Cargando…
Extraction of radiographic findings from unstructured thoracoabdominal computed tomography reports using convolutional neural network based natural language processing
BACKGROUND: Heart failure (HF) is a major cause of morbidity and mortality. However, much of the clinical data is unstructured in the form of radiology reports, while the process of data collection and curation is arduous and time-consuming. PURPOSE: We utilized a machine learning (ML)-based natural...
Autores principales: | , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7392233/ https://www.ncbi.nlm.nih.gov/pubmed/32730362 http://dx.doi.org/10.1371/journal.pone.0236827 |
_version_ | 1783564805463867392 |
---|---|
author | Pandey, Mohit Xu, Zhuoran Sholle, Evan Maliakal, Gabriel Singh, Gurpreet Fatima, Zahra Larine, Daria Lee, Benjamin C. Wang, Jing van Rosendael, Alexander R. Baskaran, Lohendran Shaw, Leslee J. Min, James K. Al’Aref, Subhi J. |
author_facet | Pandey, Mohit Xu, Zhuoran Sholle, Evan Maliakal, Gabriel Singh, Gurpreet Fatima, Zahra Larine, Daria Lee, Benjamin C. Wang, Jing van Rosendael, Alexander R. Baskaran, Lohendran Shaw, Leslee J. Min, James K. Al’Aref, Subhi J. |
author_sort | Pandey, Mohit |
collection | PubMed |
description | BACKGROUND: Heart failure (HF) is a major cause of morbidity and mortality. However, much of the clinical data is unstructured in the form of radiology reports, while the process of data collection and curation is arduous and time-consuming. PURPOSE: We utilized a machine learning (ML)-based natural language processing (NLP) approach to extract clinical terms from unstructured radiology reports. Additionally, we investigate the prognostic value of the extracted data in predicting all-cause mortality (ACM) in HF patients. MATERIALS AND METHODS: This observational cohort study utilized 122,025 thoracoabdominal computed tomography (CT) reports from 11,808 HF patients obtained between 2008 and 2018. 1,560 CT reports were manually annotated for the presence or absence of 14 radiographic findings, in addition to age and gender. Thereafter, a Convolutional Neural Network (CNN) was trained, validated and tested to determine the presence or absence of these features. Further, the ability of CNN to predict ACM was evaluated using Cox regression analysis on the extracted features. RESULTS: 11,808 CT reports were analyzed from 11,808 patients (mean age 72.8 ± 14.8 years; 52.7% (6,217/11,808) male) from whom 3,107 died during the 10.6-year follow-up. The CNN demonstrated excellent accuracy for retrieval of the 14 radiographic findings with area-under-the-curve (AUC) ranging between 0.83–1.00 (F1 score 0.84–0.97). Cox model showed the time-dependent AUC for predicting ACM was 0.747 (95% confidence interval [CI] of 0.704–0.790) at 30 days. CONCLUSION: An ML-based NLP approach to unstructured CT reports demonstrates excellent accuracy for the extraction of predetermined radiographic findings, and provides prognostic value in HF patients. |
format | Online Article Text |
id | pubmed-7392233 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-73922332020-08-05 Extraction of radiographic findings from unstructured thoracoabdominal computed tomography reports using convolutional neural network based natural language processing Pandey, Mohit Xu, Zhuoran Sholle, Evan Maliakal, Gabriel Singh, Gurpreet Fatima, Zahra Larine, Daria Lee, Benjamin C. Wang, Jing van Rosendael, Alexander R. Baskaran, Lohendran Shaw, Leslee J. Min, James K. Al’Aref, Subhi J. PLoS One Research Article BACKGROUND: Heart failure (HF) is a major cause of morbidity and mortality. However, much of the clinical data is unstructured in the form of radiology reports, while the process of data collection and curation is arduous and time-consuming. PURPOSE: We utilized a machine learning (ML)-based natural language processing (NLP) approach to extract clinical terms from unstructured radiology reports. Additionally, we investigate the prognostic value of the extracted data in predicting all-cause mortality (ACM) in HF patients. MATERIALS AND METHODS: This observational cohort study utilized 122,025 thoracoabdominal computed tomography (CT) reports from 11,808 HF patients obtained between 2008 and 2018. 