Pre-existing and machine learning-based models for cardiovascular risk prediction
Abstract Predicting the risk of cardiovascular disease is the key to primary prevention. Machine learning has attracted attention in analyzing increasingly large, complex healthcare data. We assessed discrimination and calibration of pre-existing cardiovascular risk prediction models and developed m...
Guardado en:
Autores principales: | , , , , , , , , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/68aaa9b55dd04e6aa28fd62a172d6c4e |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:68aaa9b55dd04e6aa28fd62a172d6c4e |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:68aaa9b55dd04e6aa28fd62a172d6c4e2021-12-02T16:56:02ZPre-existing and machine learning-based models for cardiovascular risk prediction10.1038/s41598-021-88257-w2045-2322https://doaj.org/article/68aaa9b55dd04e6aa28fd62a172d6c4e2021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-88257-whttps://doaj.org/toc/2045-2322Abstract Predicting the risk of cardiovascular disease is the key to primary prevention. Machine learning has attracted attention in analyzing increasingly large, complex healthcare data. We assessed discrimination and calibration of pre-existing cardiovascular risk prediction models and developed machine learning-based prediction algorithms. This study included 222,998 Korean adults aged 40–79 years, naïve to lipid-lowering therapy, had no history of cardiovascular disease. Pre-existing models showed moderate to good discrimination in predicting future cardiovascular events (C-statistics 0.70–0.80). Pooled cohort equation (PCE) specifically showed C-statistics of 0.738. Among other machine learning models such as logistic regression, treebag, random forest, and adaboost, the neural network model showed the greatest C-statistic (0.751), which was significantly higher than that for PCE. It also showed improved agreement between the predicted risk and observed outcomes (Hosmer–Lemeshow χ2 = 86.1, P < 0.001) than PCE for whites did (Hosmer–Lemeshow χ2 = 171.1, P < 0.001). Similar improvements were observed for Framingham risk score, systematic coronary risk evaluation, and QRISK3. This study demonstrated that machine learning-based algorithms could improve performance in cardiovascular risk prediction over contemporary cardiovascular risk models in statin-naïve healthy Korean adults without cardiovascular disease. The model can be easily adopted for risk assessment and clinical decision making.Sang-Yeong ChoSun-Hwa KimSi-Hyuck KangKyong Joon LeeDongjun ChoiSeungjin KangSang Jun ParkTackeun KimChang-Hwan YoonTae-Jin YounIn-Ho ChaeNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Sang-Yeong Cho Sun-Hwa Kim Si-Hyuck Kang Kyong Joon Lee Dongjun Choi Seungjin Kang Sang Jun Park Tackeun Kim Chang-Hwan Yoon Tae-Jin Youn In-Ho Chae Pre-existing and machine learning-based models for cardiovascular risk prediction |
description |
Abstract Predicting the risk of cardiovascular disease is the key to primary prevention. Machine learning has attracted attention in analyzing increasingly large, complex healthcare data. We assessed discrimination and calibration of pre-existing cardiovascular risk prediction models and developed machine learning-based prediction algorithms. This study included 222,998 Korean adults aged 40–79 years, naïve to lipid-lowering therapy, had no history of cardiovascular disease. Pre-existing models showed moderate to good discrimination in predicting future cardiovascular events (C-statistics 0.70–0.80). Pooled cohort equation (PCE) specifically showed C-statistics of 0.738. Among other machine learning models such as logistic regression, treebag, random forest, and adaboost, the neural network model showed the greatest C-statistic (0.751), which was significantly higher than that for PCE. It also showed improved agreement between the predicted risk and observed outcomes (Hosmer–Lemeshow χ2 = 86.1, P < 0.001) than PCE for whites did (Hosmer–Lemeshow χ2 = 171.1, P < 0.001). Similar improvements were observed for Framingham risk score, systematic coronary risk evaluation, and QRISK3. This study demonstrated that machine learning-based algorithms could improve performance in cardiovascular risk prediction over contemporary cardiovascular risk models in statin-naïve healthy Korean adults without cardiovascular disease. The model can be easily adopted for risk assessment and clinical decision making. |
format |
article |
author |
Sang-Yeong Cho Sun-Hwa Kim Si-Hyuck Kang Kyong Joon Lee Dongjun Choi Seungjin Kang Sang Jun Park Tackeun Kim Chang-Hwan Yoon Tae-Jin Youn In-Ho Chae |
author_facet |
Sang-Yeong Cho Sun-Hwa Kim Si-Hyuck Kang Kyong Joon Lee Dongjun Choi Seungjin Kang Sang Jun Park Tackeun Kim Chang-Hwan Yoon Tae-Jin Youn In-Ho Chae |
author_sort |
Sang-Yeong Cho |
title |
Pre-existing and machine learning-based models for cardiovascular risk prediction |
title_short |
Pre-existing and machine learning-based models for cardiovascular risk prediction |
title_full |
Pre-existing and machine learning-based models for cardiovascular risk prediction |
title_fullStr |
Pre-existing and machine learning-based models for cardiovascular risk prediction |
title_full_unstemmed |
Pre-existing and machine learning-based models for cardiovascular risk prediction |
title_sort |
pre-existing and machine learning-based models for cardiovascular risk prediction |
publisher |
Nature Portfolio |
publishDate |
2021 |
url |
https://doaj.org/article/68aaa9b55dd04e6aa28fd62a172d6c4e |
work_keys_str_mv |
AT sangyeongcho preexistingandmachinelearningbasedmodelsforcardiovascularriskprediction AT sunhwakim preexistingandmachinelearningbasedmodelsforcardiovascularriskprediction AT sihyuckkang preexistingandmachinelearningbasedmodelsforcardiovascularriskprediction AT kyongjoonlee preexistingandmachinelearningbasedmodelsforcardiovascularriskprediction AT dongjunchoi preexistingandmachinelearningbasedmodelsforcardiovascularriskprediction AT seungjinkang preexistingandmachinelearningbasedmodelsforcardiovascularriskprediction AT sangjunpark preexistingandmachinelearningbasedmodelsforcardiovascularriskprediction AT tackeunkim preexistingandmachinelearningbasedmodelsforcardiovascularriskprediction AT changhwanyoon preexistingandmachinelearningbasedmodelsforcardiovascularriskprediction AT taejinyoun preexistingandmachinelearningbasedmodelsforcardiovascularriskprediction AT inhochae preexistingandmachinelearningbasedmodelsforcardiovascularriskprediction |
_version_ |
1718382803996901376 |