{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T21:51:35Z","timestamp":1773784295743,"version":"3.50.1"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T00:00:00Z","timestamp":1772236800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"vor","delay-in-days":17,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Objective, scalable biomarkers are needed for continuous monitoring of major depressive disorder. Smartphone-collected speech is promising, yet clinically useful signals remain elusive. We analyzed 3151 weekly voice diaries from 284 German-speaking adults (128 MDD, 156 controls) to predict Beck Depression Inventory (BDI) scores. Sentence-embedding models outperformed lexical and acoustic baselines: Qwen3-8B achieved MAE 4.65 and\n                    <jats:italic>R<\/jats:italic>\n                    <jats:sup>2<\/jats:sup>\n                    0.34, and stacked generalization of multilingual-E5 with Qwen3-8B further improved performance (MAE 4.37,\n                    <jats:italic>R<\/jats:italic>\n                    <jats:sup>2<\/jats:sup>\n                    0.41). Audio embeddings added little incremental value. In an MDD-only analysis, multilingual-E5 was the top single modality (MAE 6.74,\n                    <jats:italic>R<\/jats:italic>\n                    <jats:sup>2<\/jats:sup>\n                    0.20). To aid interpretation, BERTopic uncovered six coherent themes; BDI scores were highest for \u201cDistress &amp; care\u201d, supporting clinical face validity. Together, LLM embeddings paired with lightweight topic analysis capture the dominant signal of depression severity in everyday speech and offer a scalable route to ecologically valid digital phenotyping.\n                  <\/jats:p>","DOI":"10.1038\/s41746-026-02486-9","type":"journal-article","created":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T05:47:42Z","timestamp":1772257662000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Scalable depression monitoring with smartphone speech using a multimodal benchmark and topic analysis"],"prefix":"10.1038","volume":"9","author":[{"given":"Daniel","family":"Emden","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maike","family":"Richter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Astrid","family":"Chevance","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ramona","family":"Leenings","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julian","family":"Herpertz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lara","family":"Gutfleisch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anna","family":"Fleuchaus","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rog\u00e9rio","family":"Blitz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincent L.","family":"Holstein","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Janik","family":"Goltermann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nils R.","family":"Winter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jennifer","family":"Spanagel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Susanne","family":"Meinert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiana","family":"Borgers","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kira","family":"Flinkenfl\u00fcgel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frederike","family":"Stein","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nina","family":"Alexander","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hamidreza","family":"Jamalabadi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan","family":"Repple","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Dobel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elisabeth J.","family":"Leehr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ronny","family":"Redlich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ulrich W.","family":"Ebner-Priemer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Igor","family":"Nenadi\u0107","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tilo","family":"Kircher","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Udo","family":"Dannlowski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tim","family":"Hahn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4749-3298","authenticated-orcid":false,"given":"Nils","family":"Opel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,28]]},"reference":[{"key":"2486_CR1","doi-asserted-by":"crossref","first-page":"8","DOI":"10.4088\/JCP.v62n0103","volume":"62","author":"N Sartorius","year":"2001","unstructured":"Sartorius, N. The economic and social burden of depression. J. Clin. Psychiatry 62, 8\u201311 (2001).","journal-title":"J. Clin. Psychiatry"},{"key":"2486_CR2","doi-asserted-by":"crossref","unstructured":"K\u00f6nig, H., K\u00f6nig, H.