Abstract
In this paper, we propose a multimodal deep learning algorithm that combines convolutional neural networks (CNNs) and long short-term memory (LSTM) networks for early detection and prediction of heart disease using data collected from wearable devices. This combined multi-model deep learning algorithm is used to detect the accurate precision and accuracy value. At first, we consider, ECG and PPG signals, which are collected from the dataset. Then, the features from ECG and PPG are extracted using CNN and the accelerometer features are extracted using the LSTM model. The combined features are then classified using hybrid CNN-LSTM network architecture. The algorithm is evaluated using a publicly available benchmark dataset. The model achieved an accuracy of 99.33% in detecting heart disease, outperforming several state-of-the-art deep learning models. In addition, the model can predict the likelihood of developing heart disease with a precision of 99.33%, providing an early warning system for at-risk patients. The results demonstrate the potential of a multimodal approach for early detection and prediction of heart disease using wearable devices and deep learning algorithms.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
My manuscript has associated data in a data repository.
References
Gupta S, Yap J, Salama S, Deo RC, Merkely B (2021) Multimodal deep learning for noninvasive prediction of late recurrence in atrial fibrillation. Comput Biol Med 135:104563
Arun S, Soman KP, Poornachandran P (2021) A multimodal deep learning model for detection of cardiac diseases using ECG and PCG signals. J Ambient Intell Humaniz Comput 12(10):11779–11792
Acharya UR, Fujita H, Oh SL, Adam M, Koh JEW, Tan JH, Chua KC (2019) Application of deep learning in heart disease diagnosis. Biomed Signal Process Control 47:245–256
Moccia S, Gu Y (2019) Multimodal deep learning for cardiovascular disease diagnosis. Front Physiol 10:1261
Zegard A, Delseny C, Geurts P, Nyssen AS (2019) Multimodal deep learning for heart sound classification using convolutional and recurrent neural networks. Comput Biol Med 110:222–234
Li R, Liang Y, Jin L, Wang S (2020) Multimodal deep learning for cardiovascular disease risk prediction based on EHR Data. IEEE Access 8:106537–106547
Chen M, Liu M, Zhang X, Cai J, Yang Q (2020) Multimodal deep learning for the diagnosis of heart disease Based on ECG and speech signals. Appl Sci 10(6):1987
Gu J, Liu W, Yang Y, Ma Z, Chen Y (2021) Multimodal deep learning for chest disease detection with CT and X-ray images. Comput Biol Med 130:104213
Chen Y, Wu X, Chen H, Zhang Y, Sun C, Su Q (2018) Multimodal deep learning for heart failure prediction based on wearable devices. J Med Syst 42(6):112
Attia ZI, Kapa S, Lopez-Jimenez F, McKie PM, Ladewig DJ, Satam G, Pellikka PA, Enriquez-Sarano M, Noseworthy PA, Munger TM (2019) Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram. Nat Med 25(1):70–74
Zhang Y, Gao X, Xu L, Zhang X, Shi J, Zhang Q, Chen L (2019) Multimodal deep learning for early detection of coronary artery disease using electrocardiogram and photoplethysmogram signals. IEEE Trans Ind Inform 17(1):2750–2758
Li K, Chen C, Hu Z, Li C, Zhang S (2019) Multimodal deep learning for the diagnosis of coronary artery disease using electrocardiogram and photoplethysmography signals. Sensors 19(16):3624
Subasi A (2019) Multimodal deep learning method for detection and diagnosis of cardiovascular diseases. J Med Syst 43(3):80
Zhu Y, Feng P, Yu H (2019) Multimodal deep learning for predicting cardiovascular disease. IEEE J Biomedical Health Inf 23(4):1616–1626
Wang W, Liu C, Zhao J, Xie S (2020) Multimodal deep learning for coronary artery disease detection. Comput Math Methods Med 2(3):1–11
Siontis GC, Kolettis TM, Mantziari L (2020) A multimodal deep learning algorithm for the diagnosis of acute coronary syndromes. Comput Biol Med 122:103812
Rajpurkar P, Hannun AY, Haghpanahi M, Bourn C, Ng AY (2020) Multimodal deep learning for chest radiograph interpretation. IEEE Trans Med Imaging 39(9):3007–3018
Liu K, Wang Y, Lin B, Ma J, Huang Y, Huang L, Zhang L, Ye Z, Chen Y, Lin J (2021) Multimodal deep learning for predicting cardiovascular events using EHR data. IEEE J Biomedical Health Inf 25(6):2024–2032
Sun Z, Fan L, Huang C, Zhang Z, Wang J (2021) Multimodal deep learning for cardiovascular disease risk prediction. Front Physiol 12:606827
Balasubramaniam S, Joe CV, Manthiramoorthy C, Kumar KS (2024) Relief based feature selection and gradient squirrel search algorithm enabled deep maxout network for detection of heart disease. Biomedical Signal Processing and Control 87:105446
Singh S, Singh A, Limkar S (2024) Prediction of heart disease using deep learning and internet of medical things. International Journal of Intelligent Systems and Applications in Engineering 12(1s):512–525
Funding
The authors declare that they do not have competing interests and funding.
Author information
Authors and Affiliations
Contributions
The author read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The corresponding author states that there is no conflict of interest.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Sivasubramaniam, S., Balamurugan, S.P. Early detection and prediction of Heart Disease using Wearable devices and Deep Learning algorithms. Multimed Tools Appl (2024). https://doi.org/10.1007/s11042-024-19127-6
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11042-024-19127-6