Leveraging Machine Learning Techniques to Forecast Chronic Total Occlusion before Coronary Angiography

Abstract

Background: Chronic total occlusion (CTO) remains the most challenging procedure in coronary artery disease (CAD) for interventional cardiology. Although some clinical risk factors for CAD have been identified, there is no personalized prognosis test available to confidently identify patients at high or low risk for CTO CAD. This investigation aimed to use a machine learning algorithm for clinical features from clinical routine to develop a precision medicine tool to predict CTO before CAG. Methods: Data from 1473 CAD patients were obtained, including 1105 in the training cohort and 368 in the testing cohort. The baseline clinical characteristics were collected. Univariate and multivariate logistic regression analyses were conducted to identify independent risk factors that impact the diagnosis of CTO. A CTO predicting model was established and validated based on the independent predictors using a machine learning algorithm. The area under the curve (AUC) was used to evaluate the model. Results: The CTO prediction model was developed with the training cohort using the machine learning algorithm. Eight variables were confirmed as ‘important’: gender (male), neutrophil percentage (NE%), hematocrit (HCT), total cholesterol (TC), high-density lipoprotein cholesterol (HDL), ejection fraction (EF), troponin I (TnI), and N-terminal pro-B-type natriuretic peptide (NT-proBNP). The model achieved good concordance indices of 0.724 and 0.719 in the training and testing cohorts, respectively. Conclusions: An easy-to-use tool to predict CTO in patients with CAD was developed and validated. More research with larger cohorts are warranted to improve the prediction model, which can support clinician decisions on the early discerning CTO in CAD patients.

A LASSO-derived developing and validating risk model for chronic total occlusion in Asian population before coronary angiography

“…In our study, we found that the occurrence of CTO in patients was linked to male sex and lipid metabolism, which is consistent with prior studies ( 16 , 17 ). However, it is noteworthy that predictive model developed using LASSO regression analysis included non-HDL rather than LDL, which has long been considered a secondary target of lipid-lowering therapy in CAD or in patients at high risk ( 18 ).…”

“…In our previous work, we developed a nomogram using logistic regression analysis ( 8 ). However, we found that LASSO regression analysis is a superior method to univariate logistic regression analysis as it accounts for multicollinearity between variables.…”

Development of a Novel Nomogram to Predict Major Adverse Cardiac Events in Patients with Chronic Total Occlusion

“…Previous predictive models have incorporated various traditional clinical indicators, including general clinical characteristics and laboratory parameters, to assess the severity and prognosis of CTO patients 31 , 32 . Their application in clinical practice remains challenging, because some models omit crucial MPI variables.…”

Machine learning-based analysis of risk factors for chronic total occlusion in an Asian population

“…5 Through analyses of CTO data embedded in clinical characteristics, along with the use of machine learning algorithms, early and accurate identification of CTO may lead to more effective treatment and better patient outcomes. 6 Here, we conducted a risk factor analysis and constructed three models to predict CTO risk based on clinical and demographic characteristics, as well as biochemical parameters and echocardiography findings. Computational analysis revealed that these models can provide clinically relevant predictions of CTO risk, highlighting the emerging opportunity to meet an important need in this field.…”

“… 5 Through analyses of CTO data embedded in clinical characteristics, along with the use of machine learning algorithms, early and accurate identification of CTO may lead to more effective treatment and better patient outcomes. 6 …”