EUVIMEDEUVIMED entdecken
Open Access

Path-BigBird: An AI-Driven Transformer Approach to Classification of Cancer Pathology Reports

Mayanka Chandrashekar iD, Isaac Lyngaas iD, Heidi A Hanson, Shang Gao iD, Xiao-Cheng Wu iD, John Gounley

JCO Clinical Cancer Informatics · 2024

DOI: 10.1200/cci.23.00148 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JCO Clinical Cancer Informatics, 2024. Verfasst von Mayanka Chandrashekar und 5 weiteren Autor:innen. Beteiligte Einrichtung: Advanced Computing for Health Sciences Section, Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN. Hauptthemen laut MEDLINE: Neoplasms. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 14 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCI NIH HHS, NCCDPHP CDC HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE Surgical pathology reports are critical for cancer diagnosis and management. To accurately extract information about tumor characteristics from pathology reports in near real time, we explore the impact of using domain-specific transformer models that understand cancer pathology reports. METHODS We built a pathology transformer model, Path-BigBird, by using 2.7 million pathology reports from six SEER cancer registries. We then compare different variations of Path-BigBird with two less computationally intensive methods: Hierarchical Self-Attention Network (HiSAN) classification model and an off-the-shelf clinical transformer model (Clinical BigBird). We use five pathology information extraction tasks for evaluation: site, subsite, laterality, histology, and behavior. Model performance is evaluated by using macro and micro F 1 scores. RESULTS We found that Path-BigBird and Clinical BigBird outperformed the HiSAN in all tasks. Clinical BigBird performed better on the site and laterality tasks. Versions of the Path-BigBird model performed best on the two most difficult tasks: subsite (micro F 1 score of 72.53, macro F 1 score of 35.76) and histology (micro F 1 score of 80.96, macro F 1 score of 37.94). The largest performance gains over the HiSAN model were for histology, for which a Path-BigBird model increased the micro F 1 score by 1.44 points and the macro F 1 score by 3.55 points. Overall, the results suggest that a Path-BigBird model with a vocabulary derived from well-curated and deidentified data is the best-performing model. CONCLUSION The Path-BigBird pathology transformer model improves automated information extraction from pathology reports. Although Path-BigBird outperforms Clinical BigBird and HiSAN, these less computationally expensive models still have utility when resources are constrained.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

NeoplasmsHumansInformation Storage and RetrievalRegistriesArtificial Intelligence

Autor:innen und Institutionen

  • Advanced Computing for Health Sciences Section, Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN.
  • Advanced Computing for Life Science & Engineering, National Center for Computational Sciences, Oak Ridge National Laboratory, Oak Ridge, TN.
  • Louisiana Tumor Registry, School of Public Health, Louisiana State University Health Sciences Center, New Orleans, LA.
  • Department of Epidemiology, School of Public Health, Louisiana State University Health Sciences Center, New Orleans, LA.

ORCID-Profile: Mayanka Chandrashekar, Isaac Lyngaas, Shang Gao, Xiao-Cheng Wu

Förderung

  • NCI NIH HHS
  • NCCDPHP CDC HHS

Zitieren

APA

Chandrashekar, M., Lyngaas, I., Hanson, H. A., Gao, S., Wu, X. C., & Gounley, J. (2024). Path-BigBird: An AI-Driven Transformer Approach to Classification of Cancer Pathology Reports. JCO Clinical Cancer Informatics. https://doi.org/10.1200/cci.23.00148

Vancouver

Chandrashekar M, Lyngaas I, Hanson HA, Gao S, Wu XC, Gounley J. Path-BigBird: An AI-Driven Transformer Approach to Classification of Cancer Pathology Reports. JCO Clinical Cancer Informatics. 2024. doi:10.1200/cci.23.00148

BibTeX
@article{Chandrashekar2024,
  author = {Chandrashekar, Mayanka and Lyngaas, Isaac and Hanson, Heidi A and Gao, Shang and Wu, Xiao-Cheng and Gounley, John},
  title = {Path-BigBird: An AI-Driven Transformer Approach to Classification of Cancer Pathology Reports},
  journal = {JCO Clinical Cancer Informatics},
  year = {2024},
  doi = {10.1200/cci.23.00148}
}
Kostenlos starten →