A prospective, single arm, non-randomized, pilot clinical validation study to evaluate the ability of the Kintsugi Voice Device (the Device) to aid clinical assessment for depression by comparing its output with a diagnosis made by a clinician using the Structured Clinical Interview for DSM-5 (SCID-5-CT) for up to 500 English speaking adult patients ages 22 and older living in the United States. Recruitment will occur for 1 year and participation will be for up to 2 weeks.
Depression affects approximately 30% of people every year in the United States. Detecting mental health conditions early can help patients get the help they need sooner. Machine Learning Devices may be one way to help clinicians identify patients with mental health conditions. Clinicians may then be able to help patients receive the right level of care earlier. Many researchers are working to increase mental health screening. Machine Learning can detect subtle patterns like changes in the voice when someone is experiencing mental health conditions. Changes in the voice associated with a mental health condition are voice biomarkers. The purpose of this study is to find correlations between voice and how people sound with clinical diagnoses. Kintsugi Mindful Wellness, Inc. has developed a tool, the Kintsugi Voice Device, that assesses mental health and conditions like depression by studying the voice. The study's goal is to test the ability of the Device to identify depressive symptoms. Up to 500 people will take part in this research. Subject recruitment is expected to take up to 1 year. Completion of the study activities may take about 2 hours but subjects may stay enrolled for up to 2 weeks based on clinician availability for scheduling the Structured Clinical Interview for DSM-5 (SCID) interview. Study participants will: * Answer brief self-reported eligibility confirmation questionnaires. These answers help the researchers understand participant health history. * Schedule a teleconference with a licensed Clinical Psychologist to evaluate their mental health over Zoom. The Clinical Psychologist will guide participants through the Structured Clinical Interview for DSM-5 Clinical Trials Version (SCID-5-CT). The Clinical Psychologist will be licensed in the participant's state of residence. This assessment will be video and audio recorded for quality assurance purposes. If participants do not agree to being videotaped and/or audio recorded, they will be unable to join the study. The SCID-5-CT assessment is for research purposes only and is not intended for treatment purposes. The results of the SCID will not be shared with participants. On the day of the teleconference with a licensed Clinical Psychologist participants will: * Complete three brief self-assessment surveys asking about their electronic device, mental health and quality of life: the Patient Health Questionnaire-9 (PHQ-), Generalized Anxiety Disorder-7 (GAD-7), and the World Health Organization Quality of Life (WHOQOL). These assessments will take approximately 15 minutes in total. * Participants will provide an audio recording in response to 3 prompts of their choosing. The audio recording will be inputted to the Kintsugi Voice Device to receive a prediction of current signs of depression. The Kintsugi Voice Device Prediction is for research purposes only and will not be shared with participants. * Complete the SCID-5-CT while being videotaped and audio recorded with a licensed psychologist or psychiatrist and participant responses will be recorded. The SCID will allow the clinician to assess participants' current mental status. This study is intended for research purposes and is not intended for treatment and/or diagnostic purposes. The risks to this study are minimal and/or temporary and short lived. The study team has implemented procedures to minimize them wherever possible. There is always the potential for breach of confidentiality. To minimize this risk, all entries are encrypted. Researchers de-identify personal information using IDs. Researchers will store all data in a secure, password protected database and Google Cloud Platform bucket. Participation may bring up emotional content which could temporarily impact mood. To minimize this risk, everyone will be emailed a list of mental health resources. There is no cost to subjects for participation. There may be no direct benefit from participation. Indirect benefits may include reduction in stress, learning more about mental health. Knowledge gained from the study could potentially benefit patients in the future. Only personal and health information directly related to the research is collected, for safety purposes, or as required to provide participants with payment, including: * Name * Age * Address * Phone Number * Email Address * Demographic information (e.g. race, gender, and ethnicity) * English Proficiency * Emergency Contact Information * Audio recording of the SCID-5-CT * Video recording of the SCID-5CT * Audio recordings in response to prompts * Brief Medical History and Medications * Results of the SCID-5-CT * Device Information * PHQ-9 Responses * GAD-7 Responses * Behavioral and Quality of Life Survey Responses Identifiable data will be kept for 7 years. De-identified data will be kept indefinitely.
The Kintsugi Voice Device is intended to be used to screen for the presence of voice signals consistent with a current moderate to severe depressive episode in patients aged 22 and older. The device is intended to be used by care providers licensed to screen for depression and in settings where the screening for depression occurs. The device is neither to be used in lieu of a complete patient evaluation nor to supplant any of the clinician's standard assessments for the screening or diagnosis of depression. The Kintsugi Voice Device is comprised of a software API and machine learning model that utilizes recorded voice samples as inputs and outputs the detection of signals consistent with current moderate to severe depressive episode as outputs.
Kintsugi Mindful Wellness Inc.
Berkeley, California, United States
Sensitivity and Specificity of Kintsugi Voice Device Relative to the SCID-5
Determine the performance of the KV Device in discriminating the presence of a current significant depressive episode using the SCID-5-CT diagnosis of current MDD and/or MDE using sensitivity and specificity.
Time frame: Day 1
PPV, NPV, AUC, F-Score of Kintsugi Voice Device Relative to the SCID-5
Determine the performance of the KV Device in discriminating the presence of a current significant depressive episode using the SCID-5-CT diagnosis of current MDD and/or MDE using positive predictive value, negative predictive value, area under the curve, and F-score.
Time frame: Day 1
Sensitivity, Specificity, PPV, NPV, AUC, F-Score of Kintsugi Voice Device Relative to the Severity of the SCID-5-CT
Determine the performance of the KV Device in discriminating the severity of a current significant depressive episode using the SCID-5-CT severity assessment for those with a diagnosis of current MDD and/or MDE
Time frame: Day 1
Sensitivity, Specificity, PPV, NPV, AUC, F-Score of Kintsugi Voice Device Relative to the PHQ-9
Determine the performance of the Device in discriminating the presence of a current significant depressive symptoms compared to the PHQ-9
Time frame: Day 1
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.
Study Type
OBSERVATIONAL
Enrollment
500