Predictors of Acute Myocardial Infarction: A Machine Learning Analysis After a 7-Year Follow-Up
Abstract
:1. Introduction
2. Materials and Methods
2.1. Population
2.2. Variables Measurements
2.3. Population Categories
2.4. Study Outcomes
2.5. Machine Learning: General Principles
2.6. Machine Learning Models
2.6.1. CART
2.6.2. Random Forest
2.6.3. SVM
3. Results
4. Discussion
Limitations and Future Directions
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Ibanez, B.; James, S.; Agewall, S.; Antunes, M.J.; Bucciarelli-Ducci, C.; Bueno, H.; Caforio, A.L.; Crea, F.; Goudevenos, J.A.; Halvorsen, S.; et al. 2017 ESC Guidelines for the management of acute myocardial infarction in patients presenting with ST-segment elevation. Kardiol. Pol. 2018, 76, 229–313. [Google Scholar] [PubMed]
- Townsend, N.; Wilson, L.; Bhatnagar, P.; Wickramasinghe, K.; Rayner, M.; Nichols, M. Cardiovascular disease in Europe: Epidemiological update 2016. Eur. Heart J. 2016, 37, 3232–3245. [Google Scholar]
- Zhan, C.; Shi, M.; Wu, R.; He, H.; Liu, X.; Shen, B. MIRKB: A myocardial infarction risk knowledge base. Database 2019, 2019, baz125. [Google Scholar] [CrossRef] [PubMed]
- Hubert, H.B.; Feinleib, M.; McNamara, P.M.; Castelli, W.P. Obesity as an independent risk factor for cardiovascular disease: A 26-year follow-up of participants in the Framingham Heart Study. Circulation 1983, 67, 968–977. [Google Scholar]
- Alberti, K.G.; Eckel, R.H.; Grundy, S.M.; Zimmet, P.Z.; Cleeman, J.I.; Donato, K.A.; Fruchart, J.C.; James, W.P.T.; Loria, C.M.; Smith, S.C., Jr. Harmonizing the metabolic syndrome: A joint interim statement of the International Diabetes Federation Task Forceon Epidemiology and Prevention; National Heart, Lung, and Blood Institute; American Heart Association; World HeartFederation; International Atherosclerosis Society; and International Association for the Study of Obesity. Obes. Metab. 2010, 7, 63–65. [Google Scholar]
- Grundy, S.M.; Cleeman, J.I.; Daniels, S.R.; Donato, K.A.; Eckel, R.H.; Franklin, B.A. Diagnosis and Management of the Metabolic Syndrome. Circulation 2005, 112, 2735–2752. [Google Scholar]
- Kuk, J.L.; Ardern, C.I. Are Metabolically Normal but Obese Individuals at Lower Risk for All-Cause Mortality? Diabetes Care 2009, 32, 2297–2299. [Google Scholar] [CrossRef]
- Lee, S.; Ha, H.; Park, Y.; Lee, J.; Yim, H.; Yoon, K.; Kang, M.; Lee, W.; Son, H.; Park, Y.; et al. Identifying metabolically obese but normal-weight (MONW) individuals in a nondiabetic Korean population: The Chungju Metabolic disease Cohort (CMC) study. Clin. Endocrinol. 2011, 75, 475–481. [Google Scholar] [CrossRef]
- Meigs, J.B.; Wilson, P.W.; Fox, C.S.; Vasan, R.S.; Nathan, D.M.; Sullivan, L.M.; D’Agostino, R.B. Body Mass Index, Metabolic Syndrome, and Risk of Type 2 Diabetes or Cardiovascular Disease. J. Clin. Endocrinol. Metab. 2006, 91, 2906–2912. [Google Scholar]
- Choi, K.M.; Cho, H.J.; Choi, H.Y.; Yang, S.J.; Yoo, H.J.; Seo, J.A.; Kim, S.G.; Baik, S.H.; Choi, D.S.; Kim, N.H. Higher mortality in metabolically obese normal-weight people than in metabolically healthy obese subjects in elderly Koreans. Clin. Endocrinol. 2013, 79, 364–370. [Google Scholar]
