|
1
|
Panteris E, Deda O, Papazoglou AS, Karagiannidis E, Liapikos T, Begou O, Meikopoulos T, Mouskeftara T, Sofidis G, Sianos G, Theodoridis G, Gika H. Machine Learning Algorithm to Predict Obstructive Coronary Artery Disease: Insights from the CorLipid Trial. Metabolites 2022; 12:metabo12090816. [PMID: 36144220 PMCID: PMC9504538 DOI: 10.3390/metabo12090816] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2022] [Revised: 08/21/2022] [Accepted: 08/26/2022] [Indexed: 11/16/2022] Open
Abstract
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.
Collapse
Affiliation(s)
- Eleftherios Panteris
- Laboratory of Forensic Medicine and Toxicology, School of Medicine, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece
- Biomic_Auth, Bioanalysis and Omics Lab, Centre for Interdisciplinary Research of Aristotle University of Thessaloniki, 57001 Thermi, Greece
- Correspondence: (E.P.); (O.D.); (H.G.)
| | - Olga Deda
- Laboratory of Forensic Medicine and Toxicology, School of Medicine, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece
- Biomic_Auth, Bioanalysis and Omics Lab, Centre for Interdisciplinary Research of Aristotle University of Thessaloniki, 57001 Thermi, Greece
- Correspondence: (E.P.); (O.D.); (H.G.)
| | - Andreas S. Papazoglou
- First Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, St. Kiriakidi 1, 54636 Thessaloniki, Greece
| | - Efstratios Karagiannidis
- First Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, St. Kiriakidi 1, 54636 Thessaloniki, Greece
| | - Theodoros Liapikos
- Laboratory of Analytical Chemistry, Department of Chemistry, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece
| | - Olga Begou
- Biomic_Auth, Bioanalysis and Omics Lab, Centre for Interdisciplinary Research of Aristotle University of Thessaloniki, 57001 Thermi, Greece
- Laboratory of Analytical Chemistry, Department of Chemistry, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece
| | - Thomas Meikopoulos
- Biomic_Auth, Bioanalysis and Omics Lab, Centre for Interdisciplinary Research of Aristotle University of Thessaloniki, 57001 Thermi, Greece
- Laboratory of Analytical Chemistry, Department of Chemistry, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece
| | - Thomai Mouskeftara
- Laboratory of Forensic Medicine and Toxicology, School of Medicine, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece
- Biomic_Auth, Bioanalysis and Omics Lab, Centre for Interdisciplinary Research of Aristotle University of Thessaloniki, 57001 Thermi, Greece
| | - Georgios Sofidis
- First Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, St. Kiriakidi 1, 54636 Thessaloniki, Greece
| | - Georgios Sianos
- First Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, St. Kiriakidi 1, 54636 Thessaloniki, Greece
| | - Georgios Theodoridis
- Biomic_Auth, Bioanalysis and Omics Lab, Centre for Interdisciplinary Research of Aristotle University of Thessaloniki, 57001 Thermi, Greece
- Laboratory of Analytical Chemistry, Department of Chemistry, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece
| | - Helen Gika
- Laboratory of Forensic Medicine and Toxicology, School of Medicine, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece
- Biomic_Auth, Bioanalysis and Omics Lab, Centre for Interdisciplinary Research of Aristotle University of Thessaloniki, 57001 Thermi, Greece
- Correspondence: (E.P.); (O.D.); (H.G.)
| |
Collapse
|
|
2
|
Agrawal S, Klarqvist MD, Emdin C, Patel AP, Paranjpe MD, Ellinor PT, Philippakis A, Ng K, Batra P, Khera AV. Selection of 51 predictors from 13,782 candidate multimodal features using machine learning improves coronary artery disease prediction. PATTERNS (NEW YORK, N.Y.) 2021; 2:100364. [PMID: 34950898 PMCID: PMC8672148 DOI: 10.1016/j.patter.2021.100364] [Citation(s) in RCA: 16] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/01/2021] [Revised: 06/21/2021] [Accepted: 09/16/2021] [Indexed: 12/11/2022]
Abstract
Current cardiovascular risk assessment tools use a small number of predictors. Here, we study how machine learning might: (1) enable principled selection from a large multimodal set of candidate variables and (2) improve prediction of incident coronary artery disease (CAD) events. An elastic net-based Cox model (ML4HEN-COX) trained and evaluated in 173,274 UK Biobank participants selected 51 predictors from 13,782 candidates. Beyond most traditional risk factors, ML4HEN-COX selected a polygenic score, waist circumference, socioeconomic deprivation, and several hematologic indices. A more than 30-fold gradient in 10-year risk estimates was noted across ML4HEN-COX quintiles, ranging from 0.25% to 7.8%. ML4HEN-COX improved discrimination of incident CAD (C-statistic = 0.796) compared with the Framingham risk score, pooled cohort equations, and QRISK3 (range 0.754-0.761). This approach to variable selection and model assessment is readily generalizable to a broad range of complex datasets and disease endpoints.
