Detecting Fatigue From Voice in Generalised Myasthenia Gravis

Not yet recruiting

• Conditions: Myasthenia Gravis Generalised

• Registration Number: NCT07033559
• Lead Sponsor: Thymia Limited

Brief Summary

The goal of this observational study is to learn if computer analysis of voice recordings can detect a type of exhaustion called "central fatigue" in adults with generalised myasthenia gravis.

The main questions it aims to answer are:

1. Can advanced voice analysis accurately tell when participants are experiencing deep exhaustion based on how they speak?

2. How easy and acceptable is voice-based fatigue monitoring for people with myasthenia gravis?

Participants will:

1. Record themselves reading short passages and answering questions out loud twice daily (morning and evening), twice a week, for 4 weeks.

2. Answer brief questionnaires about their energy levels, mood, and myasthenia gravis symptoms during each session.

3. Use their own devices (computer, tablet, or smartphone) to complete all study activities online from home.

Detailed Description

This study addresses a significant gap in understanding and measuring central fatigue in generalised myasthenia gravis (gMG), a debilitating symptom that differs from the characteristic muscle weakness fluctuations of the condition. Central fatigue encompasses mental and physical exhaustion originating in the central nervous system and remains poorly characterised with limited validated assessment tools.

Study Rationale and Innovation:

Recent developments in artificial intelligence and digital biomarkers have demonstrated potential for detecting fatigue-related changes in voice characteristics. This approach offers advantages over traditional assessment methods by providing objective, standardised measurements that can be collected remotely with minimal participant burden. Voice-based biomarkers may capture subtle physiological changes associated with central fatigue that are not readily apparent through conventional questionnaire-based assessments.

Study Design and Methodology:

This single-cohort observational study employs an intensive longitudinal monitoring design to capture the dynamic nature of fatigue fluctuations characteristic of gMG. The twice-daily assessment schedule (morning and evening sessions two days a week) over four weeks is designed to account for diurnal variation in fatigue symptoms commonly reported by MG patients.

Each assessment session lasts approximately 10-15 minutes and includes standardised voice recording tasks alongside validated fatigue questionnaires. Voice recording activities consist of structured reading tasks and answering questions out loud, designed to elicit natural speech patterns while maintaining consistency across sessions and participants.

Technical Approach:

Voice data will be analysed using machine learning algorithms to identify acoustic features potentially associated with central fatigue states. \[Note: Specific algorithmic approaches and feature extraction methods are proprietary and not detailed here\]. The study uses triangulated participant self-reported fatigue assessments as ground truth labels for model training and validation.

Data Collection and Management:

All data collection occurs remotely through a secure web-based platform accessible via standard internet browsers. Participants use their personal devices (computers, tablets, or smartphones) equipped with microphone capabilities. The platform captures voice recordings, questionnaire responses, and relevant metadata including device specifications and environmental conditions that may affect recording quality.

Sample Size Considerations:

The target enrolment of 240 participants is designed to generate sufficient data points for robust machine learning model development while accounting for expected attrition and technical issues.

Study Timeline

• Study First Submitted: 2025-06-03
• Study First Submitted QC: 2025-06-13
• Study First Posted: 2025-06-24
• Status Verified: 2025-09
• Last Update Submitted: 2025-09-23
• Last Update Posted: 2025-09-29
• Study Start: 2025-11-01
• Primary Completion: 2026-02
• Study Completion: 2026-04-01

Recruitment & Eligibility

• Status: NOT_YET_RECRUITING
• Sex: All
• Target Recruitment: 240

Inclusion Criteria

• Adults ≥18 years old
• Self-reported generalised Myasthenia Gravis diagnosis confirmed by healthcare provider for ≥6 months
• Disease stability for ≥6 months (no hospitalisations, medication changes, or significant symptom worsening)
• English as first language
• Residence in US or UK
• Vision adequate for screen reading (with aid or correction if necessary)
• Access to internet-connected device with compatible browser and microphone
• Adequate internet connectivity (≥5 Mbps download, ≥3 Mbps upload)
• Ability to complete twice-daily assessments during specified time windows
• Signed electronic informed consent

Exclusion Criteria

• Pure ocular Myasthenia Gravis
• Diagnosed mild cognitive impairment or dyslexia
• Speech or hearing impairments affecting voice recording
• Unable to provide credible diagnostic information (healthcare provider diagnosis, antibody test results, current medications)
• Major inconsistencies in reported medical history
• Unsigned informed consent

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
Accuracy of AI Model for Binary Central Fatigue Classification as Assessed by Voice Biomarker Analysis	Across 16 assessment sessions over 4 weeks from enrolment	Binary classification performance (presence vs. absence of central fatigue) of the artificial intelligence-based system using voice biomarker analysis, with the subjective fatigue scale serving as ground truth. Performance will be measured using sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) metrics through cross-validation methods.

Secondary Outcome Measures

Name	Time	Method
Participant Acceptability of Voice-Based Monitoring System	At completion of final assessment session at 4 weeks	Self-reported acceptability scores including ease of use, satisfaction, and willingness for future use of the voice-based fatigue monitoring approach, assessed through three researcher developed 7-point Likert scales (1=lowest, 7=highest)
Participant Withdrawal Patterns and Reasons	From enrolment through 4 weeks or until participant withdrawal	Number and percentage of participants who withdraw from the study, categorised by stated reasons for withdrawal (technical difficulties, time burden, health reasons, other)
Study Completion Rate Among Enrolled Participants	From enrolment through completion of final assessment session at 4 weeks	Percentage of enrolled participants who complete all 16 required assessment sessions out of the total number of participants who begin the study
Individual Session Completion Rate Across All Participants	From enrolment through completion of final assessment session at 4 weeks	Percentage of individual assessment sessions completed across all enrolled participants out of the total possible sessions
Adherence to Specified Assessment Time Windows	From enrolment through completion of final assessment session at 4 weeks	Percentage of completed sessions that occur within the designated time windows out of all completed sessions