617 External Validation of the IDENTIFY Risk Calculator for Predicting Urinary Tract Cancer in Patients with Haematuria

Abstract Aim Risk-stratification for patients referred with haematuria is important in diagnosing cancer early and health resource efficiency. A recent prediction model developed from the IDENTIFY study created a risk calculator that aimed to help clinicians their decision-making investigation of haematuria. We externally validate this separate cohort development population. Method Data were collected on patient characteristics used calculator, outcome recorded. Patients previous or existing urological malignancy excluded. Development validation demographics compared. The area under receiver operating characteristic curve (AUC), calibration slope, calibration-in-the-large (CITL), Brier’s score assess external validation. Results There 3483 111 hospitals across 27 countries. 12 countries new not cohort. cohorts well matched. When comparing observed vs predicted outcomes cohort, slope was 0.97 CITL 0.33. AUC 0.79. 0.15. Conclusions External shows good accuracy discrimination predicting urinary tract underestimates slightly can be recalibrated by adjusting intercept regression equation. introduced into diagnostic pathways improve stratification allocation.