Cargando…

Classification of cervical biopsy free-text diagnoses through linear-classifier based natural language processing

Routine cervical cancer screening has significantly decreased the incidence and mortality of cervical cancer. As selection of proper screening modalities depends on well-validated clinical decision algorithms, retrospective review correlating cytology and HPV test results with cervical biopsy diagno...

Descripción completa

Detalles Bibliográficos
Autores principales: Hsu, Jim Wei-Chun, Christensen, Paul, Ge, Yimin, Long, S. Wesley
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9577054/
https://www.ncbi.nlm.nih.gov/pubmed/36268101
http://dx.doi.org/10.1016/j.jpi.2022.100123
_version_ 1784811670818783232
author Hsu, Jim Wei-Chun
Christensen, Paul
Ge, Yimin
Long, S. Wesley
author_facet Hsu, Jim Wei-Chun
Christensen, Paul
Ge, Yimin
Long, S. Wesley
author_sort Hsu, Jim Wei-Chun
collection PubMed
description Routine cervical cancer screening has significantly decreased the incidence and mortality of cervical cancer. As selection of proper screening modalities depends on well-validated clinical decision algorithms, retrospective review correlating cytology and HPV test results with cervical biopsy diagnosis is essential for validating and revising these algorithms to changing technologies, demographics, and optimal clinical practices. However, manual categorization of the free-text biopsy diagnosis into discrete categories is extremely laborious due to the overwhelming number of specimens, which may lead to significant error and bias. Advances in machine learning and natural language processing (NLP), particularly over the last decade, have led to significant accomplishments and impressive performance in computer-based classification tasks. In this work, we apply an efficient version of an NLP framework, FastText™, to an annotated cervical biopsy dataset to create a supervised classifier that can assign accurate biopsy categories to free-text biopsy interpretations with high concordance to manually annotated data (>99.6%). We present cases where the machine-learning classifier disagrees with previous annotations and examine these discrepant cases after referee review by an expert pathologist. We also show that the classifier is robust on an untrained external dataset, achieving a concordance of 97.7%. In conclusion, we demonstrate a useful application of NLP to a real-world pathology classification task and highlight the benefits and limitations of this approach.
format Online
Article
Text
id pubmed-9577054
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-95770542022-10-19 Classification of cervical biopsy free-text diagnoses through linear-classifier based natural language processing Hsu, Jim Wei-Chun Christensen, Paul Ge, Yimin Long, S. Wesley J Pathol Inform Original Research Article Routine cervical cancer screening has significantly decreased the incidence and mortality of cervical cancer. As selection of proper screening modalities depends on well-validated clinical decision algorithms, retrospective review correlating cytology and HPV test results with cervical biopsy diagnosis is essential for validating and revising these algorithms to changing technologies, demographics, and optimal clinical practices. However, manual categorization of the free-text biopsy diagnosis into discrete categories is extremely laborious due to the overwhelming number of specimens, which may lead to significant error and bias. Advances in machine learning and natural language processing (NLP), particularly over the last decade, have led to significant accomplishments and impressive performance in computer-based classification tasks. In this work, we apply an efficient version of an NLP framework, FastText™, to an annotated cervical biopsy dataset to create a supervised classifier that can assign accurate biopsy categories to free-text biopsy interpretations with high concordance to manually annotated data (>99.6%). We present cases where the machine-learning classifier disagrees with previous annotations and examine these discrepant cases after referee review by an expert pathologist. We also show that the classifier is robust on an untrained external dataset, achieving a concordance of 97.7%. In conclusion, we demonstrate a useful application of NLP to a real-world pathology classification task and highlight the benefits and limitations of this approach. Elsevier 2022-07-01 /pmc/articles/PMC9577054/ /pubmed/36268101 http://dx.doi.org/10.1016/j.jpi.2022.100123 Text en © 2022 The Authors. Published by Elsevier Inc. on behalf of Association for Pathology Informatics. https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Original Research Article
Hsu, Jim Wei-Chun
Christensen, Paul
Ge, Yimin
Long, S. Wesley
Classification of cervical biopsy free-text diagnoses through linear-classifier based natural language processing
title Classification of cervical biopsy free-text diagnoses through linear-classifier based natural language processing
title_full Classification of cervical biopsy free-text diagnoses through linear-classifier based natural language processing
title_fullStr Classification of cervical biopsy free-text diagnoses through linear-classifier based natural language processing
title_full_unstemmed Classification of cervical biopsy free-text diagnoses through linear-classifier based natural language processing
title_short Classification of cervical biopsy free-text diagnoses through linear-classifier based natural language processing
title_sort classification of cervical biopsy free-text diagnoses through linear-classifier based natural language processing
topic Original Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9577054/
https://www.ncbi.nlm.nih.gov/pubmed/36268101
http://dx.doi.org/10.1016/j.jpi.2022.100123
work_keys_str_mv AT hsujimweichun classificationofcervicalbiopsyfreetextdiagnosesthroughlinearclassifierbasednaturallanguageprocessing
AT christensenpaul classificationofcervicalbiopsyfreetextdiagnosesthroughlinearclassifierbasednaturallanguageprocessing
AT geyimin classificationofcervicalbiopsyfreetextdiagnosesthroughlinearclassifierbasednaturallanguageprocessing
AT longswesley classificationofcervicalbiopsyfreetextdiagnosesthroughlinearclassifierbasednaturallanguageprocessing