Madalina-Octavia Buciuman, Shalaila S Haas, Linda A Antonucci, Elif Sarisik, Adyasha Khuntia, Theresa Lichtenstein, Marlene Rosen, Joseph Kambeitz, Christos Pantelis, Rebekka Lencer, Alessandro Bertolino, Paolo Brambilla, Rachel Upthegrove, Stephen J Wood, Peter Falkai, Anita Riecher-Rössler, Stephan Ruhrmann, Frauke Schultze-Lutter, Eva Meisenzahl, Jarmo Hietala, Raimo K R Salokangas, Stefan Borgwardt, Dominic B Dwyer, Lana Kambeitz-Ilankovic, Nikolaos Koutsouleris
{"title":"从快照到稳定的结果：基于rs- fmri的精神病风险或新近发作的抑郁症患者的功能预后","authors":"Madalina-Octavia Buciuman, Shalaila S Haas, Linda A Antonucci, Elif Sarisik, Adyasha Khuntia, Theresa Lichtenstein, Marlene Rosen, Joseph Kambeitz, Christos Pantelis, Rebekka Lencer, Alessandro Bertolino, Paolo Brambilla, Rachel Upthegrove, Stephen J Wood, Peter Falkai, Anita Riecher-Rössler, Stephan Ruhrmann, Frauke Schultze-Lutter, Eva Meisenzahl, Jarmo Hietala, Raimo K R Salokangas, Stefan Borgwardt, Dominic B Dwyer, Lana Kambeitz-Ilankovic, Nikolaos Koutsouleris","doi":"10.1016/j.biopsych.2025.07.003","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Early recovery of functioning is critical for favorable outcomes in psychotic and affective disorders. Transdiagnostic brain activity patterns may capture pathways for poor outcomes before clinical manifestation, supporting timely prevention and intervention.</p><p><strong>Methods: </strong>Using machine learning, we evaluated the transdiagnostic prognostic value of resting-state fMRI fractional amplitude of low-frequency fluctuations (fALFF, slow-5 and slow-4 sub-bands) for functional outcomes in patients at clinical high-risk for psychosis (n=217) or with recent-onset depression (n=198) from the multi-site PRONIA study. Leave-site-out cross-validation assessed geographic generalizability of models across disability and symptoms domains, with outcomes defined as 'snapshots' at 9- or 18-month follow-up or across both timepoints. We examined diagnosis-specific performance, generalization to recent-onset psychosis (ROP, n=140), and negative symptoms, and the added value of fALFF over clinical prognostication.</p><p><strong>Results: </strong>Transdiagnostic models predicting stable good functioning across follow-ups showed up to 10% higher balanced accuracy (BAC) than 'snapshot' models. Decreased slow-5 fALFF in the default-mode, executive control (EC), and dorsal attentional (DA) networks, and increased fALFF in salience, EC, and DA networks predicted impairment with BAC=67% (Sensitivity=65%, Specificity=70%, P<.001). This model generalized to ROP (BAC=62%, Sensitivity=64%, Specificity=59%, P<.001) and predicted (BAC=65%, Sensitivity=66%, Specificity=65%, P<.001) and was mediated by negative symptoms. Slow-5-based models improved prognostic accuracy over expert ratings in disability (BAC<sub>raters</sub>=66%, BAC<sub>raters+slow-5</sub>=75%, W=1680, P<.001) and symptoms domains (BAC<sub>raters</sub>=61%, BAC<sub>raters+slow-5</sub>=71%, W=1444, P<.001).</p><p><strong>Conclusions: </strong>We highlighted the prognostic value of fALFF for functional impairment in psychosis-risk and early depression. Leveraging trajectorial information, we identified candidate imaging biomarkers to improve prognostication, supporting personalized prevention and recovery strategies.</p>","PeriodicalId":8918,"journal":{"name":"Biological Psychiatry","volume":" ","pages":""},"PeriodicalIF":9.6000,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"From Snapshots to Stable Outcomes: rs-fMRI-based Prognosis of Functioning in Patients with Psychosis Risk or Recent-Onset Depression.\",\"authors\":\"Madalina-Octavia Buciuman, Shalaila S Haas, Linda A Antonucci, Elif Sarisik, Adyasha Khuntia, Theresa Lichtenstein, Marlene Rosen, Joseph Kambeitz, Christos Pantelis, Rebekka Lencer, Alessandro Bertolino, Paolo Brambilla, Rachel Upthegrove, Stephen J Wood, Peter Falkai, Anita Riecher-Rössler, Stephan Ruhrmann, Frauke Schultze-Lutter, Eva Meisenzahl, Jarmo Hietala, Raimo K R Salokangas, Stefan Borgwardt, Dominic B Dwyer, Lana Kambeitz-Ilankovic, Nikolaos Koutsouleris\",\"doi\":\"10.1016/j.biopsych.2025.07.003\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Early recovery of functioning is critical for favorable outcomes in psychotic and affective disorders. Transdiagnostic brain activity patterns may capture pathways for poor outcomes before clinical manifestation, supporting timely prevention and intervention.</p><p><strong>Methods: </strong>Using machine learning, we evaluated the transdiagnostic prognostic value of resting-state fMRI fractional amplitude of low-frequency fluctuations (fALFF, slow-5 and slow-4 sub-bands) for functional outcomes in patients at clinical high-risk for psychosis (n=217) or with recent-onset depression (n=198) from the multi-site PRONIA study. Leave-site-out cross-validation assessed geographic generalizability of models across disability and symptoms domains, with outcomes defined as 'snapshots' at 9- or 18-month follow-up or across both timepoints. We examined diagnosis-specific performance, generalization to recent-onset psychosis (ROP, n=140), and negative symptoms, and the added value of fALFF over clinical prognostication.