Multicenter validation of the diagnostic accuracy of a blood-based gene expression test for assessing obstructive coronary artery disease in nondiabetic patients

Abstract

Background: Diagnosing obstructive coronary artery disease (CAD) in at-risk patients can be challenging and typically requires both noninvasive imaging methods and coronary angiography, the gold standard. Previous studies have suggested that peripheral blood gene expression can indicate the presence of CAD.

Objective: To validate a previously developed 23-gene, expression-based classification test for diagnosis of obstructive CAD in nondiabetic patients.

Design: Multicenter prospective trial with blood samples obtained before coronary angiography. (ClinicalTrials.gov registration number: NCT00500617) SETTING: 39 centers in the United States.

Patients: An independent validation cohort of 526 nondiabetic patients with a clinical indication for coronary angiography.

Measurements: Receiver-operating characteristic (ROC) analysis of classifier score measured by real-time polymerase chain reaction, additivity to clinical factors, and reclassification of patient disease likelihood versus disease status defined by quantitative coronary angiography. Obstructive CAD was defined as 50% or greater stenosis in 1 or more major coronary arteries by quantitative coronary angiography.

Results: The area under the ROC curve (AUC) was 0.70 ± 0.02 (P < 0.001); the test added to clinical variables (Diamond-Forrester method) (AUC, 0.72 with the test vs. 0.66 without; P = 0.003) and added somewhat to an expanded clinical model (AUC, 0.745 with the test vs. 0.732 without; P = 0.089). The test improved net reclassification over both the Diamond-Forrester method and the expanded clinical model (P < 0.001). At a score threshold that corresponded to a 20% likelihood of obstructive CAD (14.75), the sensitivity and specificity were 85% and 43% (yielding a negative predictive value of 83% and a positive predictive value of 46%), with 33% of patient scores below this threshold.

Limitation: Patients with chronic inflammatory disorders, elevated levels of leukocytes or cardiac protein markers, or diabetes were excluded.

Conclusion: A noninvasive whole-blood test based on gene expression and demographic characteristics may be useful for assessing obstructive CAD in nondiabetic patients without known CAD.

Primary funding source: CardioDx.

Figure 1

Allocation of Patients from the PREDICT trial for algorithm development and validation. From a total of 1569 subjects meeting the study inclusion/exclusion criteria 226 were used for gene discovery. The remaining 1343 were divided into independent cohorts for algorithm development (694) and validation (649) as shown; 94% of patients in these cohorts came from the same centers. For algorithm development a total of 640 patient samples were used; 54 were excluded due to incomplete data (13), inadequate blood volume (19), sex mismatch between experimental and clinical records (5), or statistical outlier assessment (17) (see Supplement for details). For the validation cohort a total of 123 samples were excluded based on: inadequate blood volume or RNA yield (43), significant contamination with genomic DNA (78), or prespecified statistical outlier assessment (2).

Figure 2

Schematic of the Algorithm Structure and Genes. The algorithm consists of overlapping gene expression functions for males and females with a sex-specific linear age function for the former and a non-linear age function for the latter. For the gene expression components shown 16/23 genes in 4 terms are gender independent: term 1 – neutrophil activation and apoptosis, term 3 – NK cell activation to T cell ratio, term 4, B to T cell ratio, and term 5 –expression of gene AF289562 normalized to the mean of TFCP2 and HNRPF. In addition, Term 2 consists of 3 sex-independent neutrophil/innate immunity genes normalized in a sex-specific way to neutrophil gene expression (AQP9,NCF4) for females and to RPL28 (lymphocytes) in males. The final male specific term is the normalized expression of TSPAN16. The raw algorithm score is calculated from RT-PCR data as described (Appendix 3); for clinical use, the raw score was converted to a 0–40 scale by linear transformation.

Figure 3

ROC analysis of Validation Cohort Performance For Algorithm and Clinical Variables. Algorithm performance adds to Clinical Factors by Diamond-Forrester. Comparison of the combination of D–F score and algorithm score (heavy solid line) to D–F score alone (---) in ROC analysis is shown. The AUC=0.50 line (light solid line) is shown for reference. A total of 525 of the 526 validation cohort patients had information available to calculate D–F scores. The AUCs for the two ROC curves are 0.721 ± 0.023 and 0.663 ±0.025, p = 0.003.

Figure 4

Dependence of Algorithm Score on % Maximum Stenosis in the Validation Cohort. The extent of disease for each patient was quantified by QCA maximum % stenosis and grouped into 5 categories: no measurable disease, 1–24%, 25–49% in ≥1 vessel, 1 vessel >50%, and >1 vessel >50%. The average algorithm score for each group is illustrated; error bars correspond to 95% confidence intervals. The complete relationship of algorithm score to obstructive CAD likelihood is depicted in Supplementary Figure 1; in Figure 4 scores of 10, 20, and 30 correspond to 15, 30, and 57% disease likelihood. A score of 15, corresponding to a 20% likelihood was used for dichotomous analyses as described in the text.