A Boosted Ensemble Algorithm for Determination of Plaque Stability in High-Risk Patients on Coronary CTA

Subhi J. Al'Aref; Gurpreet Singh; Jeong W. Choi; Zhuoran Xu; Gabriel Maliakal; Alexander R. van Rosendael; Benjamin C. Lee; Zahra Fatima; Daniele Andreini; Jeroen J. Bax; Filippo Cademartiri; Kavitha Chinnaiyan; Benjamin J.W. Chow; Edoardo Conte; Ricardo C. Cury; Gudruf Feuchtner; Martin Hadamitzky; Yong Jin Kim; Sang Eun Lee; Jonathon A. Leipsic; Erica Maffei; Hugo Marques; Fabian Plank; Gianluca Pontone; Gilbert L. Raff; Todd C. Villines; Harald G. Weirich; Iksung Cho; Ibrahim Danad; Donghee Han; Ran Heo; Ji Hyun Lee; Asim Rizvi; Wijnand J. Stuijfzand; Heidi Gransar; Yao Lu; Ji Min Sung; Hyung Bok Park; Daniel S. Berman; Matthew J. Budoff; Habib Samady; Peter H. Stone; Renu Virmani; Jagat Narula; Hyuk Jae Chang; Fay Y. Lin; Lohendran Baskaran; Leslee J. Shaw; James K. Min

doi:10.1016/j.jcmg.2020.03.025

A Boosted Ensemble Algorithm for Determination of Plaque Stability in High-Risk Patients on Coronary CTA

Subhi J. Al'Aref, Gurpreet Singh, Jeong W. Choi, Zhuoran Xu, Gabriel Maliakal, Alexander R. van Rosendael, Benjamin C. Lee, Zahra Fatima, Daniele Andreini, Jeroen J. Bax, Filippo Cademartiri, Kavitha Chinnaiyan, Benjamin J.W. Chow, Edoardo Conte, Ricardo C. Cury, Gudruf Feuchtner, Martin Hadamitzky, Yong Jin Kim, Sang Eun Lee, Jonathon A. LeipsicErica Maffei, Hugo Marques, Fabian Plank, Gianluca Pontone, Gilbert L. Raff, Todd C. Villines, Harald G. Weirich, Iksung Cho, Ibrahim Danad, Donghee Han, Ran Heo, Ji Hyun Lee, Asim Rizvi, Wijnand J. Stuijfzand, Heidi Gransar, Yao Lu, Ji Min Sung, Hyung Bok Park, Daniel S. Berman, Matthew J. Budoff, Habib Samady, Peter H. Stone, Renu Virmani, Jagat Narula, Hyuk Jae Chang, Fay Y. Lin, Lohendran Baskaran, Leslee J. Shaw, James K. Min

Research output: Contribution to journal › Article › peer-review

41 Scopus citations

Abstract

Objectives: This study sought to identify culprit lesion (CL) precursors among acute coronary syndrome (ACS) patients based on qualitative and quantitative computed tomography–based plaque characteristics. Background: Coronary computed tomography angiography (CTA) has been validated for patient-level prediction of ACS. However, the applicability of coronary CTA to CL assessment is not known. Methods: Utilizing the ICONIC (Incident COroNary Syndromes Identified by Computed Tomography) study, a nested case-control study of 468 patients with baseline coronary CTA, the study included ACS patients with invasive coronary angiography–adjudicated CLs that could be aligned to CL precursors on baseline coronary CTA. Separate blinded core laboratories adjudicated CLs and performed atherosclerotic plaque evaluation. Thereafter, the study used a boosted ensemble algorithm (XGBoost) to develop a predictive model of CLs. Data were randomly split into a training set (80%) and a test set (20%). The area under the receiver-operating characteristic curve of this model was compared with that of diameter stenosis (model 1), high-risk plaque features (model 2), and lesion-level features of CL precursors from the ICONIC study (model 3). Thereafter, the machine learning (ML) model was applied to 234 non-ACS patients with 864 lesions to determine model performance for CL exclusion. Results: CL precursors were identified by both coronary angiography and baseline coronary CTA in 124 of 234 (53.0%) patients, with a total of 582 lesions (containing 124 CLs) included in the analysis. The ML model demonstrated significantly higher area under the receiver-operating characteristic curve for discriminating CL precursors (0.774; 95% confidence interval [CI]: 0.758 to 0.790) compared with model 1 (0.599; 95% CI: 0.599 to 0.599; p < 0.01), model 2 (0.532; 95% CI: 0.501 to 0.563; p < 0.01), and model 3 (0.672; 95% CI: 0.662 to 0.682; p < 0.01). When applied to the non-ACS cohort, the ML model had a specificity of 89.3% for excluding CLs. Conclusions: In a high-risk cohort, a boosted ensemble algorithm can be used to predict CL from non-CL precursors on coronary CTA.

