Comparison of conventional scoring systems to machine learning models for the prediction of major adverse cardiovascular events in patients undergoing coronary computed tomography angiography
BackgroundThe study aims to compare the prognostic performance of conventional scoring systems to a machine learning (ML) model on coronary computed tomography angiography (CCTA) to discriminate between the patients with and without major adverse cardiovascular events (MACEs) and to find the most im...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-10-01
|
| Series: | Frontiers in Cardiovascular Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcvm.2022.994483/full |
| _version_ | 1811234474472505344 |
|---|---|
| author | Seyyed Mojtaba Ghorashi Amir Fazeli Behnam Hedayat Hamid Mokhtari Arash Jalali Pooria Ahmadi Hamid Chalian Nicola Luigi Bragazzi Shapour Shirani Negar Omidi |
| author_facet | Seyyed Mojtaba Ghorashi Amir Fazeli Behnam Hedayat Hamid Mokhtari Arash Jalali Pooria Ahmadi Hamid Chalian Nicola Luigi Bragazzi Shapour Shirani Negar Omidi |
| author_sort | Seyyed Mojtaba Ghorashi |
| collection | DOAJ |
| description | BackgroundThe study aims to compare the prognostic performance of conventional scoring systems to a machine learning (ML) model on coronary computed tomography angiography (CCTA) to discriminate between the patients with and without major adverse cardiovascular events (MACEs) and to find the most important contributing factor of MACE.Materials and methodsFrom November to December 2019, 500 of 1586 CCTA scans were included and analyzed, then six conventional scores were calculated for each participant, and seven ML models were designed. Our study endpoints were all-cause mortality, non-fatal myocardial infarction, late coronary revascularization, and hospitalization for unstable angina or heart failure. Score performance was assessed by area under the curve (AUC) analysis.ResultsOf 500 patients (mean age: 60 ± 10; 53.8% male subjects) referred for CCTA, 416 patients have met inclusion criteria, 46 patients with early (<90 days) cardiac evaluation (due to the inability to clarify the reason for the assessment, deterioration of the symptoms vs. the CCTA result), and 38 patients because of missed follow-up were not enrolled in the final analysis. Forty-six patients (11.0%) developed MACE within 20.5 ± 7.9 months of follow-up. Compared to conventional scores, ML models showed better performance, except only one model which is eXtreme Gradient Boosting had lower performance than conventional scoring systems (AUC:0.824, 95% confidence interval (CI): 0.701–0.947). Between ML models, random forest, ensemble with generalized linear, and ensemble with naive Bayes were shown to have higher prognostic performance (AUC: 0.92, 95% CI: 0.85–0.99, AUC: 0.90, 95% CI: 0.81–0.98, and AUC: 0.89, 95% CI: 0.82–0.97), respectively. Coronary artery calcium score (CACS) had the highest correlation with MACE.ConclusionCompared to the conventional scoring system, ML models using CCTA scans show improved prognostic prediction for MACE. Anatomical features were more important than clinical characteristics. |
| first_indexed | 2024-04-12T11:36:54Z |
| format | Article |
| id | doaj.art-d543d216f59948d69648e6128252e559 |
| institution | Directory Open Access Journal |
| issn | 2297-055X |
| language | English |
| last_indexed | 2024-04-12T11:36:54Z |
| publishDate | 2022-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Cardiovascular Medicine |
| spelling | doaj.art-d543d216f59948d69648e6128252e5592022-12-22T03:34:49ZengFrontiers Media S.A.Frontiers in Cardiovascular Medicine2297-055X2022-10-01910.3389/fcvm.2022.994483994483Comparison of conventional scoring systems to machine learning models for the prediction of major adverse cardiovascular events in patients undergoing coronary computed tomography angiographySeyyed Mojtaba Ghorashi0Amir Fazeli1Behnam Hedayat2Hamid Mokhtari3Arash Jalali4Pooria Ahmadi5Hamid Chalian6Nicola Luigi Bragazzi7Shapour Shirani8Negar Omidi9Tehran Heart Center, Tehran University of Medical Science, Tehran, IranTehran Heart Center, Tehran University of Medical Science, Tehran, IranTehran Heart Center, Tehran University of Medical Science, Tehran, IranBiomedical Engineering and Physics Department, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, IranTehran Heart Center, Tehran University of Medical Science, Tehran, IranTehran Heart Center, Tehran University of Medical Science, Tehran, IranDivision of Cardiothoracic Imaging, Department of Radiology, University of Washington, Seattle, WA, United StatesLaboratory for Industrial and Applied Mathematics (LIAM), Department of Mathematics and Statistics, York University, Toronto, ON, CanadaDepartment of Cardiovascular Imaging, Tehran Heart Center, Tehran University of Medical Sciences, Tehran, IranDepartment of Cardiovascular Imaging, Tehran Heart Center, Tehran University of Medical Sciences, Tehran, IranBackgroundThe study aims to compare the prognostic performance of conventional scoring systems to a machine learning (ML) model on coronary computed tomography angiography (CCTA) to discriminate between the patients with and without major adverse cardiovascular events (MACEs) and to find the most important contributing factor of MACE.Materials and methodsFrom November to December 2019, 500 of 1586 CCTA scans were included and analyzed, then six conventional scores were calculated for each participant, and seven ML models were designed. Our study endpoints were all-cause mortality, non-fatal