Data Sheet 1_Integrating CT radiomics and transcriptomics: a biologically-informed machine

A retrospective analysis of 161 advanced laryngeal cancer patients treated with induction chemotherapy. The dataset, authored by Xin Xiong and last updated in April 2026, contains radiomics features extracted from pre-treatment CT images and clinical data used to build a predictive machine learning model.

Use Cases

• Building a machine learning model to predict chemotherapy response based on radiomics features and clinical predictors.
• Analyzing the biological basis of radiomics signatures through transcriptomic data mentioned in the description.
• Performing feature importance analysis using SHAP to interpret model predictions for clinical decision-making.
• Comparing the performance of different ML algorithms (e.g., Random Forest) for clinical outcome prediction.

Strengths

• Model performance is documented with specific metrics, including a Random Forest AUC of 0.810 in an external test set.
• The study integrates 1,321 extracted radiomics features with clinical data for a multimodal approach.
• Dataset is openly licensed under CC-BY-4.0, facilitating reuse and validation.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Data is small in scale at 23.4 KB, indicating limited raw data or a summary dataset.

Provenance

Source

figshare

Collection Method

Retrospective analysis of patient data; radiomics features extracted from CT images.

Time Range

Temporal coverage of the patient cohort is not specified.

Freshness

Last updated 2026-04-15 04:37:01; freshness should be verified.

Geography

Spatial coverage is not specified.