Cargando…

Artificial neural networks versus LASSO regression for the prediction of long-term survival after surgery for invasive IPMN of the pancreas

Prediction of long-term survival in patients with invasive intraductal papillary mucinous neoplasm (IPMN) of the pancreas may aid in patient assessment, risk stratification and personalization of treatment. This study aimed to investigate the predictive ability of artificial neural networks (ANN) an...

Descripción completa

Detalles Bibliográficos
Autores principales: Aronsson, Linus, Andersson, Roland, Ansari, Daniel
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7993879/
https://www.ncbi.nlm.nih.gov/pubmed/33765078
http://dx.doi.org/10.1371/journal.pone.0249206
_version_ 1783669646753267712
author Aronsson, Linus
Andersson, Roland
Ansari, Daniel
author_facet Aronsson, Linus
Andersson, Roland
Ansari, Daniel
author_sort Aronsson, Linus
collection PubMed
description Prediction of long-term survival in patients with invasive intraductal papillary mucinous neoplasm (IPMN) of the pancreas may aid in patient assessment, risk stratification and personalization of treatment. This study aimed to investigate the predictive ability of artificial neural networks (ANN) and LASSO regression in terms of 5-year disease-specific survival. ANN work in a non-linear fashion, having a potential advantage in analysis of variables with complex correlations compared to regression models. LASSO is a type of regression analysis facilitating variable selection and regularization. A total of 440 patients undergoing surgical treatment for invasive IPMN of the pancreas registered in the Surveillance, Epidemiology and End Results (SEER) database between 2004 and 2016 were analyzed. The dataset was prior to analysis randomly split into a modelling and test set (7:3). The accuracy, precision and F1 score for predicting mortality were 0.82, 0.83 and 0.89, respectively for ANN with variable selection compared to 0.79, 0.85 and 0.87, respectively for the LASSO-model. ANN using all variables showed similar accuracy, precision and F1 score of 0.81, 0.85 and 0.88, respectively compared to a logistic regression analysis. McNemar´s test showed no statistical difference between the models. The models showed high and similar performance with regard to accuracy and precision for predicting 5-year survival status.
format Online
Article
Text
id pubmed-7993879
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-79938792021-04-05 Artificial neural networks versus LASSO regression for the prediction of long-term survival after surgery for invasive IPMN of the pancreas Aronsson, Linus Andersson, Roland Ansari, Daniel PLoS One Research Article Prediction of long-term survival in patients with invasive intraductal papillary mucinous neoplasm (IPMN) of the pancreas may aid in patient assessment, risk stratification and personalization of treatment. This study aimed to investigate the predictive ability of artificial neural networks (ANN) and LASSO regression in terms of 5-year disease-specific survival. ANN work in a non-linear fashion, having a potential advantage in analysis of variables with complex correlations compared to regression models. LASSO is a type of regression analysis facilitating variable selection and regularization. A total of 440 patients undergoing surgical treatment for invasive IPMN of the pancreas registered in the Surveillance, Epidemiology and End Results (SEER) database between 2004 and 2016 were analyzed. The dataset was prior to analysis randomly split into a modelling and test set (7:3). The accuracy, precision and F1 score for predicting mortality were 0.82, 0.83 and 0.89, respectively for ANN with variable selection compared to 0.79, 0.85 and 0.87, respectively for the LASSO-model. ANN using all variables showed similar accuracy, precision and F1 score of 0.81, 0.85 and 0.88, respectively compared to a logistic regression analysis. McNemar´s test showed no statistical difference between the models. The models showed high and similar performance with regard to accuracy and precision for predicting 5-year survival status. Public Library of Science 2021-03-25 /pmc/articles/PMC7993879/ /pubmed/33765078 http://dx.doi.org/10.1371/journal.pone.0249206 Text en © 2021 Aronsson 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
Aronsson, Linus
Andersson, Roland
Ansari, Daniel
Artificial neural networks versus LASSO regression for the prediction of long-term survival after surgery for invasive IPMN of the pancreas
title Artificial neural networks versus LASSO regression for the prediction of long-term survival after surgery for invasive IPMN of the pancreas
title_full Artificial neural networks versus LASSO regression for the prediction of long-term survival after surgery for invasive IPMN of the pancreas
title_fullStr Artificial neural networks versus LASSO regression for the prediction of long-term survival after surgery for invasive IPMN of the pancreas
title_full_unstemmed Artificial neural networks versus LASSO regression for the prediction of long-term survival after surgery for invasive IPMN of the pancreas
title_short Artificial neural networks versus LASSO regression for the prediction of long-term survival after surgery for invasive IPMN of the pancreas
title_sort artificial neural networks versus lasso regression for the prediction of long-term survival after surgery for invasive ipmn of the pancreas
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7993879/
https://www.ncbi.nlm.nih.gov/pubmed/33765078
http://dx.doi.org/10.1371/journal.pone.0249206
work_keys_str_mv AT aronssonlinus artificialneuralnetworksversuslassoregressionforthepredictionoflongtermsurvivalaftersurgeryforinvasiveipmnofthepancreas
AT anderssonroland artificialneuralnetworksversuslassoregressionforthepredictionoflongtermsurvivalaftersurgeryforinvasiveipmnofthepancreas
AT ansaridaniel artificialneuralnetworksversuslassoregressionforthepredictionoflongtermsurvivalaftersurgeryforinvasiveipmnofthepancreas