myocardial infarction, late coronary revascularization, and hospitalization for unstable angina or heart failure. Score performance was assessed by area under the curve (AUC) analysis.ResultsOf 500 patients (mean age: 60 ± 10; 53.8% male subjects) referred for CCTA, 416 patients have met inclusion criteria, 46 patients with early (<90 days) cardiac evaluation (due to the inability to clarify the reason for the assessment, deterioration of the symptoms vs. the CCTA result), and 38 patients because of missed follow-up were not enrolled in the final analysis. Forty-six patients (11.0%) developed MACE within 20.5 ± 7.9 months of follow-up. Compared to conventional scores, ML models showed better performance, except only one model which is eXtreme Gradient Boosting had lower performance than conventional scoring systems (AUC:0.824, 95% confidence interval (CI): 0.701–0.947). Between ML models, random forest, ensemble with generalized linear, and ensemble with naive Bayes were shown to have higher prognostic performance (AUC: 0.92, 95% CI: 0.85–0.99, AUC: 0.90, 95% CI: 0.81–0.98, and AUC: 0.89, 95% CI: 0.82–0.97), respectively. Coronary artery calcium score (CACS) had the highest correlation with MACE.ConclusionCompared to the conventional scoring system, ML models using CCTA scans show improved prognostic prediction for MACE. Anatomical features were more important than clinical characteristics.https://www.frontiersin.org/articles/10.3389/fcvm.2022.994483/fullcoronary computed tomography angiographymachine learningcoronary artery calcium scoresmajor adverse cardiovascular eventsconventional scoring |
| spellingShingle | Seyyed Mojtaba Ghorashi Amir Fazeli Behnam Hedayat Hamid Mokhtari Arash Jalali Pooria Ahmadi Hamid Chalian Nicola Luigi Bragazzi Shapour Shirani Negar Omidi Comparison of conventional scoring systems to machine learning models for the prediction of major adverse cardiovascular events in patients undergoing coronary computed tomography angiography Frontiers in Cardiovascular Medicine coronary computed tomography angiography machine learning coronary artery calcium scores major adverse cardiovascular events conventional scoring |
| title | Comparison of conventional scoring systems to machine learning models for the prediction of major adverse cardiovascular events in patients undergoing coronary computed tomography angiography |
| title_full | Comparison of conventional scoring systems to machine learning models for the prediction of major adverse cardiovascular events in patients undergoing coronary computed tomography angiography |
| title_fullStr | Comparison of conventional scoring systems to machine learning models for the prediction of major adverse cardiovascular events in patients undergoing coronary computed tomography angiography |
| title_full_unstemmed | Comparison of conventional scoring systems to machine learning models for the prediction of major adverse cardiovascular events in patients undergoing coronary computed tomography angiography |
| title_short | Comparison of conventional scoring systems to machine learning models for the prediction of major adverse cardiovascular events in patients undergoing coronary computed tomography angiography |
| title_sort | comparison of conventional scoring systems to machine learning models for the prediction of major adverse cardiovascular events in patients undergoing coronary computed tomography angiography |
| topic | coronary computed tomography angiography machine learning coronary artery calcium scores major adverse cardiovascular events conventional scoring |
| url | https://www.frontiersin.org/articles/10.3389/fcvm.2022.994483/full |
| work_keys_str_mv | AT seyyedmojtabaghorashi comparisonofconventionalscoringsystemstomachinelearningmodelsforthepredictionofmajoradversecardiovasculareventsinpatientsundergoingcoronarycomputedtomographyangiography AT amirfazeli comparisonofconventionalscoringsystemstomachinelearningmodelsforthepredictionofmajoradversecardiovasculareventsinpatientsundergoingcoronarycomputedtomographyangiography AT behnamhedayat comparisonofconventionalscoringsystemstomachinelearningmodelsforthepredictionofmajoradversecardiovasculareventsinpatientsundergoingcoronarycomputedtomographyangiography AT hamidmokhtari comparisonofconventionalscoringsystemstomachinelearningmodelsforthepredictionofmajoradversecardiovasculareventsinpatientsundergoingcoronarycomputedtomographyangiography AT arashjalali comparisonofconventionalscoringsystemstomachinelearningmodelsforthepredictionofmajoradversecardiovasculareventsinpatientsundergoingcoronarycomputedtomographyangiography AT pooriaahmadi comparisonofconventionalscoringsystemstomachinelearningmodelsforthepredictionofmajoradversecardiovasculareventsinpatientsundergoingcoronarycomputedtomographyangiography AT hamidchalian comparisonofconventionalscoringsystemstomachinelearningmodelsforthepredictionofmajoradversecardiovasculareventsinpatientsundergoingcoronarycomputedtomographyangiography AT nicolaluigibragazzi comparisonofconventionalscoringsystemstomachinelearningmodelsforthepredictionofmajoradversecardiovasculareventsinpatientsundergoingcoronarycomputedtomographyangiography AT shapourshirani comparisonofconventionalscoringsystemstomachinelearningmodelsforthepredictionofmajoradversecardiovasculareventsinpatientsundergoingcoronarycomputedtomographyangiography AT negaromidi comparisonofconventionalscoringsystemstomachinelearningmodelsforthepredictionofmajoradversecardiovasculareventsinpatientsundergoingcoronarycomputedtomographyangiography |