Methods Comparison on SCZ, AD, PD, BP, and MG

10.5 KB of performance evaluation results for models on five neuropsychiatric disorders. The dataset, authored by Jiafang Li and last updated in May 2026, contains metrics like AUROC, F1-score, and AUPRC from a hold-out test set. Model selection was conducted via 5-fold cross-validation.

Use Cases

• Benchmarking machine learning models based on reported AUROC, F1-score, and AUPRC metrics.
• Comparing algorithm performance across schizophrenia (SCZ), Alzheimer's disease (AD), Parkinson's disease (PD), bipolar disorder (BP), and myasthenia gravis (MG).
• Validating model selection strategies based on the described 5-fold cross-validation process.

Strengths

• Performance metrics are evaluated on a hold-out test set, suggesting a standard validation approach.
• Model selection was conducted via 5-fold cross-validation, a common practice for robustness.
• The dataset is shared under a permissive CC-BY-4.0 license.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The description metadata is limited to performance evaluation; the underlying data features are not described.

Provenance

Source

figshare

Collection Method

Performance evaluation results from a machine learning study.

Freshness

Last updated 2026-05-29 18:00:09; freshness should be verified.