A Robust BERT-Based Deep Learning Model for Automated Cancer Type Extraction from Unstructured Pathology Reports

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tran, Minh, Chan, Jeffery C., Huang, Min Li, Kansara, Maya, Grady, John P., Napier, Christine E., Thavaneswaran, Subotheni, Ballinger, Mandy L., Thomas, David M., Lin, Frank P.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912546370355200
author Tran, Minh
Chan, Jeffery C.
Huang, Min Li
Kansara, Maya
Grady, John P.
Napier, Christine E.
Thavaneswaran, Subotheni
Ballinger, Mandy L.
Thomas, David M.
Lin, Frank P.
author_facet Tran, Minh
Chan, Jeffery C.
Huang, Min Li
Kansara, Maya
Grady, John P.
Napier, Christine E.
Thavaneswaran, Subotheni
Ballinger, Mandy L.
Thomas, David M.
Lin, Frank P.
contents The accurate extraction of clinical information from electronic medical records is particularly critical to clinical research but require much trained expertise and manual labor. In this study we developed a robust system for automated extraction of the specific cancer types for the purpose of supporting precision oncology research. from pathology reports using a fine-tuned RoBERTa model. This model significantly outperformed the baseline model and a Large Language Model, Mistral 7B, achieving F1_Bertscore 0.98 and overall exact match of 80.61%. This fine-tuning approach demonstrates the potential for scalability that can integrate seamlessly into the molecular tumour board process. Fine-tuning domain-specific models for precision tasks in oncology, may pave the way for more efficient and accurate clinical information extraction.
format Preprint
id arxiv_https___arxiv_org_abs_2508_15149
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Robust BERT-Based Deep Learning Model for Automated Cancer Type Extraction from Unstructured Pathology Reports
Tran, Minh
Chan, Jeffery C.
Huang, Min Li
Kansara, Maya
Grady, John P.
Napier, Christine E.
Thavaneswaran, Subotheni
Ballinger, Mandy L.
Thomas, David M.
Lin, Frank P.
Machine Learning
The accurate extraction of clinical information from electronic medical records is particularly critical to clinical research but require much trained expertise and manual labor. In this study we developed a robust system for automated extraction of the specific cancer types for the purpose of supporting precision oncology research. from pathology reports using a fine-tuned RoBERTa model. This model significantly outperformed the baseline model and a Large Language Model, Mistral 7B, achieving F1_Bertscore 0.98 and overall exact match of 80.61%. This fine-tuning approach demonstrates the potential for scalability that can integrate seamlessly into the molecular tumour board process. Fine-tuning domain-specific models for precision tasks in oncology, may pave the way for more efficient and accurate clinical information extraction.
title A Robust BERT-Based Deep Learning Model for Automated Cancer Type Extraction from Unstructured Pathology Reports
topic Machine Learning
url https://arxiv.org/abs/2508.15149