A Cancer Paradox: Machine-Learning Backed Propensity-Score Analysis of Coronary Angiography Findings in Cardio-Oncology

Dinu Valentin Balanescu, Dominique J. Monlezun, Teodora Donisan, David Boone, Frances Cervoni-Curet, Nicolas L Palaskas, Juan Lopez-Mattei, Peter Kim, Cezar Iliescu, Serban Mihai Balanescu

Research output: Contribution to journalArticle

Abstract

OBJECTIVES: Cancer has been proposed as a cardiovascular risk factor. We aimed to assess the cardiovascular risk profile and coronary angiography (CA) findings of cancer patients and compare them to those of patients without cancer. METHODS: A retrospective case-control analysis was conducted on randomly enrolled cancer and non-cancer patients from a high-volume cardio-oncology center and a tertiary cardiology center, respectively, who underwent CA from April 2008 to June 2018. Baseline demographics, laboratory findings, cancer status and treatment, and current and prior CA findings were collected by chart review. Coronary artery disease (CAD) burden was assessed with machine-learning (neural-network) guided propensity-score adjusted multivariable regression, controlling for known CAD confounders. RESULTS: Of the 480 enrolled patients, a total of 240 (50%) had cancer. Fewer cancer vs non-cancer patients had clinically significant lesions on the left anterior descending artery (25.00% vs 39.17%, respectively; P<.01) and left circumflex artery (15.83% vs 30.00%, respectively; P<.001). Left main and right coronary artery disease prevalence was similar. Subjects with cancer were less likely to have multivessel CAD (odds ratio, 0.53; 95% confidence interval, 0.29-0.98; P=.04) and significant left circumflex artery lesions (odds ratio, 0.47; 95% confidence interval, 0.26-0.85; P=.01), independent of known CAD confounders. CONCLUSIONS: Patients with cancer have a lower burden of angiographically detected coronary atherosclerosis. Cancer patients are more likely than non-cancer patients to undergo CA for reasons other than suspicion of CAD. Further studies should prospectively analyze the impact of cancer on the development of CAD.

Original languageEnglish (US)
Pages (from-to)21-26
Number of pages6
JournalThe Journal of invasive cardiology
Volume31
Issue number1
StatePublished - Jan 1 2019

Fingerprint

Propensity Score
Coronary Angiography
Coronary Artery Disease
Neoplasms
Arteries
Machine Learning
Odds Ratio
Confidence Intervals
Cardiology
Demography

Keywords

  • cardio-oncology
  • coronary angiography
  • coronary artery disease
  • machine learning
  • risk factors

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Cardiology and Cardiovascular Medicine

Cite this

Balanescu, D. V., Monlezun, D. J., Donisan, T., Boone, D., Cervoni-Curet, F., Palaskas, N. L., ... Balanescu, S. M. (2019). A Cancer Paradox: Machine-Learning Backed Propensity-Score Analysis of Coronary Angiography Findings in Cardio-Oncology. The Journal of invasive cardiology, 31(1), 21-26.

A Cancer Paradox : Machine-Learning Backed Propensity-Score Analysis of Coronary Angiography Findings in Cardio-Oncology. / Balanescu, Dinu Valentin; Monlezun, Dominique J.; Donisan, Teodora; Boone, David; Cervoni-Curet, Frances; Palaskas, Nicolas L; Lopez-Mattei, Juan; Kim, Peter; Iliescu, Cezar; Balanescu, Serban Mihai.

In: The Journal of invasive cardiology, Vol. 31, No. 1, 01.01.2019, p. 21-26.

Research output: Contribution to journalArticle

Balanescu, Dinu Valentin ; Monlezun, Dominique J. ; Donisan, Teodora ; Boone, David ; Cervoni-Curet, Frances ; Palaskas, Nicolas L ; Lopez-Mattei, Juan ; Kim, Peter ; Iliescu, Cezar ; Balanescu, Serban Mihai. / A Cancer Paradox : Machine-Learning Backed Propensity-Score Analysis of Coronary Angiography Findings in Cardio-Oncology. In: The Journal of invasive cardiology. 2019 ; Vol. 31, No. 1. pp. 21-26.
@article{1e7a78cdc4064c059bf9bcc1c81b1244,
title = "A Cancer Paradox: Machine-Learning Backed Propensity-Score Analysis of Coronary Angiography Findings in Cardio-Oncology",
abstract = "OBJECTIVES: Cancer has been proposed as a cardiovascular risk factor. We aimed to assess the cardiovascular risk profile and coronary angiography (CA) findings of cancer patients and compare them to those of patients without cancer. METHODS: A retrospective case-control analysis was conducted on randomly enrolled cancer and non-cancer patients from a high-volume cardio-oncology center and a tertiary cardiology center, respectively, who underwent CA from April 2008 to June 2018. Baseline demographics, laboratory findings, cancer status and treatment, and current and prior CA findings were collected by chart review. Coronary artery disease (CAD) burden was assessed with machine-learning (neural-network) guided propensity-score adjusted multivariable regression, controlling for known CAD confounders. RESULTS: Of the 480 enrolled patients, a total of 240 (50{\%}) had cancer. Fewer cancer vs non-cancer patients had clinically significant lesions on the left anterior descending artery (25.00{\%} vs 39.17{\%}, respectively; P<.01) and left circumflex artery (15.83{\%} vs 30.00{\%}, respectively; P<.001). Left main and right coronary artery disease prevalence was similar. Subjects with cancer were less likely to have multivessel CAD (odds ratio, 0.53; 95{\%} confidence interval, 0.29-0.98; P=.04) and significant left circumflex artery lesions (odds ratio, 0.47; 95{\%} confidence interval, 0.26-0.85; P=.01), independent of known CAD confounders. CONCLUSIONS: Patients with cancer have a lower burden of angiographically detected coronary atherosclerosis. Cancer patients are more likely than non-cancer patients to undergo CA for reasons other than suspicion of CAD. Further studies should prospectively analyze the impact of cancer on the development of CAD.",
keywords = "cardio-oncology, coronary angiography, coronary artery disease, machine learning, risk factors",
author = "Balanescu, {Dinu Valentin} and Monlezun, {Dominique J.} and Teodora Donisan and David Boone and Frances Cervoni-Curet and Palaskas, {Nicolas L} and Juan Lopez-Mattei and Peter Kim and Cezar Iliescu and Balanescu, {Serban Mihai}",
year = "2019",
month = "1",
day = "1",
language = "English (US)",
volume = "31",
pages = "21--26",
journal = "Journal of Invasive Cardiology",
issn = "1042-3931",
publisher = "HMP Communications",
number = "1",

