Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: A 5-year multicentre prospective registry analysis

Manish Motwani, Damini Dey, Daniel S. Berman, Guido Germano, Stephan Achenbach, Mouaz H. Al-Mallah, Daniele Andreini, Matthew J. Budoff, Filippo Cademartiri, Tracy Q. Callister, Hyuk Jae Chang, Kavitha Chinnaiyan, Benjamin J.W. Chow, Ricardo C. Cury, Augustin Delago, Millie Gomez, Heidi Gransar, Martin Hadamitzky, Joerg Hausleiter, Niree HindoyanGudrun Feuchtner, Philipp A. Kaufmann, Yong Jin Kim, Jonathon Leipsic, Fay Y. Lin, Erica Maffei, Hugo Marques, Gianluca Pontone, Gilbert Raff, Ronen Rubinshtein, Leslee J. Shaw, Julia Stehli, Todd C. Villines, Allison Dunning, James K. Min, Piotr J. Slomka

Research output: Contribution to journalArticle

104 Citations (Scopus)

Abstract

Aims Traditional prognostic risk assessment in patients undergoing non-invasive imaging is based upon a limited selection of clinical and imaging findings. Machine learning (ML) can consider a greater number and complexity of variables. Therefore, we investigated the feasibility and accuracy of ML to predict 5-year all-cause mortality (ACM) in patients undergoing coronary computed tomographic angiography (CCTA), and compared the performance to existing clinical or CCTA metrics. Methods and results The analysis included 10 030 patients with suspected coronary artery disease and 5-year follow-up from the COronary CT Angiography EvaluatioN For Clinical Outcomes: An InteRnational Multicenter registry. All patients underwent CCTA as their standard of care. Twenty-five clinical and 44 CCTA parameters were evaluated, including segment stenosis score (SSS), segment involvement score (SIS), modified Duke index (DI), number of segments with non-calcified, mixed or calcified plaques, age, sex, gender, standard cardiovascular risk factors, and Framingham risk score (FRS). Machine learning involved automated feature selection by information gain ranking, model building with a boosted ensemble algorithm, and 10-fold stratified cross-validation. Seven hundred and forty-five patients died during 5-year follow-up. Machine learning exhibited a higher area-under-curve compared with the FRS or CCTA severity scores alone (SSS, SIS, DI) for predicting all-cause mortality (ML: 0.79 vs. FRS: 0.61, SSS: 0.64, SIS: 0.64, DI: 0.62; P , 0.001). Conclusions Machine learning combining clinical and CCTA data was found to predict 5-year ACM significantly better than existing clinical or CCTA metrics alone.

Original languageEnglish
Pages (from-to)500-507
Number of pages8
JournalEuropean heart journal
Volume38
Issue number7
DOIs
Publication statusPublished - 2017 Feb 1

Fingerprint

Registries
Coronary Artery Disease
Angiography
Mortality
Pathologic Constriction
Standard of Care
Machine Learning
Coronary Angiography
Area Under Curve

