|
|
|
| Research on Cardiovascular Disease Prediction Model Based on Transformer |
| Zhang Peilong1,2, Zhao Feng3, Bi Rigege2, Si Yidan2, Zhang Haoli2, Tu Wa2, Li Hua2* |
1(Information Department, Inner Mongolia People′s Hospital, Hohhot 010020, China)
2(College of Computer Science (College of Software), Inner Mongolia University, Hohhot 010021, China)
3(Department of General Medicine, The Affiliated Hospital of Inner Mongolia Medical University, Hohhot 010050, China) |
|
|
|
|
Abstract Cardiovascular disease has become a major public health problem worldwide,and its prediction and early intervention are of great significance in reducing its morbidity and mortality. This study aimed to propose a Transformer-based cardiovascular disease prediction model to overcome the limitations of traditional models in modeling complex dependencies among multiple clinical features. The model used 13 physiological parameters (such as age, blood sugar, cholesterol, chest pain type, etc.) for standardization and encoding processing, and applied the self-attention mechanism of the Transformer to model the global dependencies among multidimensional clinical features, thereby improving the extraction of complex feature interactions.Theexperimentaldata were divided into a training set and a test set, and the modelwas trained and tested on the data. Experimental results showedthat the accuracy of the proposed Transformer modelwas 98.68% on the training set and 94.68% on the test set, whichwas 8% higher than the accuracy of traditional convolutional neural networks and deep neural networks. The loss rate of the Transformer model on the training set gradually tended to 0, which is significantly better than the loss rate of 0.13 of the CNN model and the loss rate of the DNN model of 0.22; the loss rate of the Transformer model on the test set tended to 0.1, whichwas also significantly better than that of the CNN model of 0.3 and that of the DNN model of 0.4.In conclusion, the cardiovascular disease prediction model based on Transformer made rapid diagnosis through easy-to-obtain clinical data with high accuracy,providing strong technical support for early intervention and precise treatment and displaying application prospects and practicability.
|
|
Received: 24 September 2025
|
|
|
|
Corresponding Authors:
*E-mail:cslihua@imu.edu.cn
|
|
|
|
[1] Vaduganathan M, Mensah G, Turco J, et al. The global burden of cardiovascular diseases and risk: a compass for future health[J]. J Am Coll Cardiol,2022, 80 (25): 2361-2371.
[2] 刘明波,何新叶,杨晓红,等.《中国心血管健康与疾病报告2023》概要(心血管疾病流行及介入诊疗状况)[J].中国介入心脏病学杂志,2024,32(10): 541-550.
[3] 国家卫生健康委, 国家发展改革委, 教育部, 等.关于印发健康中国行动——心脑血管疾病防治行动实施方案(2023-2030年)的通知[S].中华人民共和国国家卫生健康委员会公报,2023(11): 30-33.
[4] Lohachab A, Kumar K. A comparative study of machine learning algorithms for predicting cardiovascular disease[C]//The Future of Artificial Intelligence and Robotics. Berlin: Springer Nature Switzerland, 2024: 1-11.
[5] Amutha S, Raja Sekar J. Deep neural network based cardio vascular disease prediction using binarized butterfly optimization[J]. Intelligent Automation & Soft Computing, 2023,36(2): 1863-1880.
[6] 江昊,王由甲,金晶,等.人工智能在心血管疾病领域的应用[J].生理科学进展,2025,56(3): 210-218.
[7] Trigka M, Dritsas E. Improving cardiovascular disease prediction with deep learning and correlation-aware SMOTE[J]. IEEE Access,2025,13:44590-44606.
[8] Faizal ASM, Pua HR, Kassim H, et al. A review of risk prediction models in cardiovascular disease [J]. Comput Biol Med, 2021, 136: 104663.
[9] Alkayyali Z, Idris SAB, Abu-Naser SS, et al. A systematic literature review of deep and machine learning algorithms in cardiovascular diseases diagnosis[J]. Journal of Theoretical and Applied Information Technology, 2023,101(4): 1353-1365.
[10] Triantafyllidis A, Kondylakis H, Katehakis D, et al. Deep learning in mHealth for cardiovascular disease, diabetes, and cancer: systematic review[J]. JMIR Mhealth Uhealth, 2022,10(4): e32344.
[11] Pandey S, Kaur R, Sharma B. Deep learning and data mining techniques for cardiovascular disease prediction: a survey[C]//2023 6th International Conference on Information Systems and Computer Networks (ISCON). Piscataway: IEEE, 2023: 1-5.
[12] 彭石娟,王小满,高琴,等.基于人工智能的心血管疾病预测模型研究现状[J]. 蚌埠医科大学学报,2025,50(1): 6-13.
[13] 王健美,郭丽环,胡植双,等.基于Framingham风险评分对强直性脊柱炎心血管疾病发生风险的预测分析[J]. 中西医结合心脑血管病杂志,2023,21(22): 4245-4249.
