Skip to content

The face of neuromuscular dysfunction: artificial intelligence for the analysis of video data of facial movement, with a focus on Myasthenia Gravis

The face of neuromuscular dysfunction: artificial intelligence for the analysis of video data of facial movement, with a focus on Myasthenia Gravis - The face of Myasthenia Gravis

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
NL-OMON
Registry ID
NL-OMON52702
Enrollment
120
Registered
2021-02-03
Start date
2021-09-02
Completion date
Unknown
Last updated
2024-07-22

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

myasthenia gravis

Interventions

None listed

Sponsors

Leids Universitair Medisch Centrum
Lead Sponsor

Eligibility

Age
18 Years to 64 Years

Inclusion criteria

Inclusion criteria: definite diagnosis of myasthenia gravis (positive serologic test or electrophysiological support or positive neostigmine test)

Exclusion criteria

Exclusion criteria: Participants with active Graves* disease

Design outcomes

Primary

MeasureTime frame
1. Diagnostic yield, expressed as sensitivity, specificity and area under the curve of a receiver-operator curve (ROC) of the FaceReader algorithm, using quantitative data of facial weakness expressed in Action Units (AU), ranging between 0 (no activation) and +1 (maximal activation). Raw data from FaceReader provides the results of 20 AU*s corresponding with 20 different facial movements of 20 facial muscles based on the Facial Action Coding System (FACS). We will calculate the diagnostic yield of individual muscles and combinations of muscles to differentiate between healthy controls and MG and between different grades of MG disease severity. 2. Diagnostic yield, expressed as sensitivity, specificity and area under the curve of a receiver-operator curve (ROC) of a working narrow deep learning model to differentiate between healthy controls and MG and between different grades of MG disease severity.

Secondary

MeasureTime frame
1. Detection of medication effects by obtaining multiple videos (longitudinal) in a subset of patients. The QMG score is the parameter for change in disease severity. A previous study found a minimal clinically important difference (MCID) in QMG score of >=2 for a baseline QMG score between 0 and 16. For a baseline QMG score >16 the MCID is >=3 points change in QMG score4. For change in severity, our aim is to detect an intra-participant difference in case of a change in QMG >=2 or >=3, depending of baseline QMG score. 2. A comparison of the diagnostic yield of FaceReader parameters and classification by the deep learning model.

Countries

Netherlands

Outcome results

None listed

Source: NL-OMON (via WHO ICTRP)