Evaluating machine learning accuracy in detecting significant coronary stenosis using CCTA-derived fractional flow reserve: Meta-analysis and systematic review

Background: The use of machine learning (ML) based coronary computed tomography angiography (CCTA) derived fractional flow reserve (ML-FFRCT), shortens the time of diagnosis of ischemia considerably and eliminates unnecessary invasive procedures, when compared to invasive coronary angiography with i...

Full description

Saved in:
Bibliographic Details
Main Authors: Danny van Noort, Liang Guo, Shuang Leng, Luming Shi, Ru-San Tan, Lynette Teo, Min Sen Yew, Lohendran Baskaran, Ping Chai, Felix Keng, Mark Chan, Terrance Chua, Swee Yaw Tan, Liang Zhong
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:International Journal of Cardiology: Heart & Vasculature
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352906724001945
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850065654316531712
author Danny van Noort
Liang Guo
Shuang Leng
Luming Shi
Ru-San Tan
Lynette Teo
Min Sen Yew
Lohendran Baskaran
Ping Chai
Felix Keng
Mark Chan
Terrance Chua
Swee Yaw Tan
Liang Zhong
author_facet Danny van Noort
Liang Guo
Shuang Leng
Luming Shi
Ru-San Tan
Lynette Teo
Min Sen Yew
Lohendran Baskaran
Ping Chai
Felix Keng
Mark Chan
Terrance Chua
Swee Yaw Tan
Liang Zhong
author_sort Danny van Noort
collection DOAJ
description Background: The use of machine learning (ML) based coronary computed tomography angiography (CCTA) derived fractional flow reserve (ML-FFRCT), shortens the time of diagnosis of ischemia considerably and eliminates unnecessary invasive procedures, when compared to invasive coronary angiography with invasive FFR (iFFR). This systematic review aims to summarize the current evidence on the diagnostic accuracy of (ML-FFRCT) compared with iFFR for diagnosis of patient- and vessel-level coronary ischemia. Methods: To identify suitable studies, comprehensive literature search was performed in PubMed, the Cochrane Library, Embase, up to August 2023. The index test was ML derived FFR and studies with diagnostic test accuracy data of ML-FFRCT at a threshold of 0.8 were included for the review and meta-analysis. Quality of evidence was assessed using QUADAS-2 checklist. Results: After full text review of 230 identified studies, 17 were included for analysis, which encompassed 3255 participants (age 62.0 ± 3.7). 8 studies reported patient-level data; and 12, vessel-level data. With iFFR as the reference standard, the pooled patient-level sensitivity, specificity, and area-under-curve (AUC) of ML-FFRCT were 0.86 [95 % CI: 0.79, 0.91], 0.87 [95 % CI: 0.76, 0.94], and 0.92 [95 % CI: 0.89–0.94], respectively; and pooled vessel-level sensitivity, specificity, and AUC, 0.80 [95 % CI: 0.74–0.84], 0.84 [95 % CI: 0.77–0.89), and 0.88 [95 % CI: 0.85–0.91], respectively. Conclusions: This systemic review demonstrated the favourable diagnostic performance of ML-FFRCT against standard iFFR, although heterogeneity exists, providing support for the use of ML-FFRCT as a triage tool for non-invasive screening of coronary ischemia in the clinical setting.
