Cargando…
Identification of Women with High Grade Histopathology Results after Conisation by Artificial Neural Networks
BACKGROUND: The aim of the study was to evaluate if artificial neural networks can predict high-grade histopathology results after conisation from risk factors and their combinations in patients undergoing conisation because of pathological changes on uterine cervix. PATIENTS AND METHODS: We analyse...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Sciendo
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9400436/ https://www.ncbi.nlm.nih.gov/pubmed/35776841 http://dx.doi.org/10.2478/raon-2022-0023 |
_version_ | 1784772741699731456 |
---|---|
author | Mlinaric, Marko Krizmaric, Miljenko Takac, Iztok Repse Fokter, Alenka |
author_facet | Mlinaric, Marko Krizmaric, Miljenko Takac, Iztok Repse Fokter, Alenka |
author_sort | Mlinaric, Marko |
collection | PubMed |
description | BACKGROUND: The aim of the study was to evaluate if artificial neural networks can predict high-grade histopathology results after conisation from risk factors and their combinations in patients undergoing conisation because of pathological changes on uterine cervix. PATIENTS AND METHODS: We analysed 1475 patients who had conisation surgery at the University Clinic for Gynaecology and Obstetrics of University Clinical Centre Maribor from 1993–2005. The database in different datasets was arranged to deal with unbalance data and enhance classification performance. Weka open-source software was used for analysis with artificial neural networks. Last Papanicolaou smear (PAP) and risk factors for development of cervical dysplasia and carcinoma were used as input and high-grade dysplasia Yes/No as output result. 10-fold cross validation was used for defining training and holdout set for analysis. RESULTS: Bas eline classification and multiple runs of artificial neural network on various risk factors settings were performed. We achieved 84.19% correct classifications, area under the curve 0.87, kappa 0.64, F-measure 0.884 and Matthews correlation coefficient (MCC) 0.640 in model, where baseline prediction was 69.79%. CONCLUSIONS: With artificial neural networks we were able to identify more patients who developed high-grade squamous intraepithelial lesion on final histopathology result of conisation as with baseline prediction. But, characteristics of 1475 patients who had conisation in years 1993–2005 at the University Clinical Centre Maribor did not allow reliable prediction with artificial neural networks for every-day clinical practice. |
format | Online Article Text |
id | pubmed-9400436 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Sciendo |
record_format | MEDLINE/PubMed |
spelling | pubmed-94004362022-09-07 Identification of Women with High Grade Histopathology Results after Conisation by Artificial Neural Networks Mlinaric, Marko Krizmaric, Miljenko Takac, Iztok Repse Fokter, Alenka Radiol Oncol Research Article BACKGROUND: The aim of the study was to evaluate if artificial neural networks can predict high-grade histopathology results after conisation from risk factors and their combinations in patients undergoing conisation because of pathological changes on uterine cervix. PATIENTS AND METHODS: We analysed 1475 patients who had conisation surgery at the University Clinic for Gynaecology and Obstetrics of University Clinical Centre Maribor from 1993–2005. The database in different datasets was arranged to deal with unbalance data and enhance classification performance. Weka open-source software was used for analysis with artificial neural networks. Last Papanicolaou smear (PAP) and risk factors for development of cervical dysplasia and carcinoma were used as input and high-grade dysplasia Yes/No as output result. 10-fold cross validation was used for defining training and holdout set for analysis. RESULTS: Bas eline classification and multiple runs of artificial neural network on various risk factors settings were performed. We achieved 84.19% correct classifications, area under the curve 0.87, kappa 0.64, F-measure 0.884 and Matthews correlation coefficient (MCC) 0.640 in model, where baseline prediction was 69.79%. CONCLUSIONS: With artificial neural networks we were able to identify more patients who developed high-grade squamous intraepithelial lesion on final histopathology result of conisation as with baseline prediction. But, characteristics of 1475 patients who had conisation in years 1993–2005 at the University Clinical Centre Maribor did not allow reliable prediction with artificial neural networks for every-day clinical practice. Sciendo 2022-08-14 /pmc/articles/PMC9400436/ /pubmed/35776841 http://dx.doi.org/10.2478/raon-2022-0023 Text en © 2022 Marko Mlinaric, Miljenko Krizmaric, Iztok Takac, Alenka Repse Fokter, published by Sciendo https://creativecommons.org/licenses/by-nc-nd/4.0/This work is licensed under the Creative Commons Attribution 4.0 International License. |
spellingShingle | Research Article Mlinaric, Marko Krizmaric, Miljenko Takac, Iztok Repse Fokter, Alenka Identification of Women with High Grade Histopathology Results after Conisation by Artificial Neural Networks |
title | Identification of Women with High Grade Histopathology Results after Conisation by Artificial Neural Networks |
title_full | Identification of Women with High Grade Histopathology Results after Conisation by Artificial Neural Networks |
title_fullStr | Identification of Women with High Grade Histopathology Results after Conisation by Artificial Neural Networks |
title_full_unstemmed | Identification of Women with High Grade Histopathology Results after Conisation by Artificial Neural Networks |
title_short | Identification of Women with High Grade Histopathology Results after Conisation by Artificial Neural Networks |
title_sort | identification of women with high grade histopathology results after conisation by artificial neural networks |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9400436/ https://www.ncbi.nlm.nih.gov/pubmed/35776841 http://dx.doi.org/10.2478/raon-2022-0023 |
work_keys_str_mv | AT mlinaricmarko identificationofwomenwithhighgradehistopathologyresultsafterconisationbyartificialneuralnetworks AT krizmaricmiljenko identificationofwomenwithhighgradehistopathologyresultsafterconisationbyartificialneuralnetworks AT takaciztok identificationofwomenwithhighgradehistopathologyresultsafterconisationbyartificialneuralnetworks AT repsefokteralenka identificationofwomenwithhighgradehistopathologyresultsafterconisationbyartificialneuralnetworks |