Classifying progression status statements from radiology exams among non-small cell lung cancer patients using natural language processing
Authors:
- Anahita DavoudiADAnahita Davoudi
- Shun YuSYShun Yu
- Abigail DoucetteADAbigail Doucette
- Peter GabrielPGPeter Gabriel
- Mark MillerMMMark Miller
- Heather WilliamsHWHeather Williams
- Heena DesaiHDHeena Desai
- Anh LeALAnh Le
- Christian J StoeckertCSChristian J Stoeckert
- Kara MaxwellKMKara Maxwell
- Danielle L. MoweryDMDanielle L. Mowery
Preprint
Abstract
Although NLP has been used to support cancer research more broadly, the development of NLP algorithms to extract evidence of progression from clinical notes to support lung cancer research is still in its infancy. In this study, we trained supervised machine learning classifiers using rich semantic features to detect and classify statements of progression status from radiology exams. Our progression status classifier achieves high F1-scores for detecting and discerning progression (0.80), stable (0.82), and not relevant (0.92) sentences, demonstrating promising performance. We are actively integrating these extractions with structured electronic health record data using ontologies to instantiate a longitudinal model of progression among non-small cell lung cancer patients.Keywords
This publication has 8 references indexed in Scilit:
- Clinical Natural Language Processing for Radiation Oncology: A Review and Practical PrimerInternational Journal of Radiation Oncology - Biology - Physics (IJROBP), 2021
- Biomedical and clinical English model packages for the Stanza Python NLP libraryJournal of the American Medical Informatics Association, 2021
- Use of Natural Language Processing to Extract Clinical Cancer Phenotypes from Electronic Medical RecordsCancer Research, 2019
- Publicly Available Clinical2019
- Time-to-Progression of NSCLC from Early to Advanced Stages: An Analysis of data from SEER Registry and a Single InstituteScientific Reports, 2016
- Document-level classification of CT pulmonary angiography reports based on an extension of the ConText algorithmJournal of Biomedical Informatics, 2011
- Effectiveness of Lexico-syntactic Pattern Matching for Ontology Enrichment with Clinical DocumentsMethods of Information in Medicine, 2011
- Extracting Information from Textual Documents in the Electronic Health Record: A Review of Recent ResearchYearbook of Medical Informatics, 2008