Predicting Psychotic Relapse Using Speech-Based Early Detection

NCT06978894 | Recruiting

• 1 other identifier: 2024-979
• Study Type: observational
• Target: 250
• Locations: 1 country
• Sites: 3

Brief Summary

Psychotic disorders, including schizophrenia and affective psychosis, are severe mental health conditions marked by recurrent episodes that contribute to long-term disability. Relapses, characterized by the re-emergence of psychotic symptoms after remission, are a critical factor in the progression of these disorders, increasing risks such as suicide, cognitive impairment, and unemployment. This study aims to develop a novel, speech-based digital model to predict relapses in individuals with psychosis. Building on previous research into language abnormalities in schizophrenia, the study will employ a longitudinal design across Early Psychosis Intervention (EPI) clinics in Ontario and Quebec to advance relapse prediction

Conditions

Psychosis

Keywords

psychosis; natural language processing; relapse; speech; relapse prediction

Outcome Measures

Primary Outcomes (2)

• Likelihood of relapse estimated using Speech-NLP Metrics

  This primary outcome will assess the ability of speech-based NLP metrics (coherence, connectedness, and complexity) to predict impending relapses in psychosis. Monthly speech samples will be analyzed to determine if changes in these metrics can distinguish timepoints preceding relapses from those not followed by relapse, with the aim of predicting relapses up to four weeks in advance. The likelihood of relapse is a numerical probabilistic estimate without any units. Outcome definition: Occurrence of relapse (i.e., psychiatric hospitalization, an increase in the level of psychiatric care, or substantial clinical deterioration \>1wk that requires \>25% increase in Defined Daily Dose equivalents of antipsychotics)

  Monthly, up to 24 months

• Generalization of Speech-Based Relapse Prediction Models Across Languages and Genders

  This outcome will assess whether the speech-based relapse prediction models are valid and perform equally well across different languages (English and French) and genders (male and female). The study will evaluate how sociodemographic factors such as language and sex impact the predictive accuracy of the models. NLP metrics (coherence, connectedness, complexity) will be correlated with clinical outcomes, and model performance will be compared across linguistic and gender subgroups to ensure generalizability.

  Monthly, up to 24 months

Secondary Outcomes (1)

• Likelihood of relapse estimated using multi-level speech features

  Monthly, up to 24 months

Study Arms (1)

Early Psychosis Patients

This study will participants recruited from three Early Psychosis Intervention (EPI) programs across Ontario and Quebec. This group will consist of approximately 250 patients experiencing or having experienced psychosis, enrolled in the EPI programs.

Eligibility Criteria

• Age: 16 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

This study population will consist of approximately 250 patients experiencing or having experienced psychosis, enrolled in the EPI programs.

You may qualify if:

• Age must be 16 years and older
• Diagnosis must meet DSM-5 criteria for psychotic disorders, including schizophrenia, schizoaffective disorder, or related conditions
• Fluency in English or French
• Must be currently receiving treatment through an EPI program

You may not qualify if:

• Severe comorbid speech or language disorders (e.g., aphasia)
• Primary diagnosis of non-psychotic disorders
• Inability to provide consent or complete assessments

Sponsors & Collaborators

• Douglas Mental Health University Institute: lead

Study Sites (3)

Robarts Research Institute

London, Ontario, N6A 5B7, Canada

RECRUITING

Douglas Mental Health University Institute

Montreal, Quebec, H4H 1A8, Canada

RECRUITING

Vitam

Québec, Quebec, G1J 2G1, Canada

RECRUITING

Related Publications (1)

• Zaher F, Diallo M, Achim AM, Joober R, Roy MA, Demers MF, Subramanian P, Lavigne KM, Lepage M, Gonzalez D, Zeljkovic I, Davis K, Mackinley M, Sabesan P, Lal S, Voppel A, Palaniyappan L. Speech markers to predict and prevent recurrent episodes of psychosis: A narrative overview and emerging opportunities. Schizophr Res. 2024 Apr;266:205-215. doi: 10.1016/j.schres.2024.02.036. Epub 2024 Feb 29.

  PMID: 38428118 BACKGROUND

MeSH Terms

Conditions

Psychotic Disorders; Recurrence; Speech

Condition Hierarchy (Ancestors)

Schizophrenia Spectrum and Other Psychotic Disorders; Mental Disorders; Disease Attributes; Pathologic Processes; Pathological Conditions, Signs and Symptoms; Verbal Behavior; Communication; Behavior

Central Study Contacts

Lena Palaniyappan, MD, PHD

CONTACT

5147616131; lena.palaniyappan@mcgill.ca

Study Design

• Study Type: observational
• Observational Model: CASE ONLY
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Director, Centre of Excellence in Youth Mental Health

Study Record Dates

• First Submitted: January 13, 2025
• First Posted: May 18, 2025
• Study Start: May 27, 2024
• Primary Completion (Estimated): July 1, 2028
• Study Completion (Estimated): July 1, 2029
• Last Updated: May 18, 2025

Record last verified: 2024-11

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL
• Time Frame: December 2028 for an unlimitied amount of time. There are no plans for data destruction of the study information stored (de-identified audio and transcriptions) within TalkBank.
• Access Criteria: The anonymized speech data will be retained on an access-controlled secure database hosted by TalkBank.

Locations

CA (3)