Patient Characteristics for Head and Neck Cancer Radiation Mucositis Study

108 patient records from a study evaluating machine learning models for predicting radiation-induced oral mucositis. The dataset was created by Ling Li and published on figshare in April 2026. It includes multimodal data such as CT imaging, dose distribution, and clinical features.

Use Cases

• Compare traditional ML vs. deep learning performance for multi-class prediction based on clinical and imaging data.
• Train models to predict radiation-induced oral mucositis severity based on patient characteristics and treatment dosimetry.
• Investigate overfitting and mode collapse in high-dimensional models like 3D-CNNs using limited clinical data.
• Benchmark ensemble learning algorithms (e.g., Extra Trees) against linear models (e.g., Logistic Regression) for small-cohort radiomics.

Strengths

• Data from 108 patients with inter-rater reliability for grading reported as excellent (Cohen’s kappa = 0.82).
• Model performance was rigorously evaluated using stratified 5-fold cross-validation and metrics like AUC and MCC.
• Includes multimodal data types (CT imaging, dose distribution, clinical features) as described in the study.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 5.5 KB, indicating limited scope.

Provenance

Source

figshare, author Ling Li.

Collection Method

Multimodal data collected from 108 patients as part of a research study.

Time Range

null

Freshness

Last updated 2026-04-09 17:29:12; freshness should be verified.

Geography

null