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

IGF::OT::IGF 扩展 SEER 以包括非小细胞肺癌 (NSCLC) 的分子分析

• 批准号: 9161889
• 负责人: Eric B. Durbin
• 金额: $ 8.78万
• 依托单位: UNIVERSITY OF KENTUCKY
• 依托单位国家: 美国
• 财政年份: 2015
• 资助国家: 美国
• 起止时间: 2015-09-18 至 2016-09-17
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9161889
• 关键词: ALK gene; Algorithms; Automated Annotation; Computer software; Documentation; EGFR gene; Electronics; Epidermal Growth Factor Receptor; Gene Mutation; Kentucky; Lung; Machine Learning; Methods; Modeling; Molecular Profiling; Non-Small-Cell Lung Carcinoma; Pathology Report; Process; Registries; Reporting; Staging; Testing; c-erbB-1 Proto-Oncogenes; open source; programs; sound; validation studies

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.

这项研究试图通过NLP和机器学习方法利用电子病理(EPath)报告来自动注释具有EGFR和ALK基因突变测试结果的NSCLC肺部病例。 目标： 1)开发和实施机器学习的预测NLP模型，以自动处理ePath报告，以确定在IV期非鳞状NSCLC病例中EGFR和ALK测试的使用情况和报告结果。 2)对NLP算法进行多阶段验证研究，首先涉及肯塔基州SEER注册表中的案例，然后验证西雅图普吉特湾SEER注册表中的案例的算法。 3)开发和评估NLP算法的开源、可分发软件实施、附带的应用程序编程接口(API)以及可集成到SEER*DMS和其他注册软件应用程序中的文件。