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

本研究旨在通过NLP和机器学习方法利用电子病理学（ePath）报告，自动注释NSCLC肺部病例的EGFR和ALK基因突变检测结果。 目的： 第一章 开发和实施机器学习预测NLP模型，自动处理ePath报告，以确定EGFR和ALK检测在IV期非鳞状NSCLC病例中的使用和报告结果。 （二） 对NLP算法进行多阶段验证研究，最初涉及肯塔基州SEER登记研究中包含的病例，并对西雅图_普吉特海湾SEER登记研究中的病例进行后期验证。 第三章 开发并评估NLP算法的开源、可分发软件实现、随附的应用程序编程接口（API）以及可集成到SEER*DMS和其他注册表软件应用程序中的文档。

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.