Back

Scalable, non-invasive depression monitoring with smartphone speech: a multimodal benchmark and topic analysis

Emden, D.; Gutfleisch, L.; Herpertz, J.; Leenings, R.; Blitz, R.; Holstein, V. L.; Goltermann, J.; Richter, M.; Chevance, A.; Fleuchaus, A.; Winter, N. R.; Spanagel, J.; Meinert, S.; Borgers, T.; Flinkenflugel, K.; Stein, F.; Alexander, N.; Jamalabadi, H.; Leehr, E. J.; Redlich, R.; Ebner-Priemer, U.; Nenadic, I.; Kircher, T.; Dannlowski, U.; Hahn, T.; Opel, N.

2025-07-18 psychiatry and clinical psychology
10.1101/2025.07.17.25331744 medRxiv
Show abstract

Objective, scalable biomarkers are needed for continuous monitoring of major depressive disorder (MDD). Smartphone-collected speech is promising, yet extracting clinically useful signals remains difficult. We analysed 3 151 weekly voice diaries from 284 German-speaking adults (128 MDD, 156 controls) and regressed Beck Depression Inventory (BDI) scores. Sentence embeddings from the open-source 8-billion-parameter Qwen3-8B model predicted scores with MAE = 4.45 and R2 = 0.35, explaining 16 more points of variance than the best traditional feature set (TF-IDF). Adding lexical-prosodic or TF-IDF features provided only marginal improvement (best MAE = 4.39). To interpret the embeddings we applied BERTopic and uncovered ten coherent themes; BDI scores peaked for "Persistent Low Mood" and "Pain Distress", confirming clinical relevance. Large-language-model embeddings therefore capture the dominant signal of depression severity in everyday speech and, paired with interpretable topic analysis, offer a privacy-preserving, scalable route to digital mental-health phenotyping.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.