Copyright: ©Author(s) 2026.
World J Gastrointest Oncol. Sep 15, 2026; 18(9): 121970
Published online Sep 15, 2026. doi: 10.4251/wjgo.121970
Published online Sep 15, 2026. doi: 10.4251/wjgo.121970
Figure 4 Decision curve analysis.
Decision curve analysis based on out-of-fold predicted probabilities from repeated stratified cross-validation. A: Standard net benefit curves across threshold probabilities, comparing the full-feature, SHAP10, and SHAP5 models with “refer all” and “refer none” strategies; B: Rule-out-oriented clinical yield expressed as net avoided colonoscopies per 100 patients, calculated as true negatives gained minus harm-weighted false negatives. OOF: Out-of-fold; SHAP: SHapley Additive exPlanations; TN: True negative; FN: False negative.
- Citation: Polat YH, Kayaalp M. Clinical decision support for precolonoscopy cancer triage: A rule-out-oriented machine learning model for colorectal cancer risk. World J Gastrointest Oncol 2026; 18(9): 121970
- URL: https://www.wjgnet.com/1948-5204/full/v18/i9/121970.htm
- DOI: https://dx.doi.org/10.4251/wjgo.121970