Machine learning models for screening carotid atherosclerosis in asymptomatic adults

Abstract Carotid atherosclerosis (CAS) is a risk factor for cardiovascular and cerebrovascular events, but duplex ultrasonography isn’t recommended in routine screening for asymptomatic populations according to medical guidelines. We aim to develop machine learning models to screen CAS in asymptomat...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jian Yu, Yan Zhou, Qiong Yang, Xiaoling Liu, Lili Huang, Ping Yu, Shuyuan Chu
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/1dc4decb32624ee5aea34fbc2bb4efa4
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1dc4decb32624ee5aea34fbc2bb4efa4
record_format	dspace
spelling	oai:doaj.org-article:1dc4decb32624ee5aea34fbc2bb4efa42021-11-21T12:24:45ZMachine learning models for screening carotid atherosclerosis in asymptomatic adults10.1038/s41598-021-01456-32045-2322https://doaj.org/article/1dc4decb32624ee5aea34fbc2bb4efa42021-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-01456-3https://doaj.org/toc/2045-2322Abstract Carotid atherosclerosis (CAS) is a risk factor for cardiovascular and cerebrovascular events, but duplex ultrasonography isn’t recommended in routine screening for asymptomatic populations according to medical guidelines. We aim to develop machine learning models to screen CAS in asymptomatic adults. A total of 2732 asymptomatic subjects for routine physical examination in our hospital were included in the study. We developed machine learning models to classify subjects with or without CAS using decision tree, random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM) and multilayer perceptron (MLP) with 17 candidate features. The performance of models was assessed on the testing dataset. The model using MLP achieved the highest accuracy (0.748), positive predictive value (0.743), F1 score (0.742), area under receiver operating characteristic curve (AUC) (0.766) and Kappa score (0.445) among all classifiers. It’s followed by models using XGBoost and SVM. In conclusion, the model using MLP is the best one to screen CAS in asymptomatic adults based on the results from routine physical examination, followed by using XGBoost and SVM. Those models may provide an effective and applicable method for physician and primary care doctors to screen asymptomatic CAS without risk factors in general population, and improve risk predictions and preventions of cardiovascular and cerebrovascular events in asymptomatic adults.Jian YuYan ZhouQiong YangXiaoling LiuLili HuangPing YuShuyuan ChuNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-8 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Jian Yu Yan Zhou Qiong Yang Xiaoling Liu Lili Huang Ping Yu Shuyuan Chu Machine learning models for screening carotid atherosclerosis in asymptomatic adults
description	Abstract Carotid atherosclerosis (CAS) is a risk factor for cardiovascular and cerebrovascular events, but duplex ultrasonography isn’t recommended in routine screening for asymptomatic populations according to medical guidelines. We aim to develop machine learning models to screen CAS in asymptomatic adults. A total of 2732 asymptomatic subjects for routine physical examination in our hospital were included in the study. We developed machine learning models to classify subjects with or without CAS using decision tree, random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM) and multilayer perceptron (MLP) with 17 candidate features. The performance of models was assessed on the testing dataset. The model using MLP achieved the highest accuracy (0.748), positive predictive value (0.743), F1 score (0.742), area under receiver operating characteristic curve (AUC) (0.766) and Kappa score (0.445) among all classifiers. It’s followed by models using XGBoost and SVM. In conclusion, the model using MLP is the best one to screen CAS in asymptomatic adults based on the results from routine physical examination, followed by using XGBoost and SVM. Those models may provide an effective and applicable method for physician and primary care doctors to screen asymptomatic CAS without risk factors in general population, and improve risk predictions and preventions of cardiovascular and cerebrovascular events in asymptomatic adults.
format	article
author	Jian Yu Yan Zhou Qiong Yang Xiaoling Liu Lili Huang Ping Yu Shuyuan Chu
author_facet	Jian Yu Yan Zhou Qiong Yang Xiaoling Liu Lili Huang Ping Yu Shuyuan Chu
author_sort	Jian Yu
title	Machine learning models for screening carotid atherosclerosis in asymptomatic adults
title_short	Machine learning models for screening carotid atherosclerosis in asymptomatic adults
title_full	Machine learning models for screening carotid atherosclerosis in asymptomatic adults
title_fullStr	Machine learning models for screening carotid atherosclerosis in asymptomatic adults
title_full_unstemmed	Machine learning models for screening carotid atherosclerosis in asymptomatic adults
title_sort	machine learning models for screening carotid atherosclerosis in asymptomatic adults
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/1dc4decb32624ee5aea34fbc2bb4efa4
work_keys_str_mv	AT jianyu machinelearningmodelsforscreeningcarotidatherosclerosisinasymptomaticadults AT yanzhou machinelearningmodelsforscreeningcarotidatherosclerosisinasymptomaticadults AT qiongyang machinelearningmodelsforscreeningcarotidatherosclerosisinasymptomaticadults AT xiaolingliu machinelearningmodelsforscreeningcarotidatherosclerosisinasymptomaticadults AT lilihuang machinelearningmodelsforscreeningcarotidatherosclerosisinasymptomaticadults AT pingyu machinelearningmodelsforscreeningcarotidatherosclerosisinasymptomaticadults AT shuyuanchu machinelearningmodelsforscreeningcarotidatherosclerosisinasymptomaticadults
_version_	1718418990673428480

Machine learning models for screening carotid atherosclerosis in asymptomatic adults

Ejemplares similares