[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120578-en":3,"doc-seo-120578-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},120578,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Machine learning helps predict early onset psychosis with serum protein biomarkers, neuropsychometry, and clinicodemographic data","Early-onset psychosis creates diagnostic uncertainty because overlapping clinical features and comorbidities complicate decision-making, often requiring tertiary-level evaluation with extensive neuroimaging, neuropsychometric testing, and multidisciplinary review. This case-control study evaluates whether machine learning can unify serum protein biomarkers, neuropsychometry, and clinicodemographic variables into an objective diagnostic framework. Forty-five patients with early-onset psychosis and 34 healthy controls were assessed using BDNF/proBDNF, p75NTR, S100B, and cognitive tasks, then modeled with nested cross-validation.","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nMachine learning helps predict early onset psychosis with serum protein biomarkers, neuropsychometry, and clinicodemographic data  \nPrzemyslaw T. Zakowicz1,9, MaksymilianA. Brzezicki1,2,9􀀍, Joanna Pawlak4, Maria Skibinska4, Szymon Jurga3, Aleksandra Lewandowska5, Benedikt Vogel6, Emily Ungermann7 & Barbara Remberk8  \nEarly-onset psychosis presents diagnostic challenges due to overlapping clinical presentations and complex comorbidities, typically requiring specialized tertiary care with extensive neuroimaging, neuropsychometric testing, and multidisciplinary evaluation. This case-control study investigated whether machine learning could integrate multiple diagnostic modalities to create an objective diagnostic framework for early-onset psychosis. We recruited 45 patients with early-onset psychosis and 34 healthy controls from a tertiary referral centre. Participants underwent comprehensive assessment including serum protein biomarker analysis (brain-derived neurotrophic factor, proBDNF, p75 neurotrophin receptor, S100B), neuropsychometric testing (Iowa Gambling Task, Simple Response Time, Zabor Verbal Task), and demographic evaluation. Four machine learning algorithms (logistic regression, support vector machine, random forest, XGBoost) were trained on five feature combinations using nested cross-validation with hyperparameter optimization. XGBoost demonstrated superior performance, achieving optimal classification with the complete multimodal dataset (accuracy: 0.91 ± 0.08, precision: 0.92 ± 0.08, area under curve: 0.97 ± 0.04) . Feature importance analysis revealed cognitive measures, particularly Zabor Verbal Task errors and response time parameters, as most discriminative, with brain-derived neurotrophic factor pathway components showing highest biomarker importance. Machine learning effectively integrated neuropsychometric and protein biomarker data for high-accuracy early-onset psychosis classification, with multimodal approaches outperforming single-domain assessments.  \nKeywords Biomarkers, Adolescents, Neuropsychometry, XGBoost, Classification, Neurotrophins  \nPrimary psychotic disorder is a significant and growing contributor to the global burden of neurological diseases. It leads to a decline in disability-adjusted life years as well as a wide variety of occupational, familial, and social problems1,2. In early onset psychosis (EOS) patients often present with less demarcated clinical syndromes3 and may have various developmental and socioeconomic comorbidities, thus lowering diagnostic certainty. This leads to delays in care and up to four times longer duration of time of untreated psychosis4, which results in worse prognosis5–7, especially if the independent living, gaining employment and satisfactory school performance are to be considered as priorities of care.  \n1Department of Neural Engineering and Space Medicine, Institute of Medical Sciences, University of Zielona Góra, Zielona Góra, Poland. 2Jesus College, University of Oxford, Oxford, UK. 3Department of Neurology, University Hospital, Zielona Góra, Poland. 4Department of Genetics in Psychiatry, Poznan University of Medical Sciences, Poznan, Poland. 5Department of Child and Adolescent Psychiatry, Babinski Hospital, Lodz, Poland.  \n6Querschnittgelähmten-Zentrum, BG Klinikum, Hamburg, Germany. 7Institute of Forensic and Traffic Medicine, University Hospital Heidelberg, Heidelberg, Germany. 8Institute of Neurology and Psychiatry, Warsaw, Poland. 9Przemyslaw T. Zakowicz and Maksymilian A. Brzezicki contributed equally to this work. 􀀍 email: [mbrzezicki@neurologicalsociety.org](mbrzezicki@neurologicalsociety.org)  \n[www. nature.com/scientificreports/](www. nature.com/scientificreports/)  \nTo that end several diagnostic panels were proposed. The neurocognitive element could be measured through standardised protocols using tests such as Simple Response Time, Iowa Gambling Task8, Zabor V","cbCaiqnATT0zyNUa","https://ap.wps.com/l/cbCaiqnATT0zyNUa","pdf",2373006,1,14,"English","en",105,"# Study design and rationale\n## Participants and assessments\n## Machine learning methods\n## Results and discriminative features\n# Clinical and biomarker context\n## Diagnostic challenges in early onset psychosis\n## Neurocognitive and neuroimaging approaches\n## Genetic and polygenic risk approaches\n## Neurotrophins and serum biomarker rationale","[{\"question\":\"How was the study designed to predict early-onset psychosis?\",\"answer\":\"A case-control design compared 45 early-onset psychosis patients with 34 healthy controls using serum protein biomarker testing, neuropsychometric tasks, and clinicodemographic data. Models were trained and evaluated with nested cross-validation and hyperparameter optimization.\"},{\"question\":\"Which machine learning model performed best?\",\"answer\":\"XGBoost showed the highest performance using the complete multimodal dataset, reaching an accuracy of 0.91 ± 0.08 and an AUC of 0.97 ± 0.04.\"},{\"question\":\"Which features contributed most to classification?\",\"answer\":\"Cognitive measures, especially Zabor Verbal Task errors and response time parameters, were most discriminative. Brain-derived neurotrophic factor pathway components had the highest biomarker importance.\"}]","Machine learning helps predict early onset psychosis with serum protein biomarkers, neuropsychometry, and clinicodemographic data | PDF",1785730748,35,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-helps-predict-early-onset-psychosis-with-serum-protein-biomarkers-neuropsychometry-and-clinicodemographic-data","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-helps-predict-early-onset-psychosis-with-serum-protein-biomarkers-neuropsychometry-and-clinicodemographic-data/120578/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"How was the study designed to predict early-onset psychosis?","Question",{"text":75,"@type":76},"A case-control design compared 45 early-onset psychosis patients with 34 healthy controls using serum protein biomarker testing, neuropsychometric tasks, and clinicodemographic data. Models were trained and evaluated with nested cross-validation and hyperparameter optimization.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning model performed best?",{"text":80,"@type":76},"XGBoost showed the highest performance using the complete multimodal dataset, reaching an accuracy of 0.91 ± 0.08 and an AUC of 0.97 ± 0.04.",{"name":82,"@type":73,"acceptedAnswer":83},"Which features contributed most to classification?",{"text":84,"@type":76},"Cognitive measures, especially Zabor Verbal Task errors and response time parameters, were most discriminative. Brain-derived neurotrophic factor pathway components had the highest biomarker importance.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]