Voice Changes During ECT (VAPRE)

Voice Analysis in Patients Receiving Electroconvulsive Therapy

Depressed patients talk differently when they are depressed compared to when they are well. But it is hard to actually measure what the differences are. The study team will record voice samples from patients with mood disturbances, like depression, over the course of their receiving an electroconvulsive therapy (ECT) series. The study team will try and measure or quantify exactly what has changed in their speech and voice. The study team will choose ECT as it is one of the most effective and rapid treatment for depression. The study team will use a service provided by a company, NeuroLex, who has complex computer programs (artificial intelligence, AI) to analyze the voice samples.

Study Overview

• Status: Completed
• Conditions: Bipolar Depression; Unipolar Depression; Bipolar Disorder, Manic
• Intervention / Treatment: Other: Questionnaire

• Study Type: Observational
• Enrollment (Actual): 11

Contacts and Locations

Study Locations

• United States
  • South Carolina
    • Charleston, South Carolina, United States, 29425
      • Medical University of South Carolina

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years to 89 years (Adult, Older Adult)
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Patients undergoing electroconvulsive therapy (ECT) at the Medical University of South Carolina on an outpatient or inpatient basis.

Description

INCLUSION CRITERIA:

• Any candidate for electroconvulsive therapy who is about to initiate their ECT course at Medical University of South Carolina (MUSC) for a clinically indicated diagnosis
• Age 18 to 90 years old
• Able to speak and understand English
• Able to give consent to participate in the study

EXCLUSION CRITERIA:

• Any medical condition that limits the ability to speak or speak clearly, for example a history of head and/or neck cancer, spinal cord injury affecting speech, amyotrophic lateral sclerosis, or those with absence of critical anatomical structures involved in speech.
• Any voice characteristics that may limit the ability to speak English clearly including speech impediments or heavy accents (as evidenced by the pronunciation of the English language in such a non-standard way that research staff). If study staff have significant difficulty understanding the participant's responses in conversation, this may warrant exclusion.
• Patients who are receiving ECT by involuntary order, by order of their guardian, or by a court order, as evidenced by patient report or brief chart review.
• Patients who elect to not receive their full course of ECT at MUSC.

Study Plan

How is the study designed?

Design Details

• Observational Models: Case-Only
• Time Perspectives: Prospective

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

Intervention / Treatment

ECT and Voice Recorded Group; This is an add-on study of voice samples to be gathered during ECT clinical treatments. The ONLY research procedures are four tasks on an online form, one text task and three voice recording tasks. These voice recordings will take place in a private room on the 5th floor of the Institute of Psychiatry on the same day of a patient's ECT treatment. The questionnaire will take less than 10 minutes.