format Article
id doaj-art-da8fd6419332467d97e0467438c498ac
institution DOAJ
issn 2352-9067
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series International Journal of Cardiology: Heart & Vasculature
spelling doaj-art-da8fd6419332467d97e0467438c498ac2025-08-20T02:48:57ZengElsevierInternational Journal of Cardiology: Heart & Vasculature2352-90672024-12-015510152810.1016/j.ijcha.2024.101528Evaluating machine learning accuracy in detecting significant coronary stenosis using CCTA-derived fractional flow reserve: Meta-analysis and systematic reviewDanny van Noort0Liang Guo1Shuang Leng2Luming Shi3Ru-San Tan4Lynette Teo5Min Sen Yew6Lohendran Baskaran7Ping Chai8Felix Keng9Mark Chan10Terrance Chua11Swee Yaw Tan12Liang Zhong13NHRIS, National Heart Centre, Singapore; Corresponding author at: National Heart Centre Singapore, 5 Hospital Drive, 169609 Singapore.Singapore Clinical Research Institute, Consortium for Clinical Research and Innovation, Singapore; Cochrane, SingaporeNHRIS, National Heart Centre, SingaporeSingapore Clinical Research Institute, Consortium for Clinical Research and Innovation, Singapore; Cochrane, Singapore; Duke-NUS Medical School, SingaporeNHRIS, National Heart Centre, Singapore; Duke-NUS Medical School, SingaporeDepartment of Diagnostic Imaging, National University Hospital, Singapore; Yong Loo Lin School of Medicine, National University Hospital, SingaporeTan Tock Seng Hospital, SingaporeNHRIS, National Heart Centre, Singapore; Duke-NUS Medical School, SingaporeYong Loo Lin School of Medicine, National University Hospital, Singapore; Department of Cardiology, National University Hospital, SingaporeNHRIS, National Heart Centre, Singapore; Duke-NUS Medical School, SingaporeYong Loo Lin School of Medicine, National University Hospital, Singapore; Department of Cardiology, National University Hospital, SingaporeNHRIS, National Heart Centre, Singapore; Duke-NUS Medical School, SingaporeNHRIS, National Heart Centre, Singapore; Duke-NUS Medical School, SingaporeNHRIS, National Heart Centre, Singapore; Duke-NUS Medical School, SingaporeBackground: The use of machine learning (ML) based coronary computed tomography angiography (CCTA) derived fractional flow reserve (ML-FFRCT), shortens the time of diagnosis of ischemia considerably and eliminates unnecessary invasive procedures, when compared to invasive coronary angiography with invasive FFR (iFFR). This systematic review aims to summarize the current evidence on the diagnostic accuracy of (ML-FFRCT) compared with iFFR for diagnosis of patient- and vessel-level coronary ischemia. Methods: To identify suitable studies, comprehensive literature search was performed in PubMed, the Cochrane Library, Embase, up to August 2023. The index test was ML derived FFR and studies with diagnostic test accuracy data of ML-FFRCT at a threshold of 0.8 were included for the review and meta-analysis. Quality of evidence was assessed using QUADAS-2 checklist. Results: After full text review of 230 identified studies, 17 were included for analysis, which encompassed 3255 participants (age 62.0 ± 3.7). 8 studies reported patient-level data; and 12, vessel-level data. With iFFR as the reference standard, the pooled patient-level sensitivity, specificity, and area-under-curve (AUC) of ML-FFRCT were 0.86 [95 % CI: 0.79, 0.91], 0.87 [95 % CI: 0.76, 0.94], and 0.92 [95 % CI: 0.89–0.94], respectively; and pooled vessel-level sensitivity, specificity, and AUC, 0.80 [95 % CI: 0.74–0.84], 0.84 [95 % CI: 0.77–0.89), and 0.88 [95 % CI: 0.85–0.91], respectively. Conclusions: This systemic review demonstrated the favourable diagnostic performance of ML-FFRCT against standard iFFR, although heterogeneity exists, providing support for the use of ML-FFRCT as a triage tool for non-invasive screening of coronary ischemia in the clinical setting.http://www.sciencedirect.com/science/article/pii/S2352906724001945Machine learningCoronary computed tomography angiography (CCTA)Fractional flow reserve (FFR)Invasive coronary angiography (ICA)