All Science Journal Classification (ASJC) codes

  • Cardiology and Cardiovascular Medicine

Cite this

Motwani, Manish ; Dey, Damini ; Berman, Daniel S. ; Germano, Guido ; Achenbach, Stephan ; Al-Mallah, Mouaz H. ; Andreini, Daniele ; Budoff, Matthew J. ; Cademartiri, Filippo ; Callister, Tracy Q. ; Chang, Hyuk Jae ; Chinnaiyan, Kavitha ; Chow, Benjamin J.W. ; Cury, Ricardo C. ; Delago, Augustin ; Gomez, Millie ; Gransar, Heidi ; Hadamitzky, Martin ; Hausleiter, Joerg ; Hindoyan, Niree ; Feuchtner, Gudrun ; Kaufmann, Philipp A. ; Kim, Yong Jin ; Leipsic, Jonathon ; Lin, Fay Y. ; Maffei, Erica ; Marques, Hugo ; Pontone, Gianluca ; Raff, Gilbert ; Rubinshtein, Ronen ; Shaw, Leslee J. ; Stehli, Julia ; Villines, Todd C. ; Dunning, Allison ; Min, James K. ; Slomka, Piotr J. / Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease : A 5-year multicentre prospective registry analysis. In: European heart journal. 2017 ; Vol. 38, No. 7. pp. 500-507.
@article{5a57b1012c31492190461289a9c60530,
title = "Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: A 5-year multicentre prospective registry analysis",
abstract = "Aims Traditional prognostic risk assessment in patients undergoing non-invasive imaging is based upon a limited selection of clinical and imaging findings. Machine learning (ML) can consider a greater number and complexity of variables. Therefore, we investigated the feasibility and accuracy of ML to predict 5-year all-cause mortality (ACM) in patients undergoing coronary computed tomographic angiography (CCTA), and compared the performance to existing clinical or CCTA metrics. Methods and results The analysis included 10 030 patients with suspected coronary artery disease and 5-year follow-up from the COronary CT Angiography EvaluatioN For Clinical Outcomes: An InteRnational Multicenter registry. All patients underwent CCTA as their standard of care. Twenty-five clinical and 44 CCTA parameters were evaluated, including segment stenosis score (SSS), segment involvement score (SIS), modified Duke index (DI), number of segments with non-calcified, mixed or calcified plaques, age, sex, gender, standard cardiovascular risk factors, and Framingham risk score (FRS). Machine learning involved automated feature selection by information gain ranking, model building with a boosted ensemble algorithm, and 10-fold stratified cross-validation. Seven hundred and forty-five patients died during 5-year follow-up. Machine learning exhibited a higher area-under-curve compared with the FRS or CCTA severity scores alone (SSS, SIS, DI) for predicting all-cause mortality (ML: 0.79 vs. FRS: 0.61, SSS: 0.64, SIS: 0.64, DI: 0.62; P , 0.001). Conclusions Machine learning combining clinical and CCTA data was found to predict 5-year ACM significantly better than existing clinical or CCTA metrics alone.",
author = "Manish Motwani and Damini Dey and Berman, {Daniel S.} and Guido Germano and Stephan Achenbach and Al-Mallah, {Mouaz H.} and Daniele Andreini and Budoff, {Matthew J.} and Filippo Cademartiri and Callister, {Tracy Q.} and Chang, {Hyuk Jae} and Kavitha Chinnaiyan and Chow, {Benjamin J.W.} and Cury, {Ricardo C.} and Augustin Delago and Millie Gomez and Heidi Gransar and Martin Hadamitzky and Joerg Hausleiter and Niree Hindoyan and Gudrun Feuchtner and Kaufmann, {Philipp A.} and Kim, {Yong Jin} and Jonathon Leipsic and Lin, {Fay Y.} and Erica Maffei and Hugo Marques and Gianluca Pontone and Gilbert Raff and Ronen Rubinshtein and Shaw, {Leslee J.} and Julia Stehli and Villines, {Todd C.} and Allison Dunning and Min, {James K.} and Slomka, {Piotr J.}",
year = "2017",
month = "2",
day = "1",
doi = "10.1093/eurheartj/ehw188",
language = "English",
volume = "38",
pages = "500--507",
journal = "European Heart Journal",
issn = "0195-668X",
publisher = "Oxford University Press",
number = "7",

}

Motwani, M, Dey, D, Berman, DS, Germano, G, Achenbach, S, Al-Mallah, MH, Andreini, D, Budoff, MJ, Cademartiri, F, Callister, TQ, Chang, HJ, Chinnaiyan, K, Chow, BJW, Cury, RC, Delago, A, Gomez, M, Gransar, H, Hadamitzky, M, Hausleiter, J, Hindoyan, N, Feuchtner, G, Kaufmann, PA, Kim, YJ, Leipsic, J, Lin, FY, Maffei, E, Marques, H, Pontone, G, Raff, G, Rubinshtein, R, Shaw, LJ, Stehli, J, Villines, TC, Dunning, A, Min, JK & Slomka, PJ 2017, 'Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: A 5-year multicentre prospective registry analysis', European heart journal, vol. 38, no. 7, pp. 500-507. https://doi.org/10.1093/eurheartj/ehw188

Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease : A 5-year multicentre prospective registry analysis. / Motwani, Manish; Dey, Damini; Berman, Daniel S.; Germano, Guido; Achenbach, Stephan; Al-Mallah, Mouaz H.; Andreini, Daniele; Budoff, Matthew J.; Cademartiri, Filippo; Callister, Tracy Q.; Chang, Hyuk Jae; Chinnaiyan, Kavitha; Chow, Benjamin J.W.; Cury, Ricardo C.; Delago, Augustin; Gomez, Millie; Gransar, Heidi; Hadamitzky, Martin; Hausleiter, Joerg; Hindoyan, Niree; Feuchtner, Gudrun; Kaufmann, Philipp A.; Kim, Yong Jin; Leipsic, Jonathon; Lin, Fay Y.; Maffei, Erica; Marques, Hugo; Pontone, Gianluca; Raff, Gilbert; Rubinshtein, Ronen; Shaw, Leslee J.; Stehli, Julia; Villines, Todd C.; Dunning, Allison; Min, James K.; Slomka, Piotr J.

In: European heart journal, Vol. 38, No. 7, 01.02.2017, p. 500-507.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease

T2 - A 5-year multicentre prospective registry analysis

AU - Motwani, Manish

AU - Dey, Damini

AU - Berman, Daniel S.