Other: Questionnaire; 3 voice recording tasks and 1 text entry task will be performed.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Acoustic feature: zero crossing rate	crossings per second	Throughout a course of electroconvulsive therapy (ECT) which may last between 2 and 7 weeks.
Acoustic feature: energy and entropy	decibels	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Acoustic feature: spectral centroid, spectral spread, spectral entropy, spectral flux, spectral rolloff	hertz	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Acoustic feature: Mel-Frequency Cepstral Coefficients, Chroma Vectors, and Chroma Deviation	unitless	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Linguistic features: question ratio, filler ratio, number ratio, type token ratio	unitless ratio	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Linguistic features: verb frequency, noun frequency, pronoun frequency, adverb frequency, adjective frequency, particle frequency, conjunction frequency, pronoun frequency	percentage	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Linguistic features: standardized word entropy	decibels/log(total word count)	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Linguistic features: Brunets index	W (lexical richness)	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Linguistic features: Honores statistic	R (lexical richness)	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Linguistic features: rate of speech	words per minute	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Meta-features: fatigue	Machine learning approach to evaluate binary outcome: fatigued or awake	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Meta-features: audio quality	Machine learning approach to evaluate binary outcome: bad or good	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Meta-features: sentiment	Machine learning approach to evaluate binary outcome: sad or happy	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Meta-features: stress	Machine learning approach to evaluate binary outcome: stressed or not stressed	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Meta-features: gender	Machine learning approach to evaluate binary outcome: male or female	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Meta-features: accent	Machine learning approach to evaluate a categorical outcome of accent region: england, indian, australian, etc.	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Meta-features: length	seconds	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Meta-features: age	Machine learning approach to evaluate estimated decade-age: 10s, 20s, 30s, 40s, 50s, 60s, 70s, 80s, 90s, etc.	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Comparing the voice feature(s) with greatest statistically significant change to Patient Health Questionnaire (PHQ)-9 scores	The voice feature(s) found to have changed most significantly will be compared to Patient Health Questionnaire-9 scores which approach a total score that is less than 8, indicative of reduced depressive symptoms throughout Electroconvulsive Therapy	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Acoustic Feature Specific Changes within and across sessions	Generalized mixed linear model will be used to evaluate which acoustic features change with P value threshold of <0.05	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Linguistic Feature Specific Changes within and across sessions	Generalized mixed linear model will be used to evaluate which linguistic features change with P value threshold of <0.05	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Meta-Feature Specific Changes within and across sessions	Generalized mixed linear model will be used to evaluate which meta features change with P value threshold of <0.05	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Acoustic Feature Specific Changes between sessions	Acoustic voice features will be evaluated using continuous averages using one sample t-tests and we will be testing the difference over time to a null hypothesis of 0 (for no change) in the one sample t-test.	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Linguistic Feature Specific Changes between sessions	Linguistic voice features will be evaluated using continuous averages using one sample t-tests and we will be testing the difference over time to a null hypothesis of 0 (for no change) in the one sample t-test.	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Meta-Feature Specific Changes between sessions	Meta-voice features will be evaluated using continuous averages using one sample t-tests and we will be testing the difference over time to a null hypothesis of 0 (for no change) in the one sample t-test.	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: Age	years	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: inpatient/outpatient status	binary: inpatient or outpatient	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: gender	male, female, unspecified	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: race	african american, caucasian, hispanic, asian american, etc.	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: Psychiatric diagnosis for ECT	Diagnosis indicated for receiving ECT	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: PHQ-9 score at each session	Total (0-27) on 9 question scale	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: Psychiatric hospitalizations	Number	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: Past Psychiatric Medication Trials	Number	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: Current Psychiatric Medication Trials	Number	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: Classes of Current Psychiatric Medications	Categorical: Sedative, Selective Serotonin Reuptake Inhibitor, etc.	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: Suicidal Ideation at ECT consult	Binary: yes/no	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: Past Suicide Attempts	Number	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: Psychiatric Review of Systems	Descriptive, categorical	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: Family Psychiatric History	Categorical regarding psychiatric diagnoses of family members	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: Number of non-psychiatric medical diagnoses	Number	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: Past non-psychiatric medication trials	Number	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: Current non-psychiatric Medications	Number	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: Tobacco use history	Binary (yes/no)	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: Tobacco use pack year	pack-year (total years smoked*average packs per day)	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: Prior ECT treatment	Binary (yes/no)	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: total # of prior ECT treatments for response in the past	Numerical	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: Prior transcranial magnetic stimulation (TMS) treatment	Binary (yes/no)	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data: Prior response to ECT or TMS	Categorical	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Patient Chart Review Data against voice features	We will evaluate voice features with statistically significant changes against respective participant chart review data using a general linear model with a clustering component for repeated measures which may also be applied to contrast statements evaluating overall change over time (from baseline to end).	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Generating ROC curves: stress	Clinically determined stress level (mood) will be compared to meta-feature extractions of stressed vs. not stressed from voice recordings will be used to calculate an area under the receiver operating curve (AUOC)	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Generating ROC curves: fatigue	Clinically determined fatigue (motor) will be compared to meta-feature extractions of fatigued vs. awake from voice recordings will be used to calculate an area under the receiver operating curve (AUOC)	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.
Generating ROC curves: sentiment	Clinically determined sentiment (affect and mood) will be compared to meta-feature extractions of happy vs. sad from voice recordings will be used to calculate an area under the receiver operating curve (AUOC)	Throughout a course of electroconvulsive therapy which may last between 2 and 7 weeks.

Collaborators and Investigators

• Sponsor: Medical University of South Carolina
• Investigators: Principal Investigator: Sean Christensen, MD, Medical University of South Carolina

Study record dates

Study Major Dates

• Study Start (Actual): November 7, 2019
• Primary Completion (Actual): February 17, 2021
• Study Completion (Actual): February 17, 2021

Study Registration Dates

• First Submitted: March 10, 2020
• First Submitted That Met QC Criteria: June 3, 2020
• First Posted (Actual): June 9, 2020

Study Record Updates

• Last Update Posted (Actual): October 24, 2024
• Last Update Submitted That Met QC Criteria: October 22, 2024
• Last Verified: October 1, 2024

More Information

Terms related to this study

• Keywords: VAPRE
• Additional Relevant MeSH Terms: Bipolar and Related Disorders; Mental Disorders; Behavioral Symptoms; Mood Disorders; Depression; Depressive Disorder; Bipolar Disorder
• Other Study ID Numbers: 00089198

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No