The Application of Machine Learning to Predict Clinical Outcomes of Deep Brain Stimulation in Parkinson's Disease: A Systematic Review.

Key Points

• The aim is to review the application of machine learning in predicting clinical outcomes and adverse events following deep brain stimulation in Parkinson's disease patients.
• Systematic review of existing literature on machine learning applications in DBS for Parkinson's Disease.
• Focus on uses of preoperative clinical data for predicting outcomes.
• Assessment of methodological quality and limitations in existing studies.
• Current evidence is sparse and consists mainly of single-center studies.
• Methodological heterogeneity limits the reliability of predictions.
• Limited external validation indicates that clinical application is still premature.

Abstract