Coronary artery decision algorithm trained by two-step machine learning algorithm

Young Woo Kim; Hee Jin Yu; Jung Sun Kim; Jinyong Ha; Jongeun Choi; Joon Sang Lee

doi:10.1039/c9ra08999c

Coronary artery decision algorithm trained by two-step machine learning algorithm

Young Woo Kim, Hee Jin Yu, Jung Sun Kim, Jinyong Ha, Jongeun Choi, Joon Sang Lee

Department of Mechanical Engineering

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

Abstract

A two-step machine learning (ML) algorithm for estimating both fractional flow reserve (FFR) and decision (DEC) for the coronary artery is introduced in this study. The primary purpose of this model is to suggest the possibility of ML-based FFR to be more accurate than the FFR calculation technique based on a computational fluid dynamics (CFD) method. For this purpose, a two-step ML algorithm that considers the flow characteristics and biometric features as input features of the ML model is designed. The first step of the algorithm is based on the Gaussian progress regression model and is trained by a synthetic model using CFD analysis. The second step of the algorithm is based on a support vector machine with patient data, including flow characteristics and biometric features. Consequently, the accuracy of the FFR estimated from the first step of the algorithm was similar to that of the CFD-based method, while the accuracy of DEC in the second step was improved. This improvement in accuracy was analyzed using flow characteristics and biometric features.

Original language	English
Pages (from-to)	4014-4022
Number of pages	9
Journal	RSC Advances
Volume	10
Issue number	7
DOIs	https://doi.org/10.1039/c9ra08999c
Publication status	Published - 2020

Bibliographical note

Funding Information:
This work of Yong Woo Kim, Jung-Sun Kim, Jinyong Ha, and Joon Sang Lee was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (NRF-2017M3A9E9073371). Also, The work of Hee-Jin Yu and Jongeun Choi was supported in part by the National Research Foundation of Korea (NRF) under Grant 2018R1A4A1025986 funded by the Korea government (MSIT). Young Woo Kim and Hee-Jin Yu contributed equally to this work as rst authors. Also, Jongeun Choi and Joon Sang Lee contributed equally to this work as corresponding authors.

Publisher Copyright:
© 2020 The Royal Society of Chemistry.

All Science Journal Classification (ASJC) codes

Chemistry(all)
Chemical Engineering(all)

Access to Document

10.1039/c9ra08999c

Cite this

@article{4c96e6508a2545309ceb69de40a69002,

title = "Coronary artery decision algorithm trained by two-step machine learning algorithm",

abstract = "A two-step machine learning (ML) algorithm for estimating both fractional flow reserve (FFR) and decision (DEC) for the coronary artery is introduced in this study. The primary purpose of this model is to suggest the possibility of ML-based FFR to be more accurate than the FFR calculation technique based on a computational fluid dynamics (CFD) method. For this purpose, a two-step ML algorithm that considers the flow characteristics and biometric features as input features of the ML model is designed. The first step of the algorithm is based on the Gaussian progress regression model and is trained by a synthetic model using CFD analysis. The second step of the algorithm is based on a support vector machine with patient data, including flow characteristics and biometric features. Consequently, the accuracy of the FFR estimated from the first step of the algorithm was similar to that of the CFD-based method, while the accuracy of DEC in the second step was improved. This improvement in accuracy was analyzed using flow characteristics and biometric features.",

author = "Kim, {Young Woo} and Yu, {Hee Jin} and Kim, {Jung Sun} and Jinyong Ha and Jongeun Choi and Lee, {Joon Sang}",

note = "Funding Information: This work of Yong Woo Kim, Jung-Sun Kim, Jinyong Ha, and Joon Sang Lee was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (NRF-2017M3A9E9073371). Also, The work of Hee-Jin Yu and Jongeun Choi was supported in part by the National Research Foundation of Korea (NRF) under Grant 2018R1A4A1025986 funded by the Korea government (MSIT). Young Woo Kim and Hee-Jin Yu contributed equally to this work as rst authors. Also, Jongeun Choi and Joon Sang Lee contributed equally to this work as corresponding authors. Publisher Copyright: {\textcopyright} 2020 The Royal Society of Chemistry.",

year = "2020",

doi = "10.1039/c9ra08999c",

language = "English",

volume = "10",

pages = "4014--4022",

journal = "RSC Advances",

issn = "2046-2069",

publisher = "Royal Society of Chemistry",

number = "7",

}

TY - JOUR

T1 - Coronary artery decision algorithm trained by two-step machine learning algorithm

AU - Kim, Young Woo

AU - Yu, Hee Jin

AU - Kim, Jung Sun

AU - Ha, Jinyong

AU - Choi, Jongeun

AU - Lee, Joon Sang

N1 - Funding Information: This work of Yong Woo Kim, Jung-Sun Kim, Jinyong Ha, and Joon Sang Lee was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (NRF-2017M3A9E9073371). Also, The work of Hee-Jin Yu and Jongeun Choi was supported in part by the National Research Foundation of Korea (NRF) under Grant 2018R1A4A1025986 funded by the Korea government (MSIT). Young Woo Kim and Hee-Jin Yu contributed equally to this work as rst authors. Also, Jongeun Choi and Joon Sang Lee contributed equally to this work as corresponding authors. Publisher Copyright: © 2020 The Royal Society of Chemistry.

PY - 2020

Y1 - 2020

N2 - A two-step machine learning (ML) algorithm for estimating both fractional flow reserve (FFR) and decision (DEC) for the coronary artery is introduced in this study. The primary purpose of this model is to suggest the possibility of ML-based FFR to be more accurate than the FFR calculation technique based on a computational fluid dynamics (CFD) method. For this purpose, a two-step ML algorithm that considers the flow characteristics and biometric features as input features of the ML model is designed. The first step of the algorithm is based on the Gaussian progress regression model and is trained by a synthetic model using CFD analysis. The second step of the algorithm is based on a support vector machine with patient data, including flow characteristics and biometric features. Consequently, the accuracy of the FFR estimated from the first step of the algorithm was similar to that of the CFD-based method, while the accuracy of DEC in the second step was improved. This improvement in accuracy was analyzed using flow characteristics and biometric features.

AB - A two-step machine learning (ML) algorithm for estimating both fractional flow reserve (FFR) and decision (DEC) for the coronary artery is introduced in this study. The primary purpose of this model is to suggest the possibility of ML-based FFR to be more accurate than the FFR calculation technique based on a computational fluid dynamics (CFD) method. For this purpose, a two-step ML algorithm that considers the flow characteristics and biometric features as input features of the ML model is designed. The first step of the algorithm is based on the Gaussian progress regression model and is trained by a synthetic model using CFD analysis. The second step of the algorithm is based on a support vector machine with patient data, including flow characteristics and biometric features. Consequently, the accuracy of the FFR estimated from the first step of the algorithm was similar to that of the CFD-based method, while the accuracy of DEC in the second step was improved. This improvement in accuracy was analyzed using flow characteristics and biometric features.

UR - http://www.scopus.com/inward/record.url?scp=85078703542&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85078703542&partnerID=8YFLogxK

U2 - 10.1039/c9ra08999c

DO - 10.1039/c9ra08999c

M3 - Article

AN - SCOPUS:85078703542

SN - 2046-2069

VL - 10

SP - 4014

EP - 4022

JO - RSC Advances

JF - RSC Advances

IS - 7

ER -

Coronary artery decision algorithm trained by two-step machine learning algorithm

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this