001043715 001__ 1043715
001043715 005__ 20250804115152.0
001043715 0247_ $$2doi$$a10.1038/s41598-025-08639-2
001043715 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-03001
001043715 0247_ $$2pmid$$a40615574
001043715 0247_ $$2WOS$$aWOS:001523063600012
001043715 037__ $$aFZJ-2025-03001
001043715 082__ $$a600
001043715 1001_ $$0P:(DE-HGF)0$$aKrautz, Agnieszka Ewa$$b0$$eCorresponding author
001043715 245__ $$aPrediction of suicide using web based voice recordings analyzed by artificial intelligence
001043715 260__ $$a[London]$$bSpringer Nature$$c2025
001043715 3367_ $$2DRIVER$$aarticle
001043715 3367_ $$2DataCite$$aOutput Types/Journal article
001043715 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1752732871_23245
001043715 3367_ $$2BibTeX$$aARTICLE
001043715 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001043715 3367_ $$00$$2EndNote$$aJournal Article
001043715 520__ $$aThe integration of machine learning (ML) and deep learning models in suicide risk assessment has advanced significantly in recent years. In this study, we utilized ML in a case-control design, we predicted completed suicides using publicly available, web-based, real-world voice data, and treating speech as a biomarker. Our model demonstrated high accuracy in distinguishing between individuals who died by suicide and carefully matched controls achieving an area under the curve (AUC) of 0.74. This improved to an AUC of 0.85 and an accuracy of 76% when analyzing the subset of individuals who died by suicide within 12 months of the audio recording. The best predictive performance was observed with the Multilayer perceptron model, particularly when using the all Bene, Q + U Bene, and Q + U Raw feature sets—highlighting the importance of combining structured and unstructured paralinguistic features. The findings highlight the critical temporal proximity of voice biomarkers to suicide risk. The model’s robustness is further evidenced by its resilience to perturbations in the analytical pipeline. This is the first study to successfully predict actual suicidal behavior rather than surrogate markers, marking a major step forward in suicide prevention. By demonstrating that speech can serve as a non-invasive and objective biomarker for suicide risk, this research opens new avenues for diagnostic and prognostic applications.
001043715 536__ $$0G:(DE-HGF)POF4-5254$$a5254 - Neuroscientific Data Analytics and AI (POF4-525)$$cPOF4-525$$fPOF IV$$x0
001043715 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001043715 7001_ $$0P:(DE-HGF)0$$aVolkening, Julia$$b1
001043715 7001_ $$0P:(DE-HGF)0$$aRaue, Janik$$b2
001043715 7001_ $$0P:(DE-HGF)0$$aOtte, Christian$$b3
001043715 7001_ $$0P:(DE-Juel1)131678$$aEickhoff, Simon B.$$b4$$ufzj
001043715 7001_ $$0P:(DE-HGF)0$$aAhlers, Eike$$b5
001043715 7001_ $$0P:(DE-HGF)0$$aLangner, Jörg$$b6
001043715 773__ $$0PERI:(DE-600)2615211-3$$a10.1038/s41598-025-08639-2$$gVol. 15, no. 1, p. 23855$$n1$$p23855$$tScientific reports$$v15$$x2045-2322$$y2025
001043715 8564_ $$uhttps://juser.fz-juelich.de/record/1043715/files/s41598-025-08639-2.pdf$$yOpenAccess
001043715 909CO $$ooai:juser.fz-juelich.de:1043715$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
001043715 9101_ $$0I:(DE-HGF)0$$6P:(DE-HGF)0$$aagnieszka.krautz@peakprofiling.com $$b0
001043715 9101_ $$0I:(DE-HGF)0$$6P:(DE-HGF)0$$a PeakProfiling GmbH, Eschenallee 36, 14050, Berlin, Germany$$b0
001043715 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131678$$aForschungszentrum Jülich$$b4$$kFZJ
001043715 9101_ $$0I:(DE-HGF)0$$6P:(DE-Juel1)131678$$a HHU Düsseldorf$$b4
001043715 9131_ $$0G:(DE-HGF)POF4-525$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5254$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vDecoding Brain Organization and Dysfunction$$x0
001043715 9141_ $$y2025
001043715 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2024-12-18
001043715 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2024-12-18
001043715 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2024-12-18
001043715 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2024-12-18
001043715 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2024-12-18
001043715 915__ $$0StatID:(DE-HGF)1040$$2StatID$$aDBCoverage$$bZoological Record$$d2024-12-18
001043715 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bSCI REP-UK : 2022$$d2024-12-18
001043715 915__ $$0LIC:(DE-HGF)CCBYNCND4$$2HGFVOC$$aCreative Commons Attribution-NonCommercial-NoDerivs CC BY-NC-ND 4.0
001043715 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2024-07-29T15:28:26Z
001043715 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2024-07-29T15:28:26Z
001043715 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2024-12-18
001043715 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2024-12-18
001043715 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2024-12-18
001043715 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2024-12-18
001043715 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001043715 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2024-12-18
001043715 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2024-12-18
001043715 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2024-12-18
001043715 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2024-12-18
001043715 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2024-12-18
001043715 920__ $$lno
001043715 9201_ $$0I:(DE-Juel1)INM-7-20090406$$kINM-7$$lGehirn & Verhalten$$x0
001043715 980__ $$ajournal
001043715 980__ $$aVDB
001043715 980__ $$aUNRESTRICTED
001043715 980__ $$aI:(DE-Juel1)INM-7-20090406
001043715 9801_ $$aFullTexts