Predictive Model for Rituximab Response in Myasthenia Gravis Patients

A predictive model for minimal symptom expression after low-dose rituximab treatment in anti-acetylcholine receptor antibody-positive myasthenia gravis patients. The model was developed by Chenlu Hou using logistic regression on data from 117 patients treated between August 2019 and January 2025. It incorporates five clinical variables and achieved an AUC of 0.777.

Use Cases

• Predicting patient response to low-dose rituximab based on clinical features like baseline MG-ADL score.
• Stratifying patients into high- and low-probability groups for achieving minimal symptom expression.
• Supporting personalized therapeutic decision-making for myasthenia gravis using a nomogram.
• Validating logistic regression models for clinical outcomes in autoimmune disease treatment.

Strengths

• Model performance is quantified with an AUC of 0.777 and sensitivity/specificity metrics.
• The dataset includes 117 patient records with a defined time range from August 2019 to January 2025.
• The model identifies five specific predictive variables, including new-onset MG and baseline MG-ADL score.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data may reflect temporal and institutional bias inherent to a single-center retrospective study.

Provenance

Source

figshare

Collection Method

Retrospective review of patients who visited the research center and received RTX treatment.

Time Range

August 2019 to January 2025

Freshness

Last updated 2026-06-03 04:47:28; freshness should be verified.