[14] 廖华龙,曾小茜,李华凤,等.机器学习在疾病预测中的应用[J]. 生物医学工程研究,2021,40(2): 203-209.
[15] 王丽霞,夏雪,高凡,等.深度学习在森林火灾检测中的研究进展[J].林产工业,2023,60(11):88-92.
[16] Bhagat HV, Singh M. A machine learning model for the early prediction of cardiovascular disease in patients[C]//2023 2nd International Conference on Advances in Computational Intelligence and Communication (ICACIC). Piscataway: IEEE, 2023: 1-5.
[17] Charkha S, Zade A, Charkha P. Cardiovascular disease (CVD) prediction using deep learning algorithm[C]//2023 International Conference on Integration of Computational Intelligent System (ICICIS). Piscataway: IEEE, 2023: 1-6.
[18] Arroyo JCT, Delima AJP. An optimized neural network using genetic algorithm for cardiovascular disease prediction[J]. Journal of Advances in Information Technology, 2022, 13(1): 95-99.
[19] Paranthaman M, Yaathash B, Santhosh S, et al. Cardiovascular disease prediction using deep learning[C]//2022 6th International Conference on Trends in Electronics and Informatics (ICOEI). Piscataway: IEEE, 2022: 1399-1404.
[20] Bodiwala S, Nanavati N.CDIPEM: Cardiovascular disease incidence probability estimation CNN model[J]. Journal of Information and Optimization Sciences, 2023, 44(5): 865-894.
[21] Ampavathi A, Saradhi TV. Multi disease-prediction framework using hybrid deep learning: an optimal prediction model[J]. Comput Methods Biomech Biomed Engin, 2021,24(10): 1146-1168.
[22] 朱宵彤,庞春颖,朱涵.基于深度学习的心血管疾病预测模型[J]. 计算机应用,2021,41(S2): 346-350.
[23] 王蕾,党时鹏,王如兴.基于心电图的机器学习在心血管疾病预测中的应用进展[J]. 实用心电学杂志,2022,31(6): 392-398.
[24] 储芳芳.基于PPG信号和ECG信号的无创血压智能检测方法研究[D].南京:南京邮电大学,2022.
[25] Bahri S, Kdayem M, Zoghlami N. Long short-term memory based RNN for COVID-19 disease prediction[C]//2021 22nd IEEE International Conference on Industrial Technology (ICIT). Piscataway: IEEE, 2021: 901-906.
[26] Aiken EL, Nguyen AT, Viboud C, et al. Toward the use of neural networks for influenza prediction at multiple spatial resolutions[J]. Sci Adv, 2021, 7(25): eabb1237.
[27] 皇甫晓瑛,钱惠敏,黄敏.结合注意力机制的深度神经网络综述[J].计算机与现代化,2023(2): 40-49,57.
[28] 崔建山.基于卷积神经网络和集成学习的心血管疾病预测方法研究[D].岳阳:湖南理工学院,2024.
[29] Li K, Li J, Li J, et al. 12-Lead ECG classification based on channel self-attention mechanism integrated expert features[C]//2024 9th International Conference on Intelligent Computing and Signal Processing (ICSP). Piscataway: IEEE, 2024:616-619.
[30] 霍甜媛.基于复杂健康感知数据的疾病诊断技术的研究[D].南京:南京航空航天大学,2022.
[31] 朱景勇,李钧翔,李旭辉,等.深度学习在基于序列的蛋白质互作预测中的应用进展[J].合成生物学,2024,5(1): 88-106.
[32] 张莎莎.基于机器学习的心血管疾病诊断模型关键技术研究[D].北京:北京邮电大学,2023.
[33] 丘荣建,王剑卓.基于卷积注意力的单导联心电图房颤检测方法[J].自动化与信息工程,2024,45(4): 18-23.
[34] 陈俊竹,陈光武,石建强,等.基于1D-CNN和Transformer模型的道岔健康状态预测[J].北京交通大学学报,2025,49(3): 33-43.
[35] 王译文,黎建军,曲再鹏.基于Transformer的短期血糖预测方法研究[J].中国计量大学学报,2023,34(3): 372-378. |
| [1] |
Gao Jing, Li Lei, Zhu Lingyan, Qian Tianhe, Wang Yongfu. Using Improved Transformer Model Considering Multi-domain Features for CT Image Recognitionof Connective Tissue-Associated Interstitial Lung Disease[J]. Chinese Journal of Biomedical Engineering, 2026, 45(3): 276-287. |
| [2] |
Huang Qiufan, Ma Ye, Xu Zhiyun. Research Progress of Flexible Wearable Sensors for Cardiovascular Disease Monitoring[J]. Chinese Journal of Biomedical Engineering, 2024, 43(2): 214-226. |
|
|
|
|