</p><p><strong>Results: </strong>Transdiagnostic models predicting stable good functioning across follow-ups showed up to 10% higher balanced accuracy (BAC) than 'snapshot' models. Decreased slow-5 fALFF in the default-mode, executive control (EC), and dorsal attentional (DA) networks, and increased fALFF in salience, EC, and DA networks predicted impairment with BAC=67% (Sensitivity=65%, Specificity=70%, P<.001). This model generalized to ROP (BAC=62%, Sensitivity=64%, Specificity=59%, P<.001) and predicted (BAC=65%, Sensitivity=66%, Specificity=65%, P<.001) and was mediated by negative symptoms. Slow-5-based models improved prognostic accuracy over expert ratings in disability (BAC<sub>raters</sub>=66%, BAC<sub>raters+slow-5</sub>=75%, W=1680, P<.001) and symptoms domains (BAC<sub>raters</sub>=61%, BAC<sub>raters+slow-5</sub>=71%, W=1444, P<.001).</p><p><strong>Conclusions: </strong>We highlighted the prognostic value of fALFF for functional impairment in psychosis-risk and early depression. Leveraging trajectorial information, we identified candidate imaging biomarkers to improve prognostication, supporting personalized prevention and recovery strategies.</p>\",\"PeriodicalId\":8918,\"journal\":{\"name\":\"Biological Psychiatry\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":9.6000,\"publicationDate\":\"2025-07-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Biological Psychiatry\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1016/j.biopsych.2025.07.003\",\"RegionNum\":1,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"NEUROSCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biological Psychiatry","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1016/j.biopsych.2025.07.003","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"NEUROSCIENCES","Score":null,"Total":0}
From Snapshots to Stable Outcomes: rs-fMRI-based Prognosis of Functioning in Patients with Psychosis Risk or Recent-Onset Depression.
Background: Early recovery of functioning is critical for favorable outcomes in psychotic and affective disorders. Transdiagnostic brain activity patterns may capture pathways for poor outcomes before clinical manifestation, supporting timely prevention and intervention.
Methods: Using machine learning, we evaluated the transdiagnostic prognostic value of resting-state fMRI fractional amplitude of low-frequency fluctuations (fALFF, slow-5 and slow-4 sub-bands) for functional outcomes in patients at clinical high-risk for psychosis (n=217) or with recent-onset depression (n=198) from the multi-site PRONIA study. Leave-site-out cross-validation assessed geographic generalizability of models across disability and symptoms domains, with outcomes defined as 'snapshots' at 9- or 18-month follow-up or across both timepoints. We examined diagnosis-specific performance, generalization to recent-onset psychosis (ROP, n=140), and negative symptoms, and the added value of fALFF over clinical prognostication.
Results: Transdiagnostic models predicting stable good functioning across follow-ups showed up to 10% higher balanced accuracy (BAC) than 'snapshot' models. Decreased slow-5 fALFF in the default-mode, executive control (EC), and dorsal attentional (DA) networks, and increased fALFF in salience, EC, and DA networks predicted impairment with BAC=67% (Sensitivity=65%, Specificity=70%, P<.001). This model generalized to ROP (BAC=62%, Sensitivity=64%, Specificity=59%, P<.001) and predicted (BAC=65%, Sensitivity=66%, Specificity=65%, P<.001) and was mediated by negative symptoms. Slow-5-based models improved prognostic accuracy over expert ratings in disability (BACraters=66%, BACraters+slow-5=75%, W=1680, P<.001) and symptoms domains (BACraters=61%, BACraters+slow-5=71%, W=1444, P<.001).
Conclusions: We highlighted the prognostic value of fALFF for functional impairment in psychosis-risk and early depression. Leveraging trajectorial information, we identified candidate imaging biomarkers to improve prognostication, supporting personalized prevention and recovery strategies.
期刊介绍：
Biological Psychiatry is an official journal of the Society of Biological Psychiatry and was established in 1969. It is the first journal in the Biological Psychiatry family, which also includes Biological Psychiatry: Cognitive Neuroscience and Neuroimaging and Biological Psychiatry: Global Open Science. The Society's main goal is to promote excellence in scientific research and education in the fields related to the nature, causes, mechanisms, and treatments of disorders pertaining to thought, emotion, and behavior. To fulfill this mission, Biological Psychiatry publishes peer-reviewed, rapid-publication articles that present new findings from original basic, translational, and clinical mechanistic research, ultimately advancing our understanding of psychiatric disorders and their treatment. The journal also encourages the submission of reviews and commentaries on current research and topics of interest.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
