Voice Biomarkers Predictive of Depression and Anxiety

NCT05455905 | Completed

• 1 other identifier: 2021/08/25
• Study Type: observational
• Target: 19,533
• Locations: 1 country
• Sites: 1

Brief Summary

The objective of this study is to collect data to improve the sensitivity and specificity of Kintsugi Voice's (formerly KiVATM) predictions on audio files. A web-based audio recording tool will be used to record voice sample and ask participants the PHQ-9 and GAD-7 questions. A voluntary subset of participants will then be assessed by mental health professionals with the Hamilton Depression Rating Scale (HAM-D) and Hamilton Anxiety Rating Scale (HAM-A) scores.

Conditions

Depression, Anxiety; Healthy; Mental Health Wellness 1

Keywords

mental health; depression; anxiety; Artificial Intelligence

Outcome Measures

Primary Outcomes (2)

• Hamilton Depression Rating Scale

  Participants will be interviewed by mental health professionals using the clinically validated Hamilton Depression Rating Scale, which has a score range of 0 to 54, where higher scores are associated with higher severity of depression.

  Through study completion, on average 12months

• Hamilton Anxiety Rating Scale

  Participants will be interviewed by mental health professionals using the clinically validated Hamilton Anxiety Rating Scale, which has a score range of 0 to 56, where higher scores are associated with higher severity anxiety.

  Through study completion, on average 12 months

Study Arms (2)

Main Study Cohort

A web-based audio recording tool will be used to record voice sample answering the prompt, "How are you feeling today?" Participants are asked to speak for 1-minute. Following the recording, participants are asked to complete the Patient Health Questionnaire-9 and Generalized Anxiety Disorder-7 questions.

Diagnostic Test: Patient Health Questionnaire-9; Diagnostic Test: Generalized Anxiety Disorder-7

Selected Self-Reported Depression Cohort

The Researcher will review Patient Health Questionnaire-9 scores of all the participants and select the subset that self-reported a scored greater than 20, on a scale from 0 to 27. Participants will be approached via email to complete an additional administration of the Patient Health Questionnaire-9 and Generalized Anxiety Disorder-7 questionnaires and be offered resources for depression and anxiety and how to set up an appointment with a mental health professional.

Diagnostic Test: Patient Health Questionnaire-9; Diagnostic Test: Generalized Anxiety Disorder-7; Diagnostic Test: Hamilton Depression Rating Scale; Diagnostic Test: Hamilton Anxiety Rating Scale

Interventions

Patient Health Questionnaire-9 DIAGNOSTIC_TEST

The Patient Health Questionnaire-9 is a nine question self-administered examination in which the patient indicates how often they have experienced different feelings and sensations in the past two weeks. The Patient Health Questionnaire-9 is scored from 0 to 27 where higher scores are associated with more severe depression.

Also known as: PHQ-9

Main Study Cohort; Selected Self-Reported Depression Cohort

Generalized Anxiety Disorder-7 DIAGNOSTIC_TEST

The Generalized Anxiety Disorder-7 is a seven question self-administered examination in which the patient indicates how often they have experienced different feelings and sensations in the past two weeks. The Generalized Anxiety Disorder-7 is scored from 0 to 21 where higher scores are associated with more severe anxiety.

Also known as: GAD-7

Main Study Cohort; Selected Self-Reported Depression Cohort

Hamilton Depression Rating Scale DIAGNOSTIC_TEST

The Hamilton Depression Rating Scale is administered by a mental health profession and includes twenty-one questions asking about how the participant has been feeling in the past week. The Hamilton Depression Rating Scale is scored from 0 to 45 where higher scores are associated with more severe depression.

Also known as: HDRS, HAM-D

Selected Self-Reported Depression Cohort

Hamilton Anxiety Rating Scale DIAGNOSTIC_TEST

The Hamilton Anxiety Rating Scale is administered by a mental health profession and includes fourteen questions asking about how the participant has been feeling in the past week. The Hamilton Anxiety Rating Scale is scored from 0 to 56 where higher scores are associated with more severe anxiety.