1,560 CT reports were manually annotated for the presence or absence of 14 radiographic findings, in addition to age and gender. Thereafter, a Convolutional Neural Network (CNN) was trained, validated and tested to determine the presence or absence of these features. Further, the ability of CNN to predict ACM was evaluated using Cox regression analysis on the extracted features. RESULTS: 11,808 CT reports were analyzed from 11,808 patients (mean age 72.8 ± 14.8 years; 52.7% (6,217/11,808) male) from whom 3,107 died during the 10.6-year follow-up. The CNN demonstrated excellent accuracy for retrieval of the 14 radiographic findings with area-under-the-curve (AUC) ranging between 0.83–1.00 (F1 score 0.84–0.97). Cox model showed the time-dependent AUC for predicting ACM was 0.747 (95% confidence interval [CI] of 0.704–0.790) at 30 days. CONCLUSION: An ML-based NLP approach to unstructured CT reports demonstrates excellent accuracy for the extraction of predetermined radiographic findings, and provides prognostic value in HF patients. Public Library of Science 2020-07-30 /pmc/articles/PMC7392233/ /pubmed/32730362 http://dx.doi.org/10.1371/journal.pone.0236827 Text en © 2020 Pandey et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Pandey, Mohit Xu, Zhuoran Sholle, Evan Maliakal, Gabriel Singh, Gurpreet Fatima, Zahra Larine, Daria Lee, Benjamin C. Wang, Jing van Rosendael, Alexander R. Baskaran, Lohendran Shaw, Leslee J. Min, James K. Al’Aref, Subhi J. Extraction of radiographic findings from unstructured thoracoabdominal computed tomography reports using convolutional neural network based natural language processing |
title | Extraction of radiographic findings from unstructured thoracoabdominal computed tomography reports using convolutional neural network based natural language processing |
title_full | Extraction of radiographic findings from unstructured thoracoabdominal computed tomography reports using convolutional neural network based natural language processing |
title_fullStr | Extraction of radiographic findings from unstructured thoracoabdominal computed tomography reports using convolutional neural network based natural language processing |
title_full_unstemmed | Extraction of radiographic findings from unstructured thoracoabdominal computed tomography reports using convolutional neural network based natural language processing |
title_short | Extraction of radiographic findings from unstructured thoracoabdominal computed tomography reports using convolutional neural network based natural language processing |
title_sort | extraction of radiographic findings from unstructured thoracoabdominal computed tomography reports using convolutional neural network based natural language processing |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7392233/ https://www.ncbi.nlm.nih.gov/pubmed/32730362 http://dx.doi.org/10.1371/journal.pone.0236827 |
work_keys_str_mv | AT pandeymohit extractionofradiographicfindingsfromunstructuredthoracoabdominalcomputedtomographyreportsusingconvolutionalneuralnetworkbasednaturallanguageprocessing AT xuzhuoran extractionofradiographicfindingsfromunstructuredthoracoabdominalcomputedtomographyreportsusingconvolutionalneuralnetworkbasednaturallanguageprocessing AT sholleevan extractionofradiographicfindingsfromunstructuredthoracoabdominalcomputedtomographyreportsusingconvolutionalneuralnetworkbasednaturallanguageprocessing AT maliakalgabriel extractionofradiographicfindingsfromunstructuredthoracoabdominalcomputedtomographyreportsusingconvolutionalneuralnetworkbasednaturallanguageprocessing AT singhgurpreet extractionofradiographicfindingsfromunstructuredthoracoabdominalcomputedtomographyreportsusingconvolutionalneuralnetworkbasednaturallanguageprocessing AT fatimazahra extractionofradiographicfindingsfromunstructuredthoracoabdominalcomputedtomographyreportsusingconvolutionalneuralnetworkbasednaturallanguageprocessing AT larinedaria extractionofradiographicfindingsfromunstructuredthoracoabdominalcomputedtomographyreportsusingconvolutionalneuralnetworkbasednaturallanguageprocessing AT leebenjaminc extractionofradiographicfindingsfromunstructuredthoracoabdominalcomputedtomographyreportsusingconvolutionalneuralnetworkbasednaturallanguageprocessing AT wangjing extractionofradiographicfindingsfromunstructuredthoracoabdominalcomputedtomographyreportsusingconvolutionalneuralnetworkbasednaturallanguageprocessing AT vanrosendaelalexanderr extractionofradiographicfindingsfromunstructuredthoracoabdominalcomputedtomographyreportsusingconvolutionalneuralnetworkbasednaturallanguageprocessing AT baskaranlohendran extractionofradiographicfindingsfromunstructuredthoracoabdominalcomputedtomographyreportsusingconvolutionalneuralnetworkbasednaturallanguageprocessing AT shawlesleej extractionofradiographicfindingsfromunstructuredthoracoabdominalcomputedtomographyreportsusingconvolutionalneuralnetworkbasednaturallanguageprocessing AT minjamesk extractionofradiographicfindingsfromunstructuredthoracoabdominalcomputedtomographyreportsusingconvolutionalneuralnetworkbasednaturallanguageprocessing AT alarefsubhij extractionofradiographicfindingsfromunstructuredthoracoabdominalcomputedtomographyreportsusingconvolutionalneuralnetworkbasednaturallanguageprocessing |