Clinical and Radiomic Features for Predicting Glioma Recurrence in 89 Patients

MengYu Cheng's dataset contains clinical and radiomic data from 89 postoperative glioma patients, used to construct a nomogram for predicting progression-free survival. The data includes 944 radiomic features extracted from MRI-based habitat subregions within a 2-cm edema zone. The dataset was last updated on April 21, 2026.

Use Cases

• Predicting 1-, 2-, and 3-year progression-free survival based on combined clinical and radiomic features.
• Evaluating the performance of habitat analysis models compared to traditional radiomic models.
• Training machine learning models for glioma recurrence risk stratification using radiomic scores.
• Developing clinical nomograms to aid in postoperative radiotherapy targeting decisions.

Strengths

• Includes data from 89 patient cases, providing a basis for model development.
• Model validation reported time-dependent AUCs of 0.813, 0.933, and 0.930 for 1-, 2-, and 3-year PFS prediction.
• The constructed high-risk habitat nomogram achieved a C-index of 0.916.

Limitations

• Row count and column-level documentation are unknown, which may limit suitability assessment.
• The dataset is very small at 21.3 KB, indicating limited scope.
• Data is from a single retrospective study, which may reflect specific institutional or methodological biases.

Provenance

Source

MengYu Cheng via figshare

Collection Method

Retrospective analysis of MRI and clinical data from postoperative glioma patients.

Freshness

Last updated 2026-04-21 04:22:22; freshness should be verified.