Upper Tract Urothelial Carcinoma Prognostic Model with 606 Patient Records

606 patients from four centers were used to develop a machine learning-based prognostic signature for Upper Tract Urothelial Carcinoma (UTUC). The model integrates seven preoperative hematological markers, including RDW and PLT, to predict disease-free survival. Author Xiang Peng published this research document under a CC-BY-4.0 license on figshare in April 2026.

Use Cases

• Developing prognostic models for cancer survival based on systemic immune-inflammatory markers mentioned in the description
• Training Random Survival Forest algorithms on clinical and hematological data
• Analyzing nonlinear threshold effects of biomarkers like RDW and PLT on mortality risk
• Building composite clinical nomograms integrating machine learning scores with factors like age and tumor stage

Strengths

• Data from 606 patients across four multicenter cohorts provides a multi-source validation framework.
• Model performance is quantified with a C-index of 0.762 in the training set.
• Seven principal predictors were identified through LASSO-Cox regression, offering a focused feature set.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for the underlying clinical data is unknown, which may limit suitability assessment.
• The primary file is a 595.1 KB DOCX document, suggesting the dataset itself may be small or embedded within a research paper.

Provenance

Source

figshare, author Xiang Peng.

Collection Method

Multicenter study collecting preoperative hematological markers and clinical outcomes from UTUC patients.

Time Range

null

Freshness

Last updated 2026-04-22 05:46:06; freshness should be verified.

Geography

null