AUTHOR=Lin Guisen , Liu Qile , Chen Yuchen , Zong Xiaodan , Xi Yue , Li Tingyu , Yang Yuelong , Zeng An , Chen Minglei , Liu Chen , Liang Yanting , Xu Xiaowei , Huang Meiping 

TITLE=Machine Learning to Predict Long-Term Cardiac-Relative Prognosis in Patients With Extra-Cardiac Vascular Disease

JOURNAL=Frontiers in Cardiovascular Medicine

VOLUME=Volume 8 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/cardiovascular-medicine/articles/10.3389/fcvm.2021.771504

DOI=10.3389/fcvm.2021.771504

ISSN=2297-055X

ABSTRACT=Aims
Patients with IS, TIA and/or PAD represent a population with increased risk of coronary artery disease. Prognostic risk assessment to identify those with highest risk that may benefit from more intensified treatment remains challenging. To explore the feasibility and capability of machine learning (ML) to predict long-term adverse cardiac-related prognosis in patients with ischemic stroke (IS), transient ischemic attack (TIA) and/or peripheral artery disease (PAD). 
Methods
We analyzed 636 consecutive patients with a history of IS, TIA and/or PAD. All patients underwent a coronary computed tomography angiography (CCTA) scan. Thirty-five clinical data and 34 CCTA metrics underwent automated feature selection for machine learning (ML) model boosting. Clinical outcome included all caused mortality (ACM) and major adverse cardiac events (MACE: ACM, unstable angina requiring hospitalization, non-fatal myocardial infarction, and revascularization 90 days after the index CCTA). 
Results
During the follow-up of 3.9 ± 1.6 years, 21 patients had unstable angina requiring hospitalization, 8 had MI, 23 had revascularization and 13 deaths. Machine learning demonstrated a significant higher area-under-cure compared with MDI, SSS, SIS, and FRS for prediction of ACM (ML: 0.92 vs. MDI: 0.66, SSS: 0.68, SIS: 0.67, FRS: 0.51, all P<0.001) and MACE (ML: 0.84 vs. MDI: 0.82, SSS: 0.76, SIS: 0.73, FRS: 0.53, all P<0.05). 
Conclusion
Among patient with IS, TIA and/or PAD, ML demonstrated better prediction capability of ACM and MCAE than clinical score and CCTA metrics.