AU - Germano, Guido

AU - Achenbach, Stephan

AU - Al-Mallah, Mouaz H.

AU - Andreini, Daniele

AU - Budoff, Matthew J.

AU - Cademartiri, Filippo

AU - Callister, Tracy Q.

AU - Chang, Hyuk Jae

AU - Chinnaiyan, Kavitha

AU - Chow, Benjamin J.W.

AU - Cury, Ricardo C.

AU - Delago, Augustin

AU - Gomez, Millie

AU - Gransar, Heidi

AU - Hadamitzky, Martin

AU - Hausleiter, Joerg

AU - Hindoyan, Niree

AU - Feuchtner, Gudrun

AU - Kaufmann, Philipp A.

AU - Kim, Yong Jin

AU - Leipsic, Jonathon

AU - Lin, Fay Y.

AU - Maffei, Erica

AU - Marques, Hugo

AU - Pontone, Gianluca

AU - Raff, Gilbert

AU - Rubinshtein, Ronen

AU - Shaw, Leslee J.

AU - Stehli, Julia

AU - Villines, Todd C.

AU - Dunning, Allison

AU - Min, James K.

AU - Slomka, Piotr J.

PY - 2017/2/1

Y1 - 2017/2/1

N2 - Aims Traditional prognostic risk assessment in patients undergoing non-invasive imaging is based upon a limited selection of clinical and imaging findings. Machine learning (ML) can consider a greater number and complexity of variables. Therefore, we investigated the feasibility and accuracy of ML to predict 5-year all-cause mortality (ACM) in patients undergoing coronary computed tomographic angiography (CCTA), and compared the performance to existing clinical or CCTA metrics. Methods and results The analysis included 10 030 patients with suspected coronary artery disease and 5-year follow-up from the COronary CT Angiography EvaluatioN For Clinical Outcomes: An InteRnational Multicenter registry. All patients underwent CCTA as their standard of care. Twenty-five clinical and 44 CCTA parameters were evaluated, including segment stenosis score (SSS), segment involvement score (SIS), modified Duke index (DI), number of segments with non-calcified, mixed or calcified plaques, age, sex, gender, standard cardiovascular risk factors, and Framingham risk score (FRS). Machine learning involved automated feature selection by information gain ranking, model building with a boosted ensemble algorithm, and 10-fold stratified cross-validation. Seven hundred and forty-five patients died during 5-year follow-up. Machine learning exhibited a higher area-under-curve compared with the FRS or CCTA severity scores alone (SSS, SIS, DI) for predicting all-cause mortality (ML: 0.79 vs. FRS: 0.61, SSS: 0.64, SIS: 0.64, DI: 0.62; P , 0.001). Conclusions Machine learning combining clinical and CCTA data was found to predict 5-year ACM significantly better than existing clinical or CCTA metrics alone.

AB - Aims Traditional prognostic risk assessment in patients undergoing non-invasive imaging is based upon a limited selection of clinical and imaging findings. Machine learning (ML) can consider a greater number and complexity of variables. Therefore, we investigated the feasibility and accuracy of ML to predict 5-year all-cause mortality (ACM) in patients undergoing coronary computed tomographic angiography (CCTA), and compared the performance to existing clinical or CCTA metrics. Methods and results The analysis included 10 030 patients with suspected coronary artery disease and 5-year follow-up from the COronary CT Angiography EvaluatioN For Clinical Outcomes: An InteRnational Multicenter registry. All patients underwent CCTA as their standard of care. Twenty-five clinical and 44 CCTA parameters were evaluated, including segment stenosis score (SSS), segment involvement score (SIS), modified Duke index (DI), number of segments with non-calcified, mixed or calcified plaques, age, sex, gender, standard cardiovascular risk factors, and Framingham risk score (FRS). Machine learning involved automated feature selection by information gain ranking, model building with a boosted ensemble algorithm, and 10-fold stratified cross-validation. Seven hundred and forty-five patients died during 5-year follow-up. Machine learning exhibited a higher area-under-curve compared with the FRS or CCTA severity scores alone (SSS, SIS, DI) for predicting all-cause mortality (ML: 0.79 vs. FRS: 0.61, SSS: 0.64, SIS: 0.64, DI: 0.62; P , 0.001). Conclusions Machine learning combining clinical and CCTA data was found to predict 5-year ACM significantly better than existing clinical or CCTA metrics alone.

UR - http://www.scopus.com/inward/record.url?scp=85016207381&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016207381&partnerID=8YFLogxK

U2 - 10.1093/eurheartj/ehw188

DO - 10.1093/eurheartj/ehw188

M3 - Article

C2 - 27252451

AN - SCOPUS:85016207381

VL - 38

SP - 500

EP - 507

JO - European Heart Journal

JF - European Heart Journal

SN - 0195-668X

IS - 7

ER -