Digital assessment in myasthenia gravis: evidence, validation, and a proposed framework for autoimmune heterogeneity, remote monitoring, and clinical endpoints

Myasthenia gravis (MG) is an antibody-mediated autoimmune disorder of the neuromuscular junction in which weakness fluctuates across symptom domains, daily activities, and treatment cycles. Established measures such as the Quantitative Myasthenia Gravis score, Myasthenia Gravis Composite, Myasthenia Gravis Activities of Daily Living scale, and MG-specific quality-of-life instruments remain the principal clinical anchors, but intermittent assessments may miss intraday variability, exertional fatigability, and changes across treatment cycles. This structured narrative review examines electronic patient-reported outcomes, smartphone-based active tasks, speech and video analysis, wearable sensing, telemedicine services, prediction models, and candidate digital endpoints. It also distinguishes the validation requirements of these modalities and critically appraises the MG-specific evidence. Most published studies demonstrate feasibility, adherence, acquisition reliability, or preliminary construct validity; most are small, short, and incompletely stratified by antibody subtype, and independent external validation and impact studies remain uncommon. Accordingly, subtype-specific digital trajectories should be regarded as a research hypothesis rather than as an established feature of AChR-, MuSK-, LRP4-associated, or seronegative MG. We present an MG digital phenotype and a five-stage closed-loop workflow as organizing frameworks, not as consensus standards or validated care pathways. Near-term value is most plausible in structured remote follow-up, treatment-cycle characterization, and exploratory trial measurement, provided that outputs remain domain-specific, respiratory safety is protected, and abnormal signals undergo human clinical review.