Evaluating Comorbidity Scores for Flumatinib Therapy in Chronic Myeloid Leukemia

Retrospective data from 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 using machine learning models like XGBoost. It was authored by Yuanlan Yang and last updated in May 2026.

Use Cases

• Training machine learning models to predict molecular response based on comorbidity scores and clinical features.
• Comparing the incremental predictive value of different comorbidity scoring systems (CIRS-G, CCI, ACE-27).
• Applying SHAP analysis to interpret non-linear feature associations and interaction effects in clinical prediction models.
• Investigating threshold effects, such as how a CIRS-G score ≥8 may impact therapeutic efficacy.

Strengths

• Contains data from 559 patients, providing a substantial cohort for analysis.
• Includes evaluation of three established comorbidity scoring systems (CCI, ACE-27, CIRS-G).
• Model performance metrics are reported, such as an XGBoost AUC of 0.852.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The authors note the retrospective design may overestimate prospective model validity.

Provenance

Source

figshare, author 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.