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 language | English |
|---|---|
| Journal | Journal of Cardiovascular Computed Tomography |
| DOIs | |
| Publication status | Accepted/In press - 2019 Jan 1 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Radiology Nuclear Medicine and imaging
- Cardiology and Cardiovascular Medicine
Cite this
}
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 journal › Article
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 -