Utilizing machine learning algorithms for the prediction of carotid artery plaques in a Chinese population

Background: Ischemic stroke is a significant global health issue, imposing substantial social and economic burdens. Carotid artery plaques (CAP) serve as an important risk factor for stroke, and early screening can effectively reduce stroke incidence. However, China lacks nationwide data on carotid...

Full description

Bibliographic Details
Main Authors: Shuwei Weng, Jin Chen, Chen Ding, Die Hu, Wenwu Liu, Yanyi Yang, Daoquan Peng
Format: Article
Language:English
Published: Frontiers Media S.A. 2023-11-01
Series:Frontiers in Physiology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fphys.2023.1295371/full
_version_ 1797635634483953664
author Shuwei Weng
Shuwei Weng
Jin Chen
Jin Chen
Chen Ding
Die Hu
Die Hu
Wenwu Liu
Wenwu Liu
Yanyi Yang
Daoquan Peng
Daoquan Peng
author_facet Shuwei Weng
Shuwei Weng
Jin Chen
Jin Chen
Chen Ding
Die Hu
Die Hu
Wenwu Liu
Wenwu Liu
Yanyi Yang
Daoquan Peng
Daoquan Peng
author_sort Shuwei Weng
collection DOAJ
description Background: Ischemic stroke is a significant global health issue, imposing substantial social and economic burdens. Carotid artery plaques (CAP) serve as an important risk factor for stroke, and early screening can effectively reduce stroke incidence. However, China lacks nationwide data on carotid artery plaques. Machine learning (ML) can offer an economically efficient screening method. This study aimed to develop ML models using routine health examinations and blood markers to predict the occurrence of carotid artery plaques.Methods: This study included data from 5,211 participants aged 18–70, encompassing health check-ups and biochemical indicators. Among them, 1,164 participants were diagnosed with carotid artery plaques through carotid ultrasound. We constructed six ML models by employing feature selection with elastic net regression, selecting 13 indicators. Model performance was evaluated using accuracy, sensitivity, specificity, Positive Predictive Value (PPV), Negative Predictive Value (NPV), F1 score, kappa value, and Area Under the Curve (AUC) value. Feature importance was assessed by calculating the root mean square error (RMSE) loss after permutations for each variable in every model.Results: Among all six ML models, LightGBM achieved the highest accuracy at 91.8%. Feature importance analysis revealed that age, Low-Density Lipoprotein Cholesterol (LDL-c), and systolic blood pressure were important predictive factors in the models.Conclusion: LightGBM can effectively predict the occurrence of carotid artery plaques using demographic information, physical examination data and biochemistry data.
first_indexed 2024-03-11T12:24:16Z
format Article
id doaj.art-e87764e918c74fc69943caa641021595
institution Directory Open Access Journal
issn 1664-042X
language English
last_indexed 2024-03-11T12:24:16Z
publishDate 2023-11-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Physiology
spelling doaj.art-e87764e918c74fc69943caa6410215952023-11-06T15:52:46ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2023-11-011410.3389/fphys.2023.12953711295371Utilizing machine learning algorithms for the prediction of carotid artery plaques in a Chinese populationShuwei Weng0Shuwei Weng1Jin Chen2Jin Chen3Chen Ding4Die Hu5Die Hu6Wenwu Liu7Wenwu Liu8Yanyi Yang9Daoquan Peng10Daoquan Peng11Department of Cardiovascular Medicine, The Second Xiangya Hospital, Central South University, Changsha, Hunan, ChinaResearch Institute of Blood Lipid and Atherosclerosis, Changsha, Hunan, ChinaDepartment of Cardiovascular Medicine, The Second Xiangya Hospital, Central South University, Changsha, Hunan, ChinaResearch Institute of Blood Lipid and Atherosclerosis, Changsha, Hunan, ChinaDepartment of Cardiology, Suzhou Dushu Lake Hospital, Dushu Lake Hospital Affiliated to Soochow University, Medical Center of Soochow University, Suzhou, Jiangsu, ChinaDepartment of Cardiovascular Medicine, The Second Xiangya Hospital, Central South University, Changsha, Hunan, ChinaResearch Institute of Blood Lipid and Atherosclerosis, Changsha, Hunan, ChinaDepartment of Cardiovascular Medicine, The Second Xiangya Hospital, Central South University, Changsha, Hunan, ChinaResearch Institute of Blood Lipid and Atherosclerosis, Changsha, Hunan, ChinaHealth Management Center, The Second Xiangya Hospital, Central South University, Changsha, Hunan, ChinaDepartment of