Machine learning based risk prediction model for asymptomatic individuals who underwent coronary artery calcium score: Comparison with traditional risk prediction approaches

Donghee Han, Kranthi K. Kolli, Heidi Gransar, Ji Hyun Lee, Su Yeon Choi, Eun Ju Chun, Hae Won Han, Sung Hak Park, Jidong Sung, Hae Ok Jung, James K. Min, Hyuk Jae Chang

Research output: Contribution to journalArticle

Abstract

Background: Machine learning (ML) is a computer algorithm used to identify patterns for prediction in various tasks, and ML methods have been beneficial for developing prediction models when applied to heterogeneous and large datasets. We aim to examine the prognostic ability of a ML-based prediction algorithm utilizing routine health checkup data to predict all-cause mortality (ACM) compared to established risk prediction approaches. Methods: A total 86155 patients with seventy available parameters (35 clinical, 32 laboratory, and 3 coronary artery calcium score [CACS] parameters) were analyzed. ML involved feature selection, splitting data randomly into a training (70%) and test set (30%), and model building with a boosted ensemble algorithm. The developed ML model was validated in a separate cohort of 4915 patients. The performance of ML for predicting ACM was compared with the following models: (i) the Framingham risk score (FRS) + CACS, (ii) atherosclerotic cardiovascular disease (ASCVD) + CACS, with (iii) logistic regression (LR) model. Results: In the derivation dataset, 690 patients died during the median 4.6-year follow-up (interquartile range, 3.0–6.6 years). The AUC value in the ML model was significantly higher than the other models in test set (ML: 0.82, FRS + CACS: 0.70, ASCVD + CACS: 0.74; LR model: 0.79, p < 0.05 for all), but not statistically significantly higher in validation set (ML: 0.78, FRS + CACS: 0.62, ASCVD + CACS: 0.72; LR model: 0.74, p: 0.572 and 0.625 for ASCVD + CACS and LR model, respectively). The ML model improved reclassification over the other models in low to intermediate risk patients (p < 0.001 for all). Conclusion: The prediction algorithm derived by ML methods showed a robust ability to predict ACM and improved reclassification over established conventional risk prediction approaches in asymptomatic population undergoing a health checkup.

Original languageEnglish
JournalJournal of Cardiovascular Computed Tomography
DOIs
Publication statusAccepted/In press - 2019 Jan 1

Fingerprint

Coronary Vessels
Calcium
Logistic Models
Cardiovascular Diseases
Mortality
Machine Learning
Health
Area Under Curve
Population

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging
  • Cardiology and Cardiovascular Medicine

Cite this

Han, Donghee ; Kolli, Kranthi K. ; Gransar, Heidi ; Lee, Ji Hyun ; Choi, Su Yeon ; Chun, Eun Ju ; Han, Hae Won ; Park, Sung Hak ; Sung, Jidong ; Jung, Hae Ok ; Min, James K. ; Chang, Hyuk Jae. / Machine learning based risk prediction model for asymptomatic individuals who underwent coronary artery calcium score : Comparison with traditional risk prediction approaches. In: Journal of Cardiovascular Computed Tomography. 2019.
@article{9af9af2863624b78940ca5dc7d3ad082,
title = "Machine learning based risk prediction model for asymptomatic individuals who underwent coronary artery calcium score: Comparison with traditional risk prediction approaches",
abstract = "Background: Machine learning (ML) is a computer algorithm used to identify patterns for prediction in various tasks, and ML methods have been beneficial for developing prediction models when applied to heterogeneous and large datasets. We aim to examine the prognostic ability of a ML-based prediction algorithm utilizing routine health checkup data to predict all-cause mortality (ACM) compared to established risk prediction approaches. Methods: A total 86155 patients with seventy available parameters (35 clinical, 32 laboratory, and 3 coronary artery calcium score [CACS] parameters) were analyzed. ML involved feature selection, splitting data randomly into a training (70{\%}) and test set (30{\%}), and model building with a boosted ensemble algorithm. The developed ML model was validated in a separate cohort of 4915 patients. The performance of ML for predicting ACM was compared with the following models: (i) the Framingham risk score (FRS) + CACS, (ii) atherosclerotic cardiovascular disease (ASCVD) + CACS, with (iii) logistic regression (LR) model. Results: In the derivation dataset, 690 patients died during the median 4.6-year follow-up (interquartile range, 3.0–6.6 years). The AUC value in the ML model was significantly higher than the other models in test set (ML: 0.82, FRS + CACS: 0.70, ASCVD + CACS: 0.74; LR model: 0.79, p < 0.05 for all), but not statistically significantly higher in validation set (ML: 0.78, FRS + CACS: 0.62, ASCVD + CACS: 0.72; LR model: 0.74, p: 0.572 and 0.625 for ASCVD + CACS and LR model, respectively). The ML model improved reclassification over the other models in low to intermediate risk patients (p < 0.001 for all). Conclusion: The prediction algorithm derived by ML methods showed a robust ability to predict ACM and improved reclassification over established conventional risk prediction approaches in asymptomatic population undergoing a health checkup.",
author = "Donghee Han and Kolli, {Kranthi K.} and Heidi Gransar and Lee, {Ji Hyun} and Choi, {Su Yeon} and Chun, {Eun Ju} and Han, {Hae Won} and Park, {Sung Hak} and Jidong Sung and Jung, {Hae Ok} and Min, {James K.} and Chang, {Hyuk Jae}",
year = "2019",
month = "1",
day = "1",
doi = "10.1016/j.jcct.2019.09.005",
language = "English",
journal = "Journal of Cardiovascular Computed Tomography",
issn = "1934-5925",
publisher = "Elsevier Inc.",