Collapse
Affiliation(s)
- Saaket Agrawal
- Cardiovascular Disease Initiative, Broad Institute of MIT and Harvard, Cambridge, MA, USA
- Center for Genomic Medicine, Department of Medicine, Massachusetts General Hospital, 185 Cambridge Street, Simches Research Building | CPZN 6.256, Boston, MA 02114, USA
- Department of Medicine, Harvard Medical School, Boston, MA, USA
| | | | - Connor Emdin
- Cardiovascular Disease Initiative, Broad Institute of MIT and Harvard, Cambridge, MA, USA
- Center for Genomic Medicine, Department of Medicine, Massachusetts General Hospital, 185 Cambridge Street, Simches Research Building | CPZN 6.256, Boston, MA 02114, USA
- Department of Medicine, Harvard Medical School, Boston, MA, USA
| | - Aniruddh P. Patel
- Cardiovascular Disease Initiative, Broad Institute of MIT and Harvard, Cambridge, MA, USA
- Center for Genomic Medicine, Department of Medicine, Massachusetts General Hospital, 185 Cambridge Street, Simches Research Building | CPZN 6.256, Boston, MA 02114, USA
- Department of Medicine, Harvard Medical School, Boston, MA, USA
| | - Manish D. Paranjpe
- Cardiovascular Disease Initiative, Broad Institute of MIT and Harvard, Cambridge, MA, USA
- Center for Genomic Medicine, Department of Medicine, Massachusetts General Hospital, 185 Cambridge Street, Simches Research Building | CPZN 6.256, Boston, MA 02114, USA
- Department of Medicine, Harvard Medical School, Boston, MA, USA
| | - Patrick T. Ellinor
- Cardiovascular Disease Initiative, Broad Institute of MIT and Harvard, Cambridge, MA, USA
- Center for Genomic Medicine, Department of Medicine, Massachusetts General Hospital, 185 Cambridge Street, Simches Research Building | CPZN 6.256, Boston, MA 02114, USA
- Department of Medicine, Harvard Medical School, Boston, MA, USA
| | - Anthony Philippakis
- Data Sciences Platform, Broad Institute of MIT and Harvard, Cambridge, MA, USA
| | - Kenney Ng
- Center for Computational Health, IBM Research, Cambridge, MA, USA
| | - Puneet Batra
- Data Sciences Platform, Broad Institute of MIT and Harvard, Cambridge, MA, USA
| | - Amit V. Khera
- Cardiovascular Disease Initiative, Broad Institute of MIT and Harvard, Cambridge, MA, USA
- Center for Genomic Medicine, Department of Medicine, Massachusetts General Hospital, 185 Cambridge Street, Simches Research Building | CPZN 6.256, Boston, MA 02114, USA
- Department of Medicine, Harvard Medical School, Boston, MA, USA
| |
Collapse
|
|
4
|
Kigka VI, Sakellarios AI, Tsompou P, Kyriakidis S, Siogkas P, Andrikos I, Michalis LK, Fotiadis DI. Site specific prediction of atherosclerotic plaque progression using computational biomechanics and machine learning. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2020; 2019:6998-7001. [PMID: 31947449 DOI: 10.1109/embc.2019.8856881] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Abstract
Atheromatic plaque progression is considered as a typical pathological condition of arteries and although atherosclerosis is considered as a systemic inflammatory disorder, atheromatic plaque is not uniformly distributed in the arterial tree. Except for the systematic atherosclerosis risk factors, biomechanical forces, LDL concentration and artery geometry contribute to the atherogenesis and atherosclerotic plaque evolution. In this study, we calculate biomechanical forces acting within the artery and we develop a machine learning model for the prediction of atheromatic plaque progression. 1018 coronary sites of 3 mm, derived by 40 individuals, are utilized to develop the model and after the implementation of 4 different tree based prediction schemes, we achieve a prediction accuracy of 0.84. The best accuracy was achieved by the implementation of a tree-based classifier, the Random Forest classifier, after a ranking feature selection methodology. The novel aspect of the proposed methodology is the implementation of machine learning models in order to address the cardiovascular data modeling, aiming to predict the occurrence of an outcome and not to investigate the association of input features.
Collapse
|