Parkinson's Disease Classification Data from UCI

Clinical measurement data for Parkinson's disease classification, sourced from the UCI Machine Learning Repository. The dataset contains biomedical signals and features relevant to diagnosing the condition. The original collector and specific temporal coverage are not provided.

Use Cases

• Classify Parkinson's disease status using biomedical signal features like vocal measurements and motor scores.
• Identify key clinical predictors from features such as jitter, shimmer, and fundamental frequency.
• Train a binary classifier to distinguish healthy patients from those with Parkinson's based on provided clinical measurements.
• Perform feature selection analysis to determine the most discriminative biomedical signals for diagnosis.

Strengths

• Sourced from the authoritative UCI Machine Learning Repository, ensuring a standard format.
• Contains specific, clinically relevant features for Parkinson's disease as indicated by platform tags.

Limitations

• The exact number of patient records and features is unknown, limiting reproducibility assessments.
• Potential geographic or demographic bias exists as the data collection source and population are unspecified.

Provenance

Source

UCI Machine Learning Repository

Collection Method

null

Time Range

null

Freshness

null

Geography

null