Also known as: HARS, HAM-A

Selected Self-Reported Depression Cohort

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population will include males and females fluent in English over the age of 18 in the United States and Canada. Participants both with and without a personal history of depression and/or anxiety are eligible to participate in the study. Participants will require access to a laptop, smartphone, or tablet with a functioning microphone and provide stated willingness to comply with all study procedures and availability for the duration of the study. Participants with a visual or motor impairment that would make it difficult to use the web-based survey will be excluded from the study.

You may qualify if:

• Adult males and or females over the age of 18 at the time of informed consent. Adults with a known history of depression and/or anxiety and adults without a known history of depression and/or anxiety will be included in this study.
• Access to a laptop, smart-phone or tablet with a functioning microphone
• Stated willingness to comply with all study procedures and availability for the duration of the study
• Fluency in English

You may not qualify if:

• Visual impairment that would make it difficult for the participant to see the web-based survey
• Motor impairment that would make it difficult for the participant to use the web-based survey

Sponsors & Collaborators

• Kintsugi Mindful Wellness, Inc.: lead

Study Sites (1)

Kintsugi Mindful Wellness, Inc.

Berkeley, California, 94705, United States

Location

Related Publications (21)

• Czeisler ME, Lane RI, Petrosky E, Wiley JF, Christensen A, Njai R, Weaver MD, Robbins R, Facer-Childs ER, Barger LK, Czeisler CA, Howard ME, Rajaratnam SMW. Mental Health, Substance Use, and Suicidal Ideation During the COVID-19 Pandemic - United States, June 24-30, 2020. MMWR Morb Mortal Wkly Rep. 2020 Aug 14;69(32):1049-1057. doi: 10.15585/mmwr.mm6932a1.

  PMID: 32790653 BACKGROUND

• ADAA. Facts & statistics: Anxiety and Depression Association of America. Retrieved March 05, 2021, from https://adaa.org/about-adaa/press-room/facts-statistics

  BACKGROUND

• Low DM, Bentley KH, Ghosh SS. Automated assessment of psychiatric disorders using speech: A systematic review. Laryngoscope Investig Otolaryngol. 2020 Jan 31;5(1):96-116. doi: 10.1002/lio2.354. eCollection 2020 Feb.

  PMID: 32128436 BACKGROUND

• Mundt JC, Vogel AP, Feltner DE, Lenderking WR. Vocal acoustic biomarkers of depression severity and treatment response. Biol Psychiatry. 2012 Oct 1;72(7):580-7. doi: 10.1016/j.biopsych.2012.03.015. Epub 2012 Apr 26.

  PMID: 22541039 BACKGROUND

• Zhang L, Duvvuri R, Chandra KKL, Nguyen T, Ghomi RH. Automated voice biomarkers for depression symptoms using an online cross-sectional data collection initiative. Depress Anxiety. 2020 Jul;37(7):657-669. doi: 10.1002/da.23020. Epub 2020 May 7.

  PMID: 32383335 BACKGROUND

• Espinola, CW, Gomes, JC, Pereira, JMS et. al. Detection of major depressive disorder using vocal acoustic analysis and machine learning-an exploratory study. Res. Biomed. Eng. 2021; 37: 53-64.

  BACKGROUND

• Wang J, Zhang L, Liu T, Pan W, Hu B, Zhu T. Acoustic differences between healthy and depressed people: a cross-situation study. BMC Psychiatry. 2019 Oct 15;19(1):300. doi: 10.1186/s12888-019-2300-7.

  PMID: 31615470 BACKGROUND

• He L, Cao C. Automated depression analysis using convolutional neural networks from speech. J Biomed Inform. 2018 Jul;83:103-111. doi: 10.1016/j.jbi.2018.05.007. Epub 2018 May 29.

  PMID: 29852317 BACKGROUND

• Ozkanca Y, Ozturk MG, Ekmekci MN, Atkins DC, Demiroglu C, Ghomi RH. Depression Screening from Voice Samples of Patients Affected by Parkinson's Disease. Digit Biomark. 2019 May-Aug;3(2):72-82. doi: 10.1159/000500354. Epub 2019 Jun 12.