spellingShingle Danny van Noort
Liang Guo
Shuang Leng
Luming Shi
Ru-San Tan
Lynette Teo
Min Sen Yew
Lohendran Baskaran
Ping Chai
Felix Keng
Mark Chan
Terrance Chua
Swee Yaw Tan
Liang Zhong
Evaluating machine learning accuracy in detecting significant coronary stenosis using CCTA-derived fractional flow reserve: Meta-analysis and systematic review
International Journal of Cardiology: Heart & Vasculature
Machine learning
Coronary computed tomography angiography (CCTA)
Fractional flow reserve (FFR)
Invasive coronary angiography (ICA)
title Evaluating machine learning accuracy in detecting significant coronary stenosis using CCTA-derived fractional flow reserve: Meta-analysis and systematic review
title_full Evaluating machine learning accuracy in detecting significant coronary stenosis using CCTA-derived fractional flow reserve: Meta-analysis and systematic review
title_fullStr Evaluating machine learning accuracy in detecting significant coronary stenosis using CCTA-derived fractional flow reserve: Meta-analysis and systematic review
title_full_unstemmed Evaluating machine learning accuracy in detecting significant coronary stenosis using CCTA-derived fractional flow reserve: Meta-analysis and systematic review
title_short Evaluating machine learning accuracy in detecting significant coronary stenosis using CCTA-derived fractional flow reserve: Meta-analysis and systematic review
title_sort evaluating machine learning accuracy in detecting significant coronary stenosis using ccta derived fractional flow reserve meta analysis and systematic review
topic Machine learning
Coronary computed tomography angiography (CCTA)
Fractional flow reserve (FFR)
Invasive coronary angiography (ICA)
url http://www.sciencedirect.com/science/article/pii/S2352906724001945
work_keys_str_mv AT dannyvannoort evaluatingmachinelearningaccuracyindetectingsignificantcoronarystenosisusingcctaderivedfractionalflowreservemetaanalysisandsystematicreview
AT liangguo evaluatingmachinelearningaccuracyindetectingsignificantcoronarystenosisusingcctaderivedfractionalflowreservemetaanalysisandsystematicreview
AT shuangleng evaluatingmachinelearningaccuracyindetectingsignificantcoronarystenosisusingcctaderivedfractionalflowreservemetaanalysisandsystematicreview
AT lumingshi evaluatingmachinelearningaccuracyindetectingsignificantcoronarystenosisusingcctaderivedfractionalflowreservemetaanalysisandsystematicreview
AT rusantan evaluatingmachinelearningaccuracyindetectingsignificantcoronarystenosisusingcctaderivedfractionalflowreservemetaanalysisandsystematicreview
AT lynetteteo evaluatingmachinelearningaccuracyindetectingsignificantcoronarystenosisusingcctaderivedfractionalflowreservemetaanalysisandsystematicreview
AT minsenyew evaluatingmachinelearningaccuracyindetectingsignificantcoronarystenosisusingcctaderivedfractionalflowreservemetaanalysisandsystematicreview
AT lohendranbaskaran evaluatingmachinelearningaccuracyindetectingsignificantcoronarystenosisusingcctaderivedfractionalflowreservemetaanalysisandsystematicreview
AT pingchai evaluatingmachinelearningaccuracyindetectingsignificantcoronarystenosisusingcctaderivedfractionalflowreservemetaanalysisandsystematicreview
AT felixkeng evaluatingmachinelearningaccuracyindetectingsignificantcoronarystenosisusingcctaderivedfractionalflowreservemetaanalysisandsystematicreview
AT markchan evaluatingmachinelearningaccuracyindetectingsignificantcoronarystenosisusingcctaderivedfractionalflowreservemetaanalysisandsystematicreview
AT terrancechua evaluatingmachinelearningaccuracyindetectingsignificantcoronarystenosisusingcctaderivedfractionalflowreservemetaanalysisandsystematicreview
AT sweeyawtan evaluatingmachinelearningaccuracyindetectingsignificantcoronarystenosisusingcctaderivedfractionalflowreservemetaanalysisandsystematicreview
AT liangzhong evaluatingmachinelearningaccuracyindetectingsignificantcoronarystenosisusingcctaderivedfractionalflowreservemetaanalysisandsystematicreview