Observer variability in the assessment of CT coronary angiography and coronary artery calcium score: substudy of the Scottish COmputed Tomography of the HEART (SCOT-HEART) trial

Abstract

Introduction: Observer variability can influence the assessment of CT coronary angiography (CTCA) and the subsequent diagnosis of angina pectoris due to coronary heart disease.

Methods: We assessed 210 CTCAs from the Scottish COmputed Tomography of the HEART (SCOT-HEART) trial for intraobserver and interobserver variability. Calcium score, coronary angiography and image quality were evaluated. Coronary artery disease was defined as none (<10%), mild (10-49%), moderate (50-70%) and severe (>70%) luminal stenosis and classified as no (<10%), non-obstructive (10-70%) or obstructive (>70%) coronary artery disease. Post-CTCA diagnosis of angina pectoris due to coronary heart disease was classified as yes, probable, unlikely or no.

Results: Patients had a mean body mass index of 29 (28, 30) kg/m(2), heart rate of 58 (57, 60)/min and 62% were men. Intraobserver and interobserver agreements for the presence or absence of coronary artery disease were excellent (95% agreement, κ 0.884 (0.817 to 0.951) and good (91%, 0.791 (0.703 to 0.879)). Intraobserver and interobserver agreement for the presence or absence of angina pectoris due to coronary heart disease were excellent (93%, 0.842 (0.918 to 0.755) and good (86%, 0.701 (0.799 to 0.603)), respectively. Observer variability of calcium score was excellent for calcium scores below 1000. More segments were categorised as uninterpretable with 64-multidetector compared to 320-multidetector CTCA (10.1% vs 2.6%, p<0.001) but there was no difference in observer variability.

Conclusions: Multicentre multidetector CTCA has excellent agreement in patients under investigation for suspected angina due to coronary heart disease.

Trial registration number: NCT01149590.

Keywords: CHEST PAIN CLINIC < CORONARY ARTERY DISEASE; CORONARY ARTERY DISEASE; CT SCANNING < IMAGING AND DIAGNOSTICS; IMAGING AND DIAGNOSTICS.

Figure 1

CT coronary angiography curved planar reformations and vessel cross sections showing lesions with different stenosis severity (none, <10%; mild, 10–49%; moderate, 50–70%; severe, >70%).

Figure 2

Bland-Altman plots for intra and inter observer variability for the assessment of total Agatston score (dotted lines represent the limits of agreement).

Figure 3

Bland-Altman plots for intra and inter observer variability for the assessment of total Agatston score for patients with a calcium score less than 1000 (one outlier was excluded from the inter observer variability assessment, dotted lines represent the limits of agreement).

Figure 4

CT coronary angiography curved planar reconstruction of the left anterior descending coronary artery showing an atherosclerotic plaque with calcified and non-calcified components. The location of this plaque, which spans the origin of the first diagonal vessel, can cause differences in segmental classification between observers as it could be classified as proximal left anterior descending artery, mid left anterior descending artery, or both.

Figure 5

CT coronary angiography images of a heavily calcified left anterior descending artery. The blooming artifact from such heavily calcified plaque can lead to differences in observer classification of stenosis severity.