Movement disorders associated with neuronal antibodies: a data-driven approach

Area of Science:

• Neurology
• Immunology
• Medical Diagnostics

Background:

• Movement disorders can manifest due to anti-neuronal antibodies.
• Identifying these antibodies is crucial for diagnosis and treatment.

Purpose of the Study:

• To systematically review and analyze the association between specific anti-neuronal antibodies and movement disorders.
• To develop a data-driven algorithm, refined by expert opinion, for predicting antibody-associated movement disorders.

Main Methods:

• Conducted a systematic review of studies published before April 2020, including patients with documented anti-neuronal antibodies and movement disorders.
• Employed random forests for variable selection and recursive partitioning/regression trees for algorithm development.
• Integrated expert clinical feedback to refine the diagnostic algorithm.

Main Results:

• Analyzed 844 patients across 377 studies, identifying 13 distinct anti-neuronal antibodies.
• Specific antibodies were associated with particular movement disorder symptoms (e.g., stiffness with GAD, chorea with CRMP5/CV2, parkinsonism with NMDAR).
• A data-driven classification model predicted NMDAR with psychiatric symptoms/dyskinesia, GAD with stiffness/ataxia, ANNA-2/Ri with ataxia/opsoclonus, and CRMP5/CV2 with chorea/choreoathetosis.

Conclusions:

• Established associations between specific movement disorders and anti-neuronal antibodies.
• A combined data-driven and expert opinion approach can enhance the precision of diagnosis.
• Early diagnosis facilitated by this approach may improve patient management strategies.