Cardiac ScoreCard

A diagnostic multivariate index assay system for predicting a spectrum of cardiovascular disease

Michael P. McRae, Biykem Bozkurt, Christie M. Ballantyne, Ximena Sanchez, Nicolaos Christodoulides, Glennon Simmons, Vijay Nambi, Arunima Misra, Craig S. Miller, Jeffrey L. Ebersole, Charles Campbell, John McDevitt

Research output: Contribution to journalArticle

Abstract

Clinical decision support systems (CDSSs) have the potential to save lives and reduce unnecessary costs through early detection and frequent monitoring of both traditional risk factors and novel biomarkers for cardiovascular disease (CVD). However, the widespread adoption of CDSSs for the identification of heart diseases has been limited, likely due to the poor interpretability of clinically relevant results and the lack of seamless integration between measurements and disease predictions. In this paper we present the Cardiac ScoreCard - a multivariate index assay system with the potential to assist in the diagnosis and prognosis of a spectrum of CVD. The Cardiac ScoreCard system is based on lasso logistic regression techniques which utilize both patient demographics and novel biomarker data for the prediction of heart failure (HF) and cardiac wellness. Lasso logistic regression models were trained on a merged clinical dataset comprising 579 patients with 6 traditional risk factors and 14 biomarker measurements. The prediction performance of the Cardiac ScoreCard was assessed with 5-fold cross-validation and compared with reference methods. The experimental results reveal that the ScoreCard models improved performance in discriminating disease versus non-case (AUC = 0.8403 and 0.9412 for cardiac wellness and HF, respectively), and the models exhibit good calibration. Clinical insights to the prediction of HF and cardiac wellness are provided in the form of logistic regression coefficients which suggest that augmenting the traditional risk factors with a multimarker panel spanning a diverse cardiovascular pathophysiology provides improved performance over reference methods. Additionally, a framework is provided for seamless integration with biomarker measurements from point-of-care medical microdevices, and a lasso-based feature selection process is described for the down-selection of biomarkers in multimarker panels.

Original languageEnglish (US)
Pages (from-to)136-147
Number of pages12
JournalExpert Systems with Applications
Volume54
DOIs
StatePublished - Jul 15 2016

Fingerprint

Biomarkers
Assays
Logistics
Decision support systems
Health care
Feature extraction
Calibration
Monitoring
Costs

Keywords

  • Biomarkers
  • Cardiac wellness
  • Cardiovascular disease (CVD)
  • Heart failure (HF)
  • Lasso logistic regression
  • Programmable bio-nano-chip (p-BNC)

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Engineering(all)

Cite this

Cardiac ScoreCard : A diagnostic multivariate index assay system for predicting a spectrum of cardiovascular disease. / McRae, Michael P.; Bozkurt, Biykem; Ballantyne, Christie M.; Sanchez, Ximena; Christodoulides, Nicolaos; Simmons, Glennon; Nambi, Vijay; Misra, Arunima; Miller, Craig S.; Ebersole, Jeffrey L.; Campbell, Charles; McDevitt, John.

In: Expert Systems with Applications, Vol. 54, 15.07.2016, p. 136-147.

Research output: Contribution to journalArticle

McRae, MP, Bozkurt, B, Ballantyne, CM, Sanchez, X, Christodoulides, N, Simmons, G, Nambi, V, Misra, A, Miller, CS, Ebersole, JL, Campbell, C & McDevitt, J 2016, 'Cardiac ScoreCard: A diagnostic multivariate index assay system for predicting a spectrum of cardiovascular disease', Expert Systems with Applications, vol. 54, pp. 136-147. https://doi.org/10.1016/j.eswa.2016.01.029
McRae, Michael P. ; Bozkurt, Biykem ; Ballantyne, Christie M. ; Sanchez, Ximena ; Christodoulides, Nicolaos ; Simmons, Glennon ; Nambi, Vijay ; Misra, Arunima ; Miller, Craig S. ; Ebersole, Jeffrey L. ; Campbell, Charles ; McDevitt, John. / Cardiac ScoreCard : A diagnostic multivariate index assay system for predicting a spectrum of cardiovascular disease. In: Expert Systems with Applications. 2016 ; Vol. 54. pp. 136-147.
@article{e456a5211b1743e2971e7e12c63c0512,
title = "Cardiac ScoreCard: A diagnostic multivariate index assay system for predicting a spectrum of cardiovascular disease",
abstract = "Clinical decision support systems (CDSSs) have the potential to save lives and reduce unnecessary costs through early detection and frequent monitoring of both traditional risk factors and novel biomarkers for cardiovascular disease (CVD). However, the widespread adoption of CDSSs for the identification of heart diseases has been limited, likely due to the poor interpretability of clinically relevant results and the lack of seamless integration between measurements and disease predictions. In this paper we present the Cardiac ScoreCard - a multivariate index assay system with the potential to assist in the diagnosis and prognosis of a spectrum of CVD. The Cardiac ScoreCard system is based on lasso logistic regression techniques which utilize both patient demographics and novel biomarker data for the prediction of heart failure (HF) and cardiac wellness. Lasso logistic regression models were trained on a merged clinical dataset comprising 579 patients with 6 traditional risk factors and 14 biomarker measurements. The prediction performance of the Cardiac ScoreCard was assessed with 5-fold cross-validation and compared with reference methods. The experimental results reveal that the ScoreCard models improved performance in discriminating disease versus non-case (AUC = 0.8403 and 0.9412 for cardiac wellness and HF, respectively), and the models exhibit good calibration. Clinical insights to the prediction of HF and cardiac wellness are provided in the form of logistic regression coefficients which suggest that augmenting the traditional risk factors with a multimarker panel spanning a diverse cardiovascular pathophysiology provides improved performance over reference methods. Additionally, a framework is provided for seamless integration with biomarker measurements from point-of-care medical microdevices, and a lasso-based feature selection process is described for the down-selection of biomarkers in multimarker panels.",
keywords = "Biomarkers, Cardiac wellness, Cardiovascular disease (CVD), Heart failure (HF), Lasso logistic regression, Programmable bio-nano-chip (p-BNC)",
author = "McRae, {Michael P.} and Biykem Bozkurt and Ballantyne, {Christie M.} and Ximena Sanchez and Nicolaos Christodoulides and Glennon Simmons and Vijay Nambi and Arunima Misra and Miller, {Craig S.} and Ebersole, {Jeffrey L.} and Charles Campbell and John McDevitt",
year = "2016",
month = "7",
day = "15",
doi = "10.1016/j.eswa.2016.01.029",
language = "English (US)",
volume = "54",
pages = "136--147",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Cardiac ScoreCard

