Machine Learning Algorithm to Predict Obstructive Coronary Artery Disease: Insights from the CorLipid Trial
Developing risk assessment tools for CAD prediction remains challenging nowadays. We developed an ML predictive algorithm based on metabolic and clinical data for determining the severity of CAD, as assessed via the SYNTAX score. Analytical methods were developed to determine serum blood levels of s...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Metabolites |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-1989/12/9/816 |
| _version_ | 1797484898677686272 |
|---|---|
| author | Eleftherios Panteris Olga Deda Andreas S. Papazoglou Efstratios Karagiannidis Theodoros Liapikos Olga Begou Thomas Meikopoulos Thomai Mouskeftara Georgios Sofidis Georgios Sianos Georgios Theodoridis Helen Gika |
| author_facet | Eleftherios Panteris Olga Deda Andreas S. Papazoglou Efstratios Karagiannidis Theodoros Liapikos Olga Begou Thomas Meikopoulos Thomai Mouskeftara Georgios Sofidis Georgios Sianos Georgios Theodoridis Helen Gika |
| author_sort | Eleftherios Panteris |
| collection | DOAJ |
| description | Developing risk assessment tools for CAD prediction remains challenging nowadays. We developed an ML predictive algorithm based on metabolic and clinical data for determining the severity of CAD, as assessed via the SYNTAX score. Analytical methods were developed to determine serum blood levels of specific ceramides, acyl-carnitines, fatty acids, and proteins such as galectin-3, adiponectin, and APOB/APOA1 ratio. Patients were grouped into: obstructive CAD (SS > 0) and non-obstructive CAD (SS = 0). A risk prediction algorithm (boosted ensemble algorithm XGBoost) was developed by combining clinical characteristics with established and novel biomarkers to identify patients at high risk for complex CAD. The study population comprised 958 patients (CorLipid trial (NCT04580173)), with no prior CAD, who underwent coronary angiography. Of them, 533 (55.6%) suffered ACS, 170 (17.7%) presented with NSTEMI, 222 (23.2%) with STEMI, and 141 (14.7%) with unstable angina. Of the total sample, 681 (71%) had obstructive CAD. The algorithm dataset was 73 biochemical parameters and metabolic biomarkers as well as anthropometric and medical history variables. The performance of the XGBoost algorithm had an AUC value of 0.725 (95% CI: 0.691–0.759). Thus, a ML model incorporating clinical features in addition to certain metabolic features can estimate the pre-test likelihood of obstructive CAD. |
| first_indexed | 2024-03-09T23:12:03Z |
| format | Article |
| id | doaj.art-b679499c24764a98af51bc9923b22c69 |
| institution | Directory Open Access Journal |
| issn | 2218-1989 |
| language | English |
| last_indexed | 2024-03-09T23:12:03Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Metabolites |
| spelling | doaj.art-b679499c24764a98af51bc9923b22c692023-11-23T17:44:07ZengMDPI AGMetabolites2218-19892022-08-0112981610.3390/metabo12090816Machine Learning Algorithm to Predict Obstructive Coronary Artery Disease: Insights from the CorLipid TrialEleftherios Panteris0Olga Deda1Andreas S. Papazoglou2Efstratios Karagiannidis3Theodoros Liapikos4Olga Begou5Thomas Meikopoulos6Thomai Mouskeftara7Georgios Sofidis8Georgios Sianos9Georgios Theodoridis10Helen Gika11Laboratory of Forensic Medicine and Toxicology, School of Medicine, Aristotle University of Thessaloniki, 54124 Thessaloniki, GreeceLaboratory of Forensic Medicine and Toxicology, School of Medicine, Aristotle University of Thessaloniki, 54124 Thessaloniki, GreeceFirst Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, St. Kiriakidi 1, 54636 Thessaloniki, GreeceFirst Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, St. Kiriakidi 1, 54636 Thessaloniki, GreeceLaboratory of Analytical Chemistry, Department of Chemistry, Aristotle University of Thessaloniki, 54124 Thessaloniki, GreeceBiomic_Auth, Bioanalysis and Omics Lab, Centre for Interdisciplinary Research of Aristotle University of Thessaloniki, 57001 Thermi, GreeceBiomic_Auth, Bioanalysis and Omics Lab, Centre for Interdisciplinary Research of Aristotle University of Thessaloniki, 57001 Thermi, GreeceLaboratory of Forensic Medicine and Toxicology, School of Medicine, Aristotle University of Thessaloniki, 54124 Thessaloniki, GreeceFirst Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, St. Kiriakidi 1, 54636 Thessaloniki, GreeceFirst Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, St. Kiriakidi 1, 54636 Thessaloniki, GreeceBiomic_Auth, Bioanalysis