Content-free Speech Analysis for Measurement of Mental Health

NCT03700008 | Completed

• 1 other identifier: TONN_2018_01
• Study Type: interventional
• Target: 210
• Locations: 1 country
• Sites: 1

Brief Summary

Trial to prove the functionality and efficacy of a content-free speech analysis tool to detect problematic mental health status or phases of patients with pre known or unknown mental health disorders, focussed on affective disorders or neurodevelopmental disorders. The participants talk in free speech to the tool, this will be analyzed content-free and compared with psychological instruments to detect the mental status in conventional way.

Conditions

Mental Disorder; Conditions Influencing Health Status

Keywords

Mental Disorder; Treatment planning; Technical measurements of mental state; Course-prediction of Mental Illness

Outcome Measures

Primary Outcomes (1)

• Global scores of Symptom-Checklist 90 (SCL-90)

  The SCL-90 evaluates the psychological distress during the past seven days using nine scales for primary symptom dimensions and three scores among global distress indices. The basic psychological distress is determined by the GSI (Global Severity Index), the intensity of the responses by the PSDI (Positive Symptom Distress Index) and by the PST (Positive Symptom Total). The global scales provide an overview of the severity of the psychological distress. The scores ranged from 0.0 to 2.9 (GSI), 0-90 (PSI) and 0.0-2.9 (PSDI), all were calculated in T-values, so no cut-off but reliable T-values are published.

  score at the date of start of participation (day 1)

Secondary Outcomes (6)

• Global score of depression measured with the "Patients-Health-Questionnaire 9" (PHQ9)

  score at the date of start of participation (day 1)

• Global score of anxiety, measured with the "Generalized Anxiety Disorder 7" GAD-7

  score at the date of start of participation (day 1)

• Personality disorders and states, measured with the Big five personality test (B5T)

  score at the date of start of participation (day 1)

• Visuel analogue scale Attention-Deficit-Hyperactivity-Disorder (ADHD-VAS)

  score at the date of start of participation ("day 1")

• Changes of global scores of Symptom-Checklist 90 (SCL-90)

  scores an average 5 weeks after day 1 and changes compared to scores at day 1

Study Arms (2)

Participants with mental illness

OTHER

Participant with pre known or actually diagnosed mental disorder, especially affective or neurodevelopmental disorder. Using the speech analysis tool with 120 seconds of free speech, measure the mental state with SCL-90, PRIME-MD, B5T, ADHD-VAS as conventional psychological measurements.

Diagnostic Test: Speech analysis tool; Diagnostic Test: Conventional psychological measurements

Participants without any mental illness

OTHER

Participant with never diagnosed mental disorder, in a healthy mental state. Using the speech analysis tool with 120 seconds of free speech, measure the mental state with SCL-90, PRIME-MD, B5T, ADHD-VAS as conventional psychological measurements.

Diagnostic Test: Speech analysis tool; Diagnostic Test: Conventional psychological measurements

Interventions

Speech analysis tool DIAGNOSTIC_TEST

Using the speech analysis tool with recording 120 seconds of free speech and analysis of 200 content-free parameters of the speech including factor analytic process to compress the data to 5-10 core parameters.

Participants with mental illness; Participants without any mental illness

Conventional psychological measurements DIAGNOSTIC_TEST

Using well known and validated psychological measurements to identify the mental state of the participants.

Participants with mental illness; Participants without any mental illness

Eligibility Criteria

• Age: 18 Years - 65 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• being regular outpatient with mental disorder (verum group)
• being voluntary participant without mental disorder (control group)
• native german language speakers
• in good general health (absence of cancer, acute myocardial infarction, unstable angina, severe cardiac arrhythmia, recent cerebrovascular incident, or severe atherosclerosis)

You may not qualify if:

• schizophrenia
• dementia
• pregnancy or breastfeeding
• current or recent (less than 1 year) history of alcohol and/or drug abuse
• current or recent (less than 1 year) history of suicide attempts
• other significant comorbidities according to the Investigator's clinical assessment (for example, cancer, acute myocardial infarction, unstable angina, severe cardiac arrhythmia, recent cerebrovascular incident, or severe atherosclerosis.

Sponsors & Collaborators

• Neuropsychiatrischen Zentrums Hamburg-Altona: lead
• VoiceSense Ltd. Herzelba, Israel: collaborator

Study Sites (1)

Neuropsychiatric Center of Hamburg

Hamburg, 22769, Germany

Location

Related Publications (2)

• Tonn P, Seule L, Degani Y, Herzinger S, Klein A, Schulze N. Digital Content-Free Speech Analysis Tool to Measure Affective Distress in Mental Health: Evaluation Study. JMIR Form Res. 2022 Aug 30;6(8):e37061. doi: 10.2196/37061.

  PMID: 36040767 DERIVED

• Tonn P, Degani Y, Hershko S, Klein A, Seule L, Schulze N. Development of a Digital Content-Free Speech Analysis Tool for the Measurement of Mental Health and Follow-Up for Mental Disorders: Protocol for a Case-Control Study. JMIR Res Protoc. 2020 May 14;9(5):e13852. doi: 10.2196/13852.

  PMID: 32406862 DERIVED

MeSH Terms

Conditions

Mental Disorders

Study Officials

• Peter Tonn, MD

  Director

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Masking Details: The outcome-assessor or rater did not know which diagnosis the participant has and the participant is informed about the diagnosis after the diagnostic procedure from a physician/ psychotherapist not involved in the study.
• Purpose: DIAGNOSTIC
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Model Details: Two randomized groups of participants, blinded to rater in relation of the diagnosis of the individual proband.

Study Record Dates

• First Submitted: October 4, 2018
• First Posted: October 9, 2018
• Study Start: October 15, 2018
• Primary Completion: October 31, 2020
• Study Completion: December 30, 2020
• Last Updated: August 20, 2021

Record last verified: 2021-08

Data Sharing

• IPD Sharing: Will not share

Locations

DE (1)