Artificial intelligence (AI) has transformed key aspects of human life. Machine learning (ML), which is a subset of AI wherein machines autonomously acquire information by extracting patterns from large databases, has been increasingly used within the medical community, and specifically within the domain of cardiovascular diseases. In this review, we present a brief overview of ML methodologies that are used for the construction of inferential and predictive data-driven models. We highlight several domains of ML application such as echocardiography, electrocardiography, and recently developed non-invasive imaging modalities such as coronary artery calcium scoring and coronary computed tomography angiography. We conclude by reviewing the limitations associated with contemporary application of ML algorithms within the cardiovascular disease field.
Background The ability to accurately predict the occurrence of in‐hospital death after percutaneous coronary intervention is important for clinical decision‐making. We sought to utilize the New York Percutaneous Coronary Intervention Reporting System in order to elucidate the determinants of in‐hospital mortality in patients undergoing percutaneous coronary intervention across New York State. Methods and Results We examined 479 804 patients undergoing percutaneous coronary intervention between 2004 and 2012, utilizing traditional and advanced machine learning algorithms to determine the most significant predictors of in‐hospital mortality. The entire data were randomly split into a training (80%) and a testing set (20%). Tuned hyperparameters were used to generate a trained model while the performance of the model was independently evaluated on the testing set after plotting a receiver‐operator characteristic curve and using the output measure of the area under the curve ( AUC ) and the associated 95% CIs. Mean age was 65.2±11.9 years and 68.5% were women. There were 2549 in‐hospital deaths within the patient population. A boosted ensemble algorithm (AdaBoost) had optimal discrimination with AUC of 0.927 (95% CI 0.923–0.929) compared with AUC of 0.913 for XGB oost (95% CI 0.906–0.919, P =0.02), AUC of 0.892 for Random Forest (95% CI 0.889–0.896, P <0.01), and AUC of 0.908 for logistic regression (95% CI 0.907–0.910, P <0.01). The 2 most significant predictors were age and ejection fraction. Conclusions A big data approach that utilizes advanced machine learning algorithms identifies new associations among risk factors and provides high accuracy for the prediction of in‐hospital mortality in patients undergoing percutaneous coronary intervention.
BackgroundWall shear stress (WSS) is an established predictor of coronary atherosclerosis progression. Prior studies have reported that high WSS has been associated with high‐risk atherosclerotic plaque characteristics (APCs). WSS and APCs are quantifiable by coronary computed tomography angiography, but the relationship of coronary lesion ischemia—evaluated by fractional flow reserve—to WSS and APCs has not been examined.Methods and Results WSS measures were obtained from 100 evaluable patients who underwent coronary computed tomography angiography and invasive coronary angiography with fractional flow reserve. Patients were categorized according to tertiles of mean WSS values defined as low, intermediate, and high. Coronary ischemia was defined as fractional flow reserve ≤0.80. Stenosis severity was determined by minimal luminal diameter. APCs were defined as positive remodeling, low attenuation plaque, and spotty calcification. The likelihood of having positive remodeling and low‐attenuation plaque was greater in the high WSS group compared with the low WSS group after adjusting for minimal luminal diameter (odds ratio for positive remodeling: 2.54, 95% CI 1.12–5.77; odds ratio for low‐attenuation plaque: 2.68, 95% CI 1.02–7.06; both P<0.05). No significant relationship was observed between WSS and fractional flow reserve when adjusting for either minimal luminal diameter or APCs. WSS displayed no incremental benefit above stenosis severity and APCs for detecting lesions that caused ischemia (area under the curve for stenosis and APCs: 0.87, 95% CI 0.81–0.93; area under the curve for stenosis, APCs, and WSS: 0.88, 95% CI 0.82–0.93; P=0.30 for difference).ConclusionsHigh WSS is associated with APCs independent of stenosis severity. WSS provided no added value beyond stenosis severity and APCs for detecting lesions with significant ischemia.
