Evaluating Comorbidity Scoring Systems for Flumatinib Therapy in Chronic Myeloid Leukemia

A single-center cohort of 559 chronic-phase chronic myeloid leukemia patients treated with flumatinib between 2018 and 2024. The dataset was used to evaluate three comorbidity scoring systems (CCI, ACE-27, CIRS-G) for predicting 12-month major molecular response via machine learning models. The analysis was authored by Yuanlan Yang and shared under a CC-BY-4.0 license.

Use Cases

• Benchmarking comorbidity scoring systems (CCI, ACE-27, CIRS-G) for predictive performance in targeted cancer therapy.
• Training machine learning models, such as XGBoost, to predict molecular response outcomes in leukemia patients.
• Applying SHAP analysis to interpret non-linear feature associations and threshold effects in clinical prediction models.
• Investigating the interaction between advanced age, severe comorbidity, and reduced drug dose on predicted therapeutic efficacy.

Strengths

• Contains data from 559 patients, providing a substantial clinical cohort.
• Covers a 6-year time range (2018-2024) for longitudinal analysis.
• Includes evaluation of three established comorbidity scoring systems (CCI, ACE-27, CIRS-G).
• Reports specific model performance metrics (AUC=0.852) and incremental value (ΔAUC=0.078).

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The authors note predictive performance may overestimate prospective validity due to retrospective design and temporal variations.

Provenance

Source

Yuanlan Yang

Collection Method

Retrospective data analysis from a single-center cohort.

Time Range

2018-2024

Freshness

Last updated 2026-05-28 04:48:03; freshness should be verified.