Christian Tesche1,2,3,4, Maximilian J Bauer5,6, Moritz Baquet7, Benedikt Hedels5, Florian Straube5, Stefan Hartl5, Hunter N Gray6, David Jochheim7, Theresia Aschauer5, Sebastian Rogowski5, U Joseph Schoepf6,8, Steffen Massberg7, Ellen Hoffmann5, Ullrich Ebersberger5,7,9. 1. Department of Cardiology and Intensive Care Medicine, Heart Center Munich-Bogenhausen, Munich, Germany. tesche.christian@gmail.com. 2. Department of Cardiology, Munich University Clinic, Ludwig-Maximilians University, Munich, Germany. tesche.christian@gmail.com. 3. Department of Internal Medicine, Cardiology, St. Johannes Hospital, Johannesstrasse 9-13, 44137, Dortmund, Germany. tesche.christian@gmail.com. 4. Division of Cardiovascular Imaging, Department of Radiology and Radiological Science, Medical University of South Carolina, Charleston, SC, USA. tesche.christian@gmail.com. 5. Department of Cardiology and Intensive Care Medicine, Heart Center Munich-Bogenhausen, Munich, Germany. 6. Division of Cardiovascular Imaging, Department of Radiology and Radiological Science, Medical University of South Carolina, Charleston, SC, USA. 7. Department of Cardiology, Munich University Clinic, Ludwig-Maximilians University, Munich, Germany. 8. Division of Cardiology, Medical University of South Carolina, Charleston, SC, USA. 9. Kardiologie MVZ München-Nord, Munich, Germany.
Abstract
OBJECTIVES: To evaluate the long-term prognostic value of coronary CT angiography (cCTA)-derived plaque measures and clinical parameters on major adverse cardiac events (MACE) using machine learning (ML). METHODS: Datasets of 361 patients (61.9 ± 10.3 years, 65% male) with suspected coronary artery disease (CAD) who underwent cCTA were retrospectively analyzed. MACE was recorded. cCTA-derived adverse plaque features and conventional CT risk scores together with cardiovascular risk factors were provided to a ML model to predict MACE. A boosted ensemble algorithm (RUSBoost) utilizing decision trees as weak learners with repeated nested cross-validation to train and validate the model was used. Performance of the ML model was calculated using the area under the curve (AUC). RESULTS: MACE was observed in 31 patients (8.6%) after a median follow-up of 5.4 years. Discriminatory power was significantly higher for the ML model (AUC 0.96 [95%CI 0.93-0.98]) compared with conventional CT risk scores including Agatston calcium score (AUC 0.84 [95%CI 0.80-0.87]), segment involvement score (AUC 0.88 [95%CI 0.84-0.91]), and segment stenosis score (AUC 0.89 [95%CI 0.86-0.92], all p < 0.05). Similar results were shown for adverse plaque measures (AUCs 0.72-0.82, all p < 0.05) and clinical parameters including the Framingham risk score (AUCs 0.71-0.76, all p < 0.05). The ML model yielded significantly higher diagnostic performance compared with logistic regression analysis (AUC 0.96 vs. 0.92, p = 0.024). CONCLUSION: Integration of a ML model improves the long-term prediction of MACE when compared with conventional CT risk scores, adverse plaque measures, and clinical information. ML algorithms may improve the integration of patient's information to enhance risk stratification. KEY POINTS: • A machine learning (ML) model portends high discriminatory power to predict major adverse cardiac events (MACE). • ML-based risk stratification shows superior diagnostic performance for MACE prediction over coronary CT angiography (cCTA)-derived risk scores or clinical parameters alone. • A ML model outperforms conventional logistic regression analysis for the prediction of MACE.
OBJECTIVES: To evaluate the long-term prognostic value of coronary CT angiography (cCTA)-derived plaque measures and clinical parameters on major adverse cardiac events (MACE) using machine learning (ML). METHODS: Datasets of 361 patients (61.9 ± 10.3 years, 65% male) with suspected coronary artery disease (CAD) who underwent cCTA were retrospectively analyzed. MACE was recorded. cCTA-derived adverse plaque features and conventional CT risk scores together with cardiovascular risk factors were provided to a ML model to predict MACE. A boosted ensemble algorithm (RUSBoost) utilizing decision trees as weak learners with repeated nested cross-validation to train and validate the model was used. Performance of the ML model was calculated using the area under the curve (AUC). RESULTS: MACE was observed in 31 patients (8.6%) after a median follow-up of 5.4 years. Discriminatory power was significantly higher for the ML model (AUC 0.96 [95%CI 0.93-0.98]) compared with conventional CT risk scores including Agatston calcium score (AUC 0.84 [95%CI 0.80-0.87]), segment involvement score (AUC 0.88 [95%CI 0.84-0.91]), and segment stenosis score (AUC 0.89 [95%CI 0.86-0.92], all p < 0.05). Similar results were shown for adverse plaque measures (AUCs 0.72-0.82, all p < 0.05) and clinical parameters including the Framingham risk score (AUCs 0.71-0.76, all p < 0.05). The ML model yielded significantly higher diagnostic performance compared with logistic regression analysis (AUC 0.96 vs. 0.92, p = 0.024). CONCLUSION: Integration of a ML model improves the long-term prediction of MACE when compared with conventional CT risk scores, adverse plaque measures, and clinical information. ML algorithms may improve the integration of patient's information to enhance risk stratification. KEY POINTS: • A machine learning (ML) model portends high discriminatory power to predict major adverse cardiac events (MACE). • ML-based risk stratification shows superior diagnostic performance for MACE prediction over coronary CT angiography (cCTA)-derived risk scores or clinical parameters alone. • A ML model outperforms conventional logistic regression analysis for the prediction of MACE.
Authors: Jonathan James Hyett Bray; Moghees Ahmad Hanif; Mohammad Alradhawi; Jacob Ibbetson; Surinder Singh Dosanjh; Sabrina Lucy Smith; Mahmood Ahmad; Dominic Pimenta Journal: Eur Heart J Open Date: 2022-03-17
Authors: Giuseppe Muscogiuri; Marly Van Assen; Christian Tesche; Carlo N De Cecco; Mattia Chiesa; Stefano Scafuri; Marco Guglielmo; Andrea Baggiano; Laura Fusini; Andrea I Guaricci; Mark G Rabbat; Gianluca Pontone Journal: Biomed Res Int Date: 2020-12-16 Impact factor: 3.411