- EUGenMed Cardiovascular Clinical Study Group; Regitz-Zagrosek, V.; Oertelt-Prigione, S.; Prescott, E.; Franconi, F.; Gerdts, E.; Foryst-Ludwig, A.; Maas, A.H.; Kautzky-Willer, A.; Knappe-Wegner, D.; et al. Gender in cardiovascular diseases: Impact on clinical manifestations, management, and outcomes. Eur. Heart J. 2016, 37, 24–34. [Google Scholar] [PubMed]
- Mørkedal, B.; Vatten, L.J.; Romundstad, P.R.; Laugsand, L.E.; Janszky, I. Risk of Myocardial Infarction and Heart Failure Among Metabolically Healthy But Obese Individuals. J. Am. Coll. Cardiol. 2014, 63, 1071–1078. [Google Scholar] [PubMed]
- Dooley, J.; Chang, A.M.; Salhi, R.A.; Hollander, J.E. Relationship Between Body Mass Index and Prognosis of Patients Presenting With Potential Acute Coronary Syndromes. Acad. Emerg. Med. 2013, 20, 904–910. [Google Scholar]
- Kadakia, M.B.; Fox, C.S.; Scirica, B.M.; Murphy, S.A.; Bonaca, M.P.; Morrow, D.A. Central obesity and cardiovascular outcomes in patients with acute coronary syndrome: Observations from the MERLIN-TIMI 36 trial. Heart 2011, 97, 1782–1787. [Google Scholar] [PubMed]
- Xu, J.J.; Song, Y.; Jiang, P.; Jiang, L.; Zhao, X.Y.; Gao, Z.; Li, J.X.; Qiao, S.B.; Gao, R.L.; Yang, Y.J.; et al. Effects of metabolic syndrome on onset age and long-term outcomes in patients with acute coronary syndrome. World J. Emerg. Med. 2021, 12, 36. [Google Scholar]
- Stjrne, M.K.; Fritzell, J.; De Leon, A.P.; Hallqvist, J. Neighborhood Socioeconomic Context, Individual Income and Myocardial Infarction. Epidemiology 2006, 17, 14–23. [Google Scholar]
- Kjærulff, T.M.; Ersbøll, A.K.; Gislason, G.; Schipperijn, J. Geographical clustering of incident acute myocardial infarction in Denmark: A spatial analysis approach. Spat. Spatio-Temporal Epidemiol. 2016, 19, 46–59. [Google Scholar]
- Imbalzano, E.; Orlando, L.; Sciacqua, A.; Nato, G.; Dentali, F.; Nassisi, V.; Russo, V.; Camporese, G.; Bagnato, G.; Cicero, A.F.G.; et al. Machine Learning to Calculate Heparin Dose in COVID-19 Patients with Active Cancer. J. Clin. Med. 2021, 11, 219. [Google Scholar] [CrossRef]
- Ferre, R.; Elst, J.; Senthilnathan, S.; Lagree, A.; Tabbarah, S.; Lu, F.-I.; Sadeghi-Naini, A.; Tran, W.T.; Curpen, B. Machine learning analysis of breast ultrasound to classify triple negative and HER2+ breast cancer subtypes. Breast Dis. 2023, 42, 59–66. [Google Scholar]
- Ibrahim, L.; Mesinovic, M.; Yang, K.W.; Eid, M.A. Explainable prediction of acute myocardial infarction using machine learning and shapley values. IEEE Access 2020, 8, 210410–210417. [Google Scholar]
- Terranova, N.; Venkatakrishnan, K. Machine learning in modeling disease trajectory and treatment outcomes: An emerging enabler for model-informed precision medicine. Clin. Pharmacol. Ther. 2024, 115, 720–726. [Google Scholar] [PubMed]
- Lin, J.S.; Chen, K.H. A novel decision support system based on computational intelligence and machine learning: Towards zero-defect manufacturing in injection molding. J. Ind. Inf. Integr. 2024, 40, 100621. [Google Scholar] [CrossRef]
