IGF::OT::IGF EXPANDING SEER TO INCLUDE MOLECULAR PROFILING IN NON-SMALL CELL LUNG CANCER (NSCLC)

University Of Kentucky, Lexington KY

Investigators

Abstract

This study seeks to leverage electronic pathology (ePath) reports through NLP and machine learning methods to automate the annotation of NSCLC lung cases with results from EGFR and ALK gene mutation testing. Objectives: 1) Develop and implement machine-learned predictive NLP models to automatically process ePath reports to ascertain the use of and reported results of EGFR and ALK testing in stage IV non-squamous NSCLC cases. 2) Conduct a multiphase validation study of the NLP algorithms initially involving cases included in the Kentucky SEER registry, and posteriorly validating the algorithms for cases in the Seattle_Puget Sound SEER registry. 3) Develop and evaluate an open source, distributable software implementation of the NLP algorithms, an accompanying application programming interface (API), and documentation that can be integrated into SEER*DMS and other registry software applications.