Automated Speech Analysis in Bipolar Disorder: The CALIBER Study Protocol and Preliminary Results.
Gerard Anmella, Michele De Prisco, Jeremiah B Joyce, Claudia Valenzuela-Pascual, Ariadna Mas-Musons, Vincenzo Oliva, Giovanna Fico, George Chatzisofroniou, Sanjeev Mishra, Majd Al-Soleiti, Filippo Corponi, Anna Giménez-Palomo, Laura Montejo, Meritxell González-Campos, Dina Popovic, Isabella Pacchiarotti, Marc Valentí, Myriam Cavero, Lluc Colomer, Iria Grande, Antoni Benabarre, Cristian-Daniel Llach, Joaquim Raduà, Melvin McInnis, Diego Hidalgo-Mazzei, Mark A Frye, Andrea Murru, Eduard Vieta
Author Information
Gerard Anmella: Department of Psychiatry and Psychology, Institute of Neuroscience, Hospital Clinic of Barcelona, 08036 Barcelona, Catalonia, Spain. ORCID
Michele De Prisco: Department of Psychiatry and Psychology, Institute of Neuroscience, Hospital Clinic of Barcelona, 08036 Barcelona, Catalonia, Spain. ORCID
Jeremiah B Joyce: School of Graduate Medical Education, Mayo Clinic, Rochester, MN 55902, USA. ORCID
Claudia Valenzuela-Pascual: Department of Psychiatry and Psychology, Institute of Neuroscience, Hospital Clinic of Barcelona, 08036 Barcelona, Catalonia, Spain. ORCID
Ariadna Mas-Musons: Department of Psychiatry and Psychology, Institute of Neuroscience, Hospital Clinic of Barcelona, 08036 Barcelona, Catalonia, Spain.
Vincenzo Oliva: Department of Psychiatry and Psychology, Institute of Neuroscience, Hospital Clinic of Barcelona, 08036 Barcelona, Catalonia, Spain. ORCID
Giovanna Fico: Department of Psychiatry and Psychology, Institute of Neuroscience, Hospital Clinic of Barcelona, 08036 Barcelona, Catalonia, Spain.
George Chatzisofroniou: Office of Information Security, Mayo Clinic, Rochester, MN 55905, USA.
Sanjeev Mishra: Alix School of Medicine, Mayo Clinic, Rochester, MN 55905, USA. ORCID
Majd Al-Soleiti: School of Graduate Medical Education, Mayo Clinic, Rochester, MN 55902, USA.
Filippo Corponi: School of Informatics, University of Edinburgh, Edinburgh EH16 4TJ, UK.
Anna Giménez-Palomo: Department of Psychiatry and Psychology, Institute of Neuroscience, Hospital Clinic of Barcelona, 08036 Barcelona, Catalonia, Spain. ORCID
Laura Montejo: Department of Psychiatry and Psychology, Institute of Neuroscience, Hospital Clinic of Barcelona, 08036 Barcelona, Catalonia, Spain.
Meritxell González-Campos: Department of Psychiatry and Psychology, Institute of Neuroscience, Hospital Clinic of Barcelona, 08036 Barcelona, Catalonia, Spain. ORCID
Dina Popovic: Department of Psychiatry and Psychology, Institute of Neuroscience, Hospital Clinic of Barcelona, 08036 Barcelona, Catalonia, Spain.
Isabella Pacchiarotti: Department of Psychiatry and Psychology, Institute of Neuroscience, Hospital Clinic of Barcelona, 08036 Barcelona, Catalonia, Spain.
Marc Valentí: Department of Psychiatry and Psychology, Institute of Neuroscience, Hospital Clinic of Barcelona, 08036 Barcelona, Catalonia, Spain.
Myriam Cavero: Department of Psychiatry and Psychology, Institute of Neuroscience, Hospital Clinic of Barcelona, 08036 Barcelona, Catalonia, Spain. ORCID
Lluc Colomer: Department of Psychiatry and Psychology, Institute of Neuroscience, Hospital Clinic of Barcelona, 08036 Barcelona, Catalonia, Spain. ORCID
Iria Grande: Department of Psychiatry and Psychology, Institute of Neuroscience, Hospital Clinic of Barcelona, 08036 Barcelona, Catalonia, Spain.
Antoni Benabarre: Department of Psychiatry and Psychology, Institute of Neuroscience, Hospital Clinic of Barcelona, 08036 Barcelona, Catalonia, Spain.
Cristian-Daniel Llach: Mood Disorders Psychopharmacology Unit, University Health Network, Toronto, ON M5G 1M9, Canada. ORCID
Joaquim Raduà: Biomedical Research Networking Centre Consortium on Mental Health (CIBERSAM), Instituto de Salud Carlos III, 28029 Madrid, Madrid, Spain.
Melvin McInnis: Department of Psychiatry, University of Michigan, Ann Arbor, MI 48109, USA.
Diego Hidalgo-Mazzei: Department of Psychiatry and Psychology, Institute of Neuroscience, Hospital Clinic of Barcelona, 08036 Barcelona, Catalonia, Spain.
Mark A Frye: Department of Psychiatry and Psychology, Mayo Clinic, Rochester, MN 55905, USA.
Andrea Murru: Department of Psychiatry and Psychology, Institute of Neuroscience, Hospital Clinic of Barcelona, 08036 Barcelona, Catalonia, Spain.
Eduard Vieta: Department of Psychiatry and Psychology, Institute of Neuroscience, Hospital Clinic of Barcelona, 08036 Barcelona, Catalonia, Spain. ORCID
: Bipolar disorder (BD) involves significant mood and energy shifts reflected in speech patterns. Detecting these patterns is crucial for diagnosis and monitoring, currently assessed subjectively. Advances in natural language processing offer opportunities to objectively analyze them. : To (i) correlate speech features with manic-depressive symptom severity in BD, (ii) develop predictive models for diagnostic and treatment outcomes, and (iii) determine the most relevant speech features and tasks for these analyses. : This naturalistic, observational study involved longitudinal audio recordings of BD patients at euthymia, during acute manic/depressive phases, and after-response. Patients participated in clinical evaluations, cognitive tasks, standard text readings, and storytelling. After automatic diarization and transcription, speech features, including acoustics, content, formal aspects, and emotionality, will be extracted. Statistical analyses will (i) correlate speech features with clinical scales, (ii) use lasso logistic regression to develop predictive models, and (iii) identify relevant speech features. : Audio recordings from 76 patients (24 manic, 21 depressed, 31 euthymic) were collected. The mean age was 46.0 ± 14.4 years, with 63.2% female. The mean YMRS score for manic patients was 22.9 ± 7.1, reducing to 5.3 ± 5.3 post-response. Depressed patients had a mean HDRS-17 score of 17.1 ± 4.4, decreasing to 3.3 ± 2.8 post-response. Euthymic patients had mean YMRS and HDRS-17 scores of 0.97 ± 1.4 and 3.9 ± 2.9, respectively. Following data pre-processing, including noise reduction and feature extraction, comprehensive statistical analyses will be conducted to explore correlations and develop predictive models. : Automated speech analysis in BD could provide objective markers for psychopathological alterations, improving diagnosis, monitoring, and response prediction. This technology could identify subtle alterations, signaling early signs of relapse. Establishing standardized protocols is crucial for creating a global speech cohort, fostering collaboration, and advancing BD understanding.