- Mourouzis, K.; Siasos, G.; Bozini, N.; Oikonomou, E.; Zaromitidou, M.; Tsigkou, V.; Kokkou, E.; Bletsa, E.; Stampouloglou, P.; Vavuranakis, M.; et al. Association of Growth Differentiation Factor 15 with Arterial Stiffness and Endothelial Function in Subpopulations of Patients with Coronary Artery Disease: A Proof-of-Concept Study. Recent Adv. Inflamm. Allergy Drug Discov. 2022, 16, 107–115. [Google Scholar]
- Bluemke, D.A.; Kronmal, R.A.; Lima, J.A.; Liu, K.; Olson, J.; Burke, G.L.; Folsom, A.R. The Relationship of Left Ventricular Mass and Geometry to Incident Cardiovascular Events. J. Am. Coll. Cardiol. 2008, 52, 2148–2155. [Google Scholar] [CrossRef] [PubMed]
- Laurent, S.; Boutouyrie, P.; Lacolley, P. Structural and Genetic Bases of Arterial Stiffness. Hypertension 2005, 45, 1050–1055. [Google Scholar]
- Mattace-Raso, F.U.; van der Cammen, T.J.; Hofman, A.; Van Popele, N.M.; Bos, M.L.; Schalekamp, M.A.D.H. Arterial Stiffness and Risk of Coronary Heart Disease and Stroke. Circulation 2006, 113, 657–663. [Google Scholar] [CrossRef]
- Blacher, J.; Guerin, A.P.; Pannier, B.; Marchais, S.J.; Safar, M.E.; London, G.M. Impact of Aortic Stiffness on Survival in End-Stage Renal Disease. Circulation 1999, 99, 2434–2439. [Google Scholar]
- Mitchell, G.F.; Moyé, L.A.; Braunwald, E.; Rouleau, J.-L.; Bernstein, V.; Geltman, E.M.; Flaker, G.C.; Pfeffer, M.A. Sphygmomanometrically Determined Pulse Pressure Is a Powerful Independent Predictor of Recurrent Events After Myocardial Infarction in Patients With Impaired Left Ventricular Function. Circulation 1997, 96, 4254–4260. [Google Scholar] [CrossRef]
- Meiszterics, Z.; Simor, T.; van der Geest, R.J.; Farkas, N.; Gaszner, B. Evaluation of pulse wave velocity for predicting major adverse cardiovascular events in post-infarcted patients; comparison of oscillometric and MRI methods. Rev. Cardiovasc. Med. 2021, 22, 1701. [Google Scholar]
- Imbalzano, E.; Vatrano, M.; Mandraffino, G.; Ghiadoni, L.; Gangemi, S.; Bruno, R.M.; Ciconte, V.A.; Paunovic, N.; Costantino, R.; Mormina, E.M.; et al. Arterial stiffness as a predictor of recovery of left ventricular systolic function after acute myocardial infarction treated with primary percutaneous coronary intervention. Int. J. Cardiovasc. Imaging 2015, 31, 1545–1551. [Google Scholar] [CrossRef]
- Imbalzano, E.; Vatrano, M.; Ghiadoni, L.; Mandraffino, G.; Dalbeni, A.; Khandheria, B.K.; Costantino, R.; Trapani, G.; Manganaro, R.; Piccione, M.C.; et al. Arterial stiffness and mitral regurgitation in arterial hypertension: An intriguing pathophysiological link. Vasc. Pharmacol. 2018, 111, 71–76. [Google Scholar] [CrossRef]
- Carluccio, E.; Tommasi, S.; Bentivoglio, M.; Buccolieri, M.; Filippucci, L.; Prosciutti, L.; Corea, L. Prognostic value of left ventricular hypertrophy and geometry in patients with a first, uncomplicated myocardial infarction. Int. J. Cardiol. 2000, 74, 177–183. [Google Scholar] [CrossRef] [PubMed]
- Verma, A.; Meris, A.; Skali, H.; Ghali, J.K.; Arnold, J.M.O.; Bourgoun, M.; Velazquez, E.J.; McMurray, J.J.V.; Kober, L.; Pfeffer, M.A.; et al. Prognostic Implications of Left Ventricular Mass and Geometry Following Myocardial Infarction. JACC Cardiovasc. Imaging 2008, 1, 582–591. [Google Scholar] [CrossRef] [PubMed]
- Verdecchia, P.; Schillaci, G.; Borgioni, C.; Ciucci, A.; Gattobigio, R.; Zampi, I.; Reboldi, G.; Porcellati, C. Prognostic Significance of Serial Changes in Left Ventricular Mass in Essential Hypertension. Circulation 1998, 97, 48–54. [Google Scholar] [CrossRef]
- Kjeldsen, S.E.; Aksnes, T.A.; Ruilope, L.M. Clinical Implications of the 2013 ESH/ESC Hypertension Guidelines: Targets, Choice of Therapy, and Blood Pressure Monitoring. Drugs RD 2014, 14, 31–43. [Google Scholar] [CrossRef]
- Nepper-Christensen, L.; Lønborg, J.; Ahtarovski, K.A.; Høfsten, D.E.; Kyhl, K.; Ghotbi, A.A.; Schoos, M.M.; Göransson, C.; Bertelsen, L.; Køber, L.; et al. Left Ventricular Hypertrophy Is Associated With Increased Infarct Size and Decreased Myocardial Salvage in Patients With ST-Segment Elevation Myocardial Infarction Undergoing Primary Percutaneous Coronary Intervention. J. Am. Heart Assoc. 2017, 6, e004823. [Google Scholar] [CrossRef] [PubMed]
- Khalid, K.; Padda, J.; Ismail, D.; Abdullah, M.; Gupta, D.; Pradeep, R.; Hameed, W.; Cooper, A.C.; Jean-Charles, G. Correlation of Coronary Artery Disease and Left Ventricular Hypertrophy. Cureus 2021, 13, e17550. [Google Scholar] [CrossRef]
- Turakhia, M.P.; Schiller, N.B.; Whooley, M.A. Prognostic Significance of Increased Left Ventricular Mass Index to Mortality and Sudden Death in Patients With Stable Coronary Heart Disease (from the Heart and Soul Study). Am. J. Cardiol. 2008, 102, 1131–1135. [Google Scholar] [CrossRef]
- Han, M.-M.; Zhao, W.-S.; Wang, X.; He, S.; Xu, X.-R.; Dang, C.-J.; Zhang, J.; Liu, J.-M.; Chen, M.-L.; Xu, L.; et al. Echocardiographic Parameters Predict Short- and Long-Term Adverse Cardiovascular Events in Patients with Acute Myocardial Infarction. Int. J. Gen. Med. 2021, 14, 2297–2303. [Google Scholar] [CrossRef]
- Kim, M.C.; Lim, Y.; Ahn, Y.; Ahn, J.H.; Lee, S.H.; Hyun, D.Y.; Cho, K.H.; Sim, D.S.; Hong, Y.J.; Kim, J.H.; et al. Incidence, Predictive Factors and Long-Term Clinical Impact of Left Ventricular Remodeling According to the Completeness of Revascularization in Patients with ST-Elevation Myocardial Infarction and Multivessel Disease. J. Clin. Med. 2022, 11, 6252. [Google Scholar] [CrossRef]
- Roman, M.J.; Ganau, A.; Saba, P.S.; Pini, R.; Pickering, T.G.; Devereux, R.B. Impact of Arterial Stiffening on Left Ventricular Structure. Hypertension 2000, 36, 489–494. [Google Scholar] [PubMed]
TOTAL (652 pts) | MHNW (358 pts) | MUNW (168 pts) | MHO (40 pts) | MUO (86 pts) | p-Value | |
Demographic characteristics | ||||||
Male sex (%) | 74.8 | 77.4 | 71.3 | 70.0 | 72.7 | 0.365 |
Age (year) | 64.0 | 64.1 | 64.3 | 63.2 | 63.5 | 0.924 |
Cardiovascular risk factors | ||||||
Smokers (%) | 38.6 | 40.2 | 42.1 | 35.0 | 26.1 | 0.062 |
Hypertension (%) | 65.7 | 58.4 | 71.3 | 62.5 | 86.4 | <0.001 |
Diabetes mellitus (%) | 28.0 | 19.0 | 44.9 | 12.5 | 38.6 | <0.001 |
Clinical parameters | ||||||
Systolic BP (mmHg) | 142.6 | 139.0 | 149.7 | 133.6 | 146.3 | <0.001 |
Diastolic BP (mmHg) | 79.6 | 78.2 | 79.6 | 81.2 | 84.8 | 0.001 |
Heart rate (beats/min) | 71.9 | 71.3 | 72.4 | 69.8 | 74.3 | 0.320 |
Ejection fraction (%) | 53.8 | 54.3 | 52.3 | 56.5 | 54.3 | 0.316 |
E/A | 0.3 | 0.2 | 0.4 | 0.1 | 0.4 | 0.09 |