and Omics Lab, Centre for Interdisciplinary Research of Aristotle University of Thessaloniki, 57001 Thermi, GreeceLaboratory of Forensic Medicine and Toxicology, School of Medicine, Aristotle University of Thessaloniki, 54124 Thessaloniki, GreeceDeveloping risk assessment tools for CAD prediction remains challenging nowadays. We developed an ML predictive algorithm based on metabolic and clinical data for determining the severity of CAD, as assessed via the SYNTAX score. Analytical methods were developed to determine serum blood levels of specific ceramides, acyl-carnitines, fatty acids, and proteins such as galectin-3, adiponectin, and APOB/APOA1 ratio. Patients were grouped into: obstructive CAD (SS > 0) and non-obstructive CAD (SS = 0). A risk prediction algorithm (boosted ensemble algorithm XGBoost) was developed by combining clinical characteristics with established and novel biomarkers to identify patients at high risk for complex CAD. The study population comprised 958 patients (CorLipid trial (NCT04580173)), with no prior CAD, who underwent coronary angiography. Of them, 533 (55.6%) suffered ACS, 170 (17.7%) presented with NSTEMI, 222 (23.2%) with STEMI, and 141 (14.7%) with unstable angina. Of the total sample, 681 (71%) had obstructive CAD. The algorithm dataset was 73 biochemical parameters and metabolic biomarkers as well as anthropometric and medical history variables. The performance of the XGBoost algorithm had an AUC value of 0.725 (95% CI: 0.691–0.759). Thus, a ML model incorporating clinical features in addition to certain metabolic features can estimate the pre-test likelihood of obstructive CAD.https://www.mdpi.com/2218-1989/12/9/816metabolic markersceramidesacylcarnitineslipidsbiomarkerscoronary artery disease |
| spellingShingle | Eleftherios Panteris Olga Deda Andreas S. Papazoglou Efstratios Karagiannidis Theodoros Liapikos Olga Begou Thomas Meikopoulos Thomai Mouskeftara Georgios Sofidis Georgios Sianos Georgios Theodoridis Helen Gika Machine Learning Algorithm to Predict Obstructive Coronary Artery Disease: Insights from the CorLipid Trial Metabolites metabolic markers ceramides acylcarnitines lipids biomarkers coronary artery disease |
| title | Machine Learning Algorithm to Predict Obstructive Coronary Artery Disease: Insights from the CorLipid Trial |
| title_full | Machine Learning Algorithm to Predict Obstructive Coronary Artery Disease: Insights from the CorLipid Trial |
| title_fullStr | Machine Learning Algorithm to Predict Obstructive Coronary Artery Disease: Insights from the CorLipid Trial |
| title_full_unstemmed | Machine Learning Algorithm to Predict Obstructive Coronary Artery Disease: Insights from the CorLipid Trial |
| title_short | Machine Learning Algorithm to Predict Obstructive Coronary Artery Disease: Insights from the CorLipid Trial |
| title_sort | machine learning algorithm to predict obstructive coronary artery disease insights from the corlipid trial |
| topic | metabolic markers ceramides acylcarnitines lipids biomarkers coronary artery disease |
| url | https://www.mdpi.com/2218-1989/12/9/816 |
| work_keys_str_mv | AT eleftheriospanteris machinelearningalgorithmtopredictobstructivecoronaryarterydiseaseinsightsfromthecorlipidtrial AT olgadeda machinelearningalgorithmtopredictobstructivecoronaryarterydiseaseinsightsfromthecorlipidtrial AT andreasspapazoglou machinelearningalgorithmtopredictobstructivecoronaryarterydiseaseinsightsfromthecorlipidtrial AT efstratioskaragiannidis machinelearningalgorithmtopredictobstructivecoronaryarterydiseaseinsightsfromthecorlipidtrial AT theodorosliapikos machinelearningalgorithmtopredictobstructivecoronaryarterydiseaseinsightsfromthecorlipidtrial AT olgabegou machinelearningalgorithmtopredictobstructivecoronaryarterydiseaseinsightsfromthecorlipidtrial AT thomasmeikopoulos machinelearningalgorithmtopredictobstructivecoronaryarterydiseaseinsightsfromthecorlipidtrial AT thomaimouskeftara machinelearningalgorithmtopredictobstructivecoronaryarterydiseaseinsightsfromthecorlipidtrial AT georgiossofidis machinelearningalgorithmtopredictobstructivecoronaryarterydiseaseinsightsfromthecorlipidtrial AT georgiossianos machinelearningalgorithmtopredictobstructivecoronaryarterydiseaseinsightsfromthecorlipidtrial AT georgiostheodoridis machinelearningalgorithmtopredictobstructivecoronaryarterydiseaseinsightsfromthecorlipidtrial AT helengika machinelearningalgorithmtopredictobstructivecoronaryarterydiseaseinsightsfromthecorlipidtrial |