AI models accurately classify Parkinson's disease severity using sensor data

Researchers have developed a machine learning approach to classify Parkinson's disease severity using data from triaxial inertial measurement unit (IMU) sensors. The study compared several classification models, with the LightGBM model achieving the highest performance, reaching approximately 97% accuracy, precision, recall, and F1-score. Other models like Decision Tree and XGBoost performed close to 96%, while k-nearest neighbors and support vector machines showed accuracies around 90% and 94% respectively. This AI-driven method demonstrates an effective capability for non-invasive PD severity prediction. AI

IMPACT Demonstrates potential for AI-driven, non-invasive diagnostic tools in healthcare.

RANK_REASON Academic paper detailing a novel application of machine learning for disease classification. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• decision tree
• kNearest Neighbors
• k-nearest neighbors algorithm
• LightGBM
• logistic regression model
• Muhammad Junaid Asif
• Parkinson Disease
• support vector machine
• XGBoost

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →