The goal of this observational and diagnostic study is to develop and validate an artificial intelligence assisted approach for coronary computer tomography angiography-(CCTA)-based screening and diagnosis of cardiomyopathies in patients with suspected coronary artery diseases. This study aims to develop a computerized CCTA interpretation using artificial intelligence for multi-label classification task to assist cardiomyopathy diagnosis in the clinical workflow.
Cardiovascular diseases (CVD) are the leading causes of death and disability worldwide. With coronary artery disease accounting for a large proportion of CVD disease burden, coronary computer tomography angiography (CCTA) has become widely used for a comprehensive assessment of the total coronary atherosclerotic burden. In contrast, cardiac magnetic resonance (CMR) remains the gold standard for evaluating and diagnosing cardiomyopathies. However, clinical application of CMR has been hindered by the time and cost of examination and shortage of qualified doctors and staff. Consequently, the value of CCTA in screening and diagnosis in cardiomyopathies warrants further investigation. The ability of artificial intelligence to learn distinctive features and to recognize characteristic patterns on big data without extensive manual labor makes it highly effective for interpreting CCTA data. Although very few studies investigated the diagnostic value of CCTA for myocardiopathies, which is by far not established or applied in clinical practice by radiologists, automated image analysis has a clear advantage compared to humans by offering objective and uniform solutions. Further, whether a comprehensive, end-to-end, artificial intelligent approach can be used to analyse CCTA for diagnosis multi-classifications of cardiomyopathies remains unknown. Therefore, this study aims to develop and validate an artificial intelligence assisted approach on CCTA for screening and diagnosis of cardiomyopathies in patients with suspected coronary artery diseases.
Study Type
OBSERVATIONAL
Enrollment
5,000
Using a derivative sub-cohort, the investigators aim to first develop an CCTA-based AI-assisted (CCTAI) screening model to distinguish patients with cardiac abnormalities from those normal controls. Second, the investigators target at developing a CCTAI diagnostic model with multi-classification output of cardiomyopathy diagnosis. Both models will be tested in internal validation cohort and external validation cohort.
Diagnostic performance
The performance of the AI models is evaluated by assessing their sensitivity, specificity, precision and F1 score (harmonic mean of the predictive positive value and sensitivity), with two-sided 95% CIs, as well as the AUC of the ROC with two-sided CIs. The F1 score is complementary to the AUC, which is particularly useful in the setting of multiclass prediction and less sensitive than the AUC in settings of class imbalance. For an aggregate measure of model performance, the investigators compute the class frequency-weighted mean for the F1 score and the AUC. Other diagnostic performance assessing metrics include true-positive rate, true-negative rate, false-positive rate, false-negative rate, precision, sensitivity (recall), specificity, positive predictive value, and negative predictive value.
Time frame: CCTA examination before surgical or interventional treatments.
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.