Comparison of Vocal Biomarkers for Depression and Anxiety to Formal Clinical Assessments

Prediction of a Structured Clinical Assessment by Patient Reported Outcomes and Machine Learning Algorithms: A Comparative Study

Participants will be recruited to complete self reported surveys normally used as standards of care for screening and monitoring depression and anxiety symptom severity, provide a voice sample composed of an answer to open ended questions and then be assessed by a mental health professional using structured and clinically validated assessment tools for depression and anxiety. Their voice will be analyzed by machine learning models that predict the severity of depression and anxiety symptoms. The models' performance will be compared to the clinician assessments and how that correlation compares to a similar comparison between the clinician assessments with the self reported surveys. It is hypothesized that the performance of the machine learning models in assessing the severity of depression and anxiety symptoms is no worse than the self reported surveys when both are compared to clinician assessments. It is also hypothesized that presence or absence of the diagnoses of Major Depressive Disorder and Generalized Anxiety Disorder can be predicted better than chance by the analysis of the participant's voice sample using machine learning models.

Study Overview

• Status: Enrolling by invitation
• Conditions: Depression/Anxiety

• Study Type: Observational
• Enrollment (Estimated): 540

Contacts and Locations

Study Locations

• United States
  • California
    • San Francisco, California, United States, 94104
      • Ellipsis Health

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

• Sampling Method: Non-Probability Sample

Study Population

~540 individuals aged 18 and above, of any gender, race, culture, ethnicity, sexual orientation or educational level residing anywhere in the United States.

Description

Inclusion Criteria:

• Native speaker or conversant in English
• Access to smartphone or computer with microphone
• Provision of esigned and dated informed consent form
• Willingness to adhere to the study protocol
• To participate in the subsequent clinical interview portion of this study in addition to the above inclusion criteria, a participant must provide an evaluable and qualified voice sample.

Exclusion Criteria:

• Speech impairments or other conditions that impact their ability to speak clearly
• Under the influence of recreational drugs or alcohol
• Ill or experiencing heavy allergies or temporary conditions affecting respiration, voice, or speaking.

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Primary Outcome A	Extent of categorical agreement, measured in weighted kappa, between Ellipsis Health Software as a Medical Device severity of depression and clinician's rating of severity of depression.	4 days
Primary Outcome B	Extent of categorical agreement, measured in weighted kappa, between Ellipsis Health Software as a Medical Device severity of anxiety and clinician's rating of severity of anxiety.	4 days

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Secondary Outcome A	Extent of agreement of presence, measured in the Equal Error Rate on the Receiver Operating Characteristic curve, between Ellipsis Health Software aa a Medical Device detection of Major Depressive Disorder and clinician's assessment for the diagnosis of Major Depressive Disorder, as expressed as Sensitivity and Specificity.	4 days
Secondary Outcome B	Extent of agreement of presence, measured in the Equal Error Rate on the Receiver Operating Characteristic curve, between Ellipsis Health Software as a Medical Device detection of Generalized Anxiety Disorder and clinician's assessment for the diagnosis of Generalized Anxiety Disorder, as expressed as Sensitivity and Specificity.	4 days

Collaborators and Investigators

• Sponsor: Ellipsis Health

Study record dates

Study Major Dates

• Study Start (Actual): January 12, 2024
• Primary Completion (Estimated): June 1, 2024
• Study Completion (Estimated): June 1, 2024

Study Registration Dates

• First Submitted: June 13, 2024
• First Submitted That Met QC Criteria: June 13, 2024
• First Posted (Actual): June 18, 2024

Study Record Updates

• Last Update Posted (Actual): June 18, 2024
• Last Update Submitted That Met QC Criteria: June 13, 2024
• Last Verified: May 1, 2024

More Information

Terms related to this study

• Keywords: Depression; Anxiety; Vocal biomarker; Structured clinical assessment
• Additional Relevant MeSH Terms: Behavioral Symptoms; Mental Disorders; Mood Disorders; Depression; Depressive Disorder; Anxiety Disorders
• Other Study ID Numbers: Pro00070013

Drug and device information, study documents

• Studies a U.S. FDA-regulated device product: No