Cardiovascular Medicine, The Second Xiangya Hospital, Central South University, Changsha, Hunan, ChinaResearch Institute of Blood Lipid and Atherosclerosis, Changsha, Hunan, ChinaBackground: Ischemic stroke is a significant global health issue, imposing substantial social and economic burdens. Carotid artery plaques (CAP) serve as an important risk factor for stroke, and early screening can effectively reduce stroke incidence. However, China lacks nationwide data on carotid artery plaques. Machine learning (ML) can offer an economically efficient screening method. This study aimed to develop ML models using routine health examinations and blood markers to predict the occurrence of carotid artery plaques.Methods: This study included data from 5,211 participants aged 18–70, encompassing health check-ups and biochemical indicators. Among them, 1,164 participants were diagnosed with carotid artery plaques through carotid ultrasound. We constructed six ML models by employing feature selection with elastic net regression, selecting 13 indicators. Model performance was evaluated using accuracy, sensitivity, specificity, Positive Predictive Value (PPV), Negative Predictive Value (NPV), F1 score, kappa value, and Area Under the Curve (AUC) value. Feature importance was assessed by calculating the root mean square error (RMSE) loss after permutations for each variable in every model.Results: Among all six ML models, LightGBM achieved the highest accuracy at 91.8%. Feature importance analysis revealed that age, Low-Density Lipoprotein Cholesterol (LDL-c), and systolic blood pressure were important predictive factors in the models.Conclusion: LightGBM can effectively predict the occurrence of carotid artery plaques using demographic information, physical examination data and biochemistry data.https://www.frontiersin.org/articles/10.3389/fphys.2023.1295371/fullcarotid artery plaquemachine learningLightGBMscreeningprimary prevention
spellingShingle Shuwei Weng
Shuwei Weng
Jin Chen
Jin Chen
Chen Ding
Die Hu
Die Hu
Wenwu Liu
Wenwu Liu
Yanyi Yang
Daoquan Peng
Daoquan Peng
Utilizing machine learning algorithms for the prediction of carotid artery plaques in a Chinese population
Frontiers in Physiology
carotid artery plaque
machine learning
LightGBM
screening
primary prevention
title Utilizing machine learning algorithms for the prediction of carotid artery plaques in a Chinese population
title_full Utilizing machine learning algorithms for the prediction of carotid artery plaques in a Chinese population
title_fullStr Utilizing machine learning algorithms for the prediction of carotid artery plaques in a Chinese population
title_full_unstemmed Utilizing machine learning algorithms for the prediction of carotid artery plaques in a Chinese population
title_short Utilizing machine learning algorithms for the prediction of carotid artery plaques in a Chinese population
title_sort utilizing machine learning algorithms for the prediction of carotid artery plaques in a chinese population
topic carotid artery plaque
machine learning
LightGBM
screening
primary prevention
url https://www.frontiersin.org/articles/10.3389/fphys.2023.1295371/full
work_keys_str_mv AT shuweiweng utilizingmachinelearningalgorithmsforthepredictionofcarotidarteryplaquesinachinesepopulation
AT shuweiweng utilizingmachinelearningalgorithmsforthepredictionofcarotidarteryplaquesinachinesepopulation
AT jinchen utilizingmachinelearningalgorithmsforthepredictionofcarotidarteryplaquesinachinesepopulation
AT jinchen utilizingmachinelearningalgorithmsforthepredictionofcarotidarteryplaquesinachinesepopulation
AT chending utilizingmachinelearningalgorithmsforthepredictionofcarotidarteryplaquesinachinesepopulation
AT diehu utilizingmachinelearningalgorithmsforthepredictionofcarotidarteryplaquesinachinesepopulation
AT diehu utilizingmachinelearningalgorithmsforthepredictionofcarotidarteryplaquesinachinesepopulation
AT wenwuliu utilizingmachinelearningalgorithmsforthepredictionofcarotidarteryplaquesinachinesepopulation
AT wenwuliu utilizingmachinelearningalgorithmsforthepredictionofcarotidarteryplaquesinachinesepopulation
AT yanyiyang utilizingmachinelearningalgorithmsforthepredictionofcarotidarteryplaquesinachinesepopulation
AT daoquanpeng utilizingmachinelearningalgorithmsforthepredictionofcarotidarteryplaquesinachinesepopulation
AT daoquanpeng utilizingmachinelearningalgorithmsforthepredictionofcarotidarteryplaquesinachinesepopulation