Prognostic Inflammatory Markers for Resectable NSCLC, Multi-Center Study

460 NSCLC patient records from two hospitals, with an external validation cohort of 50 patients. The data includes preoperative neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), systemic immune-inflammation index (SII), and systemic inflammation response index (SIRI) values, along with survival outcomes. This retrospective study by Xinying Cai, last updated in April 2026, used logistic regression and machine learning techniques to assess prognostic value.

Use Cases

• Training survival prediction models based on preoperative inflammatory markers like NLR and SIRI.
• Validating machine learning feature selection methods (LASSO, Random Forest, SVM) on clinical oncology data.
• Conducting discriminative, calibration, and clinical decision curve analysis (DCA) for prognostic indices.
• Investigating the relationship between systemic inflammation and cancer progression-free survival (PFS).

Strengths

• Includes an external validation cohort of 50 patients for model reliability assessment.
• Reports specific optimal cut-off values for NLR (3.470), PLR (186), SII (853.71), and SIRI (1.66).
• Applies multiple analytical methods: Kaplan-Meier, Cox regression, and three machine learning techniques.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for the primary dataset is unknown, which may limit suitability assessment.
• Data may reflect temporal and institutional bias inherent to the two source hospitals.

Provenance

Source

Retrospective data from two comprehensive hospitals, shared by author Xinying Cai on figshare.

Collection Method

Multi-center retrospective study.

Time Range

Preoperative measurements taken 15 days prior to surgery; study period not specified.

Freshness

Last updated 2026-04-22 05:46:14; freshness should be verified.

Geography

Hospital locations not specified; likely a multi-center study.