Digitized Spiral Test Data for Parkinson's Disease Monitoring

Digitized spiral drawings from a graphics tablet provide objective motor function data for Parkinson's disease assessment. The dataset, sourced from the UCI Machine Learning Repository, contains time-series features extracted from patient handwriting tasks. It is designed for developing quantitative tools to monitor disease progression.

Use Cases

• Classify Parkinson's disease patients from healthy controls using features like pen pressure, velocity, and spiral shape metrics.
• Predict disease severity scores by analyzing time-series kinematics from the digitized drawing task.
• Detect motor symptom fluctuations by modeling temporal patterns in pen lift events and drawing smoothness.
• Identify early-stage Parkinson's through subtle anomalies in spiral coordination and tremor features.

Strengths

• Data captures high-resolution, objective motor metrics difficult to obtain from traditional clinical tests.
• Features are derived from a standardized, reproducible assessment task (spiral drawing).

Limitations

• The specific sample size, demographic diversity, and clinical label details are not provided in the metadata.
• Potential limitations include a single assessment modality and unknown longitudinal coverage for tracking progression.

Provenance

Source

UCI Machine Learning Repository

Collection Method

Data collected using a digitized graphics tablet during a spiral drawing task performed by patients.

Time Range

null

Freshness

null

Geography

null