Original language	English (US)
Pages (from-to)	2162-2173
Number of pages	12
Journal	JACC: Cardiovascular Imaging
Volume	13
Issue number	10
DOIs	https://doi.org/10.1016/j.jcmg.2020.03.025
State	Published - Oct 2020
Externally published	Yes

Keywords

acute coronary syndrome
coronary computed tomography angiography
diameter stenosis
machine learning

ASJC Scopus subject areas

Radiology Nuclear Medicine and imaging
Cardiology and Cardiovascular Medicine

Access to Document

10.1016/j.jcmg.2020.03.025

Cite this

Al'Aref, S. J., Singh, G., Choi, J. W., Xu, Z., Maliakal, G., van Rosendael, A. R., Lee, B. C., Fatima, Z., Andreini, D., Bax, J. J., Cademartiri, F., Chinnaiyan, K., Chow, B. J. W., Conte, E., Cury, R. C., Feuchtner, G., Hadamitzky, M., Kim, Y. J., Lee, S. E., ... Min, J. K. (2020). A Boosted Ensemble Algorithm for Determination of Plaque Stability in High-Risk Patients on Coronary CTA. JACC: Cardiovascular Imaging, 13(10), 2162-2173. https://doi.org/10.1016/j.jcmg.2020.03.025

Al'Aref, SJ, Singh, G, Choi, JW, Xu, Z, Maliakal, G, van Rosendael, AR, Lee, BC, Fatima, Z, Andreini, D, Bax, JJ, Cademartiri, F, Chinnaiyan, K, Chow, BJW, Conte, E, Cury, RC, Feuchtner, G, Hadamitzky, M, Kim, YJ, Lee, SE, Leipsic, JA, Maffei, E, Marques, H, Plank, F, Pontone, G, Raff, GL, Villines, TC, Weirich, HG, Cho, I, Danad, I, Han, D, Heo, R, Lee, JH, Rizvi, A, Stuijfzand, WJ, Gransar, H, Lu, Y, Sung, JM, Park, HB, Berman, DS, Budoff, MJ, Samady, H, Stone, PH, Virmani, R, Narula, J, Chang, HJ, Lin, FY, Baskaran, L, Shaw, LJ & Min, JK 2020, 'A Boosted Ensemble Algorithm for Determination of Plaque Stability in High-Risk Patients on Coronary CTA', JACC: Cardiovascular Imaging, vol. 13, no. 10, pp. 2162-2173. https://doi.org/10.1016/j.jcmg.2020.03.025

@article{a4b2aa9fb0aa466db0a31ea04160a73f,

title = "A Boosted Ensemble Algorithm for Determination of Plaque Stability in High-Risk Patients on Coronary CTA",

abstract = "Objectives: This study sought to identify culprit lesion (CL) precursors among acute coronary syndrome (ACS) patients based on qualitative and quantitative computed tomography–based plaque characteristics. Background: Coronary computed tomography angiography (CTA) has been validated for patient-level prediction of ACS. However, the applicability of coronary CTA to CL assessment is not known. Methods: Utilizing the ICONIC (Incident COroNary Syndromes Identified by Computed Tomography) study, a nested case-control study of 468 patients with baseline coronary CTA, the study included ACS patients with invasive coronary angiography–adjudicated CLs that could be aligned to CL precursors on baseline coronary CTA. Separate blinded core laboratories adjudicated CLs and performed atherosclerotic plaque evaluation. Thereafter, the study used a boosted ensemble algorithm (XGBoost) to develop a predictive model of CLs. Data were randomly split into a training set (80%) and a test set (20%). The area under the receiver-operating characteristic curve of this model was compared with that of diameter stenosis (model 1), high-risk plaque features (model 2), and lesion-level features of CL precursors from the ICONIC study (model 3). Thereafter, the machine learning (ML) model was applied to 234 non-ACS patients with 864 lesions to determine model performance for CL exclusion. Results: CL precursors were identified by both coronary angiography and baseline coronary CTA in 124 of 234 (53.0%) patients, with a total of 582 lesions (containing 124 CLs) included in the analysis. The ML model demonstrated significantly higher area under the receiver-operating characteristic curve for discriminating CL precursors (0.774; 95% confidence interval [CI]: 0.758 to 0.790) compared with model 1 (0.599; 95% CI: 0.599 to 0.599; p < 0.01), model 2 (0.532; 95% CI: 0.501 to 0.563; p < 0.01), and model 3 (0.672; 95% CI: 0.662 to 0.682; p < 0.01). When applied to the non-ACS cohort, the ML model had a specificity of 89.3% for excluding CLs. Conclusions: In a high-risk cohort, a boosted ensemble algorithm can be used to predict CL from non-CL precursors on coronary CTA.",