T2 - A diagnostic multivariate index assay system for predicting a spectrum of cardiovascular disease

AU - McRae, Michael P.

AU - Bozkurt, Biykem

AU - Ballantyne, Christie M.

AU - Sanchez, Ximena

AU - Christodoulides, Nicolaos

AU - Simmons, Glennon

AU - Nambi, Vijay

AU - Misra, Arunima

AU - Miller, Craig S.

AU - Ebersole, Jeffrey L.

AU - Campbell, Charles

AU - McDevitt, John

PY - 2016/7/15

Y1 - 2016/7/15

N2 - Clinical decision support systems (CDSSs) have the potential to save lives and reduce unnecessary costs through early detection and frequent monitoring of both traditional risk factors and novel biomarkers for cardiovascular disease (CVD). However, the widespread adoption of CDSSs for the identification of heart diseases has been limited, likely due to the poor interpretability of clinically relevant results and the lack of seamless integration between measurements and disease predictions. In this paper we present the Cardiac ScoreCard - a multivariate index assay system with the potential to assist in the diagnosis and prognosis of a spectrum of CVD. The Cardiac ScoreCard system is based on lasso logistic regression techniques which utilize both patient demographics and novel biomarker data for the prediction of heart failure (HF) and cardiac wellness. Lasso logistic regression models were trained on a merged clinical dataset comprising 579 patients with 6 traditional risk factors and 14 biomarker measurements. The prediction performance of the Cardiac ScoreCard was assessed with 5-fold cross-validation and compared with reference methods. The experimental results reveal that the ScoreCard models improved performance in discriminating disease versus non-case (AUC = 0.8403 and 0.9412 for cardiac wellness and HF, respectively), and the models exhibit good calibration. Clinical insights to the prediction of HF and cardiac wellness are provided in the form of logistic regression coefficients which suggest that augmenting the traditional risk factors with a multimarker panel spanning a diverse cardiovascular pathophysiology provides improved performance over reference methods. Additionally, a framework is provided for seamless integration with biomarker measurements from point-of-care medical microdevices, and a lasso-based feature selection process is described for the down-selection of biomarkers in multimarker panels.

AB - Clinical decision support systems (CDSSs) have the potential to save lives and reduce unnecessary costs through early detection and frequent monitoring of both traditional risk factors and novel biomarkers for cardiovascular disease (CVD). However, the widespread adoption of CDSSs for the identification of heart diseases has been limited, likely due to the poor interpretability of clinically relevant results and the lack of seamless integration between measurements and disease predictions. In this paper we present the Cardiac ScoreCard - a multivariate index assay system with the potential to assist in the diagnosis and prognosis of a spectrum of CVD. The Cardiac ScoreCard system is based on lasso logistic regression techniques which utilize both patient demographics and novel biomarker data for the prediction of heart failure (HF) and cardiac wellness. Lasso logistic regression models were trained on a merged clinical dataset comprising 579 patients with 6 traditional risk factors and 14 biomarker measurements. The prediction performance of the Cardiac ScoreCard was assessed with 5-fold cross-validation and compared with reference methods. The experimental results reveal that the ScoreCard models improved performance in discriminating disease versus non-case (AUC = 0.8403 and 0.9412 for cardiac wellness and HF, respectively), and the models exhibit good calibration. Clinical insights to the prediction of HF and cardiac wellness are provided in the form of logistic regression coefficients which suggest that augmenting the traditional risk factors with a multimarker panel spanning a diverse cardiovascular pathophysiology provides improved performance over reference methods. Additionally, a framework is provided for seamless integration with biomarker measurements from point-of-care medical microdevices, and a lasso-based feature selection process is described for the down-selection of biomarkers in multimarker panels.

KW - Biomarkers

KW - Cardiac wellness

KW - Cardiovascular disease (CVD)

KW - Heart failure (HF)

KW - Lasso logistic regression

KW - Programmable bio-nano-chip (p-BNC)

UR - http://www.scopus.com/inward/record.url?scp=84958543125&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84958543125&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2016.01.029

DO - 10.1016/j.eswa.2016.01.029

M3 - Article

VL - 54

SP - 136

EP - 147

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

ER -