Data Sheet 2_Integrating CT radiomics and transcriptomics: a biologically-informed machine

161 advanced laryngeal cancer patient records with 1,321 extracted radiomics features from pre-treatment CT scans. Xin Xiong developed a Random Forest model integrating radiomics and clinical features, achieving an AUC of 0.810 in an external test set. The dataset was last updated on April 15, 2026.

Use Cases

• Predicting induction chemotherapy response in advanced laryngeal cancer based on radiomics scores and clinical features.
• Training machine learning models for clinical risk stratification using the identified independent predictors like Rad-score and gap invasion.
• Interpreting model predictions for personalized treatment decisions using SHAP analysis on the integrated features.

Strengths

• Includes 1,321 radiomics features extracted from pre-treatment CT images for 161 patients.
• Model performance is documented with specific metrics, including an AUC of 0.856 in the validation set.
• Dataset is licensed under CC-BY-4.0, permitting open reuse and modification.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data is retrospective and from a single study, which may reflect inherent source bias.

Provenance

Source

figshare, author Xin Xiong.

Collection Method

Retrospective analysis of patient records and CT image feature extraction.

Time Range

null

Freshness

Last updated 2026-04-15 04:37:00; freshness should be verified.

Geography

null