Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Sep 11;1(2):qyad026.
doi: 10.1093/ehjimp/qyad026. eCollection 2023 Sep.

Pre-screening for non-diagnostic coronary computed tomography angiography

Ramtin Hakimjavadi  1 , Juan Lu  2   3   4 , Yeung Yam  1 , Girish Dwivedi  2   4   5 , Gary R Small  1 , Benjamin J W Chow  1   6
Affiliations

Pre-screening for non-diagnostic coronary computed tomography angiography

Ramtin Hakimjavadi et al. Eur Heart J Imaging Methods Pract. .

Abstract

Aims: Indiscriminate coronary computed tomography angiography (CCTA) referrals for suspected coronary artery disease could result in a higher rate of equivocal and non-diagnostic studies, leading to inappropriate downstream resource utilization or delayed time to diagnosis. We sought to develop a simple clinical tool for predicting the likelihood of a non-diagnostic CCTA to help identify patients who might be better served with a different test.

Methods and results: We developed a clinical scoring system from a cohort of 21 492 consecutive patients who underwent CCTA between February 2006 and May 2021. Coronary computed tomography angiography study results were categorized as normal, abnormal, or non-diagnostic. Multivariable logistic regression analysis was conducted to produce a model that predicted the likelihood of a non-diagnostic test. Machine learning (ML) models were utilized to validate the predictor selection and prediction performance. Both logistic regression and ML models achieved fair discriminate ability with an area under the curve of 0.630 [95% confidence interval (CI) 0.618-0.641] and 0.634 (95% CI 0.612-0.656), respectively. The presence of a cardiac implant and weight >100 kg were among the most influential predictors of a non-diagnostic study.

Conclusion: We developed a model that could be implemented at the 'point-of-scheduling' to identify patients who would be best served by another non-invasive diagnostic test.

Keywords: cardiac imaging techniques; coronary computed tomographic angiography; image interpretation; non-diagnostic tests; prediction model.

PubMed Disclaimer

Conflict of interest statement

Conflicts of interest: Benjamin Chow holds the Saul and Edna Goldfarb Chair in Cardiac Imaging Research. He receives research support from TD Bank, AusculSciences, Siemens Healthineers, and Artrya. The remaining authors have nothing to disclose.

Figures

Graphical abstract
Graphical abstract
Point scoring system for prediction of non-diagnostic coronary computed tomographic angiography (CCTA). Points are assigned for each variable in the table. The risk of obtaining a non-diagnostic CCTA study for the patient being considered is based on the total score. A patient with a score greater than 23 has a high likelihood of receiving a non-diagnostic CCTA study. ASA, acetylsalicylic acid; CCTA, coronary computed tomographic angiography; CRT, cardiac resynchronization therapy; ICD, implantable cardioverter-defibrillator; PPM, permanent pacemaker.
Figure 1
Figure 1
Receiver operating characteristic curve of the model to predict non-diagnostic CCTA in the model derivation cohort.
Figure 2
Figure 2
Variable (feature) importance plot for the GBDT model. The top 20 input variables are shown in this figure. The blue and red points in each row represent patients’ low to high values of the specific variable, while the x-axis gives the SHAP values which measures the feature impact on the model. Positive SHAP values indicate the variable tend to drive the predictions towards events, and negative SHAP values indicate the variable tend to drive the prediction towards non-events. ACE, angiotensin-converting enzyme inhibitor; ASA, acetylsalicylic acid; CP, chest pain; MRI, magnetic resonance imaging; PPI, proton pump inhibitors; SHAP , Shapley additive explanation.
Figure 3
Figure 3
Prevalence of non-diagnostic CCTA at different scores. The distribution of the model derivation cohort according to the number of points assigned based on the scoring system to predict non-diagnostic CCTA. CCTA, coronary computed tomographic angiography.
See this image and copyright information in PMC

References

    1. Knuuti J, Wijns W, Saraste A, Capodanno D, Barbato E, Funck-Brentano Cet al. . 2019 ESC guidelines for the diagnosis and management of chronic coronary syndromes. Eur Heart J 2020;41:407–77. - PubMed
    1. Timmis A, Roobottom CA. National Institute for Health and Care Excellence updates the stable chest pain guideline with radical changes to the diagnostic paradigm. Heart Br Card Soc 2017;103:982–6. - PubMed
    1. Achenbach S. Coronary CT angiography: native vessels. In: Budoff MJ and Shinbane JS (eds.), Cardiac CT Imaging: Diagnosis of Cardiovascular Disease [Internet]. Cham: Springer International Publishing; 2016. p157–78. [cited 2021 Jul 16] .
    1. Dewey M, Vavere AL, Arbab-Zadeh A, Miller JM, Sara L, Cox Cet al. . Patient characteristics as predictors of image quality and diagnostic accuracy of MDCT compared with conventional coronary angiography for detecting coronary artery stenoses: CORE-64 multicenter international trial. AJR Am J Roentgenol 2010;194:93–102. - PMC - PubMed
    1. Engel LC, Thai WEE, Medina-Zuluaga H, Karolyi M, Sidhu MS, Maurovich-Horvat Pet al. . Non-diagnostic coronary artery calcification and stenosis: a correlation of coronary computed tomography angiography and invasive coronary angiography. Acta Radiol 2017;58:528–36. - PubMed

LinkOut - more resources