Prediction of suicide using web based voice recordings analyzed by artificial intelligence
Abstract The 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 tr...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-08639-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849334819575562240 |
|---|---|
| author | Agnieszka Ewa Krautz Julia Volkening Janik Raue Christian Otte Simon B. Eickhoff Eike Ahlers Jörg Langner |
| author_facet | Agnieszka Ewa Krautz Julia Volkening Janik Raue Christian Otte Simon B. Eickhoff Eike Ahlers Jörg Langner |
| author_sort | Agnieszka Ewa Krautz |
| collection | DOAJ |
| description | Abstract The 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. |
| format | Article |
| id | doaj-art-eac7a319f2124fe787ad0778f273ab04 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-eac7a319f2124fe787ad0778f273ab042025-08-20T03:45:28ZengNature PortfolioScientific Reports2045-23222025-07-0115111010.1038/s41598-025-08639-2Prediction of suicide using web based voice recordings analyzed by artificial intelligenceAgnieszka Ewa Krautz0Julia Volkening1Janik Raue2Christian Otte3Simon B. Eickhoff4Eike Ahlers5Jörg Langner6PeakProfiling GmbHPeakProfiling GmbHPeakProfiling GmbHDepartment of Psychiatry and Psychotherapy, Charité – University Hospital Berlin, Corporate Member of Free University of Berlin, Humboldt University of Berlin and Berlin Institute of Health, Campus Benjamin FranklinResearch Centre Jülich, Institute of Neuroscience and Medicine, Brain & Behaviour (INM-7)Department of Psychiatry and Psychotherapy, Charité – University Hospital Berlin, Corporate Member of Free University of Berlin, Humboldt University of Berlin and Berlin Institute of Health, Campus Benjamin FranklinPeakProfiling GmbHAbstract The 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.https://doi.org/10.1038/s41598-025-08639-2SuicideVoice biomarkerArtificial intelligenceMachine learningMental health diagnostics |
| spellingShingle | Agnieszka Ewa Krautz Julia Volkening Janik Raue Christian Otte Simon B. Eickhoff Eike Ahlers Jörg Langner Prediction of suicide using web based voice recordings analyzed by artificial intelligence Scientific Reports Suicide Voice biomarker Artificial intelligence Machine learning Mental health diagnostics |
| title | Prediction of suicide using web based voice recordings analyzed by artificial intelligence |
| title_full | Prediction of suicide using web based voice recordings analyzed by artificial intelligence |
| title_fullStr | Prediction of suicide using web based voice recordings analyzed by artificial intelligence |
| title_full_unstemmed | Prediction of suicide using web based voice recordings analyzed by artificial intelligence |
| title_short | Prediction of suicide using web based voice recordings analyzed by artificial intelligence |
| title_sort | prediction of suicide using web based voice recordings analyzed by artificial intelligence |
| topic | Suicide Voice biomarker Artificial intelligence Machine learning Mental health diagnostics |
| url | https://doi.org/10.1038/s41598-025-08639-2 |
| work_keys_str_mv | AT agnieszkaewakrautz predictionofsuicideusingwebbasedvoicerecordingsanalyzedbyartificialintelligence AT juliavolkening predictionofsuicideusingwebbasedvoicerecordingsanalyzedbyartificialintelligence AT janikraue predictionofsuicideusingwebbasedvoicerecordingsanalyzedbyartificialintelligence AT christianotte predictionofsuicideusingwebbasedvoicerecordingsanalyzedbyartificialintelligence AT simonbeickhoff predictionofsuicideusingwebbasedvoicerecordingsanalyzedbyartificialintelligence AT eikeahlers predictionofsuicideusingwebbasedvoicerecordingsanalyzedbyartificialintelligence AT jorglangner predictionofsuicideusingwebbasedvoicerecordingsanalyzedbyartificialintelligence |