Full Signal Classification Scores for Needle Electromyography Diagnosis

Ilhan Yoo published a dataset of needle electromyography (nEMG) signal classification scores on 2026-05-19. The data contains model performance metrics from a study using 376 nEMG signals from 57 patients to classify conditions as normal, myopathy, or neuropathy. The deep learning model's performance was compared against six electromyographers.

Use Cases

• Benchmarking diagnostic AI models based on nEMG signal classification scores mentioned in the description
• Training or validating machine learning classifiers for myopathy and neuropathy based on the three-category labels
• Analyzing the performance gap between AI and human experts based on the reported accuracy, precision, sensitivity, and specificity metrics

Strengths

• Performance metrics for a deep learning model are provided, including median accuracy (0.70), precision (0.70), sensitivity (0.70), and specificity (0.85)
• Data is derived from a clinical study involving 376 nEMG signals from 57 patients at a tertiary university hospital
• Model performance is directly compared against six human electromyographers, providing a relative benchmark

Limitations

• Column-level documentation is absent; field semantics must be inferred after download
• Row count is unknown, which may limit suitability assessment
• The dataset is very small at 17.4 KB, indicating limited scope

Provenance

Source

figshare, author Ilhan Yoo

Collection Method

Signals were collected from a tertiary university hospital database and used in a nested k-fold cross-validation study.

Freshness

Last updated 2026-05-19 17:38:34; freshness should be verified