Enhancing Clinical Reliability in Coronary Artery Disease (CAD) Diagnosis: A Hybrid Machine Learning Approach Utilizing Genetic Algorithm-Optimized AdaBoost Decision Trees

Document Type : Original Article

Authors

1 Health Human Resources Research Center, Shiraz University of Medical Sciences, Shiraz, Iran

2 Department of Management and Health Information Technology, School of Management and Medical Information Sciences, Isfahan University of Medical Sciences, Isfahan, Iran Health Information Technology Research Center, Isfahan University of Medical Sciences, Isfahan, Iran

Abstract

Introduction: Accurate and reliable diagnosis of coronary artery disease (CAD) is critical, requiring predictive models that minimize classification errors, particularly False Positives (FPs), given the high clinical and ethical costs associated with them. This study aimed to identify an optimized classifier with maximal predictive reliability using the Z-Alizadeh Sani dataset.
Methods: The methodology employed a dual-stage feature selection process comparing the Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The Synthetic Minority Over-Sampling Technique (SMOTE) was subsequently applied to mitigate class imbalance. Models were evaluated using a strict performance criterion that considered a comprehensive set of metrics, including Sensitivity, Accuracy, and the Area Under the Receiver Operating Characteristic curve (AUC).
Results: The proposed hybrid model, GA + AdaBoost DT, demonstrated the highest overall predictive reliability. It achieved an accuracy of 95.88% and an exceptionally high Specificity of 98.08%, significantly surpassing comparable high-accuracy models in the literature. Furthermore, the model achieved a robust AUC of 0.972. The analysis confirmed that the GA effectively identified a superior, minimal feature subset.
Conclusion: The model offers a clinically superior diagnostic tool, with a low false-positive rate, ensuring highly reliable patient screening. This study establishes a new benchmark for reliable CAD diagnosis by prioritizing clinical safety while optimizing specificity.

