JACC Publication

“A Clinical and Biomarker Scoring System to Predict the Presence of Obstructive Coronary Artery Disease”

Journal of the American College of Cardiology (JACC)

March 7, 2017 (Print Issue)

Highlights

  • The HART CAD panel consisted of clinical variables (male sex, prior percutaneous coronary intervention [PCI]) and four biomarkers (midkine, adiponectin, apolipoprotein C-I, kidney injury molecule-1). 

  • The HART CAD panel generated had an AUC of 0.87. 

  • Results from dividing the score into 5 categories of predicted risk demonstrated a NPV of 91% and a PPV of 93%.

  • As compared to cardiac stress testing (standard of care), The HART CAD panel was substantially more accurate for predicting angiographically severe CAD (0.87 vs. 0.52; <0.001 for difference in AUC).

  • The HART CAD panel performed particularly well in women, and while one element of the score was prior PCI, the score performance was similar in subjects without a history of CAD.

Study Overview

APPROACH

Using patients referred to coronary angiography for a broad range of indications, a novel scoring system (HART CAD panel) has been developed to predict the presence of severe epicardial Coronary Artery Disease (CAD) defined as ≥70% stenosis in at least one major vessel.

GOAL

Identify clinical and biomarker predictors of clinically significant CAD in an at-risk population of subjects enrolled in the Catheter Sampled Blood Archive in Cardiovascular Diseases Study (CASABLANCA; Clinical Trials.Gov NCT00842868) undergoing coronary angiography for numerous indications.

HYPOTHESIS

The addition of plasma biomarkers to known clinical risk factors may increase the accuracy of predicting clinically significant CAD.

METHODS

A convenience sample of 1251 patients undergoing coronary and/or peripheral angiography with or without intervention between 2008 and 2011 were prospectively enrolled at the Massachusetts General Hospital in Boston, Massachusetts.

The CASABLANCA patients selected for this analysis consisted of the chronologically initial 927 patients who received a coronary angiogram. These include patients who may have also received a peripheral angiogram concomitantly. The 927 patients selected for analysis were randomly split into a training set (70%, or n=649) and a holdout validation set (30%, or n=278).

MACHINE LEARNING & BIG DATA
Candiate panels of biomarkers and clinical variables were generated and evaluated with machine learning statistical techniques, a subset of Artificial Intelligence (AI). The ultimate result of this process was a final test panel and scoring system predicting the outcome of the presence of ≥ 70% obstruction in at least one coronary artery, using only the variables in the panel of interest.

Multivariable logistic regression evaluated the performance of the model in the training set as a whole as well as in several relevant subgroups. Operating characteristics of the score were calculated, with sensitivity, specificity, positive and negative predictive value (PPV, NPV) generated. The range of the diagnostic model was the partitioned into five different risk levels, corresponding to the multiple levels of risk for CAD.

Lastly, to evaluate prognostic meaning of the HART CAD score, age- and CAD score-adjusted Cox proportional hazards analyses were performed to evaluate whether a score above the optimal threshold for CAD diagnosis also predicted future acute myocardial infarction (MI). Also, the time to first acute MI event as a function of elevated HART CAD score was calculated. 

Key Findings

SCORING SYSTEM
The HART CAD panel consisted of clinical variables (male sex, prior percutaneous coronary intervention) and four biomarkers (midkine, adiponectin, apolipoprotein C-I, kidney injury molecule-1).  In ROC testing, for the gold-standard diagnosis of ≥70% stenosis of any major epicardial coronary artery, the scores generated had an AUC of 0.87.  The AUC of the score for predicting severe CAD in subjects presenting without an acute MI was also 0.87.

The results from dividing the score into 5 categories of predicted risk demonstrated a NPV of 91% for a score of 1 (very low likelihood of CAD) and a PPV of 93% for a score of 5 (very high likelihood of CAD).

COMPARISON TO STRESS TESTING

Among the patients undergoing cardiac stress testing per standard of care, the CAD score was substantially more accurate for predicting angiographically severe CAD (0.87 vs. 0.52; <0.001 for difference in AUC).

PROGNOSTIC VALUE

During a mean follow up of 3.6 years, in the entire cohort of subjects, the CAD scoring system independently predicted subsequent incident acute MI in age and score-adjusted models.
 

OTHER FINDINGS

Importantly, The HART CAD panel performed particularly well in women, and while one element of the score was prior PCI, the score performance was similar in subjects without a history of CAD. It was also accurate for predicting significant epicardial stenoses in those without prevalent MI.

Conclusions

A clinical and biomarker scoring strategy to reliably diagnose presence of severe epicardial CAD has been developed.  Advantages of a reliable clinical and biomarker score for diagnosing CAD presence include the fact such a technology can be widely disseminated in a cost-effective manner, easily interpreted, and may be associated with a well-defined sequence of therapeutic steps to reduce risk for CAD-related complications, such as antiplatelet or lipid lowering therapy. Further studies using our scoring system are planned.

Scroll Down for JACC Publication

The Publication