Cargando…
Survival Prediction in Intrahepatic Cholangiocarcinoma: A Proof of Concept Study Using Artificial Intelligence for Risk Assessment
Several scoring systems have been devised to objectively predict survival for patients with intrahepatic cholangiocellular carcinoma (ICC) and support treatment stratification, but they have failed external validation. The aim of the present study was to improve prognostication using an artificial i...
Autores principales: | , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8150393/ https://www.ncbi.nlm.nih.gov/pubmed/34066001 http://dx.doi.org/10.3390/jcm10102071 |
_version_ | 1783698141420191744 |
---|---|
author | Müller, Lukas Mähringer-Kunz, Aline Gairing, Simon Johannes Foerster, Friedrich Weinmann, Arndt Bartsch, Fabian Heuft, Lisa-Katharina Baumgart, Janine Düber, Christoph Hahn, Felix Kloeckner, Roman |
author_facet | Müller, Lukas Mähringer-Kunz, Aline Gairing, Simon Johannes Foerster, Friedrich Weinmann, Arndt Bartsch, Fabian Heuft, Lisa-Katharina Baumgart, Janine Düber, Christoph Hahn, Felix Kloeckner, Roman |
author_sort | Müller, Lukas |
collection | PubMed |
description | Several scoring systems have been devised to objectively predict survival for patients with intrahepatic cholangiocellular carcinoma (ICC) and support treatment stratification, but they have failed external validation. The aim of the present study was to improve prognostication using an artificial intelligence-based approach. We retrospectively identified 417 patients with ICC who were referred to our tertiary care center between 1997 and 2018. Of these, 293 met the inclusion criteria. Established risk factors served as input nodes for an artificial neural network (ANN). We compared the performance of the trained model to the most widely used conventional scoring system, the Fudan score. Predicting 1-year survival, the ANN reached an area under the ROC curve (AUC) of 0.89 for the training set and 0.80 for the validation set. The AUC of the Fudan score was significantly lower in the validation set (0.77, p < 0.001). In the training set, the Fudan score yielded a lower AUC (0.74) without reaching significance (p = 0.24). Thus, ANNs incorporating a multitude of known risk factors can outperform conventional risk scores, which typically consist of a limited number of parameters. In the future, such artificial intelligence-based approaches have the potential to improve treatment stratification when models trained on large multicenter data are openly available. |
format | Online Article Text |
id | pubmed-8150393 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-81503932021-05-27 Survival Prediction in Intrahepatic Cholangiocarcinoma: A Proof of Concept Study Using Artificial Intelligence for Risk Assessment Müller, Lukas Mähringer-Kunz, Aline Gairing, Simon Johannes Foerster, Friedrich Weinmann, Arndt Bartsch, Fabian Heuft, Lisa-Katharina Baumgart, Janine Düber, Christoph Hahn, Felix Kloeckner, Roman J Clin Med Article Several scoring systems have been devised to objectively predict survival for patients with intrahepatic cholangiocellular carcinoma (ICC) and support treatment stratification, but they have failed external validation. The aim of the present study was to improve prognostication using an artificial intelligence-based approach. We retrospectively identified 417 patients with ICC who were referred to our tertiary care center between 1997 and 2018. Of these, 293 met the inclusion criteria. Established risk factors served as input nodes for an artificial neural network (ANN). We compared the performance of the trained model to the most widely used conventional scoring system, the Fudan score. Predicting 1-year survival, the ANN reached an area under the ROC curve (AUC) of 0.89 for the training set and 0.80 for the validation set. The AUC of the Fudan score was significantly lower in the validation set (0.77, p < 0.001). In the training set, the Fudan score yielded a lower AUC (0.74) without reaching significance (p = 0.24). Thus, ANNs incorporating a multitude of known risk factors can outperform conventional risk scores, which typically consist of a limited number of parameters. In the future, such artificial intelligence-based approaches have the potential to improve treatment stratification when models trained on large multicenter data are openly available. MDPI 2021-05-12 /pmc/articles/PMC8150393/ /pubmed/34066001 http://dx.doi.org/10.3390/jcm10102071 Text en © 2021 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 Müller, Lukas Mähringer-Kunz, Aline Gairing, Simon Johannes Foerster, Friedrich Weinmann, Arndt Bartsch, Fabian Heuft, Lisa-Katharina Baumgart, Janine Düber, Christoph Hahn, Felix Kloeckner, Roman Survival Prediction in Intrahepatic Cholangiocarcinoma: A Proof of Concept Study Using Artificial Intelligence for Risk Assessment |
title | Survival Prediction in Intrahepatic Cholangiocarcinoma: A Proof of Concept Study Using Artificial Intelligence for Risk Assessment |
title_full | Survival Prediction in Intrahepatic Cholangiocarcinoma: A Proof of Concept Study Using Artificial Intelligence for Risk Assessment |
title_fullStr | Survival Prediction in Intrahepatic Cholangiocarcinoma: A Proof of Concept Study Using Artificial Intelligence for Risk Assessment |
title_full_unstemmed | Survival Prediction in Intrahepatic Cholangiocarcinoma: A Proof of Concept Study Using Artificial Intelligence for Risk Assessment |
title_short | Survival Prediction in Intrahepatic Cholangiocarcinoma: A Proof of Concept Study Using Artificial Intelligence for Risk Assessment |
title_sort | survival prediction in intrahepatic cholangiocarcinoma: a proof of concept study using artificial intelligence for risk assessment |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8150393/ https://www.ncbi.nlm.nih.gov/pubmed/34066001 http://dx.doi.org/10.3390/jcm10102071 |
work_keys_str_mv | AT mullerlukas survivalpredictioninintrahepaticcholangiocarcinomaaproofofconceptstudyusingartificialintelligenceforriskassessment AT mahringerkunzaline survivalpredictioninintrahepaticcholangiocarcinomaaproofofconceptstudyusingartificialintelligenceforriskassessment AT gairingsimonjohannes survivalpredictioninintrahepaticcholangiocarcinomaaproofofconceptstudyusingartificialintelligenceforriskassessment AT foersterfriedrich survivalpredictioninintrahepaticcholangiocarcinomaaproofofconceptstudyusingartificialintelligenceforriskassessment AT weinmannarndt survivalpredictioninintrahepaticcholangiocarcinomaaproofofconceptstudyusingartificialintelligenceforriskassessment AT bartschfabian survivalpredictioninintrahepaticcholangiocarcinomaaproofofconceptstudyusingartificialintelligenceforriskassessment AT heuftlisakatharina survivalpredictioninintrahepaticcholangiocarcinomaaproofofconceptstudyusingartificialintelligenceforriskassessment AT baumgartjanine survivalpredictioninintrahepaticcholangiocarcinomaaproofofconceptstudyusingartificialintelligenceforriskassessment AT duberchristoph survivalpredictioninintrahepaticcholangiocarcinomaaproofofconceptstudyusingartificialintelligenceforriskassessment AT hahnfelix survivalpredictioninintrahepaticcholangiocarcinomaaproofofconceptstudyusingartificialintelligenceforriskassessment AT kloecknerroman survivalpredictioninintrahepaticcholangiocarcinomaaproofofconceptstudyusingartificialintelligenceforriskassessment |