs) has increased recently. However, most of the current governance strategies are palliative and lack effective therapeutic drugs. Therefore, elucidating the pathological mechanism of NDs is the key to the development of targeted drugs. As a member of the tyrosine phosphatase family, the role of Shp2 has been studied in tumors, but the research in the nervous system is still in a sporadic state. It can be phosphorylated by tyrosine kinases and then positively regulate tyrosine kinase-dependent signaling pathways. It could also be used as an adaptor protein to mediate downstream signaling pathways. Most of the existing studies have shown that Shp2 may be a potential molecular \"checkpoint\" against NDs, but its role in promoting degenerative lesions is difficult to ignore as well, and its two-way effect of both activation and inhibition is very distinctive. Shp2 is closely related to NDs-related pathogenic factors such as oxidative stress, mitochondrial dysfunction, excitatory toxicity, immune inflammation, apoptosis, and autophagy. Its bidirectional effects interfere with these pathogenic factors, making it a core component of the feedback and crosstalk network between multiple signaling pathways. Therefore, this article reviews the molecular mechanism of Shp2 regulation in NDs and its regulatory role in various pathogenic factors, providing evidence for the treatment of NDs by targeting Shp2 and the development of molecular targeted drugs.</p>","PeriodicalId":23278,"journal":{"name":"Translational Psychiatry","volume":"15 1","pages":"6"},"PeriodicalIF":5.8,"publicationDate":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11724000/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142966612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Auditory evoked-potential abnormalities in a mouse model of 22q11.2 Deletion Syndrome and their interactions with hearing impairment.","authors":"Chen Lu, Jennifer F Linden","doi":"10.1038/s41398-024-03218-x","DOIUrl":"10.1038/s41398-024-03218-x","url":null,"abstract":"<p><p>The 22q11.2 deletion is a risk factor for multiple psychiatric disorders including schizophrenia and also increases vulnerability to middle-ear problems that can cause hearing impairment. Up to 60% of deletion carriers experience hearing impairment and ~30% develop schizophrenia in adulthood. It is not known if these risks interact. Here we used the Df1/+ mouse model of the 22q11.2 deletion to investigate how hearing impairment might interact with increased genetic vulnerability to psychiatric disease to affect brain function. We measured brain function using cortical auditory evoked potentials (AEPs), which are commonly measured non-invasively in humans. After identifying one of the simplest and best-validated methods for AEP measurement in mice from the diversity of previous approaches, we measured peripheral hearing sensitivity and cortical AEPs in Df1/+ mice and their WT littermates. We exploited large inter-individual variation in hearing ability among Df1/+ mice to distinguish effects of genetic background from effects of hearing impairment. Central auditory gain and adaptation were quantified by comparing brainstem activity and cortical AEPs and by analyzing the growth of cortical AEPs with increasing sound level or inter-tone interval duration. We found that level-dependent AEP growth was abnormally large in Df1/+ mice regardless of hearing impairment, but other AEP measures of central auditory gain and adaptation depended on both genotype and hearing phenotype. Our results demonstrate the relevance of comorbid hearing loss to auditory brain dysfunction in 22q11.2DS and also identify potential biomarkers for psychiatric disease that are robust to hearing impairment.</p>","PeriodicalId":23278,"journal":{"name":"Translational Psychiatry","volume":"15 1","pages":"4"},"PeriodicalIF":5.8,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11711659/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142955597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting clinical outcomes in a blended care intervention for early psychosis: Acceptance and Commitment Therapy in Daily-Life (ACT-DL).","authors":"Rafaël A Bonnier, Joanne R Beames, Glenn Kiekens, Evelyne van Aubel, Frederike Schirmbeck, Lieuwe de Haan, Machteld Marcelis, Mark van der Gaag, Ruud van Winkel, Therese van Amelsvoort, Thomas Vaessen, Ulrich Reininghaus, Ginette Lafit, Inez Myin-Germeys","doi":"10.1038/s41398-024-03214-1","DOIUrl":"10.1038/s41398-024-03214-1","url":null,"abstract":"<p><p>ACT in Daily Life (ACT-DL) is a blended-care Ecological