This research is a single-center, exploratory, observational study to be carried out in the outpatient or inpatient ward of the Neurology Department at Huashan Hospital, affiliated to Fudan University. The aim is to develop a digital assessment model for Myasthenia Gravis by gathering multimodal digital phenotypic data from MG patients. This includes physiological signals, facial videos, eye movements, speech, limb movements, various scales, and quality of life metrics.
The goal is to define the multimodal digital phenotypes of myasthenia gravis patients, determine the specificities of their symptoms, and develop a digital evaluation model and remote assessment system that is objective, precise, and user-friendly. This will provide a scientific foundation and technical support for diagnosing, treating, and rehabilitating individuals with MG. Key issues to be addressed include: * Whether digital phenotyping can comprehensively represent the disease characteristics and severity gradations in MG. * The feasibility of using multimodal digital phenotypic modeling for the objective evaluation of MG. * The challenges and obstacles faced by the AI-enhanced medical model in clinical demonstration applications. The study is focused on three main objectives: 1. Perform a descriptive analysis and comparison of phenotypic data across various subgroups to pinpoint key characteristics associated with MG disease grade and scale score. 2. Construct a digital evaluation model for MG patients using chosen features, validate the model with prospectively gathered data, and conduct a correlative analysis with the clinical functional scales to assess its effectiveness on predicting MG symptom grading and disease progression. 3. Develop a patient-centric remote evaluation system utilizing the refined MG digital evaluation model to facilitate its application in real-world clinical settings.
Study Type
OBSERVATIONAL
Enrollment
180
Huashan Hospital, affiliated to Fudan University
Shanghai, China
RECRUITINGDescriptive Analysis and Comparison of Digital Phenotypic Data across Subgroups
Quantitative descriptive analysis of multimodal digital phenotypic data (motor performance, ocular metrics, and speech-derived features) to compare subgroup-specific patterns among patients with myasthenia gravis. Metrics will include summary statistics (mean, standard deviation, distribution profiles) for each modality, with subgroup comparisons performed to assess variability.
Time frame: At baseline (single study visit)
Correlation Between Digital Evaluation Model and Quantitative Myasthenia Gravis (QMG) Scale
This outcome measure will assess the convergent validity of the digital evaluation model by calculating the correlation coefficient (Pearson's or Spearman's) between the model-derived composite score and the Quantitative Myasthenia Gravis (QMG) clinical scale score in patients with myasthenia gravis.
Time frame: At baseline (single study visit)
Interclass Correlation Coefficient (ICC) of the Digital Outcome Assessment Model
This outcome measure will assess test-retest reliability of the digital assessment.
Time frame: Baseline and Week 2
Prospectively validate the model effectiveness
This outcome measure prospectively validates the scoring effectiveness in a prospectively enrolled MG cohort
Time frame: 1 year
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.