Discriminating between Patients with Unipolar disorder, Bipolar Disorder and Healthy Control Individuals based on Voice Features Collected from Naturalistic Smartphone Calls

Maria Faurholt‐Jepsen*, Darius Adam Rohani, Jonas Busk, Morten Lindberg Tønning, Maj Vinberg, Jakob Eyvind Bardram, Lars Vedel Kessing

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

73 Downloads (Pure)

Abstract

Background
It is of crucial importance to be able to discriminate unipolar disorder (UD) from bipolar disorder (BD), as treatments, as well as course of illness, differ between the two disorders. Aims: to investigate whether voice features from naturalistic phone calls could discriminate between 1) UD, BD, and healthy control individuals (HC); 2) different states within UD.

Methods
Voice features were collected daily during naturalistic phone calls for up to 972 days. A total of 48 patients with UD, 121 patients with BD, and 38 HC were included. A total of 115483 voice data entries were collected (UD (n= 16454), BD (n= 78733), and HC (n =20296)). Patients evaluated symptoms daily using a smartphone-based system, making it possible to define illness states within UD and BD. Data were analyzed using random forest algorithms.

Results
Compared to BD, UD was classified with a specificity of 0.84 (SD 0.07) /AUC of 0.58 (SD 0.07) and compared to HC with a sensitivity of 0.74 (SD 0.10)/ AUC=0.74 (SD 0.06). Compared to BD during euthymia, UD during euthymia was classified with a specificity of 0.79 (SD 0.05)/ AUC=0.43 (SD 0.16).

Compared to BD during depression, UD during depression was classified with a specificity of 0.81 (SD 0.09)/ AUC=0.48 (SD 0.12). Within UD, compared to euthymia, depression was classified with a specificity of 0.70 (SD 0.31)/ AUC=0.65 (SD 0.11). In all models the user-dependent models outperformed the user-independent models.

Conclusions
The results from the present study are promising, but as reflected by the low AUCs, does not support that voice features collected during naturalistic phone calls at the current state of art can be implemented in clinical practice as a supplementary and assisting tool. Further studies are needed.
Original languageEnglish
JournalActa Psychiatrica Scandinavica
Volume145
Issue number3
Pages (from-to)255-267
Number of pages13
ISSN0001-690X
DOIs
Publication statusPublished - 2022

Keywords

  • Voice analysis
  • Classification
  • Random Forest
  • Unipolar disorder
  • Bipolar Disorder
  • openSMILE

Fingerprint

Dive into the research topics of 'Discriminating between Patients with Unipolar disorder, Bipolar Disorder and Healthy Control Individuals based on Voice Features Collected from Naturalistic Smartphone Calls'. Together they form a unique fingerprint.

Cite this