Explainable machine learning can outperform Cox regression predictions and provide insights in breast cancer survival

Abstract Cox Proportional Hazards (CPH) analysis is the standard for survival analysis in oncology. Recently, several machine learning (ML) techniques have been adapted for this task. Although they have shown to yield results at least as good as classical methods, they are often disregarded because...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Arturo Moncada-Torres, Marissa C. van Maaren, Mathijs P. Hendriks, Sabine Siesling, Gijs Geleijnse
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/60066ac6361b4955b3637a97e5f0b826
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:60066ac6361b4955b3637a97e5f0b826
record_format	dspace
spelling	oai:doaj.org-article:60066ac6361b4955b3637a97e5f0b8262021-12-02T17:04:07ZExplainable machine learning can outperform Cox regression predictions and provide insights in breast cancer survival10.1038/s41598-021-86327-72045-2322https://doaj.org/article/60066ac6361b4955b3637a97e5f0b8262021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-86327-7https://doaj.org/toc/2045-2322Abstract Cox Proportional Hazards (CPH) analysis is the standard for survival analysis in oncology. Recently, several machine learning (ML) techniques have been adapted for this task. Although they have shown to yield results at least as good as classical methods, they are often disregarded because of their lack of transparency and little to no explainability, which are key for their adoption in clinical settings. In this paper, we used data from the Netherlands Cancer Registry of 36,658 non-metastatic breast cancer patients to compare the performance of CPH with ML techniques (Random Survival Forests, Survival Support Vector Machines, and Extreme Gradient Boosting [XGB]) in predicting survival using the $$c$$ c -index. We demonstrated that in our dataset, ML-based models can perform at least as good as the classical CPH regression ( $$c$$ c -index $$\sim \,0.63$$ ∼ 0.63 ), and in the case of XGB even better ( $$c$$ c -index $$\sim 0.73$$ ∼ 0.73 ). Furthermore, we used Shapley Additive Explanation (SHAP) values to explain the models’ predictions. We concluded that the difference in performance can be attributed to XGB’s ability to model nonlinearities and complex interactions. We also investigated the impact of specific features on the models’ predictions as well as their corresponding insights. Lastly, we showed that explainable ML can generate explicit knowledge of how models make their predictions, which is crucial in increasing the trust and adoption of innovative ML techniques in oncology and healthcare overall.Arturo Moncada-TorresMarissa C. van MaarenMathijs P. HendriksSabine SieslingGijs GeleijnseNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Arturo Moncada-Torres Marissa C. van Maaren Mathijs P. Hendriks Sabine Siesling Gijs Geleijnse Explainable machine learning can outperform Cox regression predictions and provide insights in breast cancer survival
description	Abstract Cox Proportional Hazards (CPH) analysis is the standard for survival analysis in oncology. Recently, several machine learning (ML) techniques have been adapted for this task. Although they have shown to yield results at least as good as classical methods, they are often disregarded because of their lack of transparency and little to no explainability, which are key for their adoption in clinical settings. In this paper, we used data from the Netherlands Cancer Registry of 36,658 non-metastatic breast cancer patients to compare the performance of CPH with ML techniques (Random Survival Forests, Survival Support Vector Machines, and Extreme Gradient Boosting [XGB]) in predicting survival using the $$c$$ c -index. We demonstrated that in our dataset, ML-based models can perform at least as good as the classical CPH regression ( $$c$$ c -index $$\sim \,0.63$$ ∼ 0.63 ), and in the case of XGB even better ( $$c$$ c -index $$\sim 0.73$$ ∼ 0.73 ). Furthermore, we used Shapley Additive Explanation (SHAP) values to explain the models’ predictions. We concluded that the difference in performance can be attributed to XGB’s ability to model nonlinearities and complex interactions. We also investigated the impact of specific features on the models’ predictions as well as their corresponding insights. Lastly, we showed that explainable ML can generate explicit knowledge of how models make their predictions, which is crucial in increasing the trust and adoption of innovative ML techniques in oncology and healthcare overall.
format	article
author	Arturo Moncada-Torres Marissa C. van Maaren Mathijs P. Hendriks Sabine Siesling Gijs Geleijnse
author_facet	Arturo Moncada-Torres Marissa C. van Maaren Mathijs P. Hendriks Sabine Siesling Gijs Geleijnse
author_sort	Arturo Moncada-Torres
title	Explainable machine learning can outperform Cox regression predictions and provide insights in breast cancer survival
title_short	Explainable machine learning can outperform Cox regression predictions and provide insights in breast cancer survival
title_full	Explainable machine learning can outperform Cox regression predictions and provide insights in breast cancer survival
title_fullStr	Explainable machine learning can outperform Cox regression predictions and provide insights in breast cancer survival
title_full_unstemmed	Explainable machine learning can outperform Cox regression predictions and provide insights in breast cancer survival
title_sort	explainable machine learning can outperform cox regression predictions and provide insights in breast cancer survival
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/60066ac6361b4955b3637a97e5f0b826
work_keys_str_mv	AT arturomoncadatorres explainablemachinelearningcanoutperformcoxregressionpredictionsandprovideinsightsinbreastcancersurvival AT marissacvanmaaren explainablemachinelearningcanoutperformcoxregressionpredictionsandprovideinsightsinbreastcancersurvival AT mathijsphendriks explainablemachinelearningcanoutperformcoxregressionpredictionsandprovideinsightsinbreastcancersurvival AT sabinesiesling explainablemachinelearningcanoutperformcoxregressionpredictionsandprovideinsightsinbreastcancersurvival AT gijsgeleijnse explainablemachinelearningcanoutperformcoxregressionpredictionsandprovideinsightsinbreastcancersurvival
_version_	1718381850758479872

Explainable machine learning can outperform Cox regression predictions and provide insights in breast cancer survival

Ejemplares similares