}

TY - JOUR

T1 - A Cancer Paradox

T2 - Machine-Learning Backed Propensity-Score Analysis of Coronary Angiography Findings in Cardio-Oncology

AU - Balanescu, Dinu Valentin

AU - Monlezun, Dominique J.

AU - Donisan, Teodora

AU - Boone, David

AU - Cervoni-Curet, Frances

AU - Palaskas, Nicolas L

AU - Lopez-Mattei, Juan

AU - Kim, Peter

AU - Iliescu, Cezar

AU - Balanescu, Serban Mihai

PY - 2019/1/1

Y1 - 2019/1/1

N2 - OBJECTIVES: Cancer has been proposed as a cardiovascular risk factor. We aimed to assess the cardiovascular risk profile and coronary angiography (CA) findings of cancer patients and compare them to those of patients without cancer. METHODS: A retrospective case-control analysis was conducted on randomly enrolled cancer and non-cancer patients from a high-volume cardio-oncology center and a tertiary cardiology center, respectively, who underwent CA from April 2008 to June 2018. Baseline demographics, laboratory findings, cancer status and treatment, and current and prior CA findings were collected by chart review. Coronary artery disease (CAD) burden was assessed with machine-learning (neural-network) guided propensity-score adjusted multivariable regression, controlling for known CAD confounders. RESULTS: Of the 480 enrolled patients, a total of 240 (50%) had cancer. Fewer cancer vs non-cancer patients had clinically significant lesions on the left anterior descending artery (25.00% vs 39.17%, respectively; P<.01) and left circumflex artery (15.83% vs 30.00%, respectively; P<.001). Left main and right coronary artery disease prevalence was similar. Subjects with cancer were less likely to have multivessel CAD (odds ratio, 0.53; 95% confidence interval, 0.29-0.98; P=.04) and significant left circumflex artery lesions (odds ratio, 0.47; 95% confidence interval, 0.26-0.85; P=.01), independent of known CAD confounders. CONCLUSIONS: Patients with cancer have a lower burden of angiographically detected coronary atherosclerosis. Cancer patients are more likely than non-cancer patients to undergo CA for reasons other than suspicion of CAD. Further studies should prospectively analyze the impact of cancer on the development of CAD.

AB - OBJECTIVES: Cancer has been proposed as a cardiovascular risk factor. We aimed to assess the cardiovascular risk profile and coronary angiography (CA) findings of cancer patients and compare them to those of patients without cancer. METHODS: A retrospective case-control analysis was conducted on randomly enrolled cancer and non-cancer patients from a high-volume cardio-oncology center and a tertiary cardiology center, respectively, who underwent CA from April 2008 to June 2018. Baseline demographics, laboratory findings, cancer status and treatment, and current and prior CA findings were collected by chart review. Coronary artery disease (CAD) burden was assessed with machine-learning (neural-network) guided propensity-score adjusted multivariable regression, controlling for known CAD confounders. RESULTS: Of the 480 enrolled patients, a total of 240 (50%) had cancer. Fewer cancer vs non-cancer patients had clinically significant lesions on the left anterior descending artery (25.00% vs 39.17%, respectively; P<.01) and left circumflex artery (15.83% vs 30.00%, respectively; P<.001). Left main and right coronary artery disease prevalence was similar. Subjects with cancer were less likely to have multivessel CAD (odds ratio, 0.53; 95% confidence interval, 0.29-0.98; P=.04) and significant left circumflex artery lesions (odds ratio, 0.47; 95% confidence interval, 0.26-0.85; P=.01), independent of known CAD confounders. CONCLUSIONS: Patients with cancer have a lower burden of angiographically detected coronary atherosclerosis. Cancer patients are more likely than non-cancer patients to undergo CA for reasons other than suspicion of CAD. Further studies should prospectively analyze the impact of cancer on the development of CAD.

KW - cardio-oncology

KW - coronary angiography

KW - coronary artery disease

KW - machine learning

KW - risk factors

UR - http://www.scopus.com/inward/record.url?scp=85059498244&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059498244&partnerID=8YFLogxK

M3 - Article

VL - 31

SP - 21

EP - 26

JO - Journal of Invasive Cardiology

JF - Journal of Invasive Cardiology

SN - 1042-3931

IS - 1

ER -