TY - JOUR
T1 - Artificial Intelligence Applications to Improve Risk Prediction Tools in Electrophysiology
AU - Kowlgi, Gurukripa N.
AU - Ezzeddine, Fatima M.
AU - Kapa, Suraj
N1 - Funding Information:
We would like to acknowledge the help of I. Zachi Attia, MS (Department of Cardiovascular Medicine, Mayo Clinic College of Medicine, Rochester, MN, USA) in technical advice related to the manuscript.
Publisher Copyright:
© 2020, Springer Science+Business Media, LLC, part of Springer Nature.
PY - 2020/9/1
Y1 - 2020/9/1
N2 - Purpose of Review: Artificial intelligence (AI) is an aspect of computer technology that imitates the ability of the human mind to analyze data. Over the last few years, there has been a paradigm shift in the utilization of AI in clinical practice. It is imperative for the clinical electrophysiologist to understand the basics of AI, and its potential applications in the field as new applications are developed and implemented. Recent Findings: Multiple investigators have demonstrated various AI algorithms that can be utilized in clinical care. These include applications such as electronic stethoscopes and electrocardiographic prediction of atrial fibrillation or congestive heart failure. AI may also be used in cardiovascular imaging, to identify disease patterns and even compose preliminary reports. Summary: Herein, we seek to familiarize readers with terms associated with AI, such as machine learning and neural networks. Further, we review the applications of AI in bedside clinical calculators, electrocardiography, and the field of cardiovascular imaging. A critical appraisal of AI is provided with specific review of hurdles in the integration of AI in clinical practice.
AB - Purpose of Review: Artificial intelligence (AI) is an aspect of computer technology that imitates the ability of the human mind to analyze data. Over the last few years, there has been a paradigm shift in the utilization of AI in clinical practice. It is imperative for the clinical electrophysiologist to understand the basics of AI, and its potential applications in the field as new applications are developed and implemented. Recent Findings: Multiple investigators have demonstrated various AI algorithms that can be utilized in clinical care. These include applications such as electronic stethoscopes and electrocardiographic prediction of atrial fibrillation or congestive heart failure. AI may also be used in cardiovascular imaging, to identify disease patterns and even compose preliminary reports. Summary: Herein, we seek to familiarize readers with terms associated with AI, such as machine learning and neural networks. Further, we review the applications of AI in bedside clinical calculators, electrocardiography, and the field of cardiovascular imaging. A critical appraisal of AI is provided with specific review of hurdles in the integration of AI in clinical practice.
KW - Artificial intelligence
KW - Big data
KW - Electrophysiology
KW - Machine learning
KW - Risk scores
UR - http://www.scopus.com/inward/record.url?scp=85089076010&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85089076010&partnerID=8YFLogxK
U2 - 10.1007/s12170-020-00649-1
DO - 10.1007/s12170-020-00649-1
M3 - Review article
AN - SCOPUS:85089076010
SN - 1932-9520
VL - 14
JO - Current Cardiovascular Risk Reports
JF - Current Cardiovascular Risk Reports
IS - 9
M1 - 13
ER -