Data Sheet 6_Integrating CT radiomics and transcriptomics: a biologically-informed machine

Data Sheet 6 by Xin Xiong, published on figshare in April 2026, contains data for a study on predicting induction chemotherapy response in advanced laryngeal cancer. The dataset likely includes 1,321 extracted radiomics features and clinical variables from a retrospective analysis of 161 patients. It was used to build and evaluate machine learning models, with the best-performing Random Forest model achieving an AUC of 0.810 on an external test set.

Use Cases

• Training machine learning models to predict chemotherapy response based on integrated radiomics and clinical features.
• Validating radiomics signatures for non-invasive cancer outcome prediction.
• Conducting SHAP analysis to interpret model predictions and identify core clinical and imaging predictors.
• Performing decision curve analysis to assess the clinical utility of a predictive model.

Strengths

• Model performance is documented with specific metrics, including an AUC of 0.810 on an external test set.
• The study integrates multiple data types, including 1,321 radiomics features and clinical variables.
• The dataset is associated with a published methodology using LASSO regression and multivariate analysis for feature selection.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Data is from a retrospective study of 161 patients; prospective validation is noted as needed.

Provenance

Source

Xin Xiong via figshare.

Collection Method

Retrospective analysis of 161 advanced laryngeal cancer patients, with radiomics features extracted from pre-treatment CT images.

Time Range

null

Freshness

Last updated 2026-04-15 04:36:53; freshness should be verified.

Geography

null