JCO Precision Oncology
How do the authors justify their hybrid survival-model selection and feature-importance interpretation in response to methodological criticism?
The reply describes an earlier framework combining 12 learners into 132 candidate modeling schemes, explains selection using average concordance across validation approaches, and discusses SHAP for feature interpretation. These are the authors' methodological arguments about prior studies. The reply does not add a new patient cohort, a new accuracy estimate, or an experiment demonstrating that SHAP removes bias. The original retrospective proctectomy study remains the source for its model results.
Ge Zhang, Shiqian Zhang, Haonan Zhang, Ruhao Wu, Haoze Zheng. Reply to: Addressing Bias in Feature Importance: A Hybrid Approach for Risk Prediction in Prognostic Survival Models. JCO Precision Oncology. 2025. https://doi.org/10.1200/po-24-00875
Reply to: Addressing Bias in Feature Importance: A Hybrid Approach for Risk Prediction in Prognostic Survival Models
A methodological reply explains hybrid survival-model selection and feature interpretation in earlier work; it reports no new cohort or performance experiment.
Learners and schemes are methodological units from prior work, not independent cohorts or additional patients.
A retrospective account of previous work, not a new model-comparison experiment in this correspondence.
| Measure | Value |
|---|---|
| learners | 12 |
| candidate modeling schemes | 132 |
Source locator: Reply PDF-text rendition p. 1, opening paragraph; reference 2 on p. 2 identifies the original proctectomy study.
Their stated rationale for scheme selection; no new C-index value or independent validation cohort is reported here.
Source locator: Reply PDF-text rendition p. 1, paragraph on consensus evaluation following the ensemble-learning discussion.
An explanation of the authors' interpretability choice; it does not establish causal effects or experimentally demonstrate freedom from bias.
Source locator: Reply PDF-text rendition pp. 1-2, paragraph addressing feature-importance bias, continuing after the p. 1 corresponding-author footer.
No. It discusses previous modeling work and contains no new cohort or clinical outcome analysis.
They count learners and candidate modeling schemes described from earlier work; they are not numbers of patients or independent validation cohorts.
Evidence: KF1
The authors describe averaging concordance across validation techniques as part of a consensus strategy for selecting a scheme.
Evidence: KF2
| Row ID | Component | Context | Finding | Evidence Level | Scope | Source Locator | Evidence refs |
|---|---|---|---|---|---|---|---|
| evidence-kf1 | The reply describes the breadth of the authors' earlier hybrid modeling framework. | A retrospective account of previous work, not a new model-comparison experiment in this correspondence. | learners: 12; candidate modeling schemes: 132 | Author explanation and defense of prior methods | Supports attribution to this correspondence; not a new experiment or independently validated clinical effect. | Reply PDF-text rendition p. 1, opening paragraph; reference 2 on p. 2 identifies the original proctectomy study. | KF1 |
| evidence-kf2 | The authors explain a consensus selection strategy using average concordance across validation techniques. | Their stated rationale for scheme selection; no new C-index value or independent validation cohort is reported here. | selection criterion described: Average concordance index across validation techniques | Author explanation and defense of prior methods | Supports attribution to this correspondence; not a new experiment or independently validated clinical effect. | Reply PDF-text rendition p. 1, paragraph on consensus evaluation following the ensemble-learning discussion. | KF2 |
| evidence-kf3 | The reply discusses SHAP as its approach to interpreting feature contributions. | An explanation of the authors' interpretability choice; it does not establish causal effects or experimentally demonstrate freedom from bias. | interpretation method: Shapley Additive Explanation (SHAP) | Author explanation and defense of prior methods | Supports attribution to this correspondence; not a new experiment or independently validated clinical effect. | Reply PDF-text rendition pp. 1-2, paragraph addressing feature-importance bias, continuing after the p. 1 corresponding-author footer. | KF3 |
No. It discusses previous modeling work and contains no new cohort or clinical outcome analysis.
Evidence: KF1, KF2
They count learners and candidate modeling schemes described from earlier work; they are not numbers of patients or independent validation cohorts.
Evidence: KF1
The authors describe averaging concordance across validation techniques as part of a consensus strategy for selecting a scheme.
Evidence: KF2
No. It explains the chosen attribution method, without a new experiment proving elimination of bias or causal interpretation.
Evidence: KF3
Study-level author-maintained evidence summary. Not participant-level data and not a ready-to-pool meta-analysis dataset. For formal citation, use the original article DOI.
Download study-level evidence CSV (UTF-8)Formula safety: cells starting with =, +, -, @ (after leading whitespace), or tab/CR/LF are prefixed with an apostrophe. Treat all cells as text; remove only that safety prefix when recovering the original string.
These records identify the same original work; database inclusion is not evidence of scientific validity or clinical benefit.