Scholarlink

<p>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 <i>R</i><sup>2</sup> 0.34, and stacked generalization of multilingual-E5 with Qwen3-8B further improved performance (MAE 4.37, <i>R</i><sup>2</sup> 0.41). Audio embeddings added little incremental value. In an MDD-only analysis, multilingual-E5 was the top single modality (MAE 6.74, <i>R</i><sup>2</sup> 0.20). To aid interpretation, BERTopic uncovered six coherent themes; BDI scores were highest for “Distress &amp; care”, 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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Scalable depression monitoring with smartphone speech using a multimodal benchmark and topic analysis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月28日

查看全文
  • Daniel Emden,
  • Maike Richter,
  • Astrid Chevance,
  • Ramona Leenings,
  • Julian Herpertz,
  • Lara Gutfleisch,
  • Anna Fleuchaus,
  • Rogério Blitz,
  • Vincent L. Holstein,
  • Janik Goltermann,
  • Nils R. Winter,
  • Jennifer Spanagel,
  • Susanne Meinert,
  • Tiana Borgers,
  • Kira Flinkenflügel,
  • Frederike Stein,
  • Nina Alexander,
  • Hamidreza Jamalabadi,
  • Jonathan Repple,
  • Christian Dobel,
  • Elisabeth J. Leehr,
  • Ronny Redlich,
  • Ulrich W. Ebner-Priemer,
  • Igor Nenadić,
  • Tilo Kircher,
  • Udo Dannlowski,
  • Tim Hahn,
  • Nils Opel

摘要

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 R2 0.34, and stacked generalization of multilingual-E5 with Qwen3-8B further improved performance (MAE 4.37, R2 0.41). Audio embeddings added little incremental value. In an MDD-only analysis, multilingual-E5 was the top single modality (MAE 6.74, R2 0.20). To aid interpretation, BERTopic uncovered six coherent themes; BDI scores were highest for “Distress & care”, 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.