Highlights

Parisa Eslami: Google Scholar

Narges Mahmoudi: Google Scholar

Keywords

Main Subjects

References

  1. Bao X, Zhang Z, Shen Y, Tang P, Si G, Kang L, et al. Cardiovascular Information and Health Engineering Medicine. 2025;8:0956.
  2. Di Cesare M, Perel P, Taylor S, Kabudula C, Bixby H, Gaziano TA, et al. The heart of the world. 2024;19(1):11.
  3. Mir MA, Dar MA, Qadir AJAJBP. Exploring the Landscape of Coronary Artery Disease: A Comprehensive Review. 2024;1:9-22.
  4. Sanyaolu SE, Wilson DO, Oguntolu BA, Salako MS, Adeyemi ROJP. Current Evidence on the Clinical Management of Coronary Artery Disease and Acute Coronary Syndrome: A Narrative Review.2:3.
  5. Netala VR, Hou T, Wang Y, Zhang Z, Teertam SKJIJoMS. Cardiovascular biomarkers: tools for precision diagnosis and prognosis. 2025;26(7):3218.
  6. Jiangping S, Zhe Z, Wei W, Yunhu S, Jie H, Hongyue W, et al. Assessment of coronary artery stenosis by coronary angiography: a head-to-head comparison with pathological coronary artery anatomy. 2013;6(3):262-8.
  7. Suzuki N, Asano T, Nakazawa G, Aoki J, Tanabe K, Hibi K, et al. Clinical expert consensus document on quantitative coronary angiography from the Japanese Association of Cardiovascular Intervention and Therapeutics. 2020;35(2):105-16.
  8. Tavakol M, Ashraf S, Brener SJJGjohs. Risks and complications of coronary angiography: a comprehensive review. 2012;4(1):65.
  9. Kluge B, Harris J, Sánchez-Collado I, Pérez-Román I, Paffett M, Harz C, et al. Cost savings from prioritization of non-invasive modalities within CAD diagnostic protocols: a systematic review. 2025;28(1):1388-404.
  10. Wang LWJIMJ. Non‐invasive screening for coronary artery disease: current perspectives, patient, public health and ethical considerations in evaluating symptomatic and asymptomatic individuals. 2025;55(4):555-63.
  11. Apostolopoulos ID, Groumpos PPJCMiB, Engineering B. Non-invasive modelling methodology for the diagnosis of coronary artery disease using fuzzy cognitive maps. 2020;23(12):879-87.
  12. Tasmurzayev N, Imanbek B, Boltaboyeva A, Dikhanbayeva G, Zhussupbekov S, Saparbayeva Q, et al. Explainable AI for Coronary Artery Disease Stratification Using Routine Clinical Data. 2025;18(11):693.
  13. Alizadehsani R, Hosseini MJ, Khosravi A, Khozeimeh F, Roshanzamir M, Sarrafzadegan N, et al. Non-invasive detection of coronary artery disease in high-risk patients based on the stenosis prediction of separate coronary arteries. 2018;162:119-27.
  14. Ezekwueme F, Tolu-Akinnawo O, Smith Z, Ogunniyi KEJC. Non-invasive Assessment of Coronary Artery Disease: The Role of AI in the Current Status and Future Directions. 2025;17(2).
  15. Ahmed Z, Mohamed K, Zeeshan S, Dong XJD. Artificial intelligence with multi-functional machine learning platform development for better healthcare and precision medicine. 2020;2020:baaa010.
  16. Vasamsetty CJIJoME, Engineering C. Clinical decision support systems and advanced data mining techniques for cardiovascular care: Unveiling patterns and trends. 2020;8(2).
  17. Alizadehsani R, Habibi J, Hosseini MJ, Mashayekhi H, Boghrati R, Ghandeharioun A, et al. A data mining approach for diagnosis of coronary artery disease. 2013;111(1):52-61.
  18. Arabasadi Z, Alizadehsani R, Roshanzamir M, Moosaei H, Yarifard AAJCm, biomedicine pi. Computer aided decision making for heart disease detection using hybrid neural network-Genetic algorithm. 2017;141:19-26.
  19. Cüvitoğlu A, Işik Z, editors. Classification of CAD dataset by using principal component analysis and machine learning approaches. 2018 5th International Conference on Electrical and Electronic Engineering (ICEEE); 2018: IEEE.
  20. Gupta A, Arora HS, Kumar R, Raman B, editors. DMHZ: a decision support system based on machine computational design for heart disease diagnosis using z-alizadeh sani dataset. 2021 International Conference on Information Networking (ICOIN); 2021: IEEE.
  21. Hashemi M, Komamardakhi SSS, Maftoun M, Zare O, Joloudari JH, Nematollahi MA, et al., editors. Enhancing Coronary Artery Disease Classification Using Optimized MLP Based on Genetic Algorithm. International Work-Conference on the Interplay Between Natural and Artificial Computation; 2024: Springer.
  22. Jalali SMJ, Karimi M, Khosravi A, Nahavandi S, editors. An efficient neuroevolution approach for heart disease detection. 2019 IEEE international conference on Systems, Man and Cybernetics (SMC); 2019: IEEE.
  23. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WPJJoair. SMOTE: synthetic minority over-sampling technique. 2002;16:321-57.
  24. Lambora A, Gupta K, Chopra K, editors. Genetic algorithm-A literature review. 2019 international conference on machine learning, big data, cloud and parallel computing (COMITCon); 2019: IEEE.
  25. Wang D, Tan D, Liu LJSc. Particle swarm optimization algorithm: an overview. 2018;22(2):387-408.
  26. Raschka SJapa. Model evaluation, model selection, and algorithm selection in machine learning. 2018.
  27. Rashidi HH, Albahra S, Robertson S, Tran NK, Hu BJFiO. Common statistical concepts in the supervised Machine Learning arena. 2023;13:1130229.
  28. Sayadi M, Varadarajan V, Sadoughi F, Chopannejad S, Langarizadeh MJL. A machine learning model for detection of coronary artery disease using noninvasive clinical parameters. 2022;12(11):1933.
  29. Nasarian E, Sharifrazi D, Mohsenirad S, Tsui K, Alizadehsani RJapa. AI Framework for Early Diagnosis of Coronary Artery Disease: An Integration of Borderline SMOTE, Autoencoders and Convolutional Neural Networks Approach. 2023.
  30. Mansoor C, Chettri SK, Naleer H, editors. Predicting Coronary Artery Disease using an Ensemble Voting Model and Machine Learning Techniques. 2023 9th International Conference on Smart Structures and Systems (ICSSS); 2023: IEEE.
  31. Vijayaraj AR, Pasupathi S, editors. Enhancing Cardiac Health: Machine Learning in Coronary Artery Disease Prediction. International Conference on Computational Intelligence in Pattern Recognition; 2024: Springer.
  32. Zhang M, Wang H, Zhao JJPo. Use machine learning models to identify and assess risk factors for coronary artery disease. 2024;19(9):e0307952.
Health Management & Information Science
Volume 13, Issue 2
April 2026
Pages 98-111

Files

Share

How to cite

Statistics