Momentary Intervention that extends ACT into the daily life of individuals, improving psychotic distress, negative symptoms, and global functioning. However, it remains unclear whether ACT-DL works equally for everyone. We investigated whether moderators (i.e., sociodemographic information, personality, and trauma history) determine clinical outcomes in individuals with early psychosis receiving ACT-DL. Seventy-one participants from the INTERACT trial, using ACT-DL, were analyzed. Outcomes included psychotic distress, negative symptoms, global functioning, and psychological flexibility. Using multivariate-multilevel models, we evaluated the effects of sociodemographics, personality, and childhood trauma across baseline, post-intervention, and six- and 12-month follow-ups. Sociodemographic characteristics and personality predicted clinical outcomes. Higher education demonstrated more substantial improvement in global functioning at 6- (B = 7.43, p = 0.04) and 12-FU (B = 10.74, p = 0.002) compared to lower education. Higher extraversion showed less improvement in negative symptoms at 12-FU (B = 1.24, p = 0.01) and more improvement in global functioning at post-intervention (B = 0.39, p = 0.046) and 6-FU (B = 1.40, p = 0.02) compared to lower extraversion. Higher negative affectivity showed more improvement in negative symptoms at 12-FU (B = -1.59, p = 0.001) and higher psychological flexibility at 12-FU (B = 8.38, p = 0.001) compared to lower negative affectivity. Our findings suggest that while ACT-DL improves clinical outcomes in individuals with early psychosis, the improvement rate is dissimilar for individuals and predictable by baseline characteristics. If replicated, these findings enable precision medicine approaches in allocating ACT-DL for early psychosis.</p>","PeriodicalId":23278,"journal":{"name":"Translational Psychiatry","volume":"15 1","pages":"3"},"PeriodicalIF":5.8,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11707341/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142955601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Associations of plasma biomarkers with cerebral perfusion and structure in Alzheimer's disease.","authors":"Yong He, Xiaojiao Liu, Fang Liu, Ping Che, Yanxin Zhang, Ruxue Fan, Yuan Li, Wen Qin, Nan Zhang","doi":"10.1038/s41398-024-03220-3","DOIUrl":"https://doi.org/10.1038/s41398-024-03220-3","url":null,"abstract":"<p><p>Plasma biomarkers have great potential in the screening, diagnosis, and monitoring of Alzheimer's disease (AD). However, findings on their associations with cerebral perfusion and structural changes are inconclusive. We examined both cross-sectional and longitudinal associations between plasma biomarkers and cerebral blood flow (CBF), gray matter (GM) volume, and white matter (WM) integrity. Forty-eight AD patients whose diagnosis was supported by amyloid-β (Aβ) PET received measurement of plasma biomarkers with a single molecular array, including Aβ42, phosphorylated tau 181 (P-tau181), neurofilament light (NfL), total tau (T-tau), and glial fibrillary acidic protein (GFAP), and both baseline and one-year follow-up magnetic resonance imaging, including pseudo-continuous arterial spin labeling, T1-weighted imaging, and diffusion tensor imaging. Correlations were found between regional CBF and several plasma biomarkers, with Aβ42 showing the strongest correlation with CBF in the left inferior temporal gyrus (r = 0.507, p = 0.001). Plasma P-tau181 and GFAP levels were correlated with GM volume in the posterior cingulate gyrus and the bilateral hippocampus and right middle temporal gyrus, respectively. Decreased CBF and GM volume in regions vulnerable to AD, such as the posterior cingulate gyrus, inferior parietal lobule and hippocampus, could be predicted by the levels of specific plasma biomarkers. Most biomarkers, except Aβ42, showed extensive correlations with longitudinal WM disruption. Plasma biomarkers exhibited varied correlations with brain perfusion, GM volume, and WM integrity and predicted their longitudinal changes in AD patients, suggesting their potential to reflect functional and structural changes and to monitor pathophysiological progression in the brain.