Facilitating validation of prediction models: A comparison of manual and semi-automated validation using registry-based data of breast cancer patients in the Netherlands

摘要: Clinical prediction models are not routinely validated. To facilitate validation procedures, the online Evidencio platform ( https://www.evidencio.com ) has developed a tool partly automating this process. This study aims to determine whether semi-automated can reliably substitute manual validation. Four different used in breast cancer care were selected: CancerMath, INFLUENCE, Predicted Probability of Axillary Metastasis, and PREDICT v.2.0. Data obtained from Netherlands Cancer Registry according inclusion criteria original development population. Calibration (intercepts slopes) discrimination (area under curve (AUC)) compared between Differences intercepts slopes all using ranged 0 0.03 validation, which was clinically relevant. AUCs identical for both methods. easy use option is good might increase number validations clinical practice. In addition, considered be user-friendly save lot time Semi-automated will contribute more accurate outcome predictions treatment recommendations target