{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T11:53:32Z","timestamp":1792065212974,"version":"4.4.0"},"reference-count":61,"publisher":"Royal College of Psychiatrists","issue":"1","license":[{"start":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:00:00Z","timestamp":1792022400000},"content-version":"unspecified","delay-in-days":287,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100005297","name":"Uniwersytet Medyczny w Bialymstoku","doi-asserted-by":"publisher","award":["B.SUB.26.435"],"award-info":[{"award-number":["B.SUB.26.435"]}],"id":[{"id":"10.13039\/501100005297","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Eur. Psychiatr."],"published-print":{"date-parts":[[2026]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec id=\"S0924933826122627_sec1\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The application of artificial intelligence (AI) to resting-state electroencephalography (EEG) data represents a burgeoning frontier in schizophrenia diagnostics. However, the inferential validity of findings is frequently compromised by methodological heterogeneity. This systematic review rigorously evaluates the diagnostic efficacy and methodological robustness of AI-generated EEG biomarkers by implementing the Prediction model Risk Of Bias Assessment Tool for Artificial Intelligence (PROBAST+AI).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"S0924933826122627_sec2\" sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      Following PRISMA guidelines, a systematic search of PubMed, Scopus, and Web of Science identified 43 primary studies encompassing 3,420 patients with schizophrenia or first-episode psychosis and 3,164 healthy controls (total\n                      <jats:italic>N<\/jats:italic>\n                      = 6,584). Methodological quality and validation strategies were assessed using the 34 signaling questions of the PROBAST+AI framework.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"S0924933826122627_sec3\" sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The aggregate mean diagnostic accuracy across the literature was 93.38%, with deep learning architectures demonstrating superior metrics relative to classical machine learning (96.83% vs. 87.68%). Critically, external validation was restricted to 4.7% of the included studies. A pronounced performance discrepancy was observed between subject-wise (88.22%) and segment-wise (98.14%) validation protocols, indicating pervasive data leakage. Overall, 76.7% of the analyzed studies were characterized by a high risk of bias, predominantly stemming from suboptimal data partitioning and inadequate independent verification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"S0924933826122627_sec4\" sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Contemporary diagnostic accuracies appear to be artifactually elevated due to structural methodological deficiencies and data leakage. Consequently, current evidence does not support the immediate clinical implementation of AI-EEG biomarkers in schizophrenia. To facilitate translational progress, we propose a standardized methodological framework optimizing validation strategies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1192\/j.eurpsy.2026.12262","type":"journal-article","created":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T11:09:55Z","timestamp":1792062595000},"source":"Crossref","is-referenced-by-count":0,"title":["Artificial intelligence EEG biomarkers for schizophrenia diagnosis: Systematic review with PROBAST+AI assessment"],"prefix":"10.1192","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9598-9728","authenticated-orcid":false,"given":"Kacper","family":"\u0141o\u015b","sequence":"first","affiliation":[{"id":[{"id":"https:\/\/ror.org\/00y4ya841","id-type":"ROR","asserted-by":"publisher"}],"name":"Medical University of Bialystok: Uniwersytet Medyczny w Bia\u0142ymstoku"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7021-5133","authenticated-orcid":false,"given":"Napoleon","family":"Waszkiewicz","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/00y4ya841","id-type":"ROR","asserted-by":"publisher"}],"name":"Medical University of Bialystok: Uniwersytet Medyczny w Bia\u0142ymstoku"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"170","published-online":{"date-parts":[[2026,10,15]]},"reference":[{"key":"S0924933826122627_r53","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2020.112938"},{"key":"S0924933826122627_r37","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2019.07.006"},{"key":"S0924933826122627_r21","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106225"},{"key":"S0924933826122627_r23","doi-asserted-by":"publisher","DOI":"10.1177\/15500594251328068"},{"key":"S0924933826122627_r39","doi-asserted-by":"publisher","DOI":"10.1016\/j.pscychresns.2025.112103"},{"key":"S0924933826122627_r56","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.14039"},{"key":"S0924933826122627_r51","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2023.3237375"},{"key":"S0924933826122627_r5","doi-asserted-by":"publisher","DOI":"10.1007\/s11920-022-01399-0"},{"key":"S0924933826122627_r22","doi-asserted-by":"publisher","DOI":"10.1016\/j.schres.2023.09.010"},{"key":"S0924933826122627_r15","first-page":"43","article-title":"Machine learning techniques in diagnostics and prediction of the clinical features of schizophrenia: a narrative review","volume":"4","author":"Gashkarimov","year":"2023","journal-title":"Consort Psychiatr"},{"key":"S0924933826122627_r3","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2025.103129"},{"key":"S0924933826122627_r2","doi-asserted-by":"publisher","DOI":"10.1016\/j.schres.2013.05.028"},{"key":"S0924933826122627_r19","doi-asserted-by":"publisher","DOI":"10.1016\/j.pscychresns.2026.112138"},{"key":"S0924933826122627_r45","doi-asserted-by":"publisher","DOI":"10.1007\/s13246-021-01038-7"},{"key":"S0924933826122627_r14","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.220232"},{"key":"S0924933826122627_r55","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105570"},{"key":"S0924933826122627_r29","first-page":"44","article-title":"SchizoNET: