Explainable machine learning model for predicting spontaneous bacterial peritonitis in cirrhotic patients with ascites

Abstract Spontaneous bacterial peritonitis (SBP) is a life-threatening complication in patients with cirrhosis. We aimed to develop an explainable machine learning model to achieve the early prediction and outcome interpretation of SBP. We used CatBoost algorithm to construct MODEL-1 with 46 variabl...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yingying Hu, Ruijia Chen, Haibing Gao, Haitao Lin, Jinye Wang, Xiaowei Wang, Jingfeng Liu, Yongyi Zeng
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/be1b9676bcb042c2997f7ade55112449
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:be1b9676bcb042c2997f7ade55112449
record_format	dspace
spelling	oai:doaj.org-article:be1b9676bcb042c2997f7ade551124492021-11-08T10:55:04ZExplainable machine learning model for predicting spontaneous bacterial peritonitis in cirrhotic patients with ascites10.1038/s41598-021-00218-52045-2322https://doaj.org/article/be1b9676bcb042c2997f7ade551124492021-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-00218-5https://doaj.org/toc/2045-2322Abstract Spontaneous bacterial peritonitis (SBP) is a life-threatening complication in patients with cirrhosis. We aimed to develop an explainable machine learning model to achieve the early prediction and outcome interpretation of SBP. We used CatBoost algorithm to construct MODEL-1 with 46 variables. After dimensionality reduction, we constructed MODEL-2. We calculated and compared the sensitivity and negative predictive value (NPV) of MODEL-1 and MODEL-2. Finally, we used the SHAP (SHapley Additive exPlanations) method to provide insights into the model’s outcome or prediction. MODEL-2 (AUROC: 0.822; 95% confidence interval [CI] 0.783–0.856), liked MODEL-1 (AUROC: 0.822; 95% CI 0.784–0.856), could well predict the risk of SBP in cirrhotic ascites patients. The 6 most influential predictive variables were total protein, C-reactive protein, prothrombin activity, cholinesterase, lymphocyte ratio and apolipoprotein A1. For binary classifier, the sensitivity and NPV of MODEL-1 were 0.894 and 0.885, respectively, while for MODEL-2 they were 0.927 and 0.904, respectively. We applied CatBoost algorithm to establish a practical and explainable prediction model for risk of SBP in cirrhotic patients with ascites. We also identified 6 important variables closely related to the occurrence of SBP.Yingying HuRuijia ChenHaibing GaoHaitao LinJinye WangXiaowei WangJingfeng LiuYongyi ZengNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Yingying Hu Ruijia Chen Haibing Gao Haitao Lin Jinye Wang Xiaowei Wang Jingfeng Liu Yongyi Zeng Explainable machine learning model for predicting spontaneous bacterial peritonitis in cirrhotic patients with ascites
description	Abstract Spontaneous bacterial peritonitis (SBP) is a life-threatening complication in patients with cirrhosis. We aimed to develop an explainable machine learning model to achieve the early prediction and outcome interpretation of SBP. We used CatBoost algorithm to construct MODEL-1 with 46 variables. After dimensionality reduction, we constructed MODEL-2. We calculated and compared the sensitivity and negative predictive value (NPV) of MODEL-1 and MODEL-2. Finally, we used the SHAP (SHapley Additive exPlanations) method to provide insights into the model’s outcome or prediction. MODEL-2 (AUROC: 0.822; 95% confidence interval [CI] 0.783–0.856), liked MODEL-1 (AUROC: 0.822; 95% CI 0.784–0.856), could well predict the risk of SBP in cirrhotic ascites patients. The 6 most influential predictive variables were total protein, C-reactive protein, prothrombin activity, cholinesterase, lymphocyte ratio and apolipoprotein A1. For binary classifier, the sensitivity and NPV of MODEL-1 were 0.894 and 0.885, respectively, while for MODEL-2 they were 0.927 and 0.904, respectively. We applied CatBoost algorithm to establish a practical and explainable prediction model for risk of SBP in cirrhotic patients with ascites. We also identified 6 important variables closely related to the occurrence of SBP.
format	article
author	Yingying Hu Ruijia Chen Haibing Gao Haitao Lin Jinye Wang Xiaowei Wang Jingfeng Liu Yongyi Zeng
author_facet	Yingying Hu Ruijia Chen Haibing Gao Haitao Lin Jinye Wang Xiaowei Wang Jingfeng Liu Yongyi Zeng
author_sort	Yingying Hu
title	Explainable machine learning model for predicting spontaneous bacterial peritonitis in cirrhotic patients with ascites
title_short	Explainable machine learning model for predicting spontaneous bacterial peritonitis in cirrhotic patients with ascites
title_full	Explainable machine learning model for predicting spontaneous bacterial peritonitis in cirrhotic patients with ascites
title_fullStr	Explainable machine learning model for predicting spontaneous bacterial peritonitis in cirrhotic patients with ascites
title_full_unstemmed	Explainable machine learning model for predicting spontaneous bacterial peritonitis in cirrhotic patients with ascites
title_sort	explainable machine learning model for predicting spontaneous bacterial peritonitis in cirrhotic patients with ascites
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/be1b9676bcb042c2997f7ade55112449
work_keys_str_mv	AT yingyinghu explainablemachinelearningmodelforpredictingspontaneousbacterialperitonitisincirrhoticpatientswithascites AT ruijiachen explainablemachinelearningmodelforpredictingspontaneousbacterialperitonitisincirrhoticpatientswithascites AT haibinggao explainablemachinelearningmodelforpredictingspontaneousbacterialperitonitisincirrhoticpatientswithascites AT haitaolin explainablemachinelearningmodelforpredictingspontaneousbacterialperitonitisincirrhoticpatientswithascites AT jinyewang explainablemachinelearningmodelforpredictingspontaneousbacterialperitonitisincirrhoticpatientswithascites AT xiaoweiwang explainablemachinelearningmodelforpredictingspontaneousbacterialperitonitisincirrhoticpatientswithascites AT jingfengliu explainablemachinelearningmodelforpredictingspontaneousbacterialperitonitisincirrhoticpatientswithascites AT yongyizeng explainablemachinelearningmodelforpredictingspontaneousbacterialperitonitisincirrhoticpatientswithascites
_version_	1718442563657007104

Explainable machine learning model for predicting spontaneous bacterial peritonitis in cirrhotic patients with ascites

Ejemplares similares