keywords = "acute coronary syndrome, coronary computed tomography angiography, diameter stenosis, machine learning",

author = "Al'Aref, {Subhi J.} and Gurpreet Singh and Choi, {Jeong W.} and Zhuoran Xu and Gabriel Maliakal and {van Rosendael}, {Alexander R.} and Lee, {Benjamin C.} and Zahra Fatima and Daniele Andreini and Bax, {Jeroen J.} and Filippo Cademartiri and Kavitha Chinnaiyan and Chow, {Benjamin J.W.} and Edoardo Conte and Cury, {Ricardo C.} and Gudruf Feuchtner and Martin Hadamitzky and Kim, {Yong Jin} and Lee, {Sang Eun} and Leipsic, {Jonathon A.} and Erica Maffei and Hugo Marques and Fabian Plank and Gianluca Pontone and Raff, {Gilbert L.} and Villines, {Todd C.} and Weirich, {Harald G.} and Iksung Cho and Ibrahim Danad and Donghee Han and Ran Heo and Lee, {Ji Hyun} and Asim Rizvi and Stuijfzand, {Wijnand J.} and Heidi Gransar and Yao Lu and Sung, {Ji Min} and Park, {Hyung Bok} and Berman, {Daniel S.} and Budoff, {Matthew J.} and Habib Samady and Stone, {Peter H.} and Renu Virmani and Jagat Narula and Chang, {Hyuk Jae} and Lin, {Fay Y.} and Lohendran Baskaran and Shaw, {Leslee J.} and Min, {James K.}",

note = "Publisher Copyright: {\textcopyright} 2020 American College of Cardiology Foundation",

year = "2020",

month = oct,

doi = "10.1016/j.jcmg.2020.03.025",

language = "English (US)",

volume = "13",

pages = "2162--2173",

journal = "JACC: Cardiovascular Imaging",

issn = "1936-878X",

publisher = "Elsevier Inc.",

number = "10",

}

TY - JOUR

T1 - A Boosted Ensemble Algorithm for Determination of Plaque Stability in High-Risk Patients on Coronary CTA

AU - Al'Aref, Subhi J.

AU - Singh, Gurpreet

AU - Choi, Jeong W.

AU - Xu, Zhuoran

AU - Maliakal, Gabriel

AU - van Rosendael, Alexander R.

AU - Lee, Benjamin C.

AU - Fatima, Zahra

AU - Andreini, Daniele

AU - Bax, Jeroen J.

AU - Cademartiri, Filippo

AU - Chinnaiyan, Kavitha

AU - Chow, Benjamin J.W.

AU - Conte, Edoardo

AU - Cury, Ricardo C.

AU - Feuchtner, Gudruf

AU - Hadamitzky, Martin

AU - Kim, Yong Jin

AU - Lee, Sang Eun

AU - Leipsic, Jonathon A.

AU - Maffei, Erica

AU - Marques, Hugo

AU - Plank, Fabian

AU - Pontone, Gianluca

AU - Raff, Gilbert L.

AU - Villines, Todd C.

AU - Weirich, Harald G.

AU - Cho, Iksung

AU - Danad, Ibrahim

AU - Han, Donghee

AU - Heo, Ran

AU - Lee, Ji Hyun

AU - Rizvi, Asim

AU - Stuijfzand, Wijnand J.

AU - Gransar, Heidi

AU - Lu, Yao

AU - Sung, Ji Min

AU - Park, Hyung Bok

AU - Berman, Daniel S.

AU - Budoff, Matthew J.

AU - Samady, Habib

AU - Stone, Peter H.

AU - Virmani, Renu

AU - Narula, Jagat

AU - Chang, Hyuk Jae

AU - Lin, Fay Y.

AU - Baskaran, Lohendran

AU - Shaw, Leslee J.

AU - Min, James K.

PY - 2020/10

Y1 - 2020/10

N2 - Objectives: This study sought to identify culprit lesion (CL) precursors among acute coronary syndrome (ACS) patients based on qualitative and quantitative computed tomography–based plaque characteristics. Background: Coronary computed tomography angiography (CTA) has been validated for patient-level prediction of ACS. However, the applicability of coronary CTA to CL assessment is not known. Methods: Utilizing the ICONIC (Incident COroNary Syndromes Identified by Computed Tomography) study, a nested case-control study of 468 patients with baseline coronary CTA, the study included ACS patients with invasive coronary angiography–adjudicated CLs that could be aligned to CL precursors on baseline coronary CTA. Separate blinded core laboratories adjudicated CLs and performed atherosclerotic plaque evaluation. Thereafter, the study used a boosted ensemble algorithm (XGBoost) to develop a predictive model of CLs. Data were randomly split into a training set (80%) and a test set (20%). The area under the receiver-operating characteristic curve of this model was compared with that of diameter stenosis (model 1), high-risk plaque features (model 2), and lesion-level features of CL precursors from the ICONIC study (model 3). Thereafter, the machine learning (ML) model was applied to 234 non-ACS patients with 864 lesions to determine model performance for CL exclusion. Results: CL precursors were identified by both coronary angiography and baseline coronary CTA in 124 of 234 (53.0%) patients, with a total of 582 lesions (containing 124 CLs) included in the analysis. The ML model demonstrated significantly higher area under the receiver-operating characteristic curve for discriminating CL precursors (0.774; 95% confidence interval [CI]: 0.758 to 0.790) compared with model 1 (0.599; 95% CI: 0.599 to 0.599; p < 0.01), model 2 (0.532; 95% CI: 0.501 to 0.563; p < 0.01), and model 3 (0.672; 95% CI: 0.662 to 0.682; p < 0.01). When applied to the non-ACS cohort, the ML model had a specificity of 89.3% for excluding CLs. Conclusions: In a high-risk cohort, a boosted ensemble algorithm can be used to predict CL from non-CL precursors on coronary CTA.

AB - Objectives: This study sought to identify culprit lesion (CL) precursors among acute coronary syndrome (ACS) patients based on qualitative and quantitative computed tomography–based plaque characteristics. Background: Coronary computed tomography angiography (CTA) has been validated for patient-level prediction of ACS. However, the applicability of coronary CTA to CL assessment is not known. Methods: Utilizing the ICONIC (Incident COroNary Syndromes Identified by Computed Tomography) study, a nested case-control study of 468 patients with baseline coronary CTA, the study included ACS patients with invasive coronary angiography–adjudicated CLs that could be aligned to CL precursors on baseline coronary CTA. Separate blinded core laboratories adjudicated CLs and performed atherosclerotic plaque evaluation. Thereafter, the study used a boosted ensemble algorithm (XGBoost) to develop a predictive model of CLs. Data were randomly split into a training set (80%) and a test set (20%). The area under the receiver-operating characteristic curve of this model was compared with that of diameter stenosis (model 1), high-risk plaque features (model 2), and lesion-level features of CL precursors from the ICONIC study (model 3). Thereafter, the machine learning (ML) model was applied to 234 non-ACS patients with 864 lesions to determine model performance for CL exclusion. Results: CL precursors were identified by both coronary angiography and baseline coronary CTA in 124 of 234 (53.0%) patients, with a total of 582 lesions (containing 124 CLs) included in the analysis. The ML model demonstrated significantly higher area under the receiver-operating characteristic curve for discriminating CL precursors (0.774; 95% confidence interval [CI]: 0.758 to 0.790) compared with model 1 (0.599; 95% CI: 0.599 to 0.599; p < 0.01), model 2 (0.532; 95% CI: 0.501 to 0.563; p < 0.01), and model 3 (0.672; 95% CI: 0.662 to 0.682; p < 0.01). When applied to the non-ACS cohort, the ML model had a specificity of 89.3% for excluding CLs. Conclusions: In a high-risk cohort, a boosted ensemble algorithm can be used to predict CL from non-CL precursors on coronary CTA.

KW - acute coronary syndrome

KW - coronary computed tomography angiography

KW - diameter stenosis

KW - machine learning

UR - http://www.scopus.com/inward/record.url?scp=85089294571&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85089294571&partnerID=8YFLogxK

U2 - 10.1016/j.jcmg.2020.03.025

DO - 10.1016/j.jcmg.2020.03.025

M3 - Article

C2 - 32682719

AN - SCOPUS:85089294571

SN - 1936-878X

VL - 13

SP - 2162

EP - 2173

JO - JACC: Cardiovascular Imaging

JF - JACC: Cardiovascular Imaging

IS - 10

ER -

A Boosted Ensemble Algorithm for Determination of Plaque Stability in High-Risk Patients on Coronary CTA

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this