-H. & Konnopka, A. The excess costs of depression: a systematic review and meta-analysis. Epidemiology and Psychiatric Sciences29 (2020). Publisher: Cambridge University Press (CUP).","DOI":"10.1017\/S2045796019000180"},{"key":"2486_CR3","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1136\/ebmental-2020-300180","volume":"23","author":"J Melcher","year":"2020","unstructured":"Melcher, J., Hays, R. & Torous, J. Digital phenotyping for mental health of college students: a clinical review. Evid. Based Ment. Health 23, 161\u2013166 (2020).","journal-title":"Evid. Based Ment. Health"},{"key":"2486_CR4","doi-asserted-by":"publisher","first-page":"e46778","DOI":"10.2196\/46778","volume":"25","author":"P Bufano","year":"2023","unstructured":"Bufano, P., Laurino, M., Said, S., Tognetti, A. & Menicucci, D. Digital Phenotyping for Monitoring Mental Disorders: Systematic Review. J. Med. Internet Res. 25, e46778 (2023).","journal-title":"J. Med. Internet Res."},{"key":"2486_CR5","doi-asserted-by":"publisher","first-page":"e58572","DOI":"10.2196\/58572","volume":"26","author":"R Riad","year":"2024","unstructured":"Riad, R. et al. Automated Speech Analysis for Risk Detection of Depression, Anxiety, Insomnia, and Fatigue: Algorithm Development and Validation Study. J. Med. Internet Res. 26, e58572 (2024).","journal-title":"J. Med. Internet Res."},{"key":"2486_CR6","doi-asserted-by":"publisher","first-page":"5731","DOI":"10.1007\/s10462-022-10144-1","volume":"55","author":"M Wankhade","year":"2022","unstructured":"Wankhade, M., Rao, A. C. S. & Kulkarni, C. A survey on sentiment analysis methods, applications, and challenges. Artif. Intell. Rev. 55, 5731\u20135780 (2022).","journal-title":"Artif. Intell. Rev."},{"key":"2486_CR7","doi-asserted-by":"publisher","first-page":"106821","DOI":"10.1016\/j.bspc.2024.106821","volume":"99","author":"M Zhang","year":"2025","unstructured":"Zhang, M. et al. Augmented dialectal speech recognition for AI-based neuropsychological scale assessment in Alzheimer\u2019s disease. Biomed. Signal Process. Control 99, 106821 (2025).","journal-title":"Biomed. Signal Process. Control"},{"key":"2486_CR8","unstructured":"Radford, A. et al. Robust Speech Recognition via Large-Scale Weak Supervision (2022). arXiv:2212.04356 [eess]."},{"key":"2486_CR9","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North, 4171\u20134186 (Association for Computational Linguistics, Minneapolis, Minnesota, 2019).","DOI":"10.18653\/v1\/N19-1423"},{"key":"2486_CR10","doi-asserted-by":"crossref","unstructured":"Hossain, M. M., Hossain, M. S., Mridha, M. F., Safran, M. & Alfarhood, S. Multi task opinion enhanced hybrid BERT model for mental health analysis. Scientific Reports15 (2025).","DOI":"10.1038\/s41598-025-86124-6"},{"key":"2486_CR11","doi-asserted-by":"publisher","first-page":"28025","DOI":"10.1109\/ACCESS.2024.3366653","volume":"12","author":"A Pourkeyvan","year":"2024","unstructured":"Pourkeyvan, A., Safa, R. & Sorourkhah, A. Harnessing the Power of Hugging Face Transformers for Predicting Mental Health Disorders in Social Networks. IEEE Access 12, 28025\u201328035 (2024).","journal-title":"IEEE Access"},{"key":"2486_CR12","doi-asserted-by":"crossref","unstructured":"Williamson, J. R. et al. Vocal biomarkers of depression based on motor incoordination. In Proceedings of the 3rd ACM international workshop on Audio\/visual emotion challenge, 41\u201348 (ACM, Barcelona Spain, 2013).","DOI":"10.1145\/2512530.2512531"},{"key":"2486_CR13","doi-asserted-by":"publisher","first-page":"256.e1\u2013256.e6","DOI":"10.1016\/j.jvoice.2016.06.006","volume":"31","author":"NW Hashim","year":"2017","unstructured":"Hashim, N. W., Wilkes, M., Salomon, R., Meggs, J. & France, D. J. Evaluation of Voice Acoustics as Predictors of Clinical Depression Scores. J. Voice 31, 256.e1\u2013256.e6 (2017).","journal-title":"J. Voice"},{"key":"2486_CR14","doi-asserted-by":"crossref","unstructured":"Harati, A. et al. Speech-Based Depression Prediction Using Encoder-Weight-Only Transfer Learning and a Large Corpus. In ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 7273\u20137277 (2021).","DOI":"10.1109\/ICASSP39728.2021.9414208"},{"key":"2486_CR15","doi-asserted-by":"crossref","unstructured":"Fara, S., Goria, S., Molimpakis, E. & Cummins, N. Speech and the n-Back task as a lens into depression. How combining both may allow us to isolate different core symptoms of depression (2022).","DOI":"10.21437\/Interspeech.2022-10393"},{"key":"2486_CR16","doi-asserted-by":"crossref","unstructured":"Bey, R. et al. Natural language processing of multi-hospital electronic health records for public health surveillance of suicidality. npj Mental Health Research3 (2024).","DOI":"10.1038\/s44184-023-00046-7"},{"key":"2486_CR17","unstructured":"Grootendorst, M. BERTopic: Neural topic modeling with a class-based TF-IDF procedure (2022). arXiv:2203.05794 Version Number: 1."},{"key":"2486_CR18","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1093\/schbul\/sbaa126","volume":"47","author":"J Irving","year":"2021","unstructured":"Irving, J. et al. Using Natural Language Processing on Electronic Health Records to Enhance Detection and Prediction of Psychosis Risk. Schizophrenia Bull. 47, 405\u2013414 (2021).","journal-title":"Schizophrenia Bull."},{"key":"2486_CR19","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.specom.2015.03.004","volume":"71","author":"N Cummins","year":"2015","unstructured":"Cummins, N. et al. A review of depression and suicide risk assessment using speech analysis. Speech Commun. 71, 10\u201349 (2015).","journal-title":"Speech Commun."},{"key":"2486_CR20","unstructured":"Gratch, J. et al. The Distress Analysis Interview Corpus of human and computer interviews. In Proceedings of LREC 2014, 3123\u20133128 (European Language Resources Association (ELRA), Reykjavik, Iceland, 2014)."},{"key":"2486_CR21","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1002\/lio2.354","volume":"5","author":"DM Low","year":"2020","unstructured":"Low, D. M., Bentley, K. H. & Ghosh, S. S. Automated assessment of psychiatric disorders using speech: A systematic review. Laryngoscope Investigative Otolaryngol. 5, 96\u2013116 (2020).","journal-title":"Laryngoscope Investigative Otolaryngol."},{"key":"2486_CR22","doi-asserted-by":"publisher","first-page":"e16","DOI":"10.2196\/mental.5165","volume":"3","author":"J Torous","year":"2016","unstructured":"Torous, J., Kiang, M. V., Lorme, J. & Onnela, J.-P. New Tools for New Research in Psychiatry: A Scalable and Customizable Platform to Empower Data Driven Smartphone Research. JMIR Ment. Health 3, e16 (2016).","journal-title":"JMIR Ment. Health"},{"key":"2486_CR23","unstructured":"Simon, P. J. D., d\u2019Ascoli, S., Chemla, E., Lakretz, Y. & King, J.-R. A Polar coordinate system represents syntax in large language models https:\/\/openreview.net\/forum?id=x2780VcMOI (2024)."},{"key":"2486_CR24","doi-asserted-by":"crossref","unstructured":"Mikhailov, V., Serikov, O. & Artemova, E. Morph Call: Probing Morphosyntactic Content of Multilingual Transformers arXiv:2104.12847 (2021).","DOI":"10.18653\/v1\/2021.sigtyp-1.10"},{"key":"2486_CR25","doi-asserted-by":"crossref","unstructured":"Arps, D., Samih, Y., Kallmeyer, L. & Sajjad, H. Probing for Constituency Structure in Neural Language Models arXiv:2204.06201 (2022).","DOI":"10.18653\/v1\/2022.findings-emnlp.502"},{"key":"2486_CR26","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.jad.2024.03.106","volume":"355","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y. et al. Identifying depression-related topics in smartphone-collected free-response speech recordings using an automatic speech recognition system and a deep learning topic model. J. Affect. Disord. 355, 40\u201349 (2024).","journal-title":"J. Affect. Disord."},{"key":"2486_CR27","doi-asserted-by":"publisher","first-page":"103417","DOI":"10.1016\/j.ipm.2023.103417","volume":"60","author":"T Zhang","year":"2023","unstructured":"Zhang, T., Yang, K., Alhuzali, H., Liu, B. & Ananiadou, S. PHQ-aware depressive symptoms identification with similarity contrastive learning on social media. Inf. Process. Manag. 60, 103417 (2023).","journal-title":"Inf. Process. Manag."},{"key":"2486_CR28","doi-asserted-by":"publisher","first-page":"450","DOI":"10.1016\/j.neuroimage.2018.01.079","volume":"172","author":"C Vogelbacher","year":"2018","unstructured":"Vogelbacher, C. et al. The Marburg-M\u00fcnster Affective Disorders Cohort Study (MACS): A quality assurance protocol for MR neuroimaging data. NeuroImage 172, 450\u2013460 (2018).","journal-title":"NeuroImage"},{"key":"2486_CR29","doi-asserted-by":"publisher","first-page":"949","DOI":"10.1007\/s00406-018-0943-x","volume":"269","author":"T Kircher","year":"2019","unstructured":"Kircher, T. et al. Neurobiology of the major psychoses: a translational perspective on brain structure and function-the FOR2107 consortium. Eur. Arch. Psychiatry Clin. Neurosci. 