Gottliebson WM, Effat MA. Influence of heart rate on fractional flow reserve, pressure drop coefficient, and lesion flow coefficient for epicardial coronary stenosis in a porcine model. Am J Physiol Heart Circ Physiol 300: H382-H387, 2011. First published October 8, 2010 doi:10.1152/ajpheart.00412.2010.-A limitation in the use of invasive coronary diagnostic indexes is that fluctuations in hemodynamic factors such as heart rate (HR), blood pressure, and contractility may alter resting or hyperemic flow measurements and may introduce uncertainties in the interpretation of these indexes. In this study, we focused on the effect of fluctuations in HR and area stenosis (AS) on diagnostic indexes. We hypothesized that the pressure drop coefficient (CDPe, ratio of transstenotic pressure drop and distal dynamic pressure), lesion flow coefficient (LFC, square root of ratio of limiting value CDP and CDP at site of stenosis) derived from fluid dynamics principles, and fractional flow reserve (FFR, ratio of average distal and proximal pressures) are independent of HR and can significantly differentiate between the severity of stenosis. Cardiac catheterization was performed on 11 Yorkshire pigs. Simultaneous measurements of distal coronary arterial pressure and flow were performed using a dual sensor-tipped guidewire for HR Ͻ 120 and HR Ͼ 120 beats/min, in the presence of epicardial coronary lesions of Ͻ50% AS and Ͼ50% AS. The mean values of FFR, CDPe, and LFC were significantly different (P Ͻ 0.05) for lesions of Ͻ50% AS and Ͼ50% AS (0.88 Ϯ 0.04, 0.76 Ϯ 0.04; 62 Ϯ 30, 151 Ϯ 35, and 0.10 Ϯ 0.02 and 0.16 Ϯ 0.01, respectively). The mean values of FFR and CDPe were not significantly different (P Ͼ 0.05) for variable HR conditions of HR Ͻ 120 and HR Ͼ 120 beats/min (FFR, 0.81 Ϯ 0.04 and 0.82 Ϯ 0.04; and CDPe, 95 Ϯ 33 and 118 Ϯ 36). The mean values of LFC do somewhat vary with HR (0.14 Ϯ 0.01 and 0.12 Ϯ 0.02). In conclusion, fluctuations in HR have no significant influence on the measured values of CDP e and FFR but have a marginal influence on the measured values of LFC. However, all three parameters can significantly differentiate between stenosis severities. These results suggest that the diagnostic parameters can be potentially used in a better assessment of coronary stenosis severity under a clinical setting. coronary disease; hemodynamics; catheterization CORONARY ANGIOGRAPHY is the current gold standard for detecting epicardial coronary artery disease. Augmenting this anatomical data with coronary functional parameters (pressure, flow, and/or velocity) provides unique information that facilitates fully informed therapeutic decision making in the catheterization laboratory. Several invasive functional approaches have been used for the past several years within the cardiac catheterization laboratory that allow for a determination of the functional significance of epicardial coronary stenoses. These methods include measurement of coronary flow reserve [CFR, the ratio of hyperemic flow to basal flow (10) (9), an advanced func...
Background Rapid coronary plaque progression (RPP) is associated with incident cardiovascular events. To date, no method exists for the identification of individuals at risk of RPP at a single point in time. This study integrated coronary computed tomography angiography–determined qualitative and quantitative plaque features within a machine learning (ML) framework to determine its performance for predicting RPP. Methods and Results Qualitative and quantitative coronary computed tomography angiography plaque characterization was performed in 1083 patients who underwent serial coronary computed tomography angiography from the PARADIGM (Progression of Atherosclerotic Plaque Determined by Computed Tomographic Angiography Imaging) registry. RPP was defined as an annual progression of percentage atheroma volume ≥1.0%. We employed the following ML models: model 1, clinical variables; model 2, model 1 plus qualitative plaque features; model 3, model 2 plus quantitative plaque features. ML models were compared with the atherosclerotic cardiovascular disease risk score, Duke coronary artery disease score, and a logistic regression statistical model. 224 patients (21%) were identified as RPP. Feature selection in ML identifies that quantitative computed tomography variables were higher‐ranking features, followed by qualitative computed tomography variables and clinical/laboratory variables. ML model 3 exhibited the highest discriminatory performance to identify individuals who would experience RPP when compared with atherosclerotic cardiovascular disease risk score, the other ML models, and the statistical model (area under the receiver operating characteristic curve in ML model 3, 0.83 [95% CI 0.78–0.89], versus atherosclerotic cardiovascular disease risk score, 0.60 [0.52–0.67]; Duke coronary artery disease score, 0.74 [0.68–0.79]; ML model 1, 0.62 [0.55–0.69]; ML model 2, 0.73 [0.67–0.80]; all P <0.001; statistical model, 0.81 [0.75–0.87], P =0.128). Conclusions Based on a ML framework, quantitative atherosclerosis characterization has been shown to be the most important feature when compared with clinical, laboratory, and qualitative measures in identifying patients at risk of RPP.
CDP, a functional parameter based on both intracoronary pressure and flow measurements, has close agreement (area under ROC curve = 86%) with FFR, the frequently used method of evaluating stenosis severity.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.