Cargando…

Validation and Improvement of a Convolutional Neural Network to Predict the Involved Pathology in a Head and Neck Surgery Cohort

The selection of patients for the constitution of a cohort is a major issue for clinical research (prospective studies and retrospective studies in real life). Our objective was to validate in real life conditions the use of a Deep Learning process based on a neural network, for the classification o...

Descripción completa

Detalles Bibliográficos
Autores principales: Culié, Dorian, Schiappa, Renaud, Contu, Sara, Scheller, Boris, Villarme, Agathe, Dassonville, Olivier, Poissonnet, Gilles, Bozec, Alexandre, Chamorey, Emmanuel
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9564535/
https://www.ncbi.nlm.nih.gov/pubmed/36231500
http://dx.doi.org/10.3390/ijerph191912200
_version_ 1784808668898787328
author Culié, Dorian
Schiappa, Renaud
Contu, Sara
Scheller, Boris
Villarme, Agathe
Dassonville, Olivier
Poissonnet, Gilles
Bozec, Alexandre
Chamorey, Emmanuel
author_facet Culié, Dorian
Schiappa, Renaud
Contu, Sara
Scheller, Boris
Villarme, Agathe
Dassonville, Olivier
Poissonnet, Gilles
Bozec, Alexandre
Chamorey, Emmanuel
author_sort Culié, Dorian
collection PubMed
description The selection of patients for the constitution of a cohort is a major issue for clinical research (prospective studies and retrospective studies in real life). Our objective was to validate in real life conditions the use of a Deep Learning process based on a neural network, for the classification of patients according to the pathology involved in a head and neck surgery department. 24,434 Electronic Health Records (EHR) from the first visit between 2000 and 2020 were extracted. More than 6000 EHR were manually classified in ten groups of interest according to the reason for consultation with a clinical relevance. A convolutional neural network (TensorFlow, previously reported by Hsu et al.) was then used to predict the group of patients based on their pathology, using two levels of classification based on clinically relevant criteria. On the first and second level of classification, macro-average performances were: 0.95, 0.83, 0.85, 0.97, 0.84 and 0.93, 0.76, 0.83, 0.96, 0.79 for accuracy, recall, precision, specificity and F1-score versus accuracy, recall and precision of 0.580, 580 and 0.582 for Hsu et al., respectively. We validated this model to predict the pathology involved and to constitute clinically relevant cohorts in a tertiary hospital. This model did not require a preprocessing stage, was used in French and showed equivalent or better performances than other already published techniques.
format Online
Article
Text
id pubmed-9564535
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-95645352022-10-15 Validation and Improvement of a Convolutional Neural Network to Predict the Involved Pathology in a Head and Neck Surgery Cohort Culié, Dorian Schiappa, Renaud Contu, Sara Scheller, Boris Villarme, Agathe Dassonville, Olivier Poissonnet, Gilles Bozec, Alexandre Chamorey, Emmanuel Int J Environ Res Public Health Article The selection of patients for the constitution of a cohort is a major issue for clinical research (prospective studies and retrospective studies in real life). Our objective was to validate in real life conditions the use of a Deep Learning process based on a neural network, for the classification of patients according to the pathology involved in a head and neck surgery department. 24,434 Electronic Health Records (EHR) from the first visit between 2000 and 2020 were extracted. More than 6000 EHR were manually classified in ten groups of interest according to the reason for consultation with a clinical relevance. A convolutional neural network (TensorFlow, previously reported by Hsu et al.) was then used to predict the group of patients based on their pathology, using two levels of classification based on clinically relevant criteria. On the first and second level of classification, macro-average performances were: 0.95, 0.83, 0.85, 0.97, 0.84 and 0.93, 0.76, 0.83, 0.96, 0.79 for accuracy, recall, precision, specificity and F1-score versus accuracy, recall and precision of 0.580, 580 and 0.582 for Hsu et al., respectively. We validated this model to predict the pathology involved and to constitute clinically relevant cohorts in a tertiary hospital. This model did not require a preprocessing stage, was used in French and showed equivalent or better performances than other already published techniques. MDPI 2022-09-26 /pmc/articles/PMC9564535/ /pubmed/36231500 http://dx.doi.org/10.3390/ijerph191912200 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Culié, Dorian
Schiappa, Renaud
Contu, Sara
Scheller, Boris
Villarme, Agathe
Dassonville, Olivier
Poissonnet, Gilles
Bozec, Alexandre
Chamorey, Emmanuel
Validation and Improvement of a Convolutional Neural Network to Predict the Involved Pathology in a Head and Neck Surgery Cohort
title Validation and Improvement of a Convolutional Neural Network to Predict the Involved Pathology in a Head and Neck Surgery Cohort
title_full Validation and Improvement of a Convolutional Neural Network to Predict the Involved Pathology in a Head and Neck Surgery Cohort
title_fullStr Validation and Improvement of a Convolutional Neural Network to Predict the Involved Pathology in a Head and Neck Surgery Cohort
title_full_unstemmed Validation and Improvement of a Convolutional Neural Network to Predict the Involved Pathology in a Head and Neck Surgery Cohort
title_short Validation and Improvement of a Convolutional Neural Network to Predict the Involved Pathology in a Head and Neck Surgery Cohort
title_sort validation and improvement of a convolutional neural network to predict the involved pathology in a head and neck surgery cohort
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9564535/
https://www.ncbi.nlm.nih.gov/pubmed/36231500
http://dx.doi.org/10.3390/ijerph191912200
work_keys_str_mv AT culiedorian validationandimprovementofaconvolutionalneuralnetworktopredicttheinvolvedpathologyinaheadandnecksurgerycohort
AT schiapparenaud validationandimprovementofaconvolutionalneuralnetworktopredicttheinvolvedpathologyinaheadandnecksurgerycohort
AT contusara validationandimprovementofaconvolutionalneuralnetworktopredicttheinvolvedpathologyinaheadandnecksurgerycohort
AT schellerboris validationandimprovementofaconvolutionalneuralnetworktopredicttheinvolvedpathologyinaheadandnecksurgerycohort
AT villarmeagathe validationandimprovementofaconvolutionalneuralnetworktopredicttheinvolvedpathologyinaheadandnecksurgerycohort
AT dassonvilleolivier validationandimprovementofaconvolutionalneuralnetworktopredicttheinvolvedpathologyinaheadandnecksurgerycohort
AT poissonnetgilles validationandimprovementofaconvolutionalneuralnetworktopredicttheinvolvedpathologyinaheadandnecksurgerycohort
AT bozecalexandre validationandimprovementofaconvolutionalneuralnetworktopredicttheinvolvedpathologyinaheadandnecksurgerycohort
AT chamoreyemmanuel validationandimprovementofaconvolutionalneuralnetworktopredicttheinvolvedpathologyinaheadandnecksurgerycohort