No Cover Image

Journal article 37 views

Development and validation of an automated basal cell carcinoma histopathology information extraction system using natural language processing

Stephen Ali, Huw Strafford, Thomas Dobbs, Beata Fonferko-Shadrach, Arron Lacey, Owen Pickrell Orcid Logo, Hayley Hutchings Orcid Logo, Iain Whitaker

Frontiers in Surgery

Swansea University Authors: Stephen Ali, Huw Strafford, Thomas Dobbs, Beata Fonferko-Shadrach, Arron Lacey, Owen Pickrell Orcid Logo, Hayley Hutchings Orcid Logo, Iain Whitaker

Full text not available from this repository: check for access using links below.

DOI (Published version): 10.3389/fsurg.2022.870494

Abstract

IntroductionRoutinely collected healthcare data are a powerful research resource, but often lack detailed disease-specific information that is collected in clinical free text such as histopathology reports. We aim to use Natural Language Processing (NLP) techniques to extract detailed clinical and p...

Full description

Published in: Frontiers in Surgery
Published:
Online Access: https://www.frontiersin.org/articles/10.3389/fsurg.2022.870494/abstract
URI: https://cronfa.swan.ac.uk/Record/cronfa60444
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: IntroductionRoutinely collected healthcare data are a powerful research resource, but often lack detailed disease-specific information that is collected in clinical free text such as histopathology reports. We aim to use Natural Language Processing (NLP) techniques to extract detailed clinical and pathological information from histopathology reports to enrich routinely collected data.MethodsWe used the general architecture for text engineering (GATE) framework to build an NLP information extraction system using rule-based techniques. During validation we deployed our rule-based NLP pipeline on 200 previously unseen, de-identified and pseudonymised BCC histopathological reports from Swansea Bay University Health Board, Wales, UK. Results of our algorithm were compared to gold standard human abstraction by two independent and blinded expert clinicians involved in skin cancer care.ResultsWe identified 11,224 items of information with a mean precision, recall and F1 score of 86.0% (95% CI 75.1-96.9), 84.2% (95% CI 72.8-96.1) and 84.5% (95% CI 73.0-95.1) respectively. The difference between clinician annotator F1 scores was 7.9% in comparison to 15.5% between the NLP pipeline and the gold standard corpus. Cohen's Kappa score on annotated tokens was 0.85.ConclusionUsing an NLP rule-based approach for NER in BCC we have been able to develop and validate a pipeline with a potential application in improving cancer registry data, service planning and enhancing the quality of routinely collected data for research.
College: Swansea University Medical School