Nicolai P Ostberg1, Mohammad A Zafar2, Sandip K Mukherjee2, Bulat A Ziganshin3, John A Elefteriades4. 1. Aortic Institute at Yale-New Haven Hospital, Yale University School of Medicine, New Haven, Conn; Department of Biomedical Data Science, Stanford University School of Medicine, Stanford, Calif. 2. Aortic Institute at Yale-New Haven Hospital, Yale University School of Medicine, New Haven, Conn. 3. Aortic Institute at Yale-New Haven Hospital, Yale University School of Medicine, New Haven, Conn; Department of Cardiovascular and Endovascular Surgery, Kazan State Medical University, Kazan, Russia. 4. Aortic Institute at Yale-New Haven Hospital, Yale University School of Medicine, New Haven, Conn. Electronic address: john.elefteriades@yale.edu.
Abstract
OBJECTIVE: To use machine learning to predict rupture, dissection, and all-cause mortality for patients with descending and thoracoabdominal aortic aneurysms in an effort to improve on diameter-based surgical intervention criteria. METHODS: Retrospective data from 1083 patients with descending aortic diameters 3.0 cm or greater were collected, with a mean follow-up time of 3.52 years and an average descending diameter of 4.13 cm. Six machine learning classifiers were trained using 44 variables to predict the occurrence of dissection, rupture, or all-cause mortality within 1, 2, or 5 years of initial patient encounter for a total of 54 (6 × 3 × 3) separate classifiers. Classifier performance was measured using area under the receiver operator curve. RESULTS: Machine learning models achieved area under the receiver operator curves of 0.842 to 0.872 when predicting type B dissection, 0.847 to 0.856 when predicting type B dissection or rupture, and 0.820 to 0.845 when predicting type B dissection, rupture, or all-cause mortality. All models consistently outperformed descending aortic diameter across all end points (area under the receiver operator curve = 0.713-0.733). Feature importance inspection showed that other features beyond aortic diameter, such as a history of myocardial infarction, hypertension, and patient sex, play an important role in improving risk prediction. CONCLUSIONS: This study provides surgeons with a more accurate, machine learning-based, risk-stratification metric to predict complications for patients with descending aortic aneurysms.
OBJECTIVE: To use machine learning to predict rupture, dissection, and all-cause mortality for patients with descending and thoracoabdominal aortic aneurysms in an effort to improve on diameter-based surgical intervention criteria. METHODS: Retrospective data from 1083 patients with descending aortic diameters 3.0 cm or greater were collected, with a mean follow-up time of 3.52 years and an average descending diameter of 4.13 cm. Six machine learning classifiers were trained using 44 variables to predict the occurrence of dissection, rupture, or all-cause mortality within 1, 2, or 5 years of initial patient encounter for a total of 54 (6 × 3 × 3) separate classifiers. Classifier performance was measured using area under the receiver operator curve. RESULTS: Machine learning models achieved area under the receiver operator curves of 0.842 to 0.872 when predicting type B dissection, 0.847 to 0.856 when predicting type B dissection or rupture, and 0.820 to 0.845 when predicting type B dissection, rupture, or all-cause mortality. All models consistently outperformed descending aortic diameter across all end points (area under the receiver operator curve = 0.713-0.733). Feature importance inspection showed that other features beyond aortic diameter, such as a history of myocardial infarction, hypertension, and patient sex, play an important role in improving risk prediction. CONCLUSIONS: This study provides surgeons with a more accurate, machine learning-based, risk-stratification metric to predict complications for patients with descending aortic aneurysms.
Authors: Somdatta Goswami; David S Li; Bruno V Rego; Marcos Latorre; Jay D Humphrey; George Em Karniadakis Journal: J R Soc Interface Date: 2022-08-31 Impact factor: 4.293