Natural Language Processing Methods Automate Molecular Marker Extraction From Glioma Pathology Reports
Simple Natural Language Processing approaches effectively automate molecular marker extraction from pathology reports with near-perfect accuracy while requiring minimal computational resources. This enables expanded sample sizes in retrospective studies, multi-institutional analyses of rare molecular subgroups, and accelerated biomarker research. Future work will focus on validation across larger data sets, infrastructure integration, and expansion to additional molecular markers.
Authors
- Andrew D. Smith (ORCID: https://orcid.org/0000-0002-8124-1038)
- Anton Alyakin
- Edward Harake (ORCID: https://orcid.org/0000-0002-8865-1267)
- John Markert (ORCID: https://orcid.org/0000-0002-7558-8270)
- David Reinecke (ORCID: https://orcid.org/0000-0002-3298-9517)
- Theodore Cogan
- Todd Charles Hollon (ORCID: https://orcid.org/0000-0001-5987-6531)
- Karen Eddy
- Daniel A. Orringer (ORCID: https://orcid.org/0000-0001-6427-8376)
- H. Weiss (ORCID: https://orcid.org/0000-0003-0280-4814)
- Nicolas K. Goff (ORCID: https://orcid.org/0000-0002-6005-1008)
- Minjun Park (ORCID: https://orcid.org/0000-0003-3053-1622)
- Nader Maarouf
- Daniel Alexander Alber
- Xu Han
- Eric K. Oermann
Institutions
- Washington University in St. Louis (US)
- University of Michigan (US)
- University of Alabama at Birmingham (US)
- NYU Langone Health (US)
- Michigan Medicine (US)
- University Hospital Cologne (DE)
- The University of Texas at Austin (US)
Publication Details
- Journal
- Neurosurgery
- Published
- 2026-03-27
- DOI
- https://doi.org/10.1227/neu.0000000000004000
- Primary Topic
- Biomedical Text Mining and Ontologies
- Type
- article
- Field-Weighted Citation Impact
- 0.00