Identifying depression-related topics in smartphone-collected free-response speech recordings using an automatic speech recognition system and a deep learning topic model.
Por:
Zhang Y, Folarin AA, Dineley J, Conde P, de Angel V, Sun S, Ranjan Y, Rashid Z, Stewart C, Laiou P, Sankesara H, Qian L, Matcham F, White K, Oetzmann C, Lamers F, Siddi S, Simblett S, Schuller BW, Vairavan S, Wykes T, Haro JM, Penninx BWJH, Narayan VA, Hotopf M, Dobson RJB and Cummins N
Publicada:
15 jun 2024
Ahead of Print:
27 mar 2024
Resumen:
BACKGROUND: Prior research has associated spoken language use with depression, yet studies often involve small or non-clinical samples and face challenges in the manual transcription of speech. This paper aimed to automatically identify depression-related topics in speech recordings collected from clinical samples. METHODS: The data included 3919 English free-response speech recordings collected via smartphones from 265 participants with a depression history. We transcribed speech recordings via automatic speech recognition (Whisper tool, OpenAI) and identified principal topics from transcriptions using a deep learning topic model (BERTopic). To identify depression risk topics and understand the context, we compared participants' depression severity and behavioral (extracted from wearable devices) and linguistic (extracted from transcribed texts) characteristics across identified topics. RESULTS: From the 29 topics identified, we identified 6 risk topics for depression: 'No Expectations', 'Sleep', 'Mental Therapy', 'Haircut', 'Studying', and 'Coursework'. Participants mentioning depression risk topics exhibited higher sleep variability, later sleep onset, and fewer daily steps and used fewer words, more negative language, and fewer leisure-related words in their speech recordings. LIMITATIONS: Our findings were derived from a depressed cohort with a specific speech task, potentially limiting the generalizability to non-clinical populations or other speech tasks. Additionally, some topics had small sample sizes, necessitating further validation in larger datasets. CONCLUSION: This study demonstrates that specific speech topics can indicate depression severity. The employed data-driven workflow provides a practical approach for analyzing large-scale speech data collected from real-world settings.
Filiaciones:
Zhang Y:
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
Folarin AA:
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
University College London, London, UK
South London and Maudsley NHS Foundation Trust, London, UK
Health Data Research UK London, University College London, London, UK
Dineley J:
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
University of Augsburg, Augsburg, Germany
Conde P:
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
de Angel V:
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
Sun S:
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
Department of Computer Science, University of Sheffield, Sheffield, UK
Ranjan Y:
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
Rashid Z:
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
Stewart C:
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
Laiou P:
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
Sankesara H:
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
Qian L:
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
Matcham F:
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
School of Psychology, University of Sussex, Falmer, East Sussex, UK
White K:
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
Oetzmann C:
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
Lamers F:
Department of Psychiatry, Amsterdam Public Health Research Institute and Amsterdam Neuroscience, Amsterdam University Medical Centre, Vrije Universiteit and GGZ InGeest, Amsterdam, the Netherlands
Siddi S:
Parc Sanitari Sant Joan de Déu, Fundació Sant Joan de Déu, CIBERSAM, Universitat de Barcelona, Barcelona, Spain
Simblett S:
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
Schuller BW:
University of Augsburg, Augsburg, Germany
GLAM - Group on Language, Audio, & Music, Imperial College London, London, UK
Vairavan S:
Janssen Research and Development LLC, Titusville, NJ, USA
Wykes T:
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
South London and Maudsley NHS Foundation Trust, London, UK
Haro JM:
Parc Sanitari Sant Joan de Déu, Fundació Sant Joan de Déu, CIBERSAM, Universitat de Barcelona, Barcelona, Spain
Penninx BWJH:
Department of Psychiatry, Amsterdam Public Health Research Institute and Amsterdam Neuroscience, Amsterdam University Medical Centre, Vrije Universiteit and GGZ InGeest, Amsterdam, the Netherlands
Narayan VA:
Davos Alzheimer's Collaborative, Geneva, Switzerland
Hotopf M:
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
South London and Maudsley NHS Foundation Trust, London, UK
Dobson RJB:
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
University College London, London, UK
South London and Maudsley NHS Foundation Trust, London, UK
Health Data Research UK London, University College London, London, UK
Cummins N:
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
Green Submitted, hybrid
|