269, 949\u2013962 (2019).","journal-title":"Eur. Arch. Psychiatry Clin. Neurosci."},{"key":"2486_CR30","unstructured":"First, M. B., Spitzer, R. L., Gibbon, M. & Williams, Janet B. W.Structured Clinical Interview for DSM-IV Axis I Disorders (SCID-I) (American Psychiatric Press, 1997)."},{"key":"2486_CR31","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1016\/j.jad.2021.07.030","volume":"294","author":"D Emden","year":"2021","unstructured":"Emden, D., Goltermann, J., Dannlowski, U., Hahn, T. & Opel, N. Technical feasibility and adherence of the Remote Monitoring Application in Psychiatry (ReMAP) for the assessment of affective symptoms. J. Affect. Disord. 294, 652\u2013660 (2021).","journal-title":"J. Affect. Disord."},{"key":"2486_CR32","doi-asserted-by":"publisher","first-page":"e24333","DOI":"10.2196\/24333","volume":"8","author":"J Goltermann","year":"2021","unstructured":"Goltermann, J. et al. Smartphone-Based Self-Reports of Depressive Symptoms Using the Remote Monitoring Application in Psychiatry (ReMAP): Interformat Validation Study. JMIR Ment. Health 8, e24333 (2021).","journal-title":"JMIR Ment. Health"},{"key":"2486_CR33","unstructured":"Zhang, Y. et al. Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models arXiv:2506.05176 (2025)."},{"key":"2486_CR34","unstructured":"Vera, H. S. et al. EmbeddingGemma: Powerful and Lightweight Text Representations arXiv:2509.20354 (2025)."},{"key":"2486_CR35","unstructured":"Wang, L. et al. Multilingual E5 Text Embeddings: A Technical Report arXiv:2402.05672 (2024)."},{"key":"2486_CR36","doi-asserted-by":"crossref","unstructured":"Reimers, N. & Gurevych, I. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 3980\u20133990 (Association for Computational Linguistics, Hong Kong, China, 2019).","DOI":"10.18653\/v1\/D19-1410"},{"key":"2486_CR37","doi-asserted-by":"crossref","unstructured":"Eyben, F., W\u00f6llmer, M. & Schuller, B. Opensmile: the munich versatile and fast open-source audio feature extractor. In Proceedings of the 18th ACM international conference on Multimedia, 1459\u20131462 (ACM, Firenze Italy, 2010).","DOI":"10.1145\/1873951.1874246"},{"key":"2486_CR38","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TAFFC.2015.2457417","volume":"7","author":"F Eyben","year":"2016","unstructured":"Eyben, F. et al. The Geneva Minimalistic Acoustic Parameter Set (GeMAPS) for Voice Research and Affective Computing. IEEE Trans. Affect. Comput. 7, 190\u2013202 (2016).","journal-title":"IEEE Trans. Affect. Comput."},{"key":"2486_CR39","doi-asserted-by":"crossref","unstructured":"Chen, S. et al. WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing arXiv:2110.13900 (2022).","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"2486_CR40","doi-asserted-by":"crossref","unstructured":"Hsu, W.-N. et al. HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units arXiv:2106.07447 (2021).","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"2486_CR41","unstructured":"Baevski, A., Zhou, H., Mohamed, A. & Auli, M. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations arXiv:2006.11477 (2020)."},{"key":"2486_CR42","unstructured":"Wagner, J. et al. Model for Dimensional Speech Emotion Recognition based on Wav2vec 2.0 (2022)."},{"key":"2486_CR43","doi-asserted-by":"crossref","unstructured":"Briganti, G. & Lechien, J. R. Speech and Voice Quality as Digital Biomarkers in Depression: A Systematic Review. Journal of Voice S0892199725001870 (2025).","DOI":"10.1016\/j.jvoice.2025.05.002"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02486-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02486-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02486-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:07:33Z","timestamp":1773770853000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02486-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,28]]},"references-count":43,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2486"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02486-9","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,28]]},"assertion":[{"value":"3 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"230"}}