Page 78 - GTM-3-1

Global Translational Medicine Evaluating ML models for CAD prediction

in different patient populations. Overall, this study’s magnitude of coronary artery disease and acute coronary
conclusion emphasizes the promise of ML in enhancing syndrome: A narrative review. J Epidemiol Glob Health.
the prediction and detection of CAD and recommends 2021;11(2):169-177.
further research to build upon the initial findings, improve doi: 10.2991/jegh.k.201217.001
the dataset, and validate the model externally.
3. Tsao CW, Aday AW, Almarzooq ZI, et al. Heart disease and
Hence, the limitations uncovered, such as the dataset’s stroke statistics-2023 update: A report from the American
relatively limited size and the simplicity of the binary heart association. Circulation. 2023;147:e93-e621.
outcomes, highlight the need for further research. To enhance doi: 10.1161/CIR.0000000000001123.
the model’s predictive power and clinical applicability, 4. Moriguchi JD, Kobashigawa JA, Ro TK, et al. At
future efforts should concentrate on enriching the dataset’s what creatinine level is angiographic dye safe for
complexity, incorporating more nuanced clinical parameters, coronary angiography in cardiac transplant recipients?
and conducting external validations across diverse patient Transplantation. 1998;65(12):S160.
cohorts. This progression work is vital to ensure the model’s 5. Alizadehsani R, Abdar M, Roshanzamir M, et al. Machine
robustness, relevance, and generalizability to different learning-based coronary artery disease diagnosis:
demographic and clinical settings, striving to integrate A comprehensive review. Comput Biol Med. 2019;111:103346.
advanced ML tools into everyday clinical practice to the
benefit of patient care and outcomes. doi: 10.1016/j.compbiomed.2019.103346
6. Alizadehsani R, Habibi J, Hosseini MJ, et al. A data mining
Acknowledgments approach for diagnosis of coronary artery disease. Comput
Methods Programs Biomed. 2013;111(1):52-61.
None.
doi: 10.1016/j.cmpb.2013.03.004
Funding 7. Goff DC Jr., Lloyd-Jones DM, Bennett G, et al. 2013 ACC/AHA
None. guideline on the assessment of cardiovascular risk: A report
of the American College of Cardiology/American Heart
Conflict of interest Association Task Force on Practice Guidelines. Circulation.
2014;129(25_suppl_2):S49-S73.
The authors declare that they have no competing interests.
doi: 10.1161/01.cir.0000437741.48606.98
Author contributions 8. DeFilippis AP, Young R, Carrubba CJ, et al. An analysis
Conceptualization: All authors of calibration and discrimination among multiple
Formal analysis: All authors cardiovascular risk scores in a modern multiethnic cohort.
Ann Intern Med. 2015;162(4):266-275.
Investigation: All authors
Methodology: All authors doi: 10.7326/M14-1281
Writing – original draft: All authors 9. Toma M, Wei OC. Predictive modeling in medicine.
Writing – review & editing: All authors Encyclopedia. 2023;3(2):590-601.

Ethics approval and consent to participate doi: 10.3390/encyclopedia3020042
10. Bekbolatova M, Mayer J, Ong CW, Toma M. Transformative
Not applicable. potential of AI in healthcare: Definitions, applications, and
Consent for publication navigating the ethical landscape and public perspectives.
Healthcare (Basel). 2024;12(2):125.
Not applicable. doi: 10.3390/healthcare12020125

Availability of data 11. Abraham A, Jose R, Ahmad J, et al. Comparative analysis
of machine learning models for image detection of colonic
All data are included in the manuscript. polyps vs. Resected polyps. J Imaging. 2023;9(10):215.

References doi: 10.3390/jimaging9100215
1. World Health Organization. The Top 10 Causes of Death. 12. Gautam N, Saluja P, Malkawi A, et al. Current and future
Available from: https://www.who.int/news-room/fact- applications of artificial intelligence in coronary artery
sheets/detail/the-top-10-causes-of-death [Last accessed on disease. Healthcare (Basel). 2022;10(2):232.
2023 Dec 22]. doi: 10.3390/healthcare10020232
2. Ralapanawa U, Sivakanesan R. Epidemiology and the 13. Davenport T, Kalakota R. The potential for artificial

Volume 3 Issue 1 (2024) 11 https://doi.org/10.36922/gtm.2669