  PMID: 31872172 BACKGROUND

• Yi H, Smiljanic R, Chandrasekaran B. The Effect of Talker and Listener Depressive Symptoms on Speech Intelligibility. J Speech Lang Hear Res. 2019 Nov 18;62(12):4269-4281. doi: 10.1044/2019_JSLHR-S-19-0112. Print 2019 Dec 18.

  PMID: 31738862 BACKGROUND

• Stassen HH, Bomben G, Gunther E. Speech characteristics in depression. Psychopathology. 1991;24(2):88-105. doi: 10.1159/000284700.

  PMID: 1886971 BACKGROUND

• Taguchi T, Tachikawa H, Nemoto K, Suzuki M, Nagano T, Tachibana R, Nishimura M, Arai T. Major depressive disorder discrimination using vocal acoustic features. J Affect Disord. 2018 Jan 1;225:214-220. doi: 10.1016/j.jad.2017.08.038. Epub 2017 Aug 16.

  PMID: 28841483 BACKGROUND

• Low LS, Maddage NC, Lech M, Sheeber LB, Allen NB. Detection of clinical depression in adolescents' speech during family interactions. IEEE Trans Biomed Eng. 2011 Mar;58(3):574-86. doi: 10.1109/TBME.2010.2091640. Epub 2010 Nov 11.

  PMID: 21075715 BACKGROUND

• Tuka A, Mohammad G, and James G. Detecting Depression with Audio/Text Sequence Modeling of Interviews. Interspeech. 2018; 2522.

  BACKGROUND

• Pan W, Flint J, Shenhav L, Liu T, Liu M, Hu B, Zhu T. Re-examining the robustness of voice features in predicting depression: Compared with baseline of confounders. PLoS One. 2019 Jun 20;14(6):e0218172. doi: 10.1371/journal.pone.0218172. eCollection 2019.

  PMID: 31220113 BACKGROUND

• Xu, M, Duan, LY, Cai, J, Chia, LT, Xu, C, & Tian, Q. HMM-based audio keyword generation. In Pacific-Rim Conference on Multimedia. 2004; November: 566-574. Springer, Berlin, Heidelberg.

  BACKGROUND

• Aizawa IK, Nakamura Y, Satoh S, et. al. Advances in Multimedia Information Processing - PCM 2004: 5th Pacific Rim Conference on Multimedia. Springer. ISBN 978-3-540-23985-7.

  BACKGROUND

• Crockford, D. (2001, April). Introducing JSON. JavaScript Object Notation. https://www.json.org/json-en.html

  BACKGROUND

• HAMILTON M. A rating scale for depression. J Neurol Neurosurg Psychiatry. 1960 Feb;23(1):56-62. doi: 10.1136/jnnp.23.1.56. No abstract available.

  PMID: 14399272 BACKGROUND

• Trajkovic G, Starcevic V, Latas M, Lestarevic M, Ille T, Bukumiric Z, Marinkovic J. Reliability of the Hamilton Rating Scale for Depression: a meta-analysis over a period of 49 years. Psychiatry Res. 2011 Aug 30;189(1):1-9. doi: 10.1016/j.psychres.2010.12.007. Epub 2011 Jan 26.

  PMID: 21276619 BACKGROUND

• HAMILTON M. The assessment of anxiety states by rating. Br J Med Psychol. 1959;32(1):50-5. doi: 10.1111/j.2044-8341.1959.tb00467.x. No abstract available.

  PMID: 13638508 BACKGROUND

MeSH Terms

Conditions

Depression; Anxiety Disorders; Psychological Well-Being

Condition Hierarchy (Ancestors)

Behavioral Symptoms; Behavior; Mental Disorders; Personal Satisfaction

Study Officials

• Mei-Hsin Cheng, PhD

  Kintsugi Mindful Wellness, Inc.

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: CROSS SECTIONAL
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: June 29, 2022
• First Posted: July 13, 2022
• Study Start: September 14, 2021
• Primary Completion: September 11, 2022
• Study Completion: September 11, 2022
• Last Updated: September 15, 2022

Record last verified: 2022-09

Data Sharing

• IPD Sharing: Will not share

Locations

US (1)