a robust and accurate Margenau-Hill time-frequency distribution based deep neural network model for schizophrenia detection using EEG signals","author":"Khare","year":"2023","journal-title":"Physiol Meas"},{"key":"S0924933826122627_r33","doi-asserted-by":"publisher","DOI":"10.1007\/s13246-021-01083-2"},{"key":"S0924933826122627_r54","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0251842"},{"key":"S0924933826122627_r9","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics14232698"},{"key":"S0924933826122627_r17","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.n160"},{"key":"S0924933826122627_r30","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhaf184"},{"key":"S0924933826122627_r34","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-84497-8"},{"key":"S0924933826122627_r40","doi-asserted-by":"publisher","DOI":"10.1016\/j.pscychresns.2025.112047"},{"key":"S0924933826122627_r44","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2021.777977"},{"key":"S0924933826122627_r4","doi-asserted-by":"publisher","DOI":"10.17691\/stm2022.14.5.06"},{"key":"S0924933826122627_r46","doi-asserted-by":"publisher","DOI":"10.1016\/j.medengphy.2023.103949"},{"key":"S0924933826122627_r49","doi-asserted-by":"publisher","DOI":"10.1007\/s40846-022-00758-9"},{"key":"S0924933826122627_r48","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2024.1452197"},{"key":"S0924933826122627_r12","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2024.1347082"},{"key":"S0924933826122627_r52","doi-asserted-by":"publisher","DOI":"10.1007\/s10548-025-01102-5"},{"key":"S0924933826122627_r50","doi-asserted-by":"publisher","DOI":"10.1007\/s13534-024-00360-9"},{"key":"S0924933826122627_r25","doi-asserted-by":"publisher","DOI":"10.1016\/j.pscychresns.2024.111886"},{"key":"S0924933826122627_r7","volume-title":"BEST (biomarkers, EndpointS, and other tools) resource","year":"2016"},{"key":"S0924933826122627_r28","doi-asserted-by":"publisher","DOI":"10.4103\/psychiatry.IndianJPsychiatry_91_20"},{"key":"S0924933826122627_r24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2024.108105"},{"key":"S0924933826122627_r42","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.2170"},{"key":"S0924933826122627_r6","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.2240"},{"key":"S0924933826122627_r20","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065724500461"},{"key":"S0924933826122627_r16","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2024-082505"},{"key":"S0924933826122627_r31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2023.11.017"},{"key":"S0924933826122627_r32","doi-asserted-by":"publisher","DOI":"10.1093\/schbul\/sbae150"},{"key":"S0924933826122627_r43","doi-asserted-by":"publisher","DOI":"10.3390\/jcm9123934"},{"key":"S0924933826122627_r18","doi-asserted-by":"publisher","DOI":"10.1016\/j.schres.2024.07.015"},{"key":"S0924933826122627_r41","doi-asserted-by":"publisher","DOI":"10.3389\/fnsys.2021.652662"},{"key":"S0924933826122627_r59","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02892-8"},{"key":"S0924933826122627_r36","doi-asserted-by":"publisher","DOI":"10.1038\/s41386-023-01658-5"},{"key":"S0924933826122627_r1","doi-asserted-by":"publisher","DOI":"10.1186\/s12888-025-07273-6"},{"key":"S0924933826122627_r10","first-page":"75","article-title":"The role of quantitative electroencephalography in diagnostic workup of mental disorders","author":"Kopanska","year":"2024","journal-title":"J Physiol Pharmacol"},{"key":"S0924933826122627_r35","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajp.2023.103687"},{"key":"S0924933826122627_r38","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-06121-7"},{"key":"S0924933826122627_r11","doi-asserted-by":"publisher","DOI":"10.12701\/jyms.2024.00668"},{"key":"S0924933826122627_r13","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15040434"},{"key":"S0924933826122627_r57","first-page":"3223","article-title":"Classification of first-episode psychosis with EEG signals: ciSSA and machine learning approach","volume":"11","author":"Genge\u00e7 Benli","year":"2023","journal-title":"Biomedicine"},{"key":"S0924933826122627_r60","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378"},{"key":"S0924933826122627_r27","doi-asserted-by":"publisher","DOI":"10.1007\/s13246-023-01225-8"},{"key":"S0924933826122627_r8","doi-asserted-by":"publisher","DOI":"10.1177\/1535370217750088"},{"key":"S0924933826122627_r61","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-45355-3"},{"key":"S0924933826122627_r47","doi-asserted-by":"publisher","DOI":"10.3390\/s24206508"},{"key":"S0924933826122627_r58","doi-asserted-by":"crossref","first-page":"15154","DOI":"10.1038\/s41598-024-66110-0","article-title":"Power spectral density-based resting-state EEG classification of first-episode psychosis","volume":"14","author":"SMd","year":"2024","journal-title":"Sci Rep"},{"key":"S0924933826122627_r26","doi-asserted-by":"publisher","DOI":"10.3390\/jcm12134375"}],"container-title":["European Psychiatry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S0924933826122627","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T11:09:58Z","timestamp":1792062598000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S0924933826122627\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":61,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026]]}},"alternative-id":["S0924933826122627"],"URL":"https:\/\/doi.org\/10.1192\/j.eurpsy.2026.12262","relation":{},"ISSN":["0924-9338","1778-3585"],"issn-type":[{"value":"0924-9338","type":"print"},{"value":"1778-3585","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"article-number":"e101"}}