}

Machine learning based risk prediction model for asymptomatic individuals who underwent coronary artery calcium score : Comparison with traditional risk prediction approaches. / Han, Donghee; Kolli, Kranthi K.; Gransar, Heidi; Lee, Ji Hyun; Choi, Su Yeon; Chun, Eun Ju; Han, Hae Won; Park, Sung Hak; Sung, Jidong; Jung, Hae Ok; Min, James K.; Chang, Hyuk Jae.

In: Journal of Cardiovascular Computed Tomography, 01.01.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Machine learning based risk prediction model for asymptomatic individuals who underwent coronary artery calcium score

T2 - Comparison with traditional risk prediction approaches

AU - Han, Donghee

AU - Kolli, Kranthi K.

AU - Gransar, Heidi

AU - Lee, Ji Hyun

AU - Choi, Su Yeon

AU - Chun, Eun Ju

AU - Han, Hae Won

AU - Park, Sung Hak

AU - Sung, Jidong

AU - Jung, Hae Ok

AU - Min, James K.

AU - Chang, Hyuk Jae

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Background: Machine learning (ML) is a computer algorithm used to identify patterns for prediction in various tasks, and ML methods have been beneficial for developing prediction models when applied to heterogeneous and large datasets. We aim to examine the prognostic ability of a ML-based prediction algorithm utilizing routine health checkup data to predict all-cause mortality (ACM) compared to established risk prediction approaches. Methods: A total 86155 patients with seventy available parameters (35 clinical, 32 laboratory, and 3 coronary artery calcium score [CACS] parameters) were analyzed. ML involved feature selection, splitting data randomly into a training (70%) and test set (30%), and model building with a boosted ensemble algorithm. The developed ML model was validated in a separate cohort of 4915 patients. The performance of ML for predicting ACM was compared with the following models: (i) the Framingham risk score (FRS) + CACS, (ii) atherosclerotic cardiovascular disease (ASCVD) + CACS, with (iii) logistic regression (LR) model. Results: In the derivation dataset, 690 patients died during the median 4.6-year follow-up (interquartile range, 3.0–6.6 years). The AUC value in the ML model was significantly higher than the other models in test set (ML: 0.82, FRS + CACS: 0.70, ASCVD + CACS: 0.74; LR model: 0.79, p < 0.05 for all), but not statistically significantly higher in validation set (ML: 0.78, FRS + CACS: 0.62, ASCVD + CACS: 0.72; LR model: 0.74, p: 0.572 and 0.625 for ASCVD + CACS and LR model, respectively). The ML model improved reclassification over the other models in low to intermediate risk patients (p < 0.001 for all). Conclusion: The prediction algorithm derived by ML methods showed a robust ability to predict ACM and improved reclassification over established conventional risk prediction approaches in asymptomatic population undergoing a health checkup.

AB - Background: Machine learning (ML) is a computer algorithm used to identify patterns for prediction in various tasks, and ML methods have been beneficial for developing prediction models when applied to heterogeneous and large datasets. We aim to examine the prognostic ability of a ML-based prediction algorithm utilizing routine health checkup data to predict all-cause mortality (ACM) compared to established risk prediction approaches. Methods: A total 86155 patients with seventy available parameters (35 clinical, 32 laboratory, and 3 coronary artery calcium score [CACS] parameters) were analyzed. ML involved feature selection, splitting data randomly into a training (70%) and test set (30%), and model building with a boosted ensemble algorithm. The developed ML model was validated in a separate cohort of 4915 patients. The performance of ML for predicting ACM was compared with the following models: (i) the Framingham risk score (FRS) + CACS, (ii) atherosclerotic cardiovascular disease (ASCVD) + CACS, with (iii) logistic regression (LR) model. Results: In the derivation dataset, 690 patients died during the median 4.6-year follow-up (interquartile range, 3.0–6.6 years). The AUC value in the ML model was significantly higher than the other models in test set (ML: 0.82, FRS + CACS: 0.70, ASCVD + CACS: 0.74; LR model: 0.79, p < 0.05 for all), but not statistically significantly higher in validation set (ML: 0.78, FRS + CACS: 0.62, ASCVD + CACS: 0.72; LR model: 0.74, p: 0.572 and 0.625 for ASCVD + CACS and LR model, respectively). The ML model improved reclassification over the other models in low to intermediate risk patients (p < 0.001 for all). Conclusion: The prediction algorithm derived by ML methods showed a robust ability to predict ACM and improved reclassification over established conventional risk prediction approaches in asymptomatic population undergoing a health checkup.

UR - http://www.scopus.com/inward/record.url?scp=85072648175&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072648175&partnerID=8YFLogxK

U2 - 10.1016/j.jcct.2019.09.005

DO - 10.1016/j.jcct.2019.09.005

M3 - Article

AN - SCOPUS:85072648175

JO - Journal of Cardiovascular Computed Tomography

JF - Journal of Cardiovascular Computed Tomography

SN - 1934-5925

ER -