Abstract IA03: Requirements for a statistical prediction model to receive AJCC endorsement

Abstract

The American Joint Committee on Cancer (AJCC) has recognizes the need for more personalized predictions than those delivered by cancer staging systems. In particular, the use of accurate risk models or calculators is seen as valuable. However, judging the quality and acceptability of a risk model is difficult. The AJCC Precision Medicine Core formed a committee to establish inclusion and exclusion criteria necessary for a risk model to potentially be endorsed by the AJCC. They identified 13 inclusion and 3 exclusion criteria for AJCC risk model endorsement. The criteria centered on performance metrics, implementation clarity, and clinical relevance. These criteria will be described. Citation Format: Michael W. Kattan. Requirements for a statistical prediction model to receive AJCC endorsement. [abstract]. In: Proceedings of the AACR Special Conference: Improving Cancer Risk Prediction for Prevention and Early Detection; Nov 16-19, 2016; Orlando, FL. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2017;26(5 Suppl):Abstract nr IA03.