</p>","PeriodicalId":23278,"journal":{"name":"Translational Psychiatry","volume":"15 1","pages":"2"},"PeriodicalIF":5.8,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11704010/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142955513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A genetic exploration of the relationship between posttraumatic stress disorder and cardiovascular diseases.","authors":"Eva Lukas, Rada R Veeneman, Dirk J A Smit, Tarunveer S Ahluwalia, Jentien M Vermeulen, Gita A Pathak, Renato Polimanti, Karin J H Verweij, Jorien L Treur","doi":"10.1038/s41398-024-03197-z","DOIUrl":"https://doi.org/10.1038/s41398-024-03197-z","url":null,"abstract":"<p><p>Experiencing a traumatic event may lead to Posttraumatic Stress Disorder (PTSD), including symptoms such as flashbacks and hyperarousal. Individuals suffering from PTSD are at increased risk of cardiovascular disease (CVD), but it is unclear why. This study assesses shared genetic liability and potential causal pathways between PTSD and CVD. We leveraged summary-level data of genome-wide association studies (PTSD: N = 1,222,882; atrial fibrillation (AF): N = 482,409; coronary artery disease (CAD): N = 1,165,690; hypertension (HT): N = 458,554; heart failure (HF): N = 977,323). First, we estimated genetic correlations and utilized genomic structural equation modeling to identify a common genetic factor for PTSD and CVD. Next, we assessed biological, behavioural, and psychosocial factors as potential mediators. Finally, we employed multivariable Mendelian randomization to examine causal pathways between PTSD and CVD, incorporating the same potential mediators. Significant genetic correlations were found between PTSD and CAD, HT, and HF (r_g = 0.21-0.32, p ≤ 3.08 · 10^-16), but not between PTSD and AF. Insomnia, smoking, alcohol dependence, waist-to-hip ratio, and inflammation (IL6, C-reactive protein) partly mediated these associations. Mendelian randomization indicated that PTSD causally increases CAD (IVW OR = 1.53, 95% CIs = 1.19-1.96, p = 0.001), HF (OR = 1.44, CIs = 1.08-1.92, p = 0.012), and to a lesser degree HT (OR = 1.25, CIs = 1.05-1.49, p = 0.012). While insomnia, smoking, alcohol, and inflammation were important mediators, independent causal effects also remained. In addition to shared genetic liability between PTSD and CVD, we present strong evidence for causal effects of PTSD on CVD. Crucially, we implicate specific lifestyle and biological mediators (insomnia, substance use, inflammation) which has important implications for interventions to prevent CVD in PTSD patients.</p>","PeriodicalId":23278,"journal":{"name":"Translational Psychiatry","volume":"15 1","pages":"1"},"PeriodicalIF":5.8,"publicationDate":"2025-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142928470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Virtual reality-assisted prediction of adult ADHD based on eye tracking, EEG, actigraphy and behavioral indices: a machine learning analysis of independent training and test samples.","authors":"Annika Wiebe, Benjamin Selaskowski, Martha Paskin, Laura Asché, Julian Pakos, Behrem Aslan, Silke Lux, Alexandra Philipsen, Niclas Braun","doi":"10.1038/s41398-024-03217-y","DOIUrl":"10.1038/s41398-024-03217-y","url":null,"abstract":"<p><p>Given the heterogeneous nature of attention-deficit/hyperactivity disorder (ADHD) and the absence of established biomarkers, accurate diagnosis and effective treatment remain a challenge in clinical practice. This study investigates the predictive utility of multimodal data, including eye tracking, EEG, actigraphy, and behavioral indices, in differentiating adults with ADHD from healthy individuals. Using a support vector machine model, we analyzed independent training (n = 50) and test (n = 36) samples from two clinically controlled studies. In both studies, participants performed an attention task (continuous performance task) in a virtual reality seminar room while encountering virtual distractions. Task performance, head movements, gaze behavior, EEG, and current self-reported inattention, hyperactivity, and impulsivity were simultaneously recorded and used for model training. Our final model based on the optimal number of features (maximal relevance minimal redundancy criterion) achieved a promising classification accuracy of 81% in the independent test set. Notably, the extracted EEG-based features had no significant contribution to this prediction and therefore were not included in the final model. Our results suggest the potential of applying ecologically valid virtual reality environments and integrating different data modalities for enhancing robustness of ADHD diagnosis.</p>","PeriodicalId":23278,"journal":{"name":"Translational Psychiatry","volume":"14 1","pages":"508"},"PeriodicalIF":5.8,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11688437/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142910908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}