An Intelligent Clinical Decision Support System for Cardiovascular Disease Prediction Using EHR-Based ML and DL Techniques
DOI:
https://doi.org/10.68337/cpsm.v1.i2.2026-023Keywords:
Medical data mining, electronic health records, data-driven healthcare, deep learning, gradient boosting, CatBoost, digital health, personalized healthcare, precision medicineAbstract
Artificial intelligence (AI) is widely used in healthcare to predict disease. Cardiovascular diseases (CVDs) remain the leading cause of death worldwide, so early detection is vital for lowering the cost of treatment and improving patient survival. Many classification techniques have been designed for CVD prediction, but high prediction accuracy is still difficult to achieve. The main goal of this study is to increase the accuracy of CVD prediction with advanced AI techniques. Because CVD poses a great threat to the global population and early identification of patients is important, the study examines machine learning (ML) and deep learning (DL) algorithms for predicting CVD from electronic health records (EHRs). The predictive capability of conventional AI algorithms was estimated and compared on a large EHR dataset. According to the results, the proposed D-t-SNE method performed better than the ensemble models it was compared with.
References
[1] Mohammad Iqbal, Muhammad Nanda Setiawan, Mohammad Isa Irawan, Ku Muhammad Naim Ku Khalif, Noryanti Muhammad, and Mohd Khairul Bazli Mohd Aziz, "Cardiovascular disease detection from high utility rare rule mining," Artif. Intell. Med., vol. 131, Art. no. 102347, 2022, doi: 10.1016/j.artmed.2022.102347.
[2] C. Kotteeswaran, Pamidi Ankitha, and Panjagalla Veera Harish, "Cardiovascular disease prediction from retinal images using deep learning," in Proc. 2026 8th Int. Conf. Intell. Sustain. Syst. (ICISS), 2026, pp. 1-8, doi: 10.1109/ICISS67859.2026.11453563.
[3] Amar Shukla, Ginika Mahajan, Shamik Tiwari, and Akhilesh Kumar Sharma, "Metaheuristic optimized random forest for multiclass cardiovascular disease prediction," in Proc. 2026 IEEE Madhya Pradesh Section Conf. (MPCON), 2026, pp. 1610-1614, doi: 10.1109/MPCON69668.2026.11509026.
[4] Mithila Mehedi, Nourin Nishat, Janifer Nahar, Muniroopesh Raasetti, A. S. M. Shoaib, Basharat Ali, and Md Amran Hossen Pabel, "Innovative machine learning approaches to cardiovascular disease prediction," in Proc. 2024 Int. Conf. Intell. Comput. Sustain. Innov. Technol. (IC-SIT), 2024, pp. 1-4, doi: 10.1109/IC-SIT63503.2024.10862741.
[5] C. Beulah Christalin Latha and S. Carolin Jeeva, "Improving the accuracy of prediction of heart disease risk based on ensemble classification techniques," Inform. Med. Unlocked, vol. 16, Art. no. 100203, 2019, doi: 10.1016/j.imu.2019.100203.
[6] Mengxiao Peng, Fan Hou, Zhixiang Cheng, Tongtong Shen, Kaixian Liu, Cai Zhao, and Wen Zheng, "Prediction of cardiovascular disease risk based on major contributing features," Sci. Rep., vol. 13, no. 1, Art. no. 4778, 2023, doi: 10.1038/s41598-023-31870-8.
[7] Madhumita Pal, Smita Parija, Ganapati Panda, Kuldeep Dhama, and Ranjan K. Mohapatra, "Risk prediction of cardiovascular disease using machine learning classifiers," Open Med., vol. 17, no. 1, pp. 1100-1113, 2022, doi: 10.1515/med-2022-0508.
[8] Abbas Rezaianzadeh, Leila Moftakhar, Mozhgan Seif, Masoumeh Ghoddusi Johari, Seyed Vahid Hosseini, and Seyed Sina Dehghani, "Incidence and risk factors of cardiovascular disease among population aged 40-70 years: A population-based cohort study in the South of Iran," Trop. Med. Health, vol. 51, no. 1, Art. no. 35, 2023, doi: 10.1186/s41182-023-00527-7.
[9] Muthiah Vaduganathan, George A. Mensah, Justine Varieur Turco, Valentin Fuster, and Gregory A. Roth, "The global burden of cardiovascular diseases and risk: A compass for future health," J. Am. Coll. Cardiol., vol. 80, no. 25, pp. 2361-2371, 2022, doi: 10.1016/j.jacc.2022.11.005.
[10] S. Blankenberg, C. Magnussen, F. Ojeda, and D. Leong, "Global effect of modifiable risk factors on cardiovascular disease and mortality," N. Engl. J. Med., vol. 389, no. 14, pp. 1273-1285, 2023, doi: 10.1056/NEJMoa2206916.
[11] Yekai Zhou, Celia Jiaxi Lin, Qiuyan Yu, Joseph Edgar Blais, Eric Yuk Fai Wan, Marco Lee, Emmanuel Wong, David Chung-Wah Siu, Vincent Wong, Esther Wai Yin Chan, Tak-Wah Lam, William Chui, Ian Chi Kei Wong, Ruibang Luo, and Celine Sze Ling Chui, "Development and validation of risk prediction model for recurrent cardiovascular events among Chinese: The personalized cardiovascular disease risk assessment for Chinese model," Eur. Heart J. Digit. Health, vol. 5, no. 3, pp. 363-370, 2024, doi: 10.1093/ehjdh/ztae018.
[12] Reshma S. Ravi, K. Vanitha, and Anjana T. K., "A survey of cardiovascular disease identification and prediction using machine learning and deep learning methods," in Proc. 2024 Int. Conf. Emerg. Res. Comput. Sci. (ICERCS), 2024, pp. 1-5, doi: 10.1109/ICERCS63125.2024.10895641.
[13] Siddh Garg, "Cardiovascular disease prediction using classical machine learning," in Proc. 2024 Int. Conf. Electr. Comput. Eng. Res. (ICECER), 2024, pp. 1-5, doi: 10.1109/ICECER62944.2024.10920302.
[14] Surjeet Dalal, Pallavi Goel, Edeh Michael Onyema, Adnan Alharbi, Amena Mahmoud, Majed A. Algarni, and Halifa Awal, "Application of machine learning for cardiovascular disease risk prediction," Comput. Intell. Neurosci., vol. 2023, Art. no. 9418666, 2023, doi: 10.1155/2023/9418666.
Downloads
Published
Data Availability Statement
The data supporting the findings of this study are available from the corresponding author upon reasonable request.Conference Proceedings Volume
Section
Categories
License
Copyright (c) 2026 The Authors
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles published in Conference Proceedings in Science and Management are made available under the Creative Commons Attribution 4.0 International License (CC BY 4.0). Authors retain copyright in their work and grant the journal first publication rights. Readers are free to share and adapt the published material for any purpose, including commercial use, provided appropriate credit is given to the author, a link to the license is provided, and any changes are indicated.
