Data Sheet 4_Integrating CT radiomics and transcriptomics: a biologically-informed machine

161 advanced laryngeal cancer patient records were analyzed, with 1,321 radiomics features extracted from pre-treatment CT scans. The dataset was created by Xin Xiong and last updated in April 2026, supporting the development of a Random Forest model for predicting chemotherapy response. It integrates radiomics scores and clinical features like gap invasion.

Use Cases

• Training machine learning models for chemotherapy response prediction based on radiomics scores and clinical features.
• Validating radiomics feature selection methods using the 1,321 extracted features mentioned in the description.
• Conducting SHAP analysis for model interpretability based on the core predictors identified in the study.
• Performing risk stratification for personalized treatment decisions in advanced laryngeal cancer.

Strengths

• Includes data from 161 patient records, providing a clinical study foundation.
• Derived from 1,321 extracted radiomics features, suggesting detailed feature engineering.
• Model performance metrics are reported, including an AUC of 0.810 in an external test set.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Data is 13.5 KB, indicating a very limited scope, likely containing summary or model data rather than raw patient records.

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 04:36:56; freshness should be verified.

Geography

null