Extent of coronary artery disease at baseline | ||||||
No significant coronary artery disease (%) | 9.8 | 12.8 | 2.8 | 20.8 | 6.8 | 0.005 |
1-vessel disease (%) | 36.9 | 37.0 | 39.9 | 35.0 | 31.8 | |
2-vessel disease (%) | 24.5 | 24.2 | 27.0 | 20.0 | 22.7 | |
3-vessel disease (%) | 28.8 | 26.1 | 30.3 | 25.0 | 38.6 | |
Coronary revascularization at baseline | ||||||
Single drug-eluting stent (%) | 43.6 | 41.0 | 48.9 | 45.0 | 43.2 | 0.386 |
Multiple drug-eluting stents with overlapping (%) | 12.0 | 12.2 | 12.4 | 7.5 | 12.5 | 0.843 |
Coronary artery bypass graft surgery (%) | 10.5 | 9.8 | 11.2 | 10.0 | 12.5 | 0.568 |
Biochemical markers | ||||||
Total cholesterol (mg/dL) | 181.7 | 179.5 | 185.7 | 184.6 | 181.3 | 0.461 |
HDL cholesterol (mg/dL) | 44.9 | 49.0 | 36.4 | 52.0 | 42.1 | <0.001 |
LDL cholesterol (mg/dL) | 107.0 | 108.1 | 107.3 | 107.4 | 101.3 | 0.565 |
Triglycerides (mg/dL) | 146.5 | 111.7 | 209.3 | 107.0 | 181.9 | <0.001 |
Fasting glucose (mg/dL) | 126.4 | 114.7 | 151.8 | 104.4 | 134.2 | <0.001 |
Creatinine (mg/dL) | 1.0 | 1.0 | 1.0 | 0.9 | 0.9 | 0.746 |
C reactive protein (mg/dL) | 10.5 | 8.5 | 11.4 | 12.4 | 15.4 | 0.280 |
Medication following coronary revascularization | ||||||
Antiplatelet therapy (%) | 99.5 | 99.4 | 99.6 | 99.2 | 100.0 | 0.954 |
Statins (%) | 99.3 | 99.7 | 99.4 | 98.9 | 99.5 | 0.944 |
Diuretics (%) | 28.3 | 27.4 | 27.7 | 28.6 | 29.7 | 0.554 |
ACE inhibitors (%) | 97.4 | 97.6 | 96.6 | 98.1 | 97.3 | 0.898 |
Beta-blockers (%) | 95.5 | 95.2 | 95.1 | 96.5 | 95.3 | 0.789 |
Metrics | CART | RANDOM FOREST | SVM | |
---|---|---|---|---|
LINEAR | RBF | |||
Accuracy (%) | 82.18 | 85.15 | 73.76 | 82.18 |
Sensitivity (%) | 14.29 | 37.50 | 11.54 | 11.54 |
Specificity (%) | 87.23 | 89.25 | 82.95 | 92.61 |
Time elapsed (s) | 37.84 | 173.17 | 2.55 | 19.22 |
Hyperparameter (s) | cp = 0.041 | mtry = 3 | cost = 5 SVs = 82 | Cost = 1 Gamma = 1 SVs = 124 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Casciaro, M.; Di Micco, P.; Tonacci, A.; Vatrano, M.; Russo, V.; Siniscalchi, C.; Gangemi, S.; Imbalzano, E. Predictors of Acute Myocardial Infarction: A Machine Learning Analysis After a 7-Year Follow-Up. Clin. Pract. 2025, 15, 72. https://doi.org/10.3390/clinpract15040072
Casciaro M, Di Micco P, Tonacci A, Vatrano M, Russo V, Siniscalchi C, Gangemi S, Imbalzano E. Predictors of Acute Myocardial Infarction: A Machine Learning Analysis After a 7-Year Follow-Up. Clinics and Practice. 2025; 15(4):72. https://doi.org/10.3390/clinpract15040072
Chicago/Turabian StyleCasciaro, Marco, Pierpaolo Di Micco, Alessandro Tonacci, Marco Vatrano, Vincenzo Russo, Carmine Siniscalchi, Sebastiano Gangemi, and Egidio Imbalzano. 2025. "Predictors of Acute Myocardial Infarction: A Machine Learning Analysis After a 7-Year Follow-Up" Clinics and Practice 15, no. 4: 72. https://doi.org/10.3390/clinpract15040072
APA StyleCasciaro, M., Di Micco, P., Tonacci, A., Vatrano, M., Russo, V., Siniscalchi, C., Gangemi, S., & Imbalzano, E. (2025). Predictors of Acute Myocardial Infarction: A Machine Learning Analysis After a 7-Year Follow-Up. Clinics and Practice, 15(4), 72. https://doi.org/10.3390/clinpract15040072