International Journal of Computer Science & Network Security

국제컴퓨터통신보호논문지학회 (International Journal of Computer Science & Network Security)
권호 표지
DOI QR코드

DOI QR Code

Hybrid LSTM and Deep Belief Networks with Attention Mechanism for Accurate Heart Attack Data Analytics

  • Mubarak Albathan (College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU))
  • 투고 : 2024.10.05
  • 발행 : 2024.10.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Due to its complexity and high diagnosis and treatment costs, heart attack (HA) is the top cause of death globally. Heart failure's widespread effect and high morbidity and death rates make accurate and fast prognosis and diagnosis crucial. Due to the complexity of medical data, early and accurate prediction of HA is difficult. Healthcare providers must evaluate data quickly and accurately to intervene. This novel hybrid approach predicts HA using Long Short-Term Memory (LSTM) networks, Deep belief networks (DBNs) with attention mechanism, and robust data mining to fill this essential gap. HA is predicted using Kaggle, PhysioNet, and UCI datasets. Wearable sensor data, ECG signals, and demographic and clinical data provide a solid analytical base. To maintain consistency, ECG signals are normalized and segmented after thorough cleaning to remove missing values and noise. Feature extraction employs complex approaches like Principal Component Analysis (PCA) and Autoencoders to pick time-domain (MNN, SDNN, RMSSD, PNN50) and frequency-domain (PSD at VLF, LF, HF bands) characteristics. The hybrid model architecture uses LSTM networks for sequence learning and DBNs for feature representation and selection to create a robust and comprehensive prediction model. Accuracy, precision, recall, F1-score, and ROC-AUC are measured after cross-entropy loss and SGD optimization. The LSTM-DBN model outperforms predictive methods in accuracy, sensitivity, and specificity. The findings show that several data sources and powerful algorithms can improve heart attack predictions. The proposed architecture performed well on many datasets, with an accuracy rate of 96.00%, sensitivity of 98%, AUC of 0.98, and F1-score of 0.97. High performance proves this system's dependability. Moreover, the proposed approach is outperformed compared to state-of-the-art systems.

키워드

참고문헌

  1. Janarthanan, Vijayaraj, Tamizhselvi Annamalai, and Mahendran Arumugam. "Enhancing healthcare in the digital era: A secure e-health system for heart disease prediction and cloud security." Expert Systems with Applications 255 (2024): 124479.
  2. Paulino, Emanuel Tenorio. "development of the cardioprotective drugs based on pathophysiology of myocardial infraction: A comprehensive review", Current Problems in Cardiology (2024): 102480.
  3. Yenurkar, Ganesh Keshaorao, Sandip Mal, Advait Wakulkar, Kartik Umbarkar, Aniruddha Bhat, Akash Bhasharkar, and Aniket Pathade. "Future prediction for precautionary measures associated with heart-related issues based on IoT prototype." Multimedia Tools and Applications (2024): 1-31.
  4. Ramesh, B., and Kuruva Lakshmanna. "A Novel Early Detection and Prevention of Coronary Heart Disease Framework Using Hybrid Deep Learning Model and Neural Fuzzy Inference System." IEEE Access 12 (2024): 26683-26695.
  5. Samuel, P.O., Edo, G.I., Emakpor, O.L., Oloni, G.O., Ezekiel, G.O., Essaghah, A.E.A., Agoh, E. and Agbo, J.J., 2024. Lifestyle modifications for preventing and managing cardiovascular diseases. Sport Sciences for Health, 20(1), pp.23-36.
  6. Naser, M.A., Majeed, A.A., Alsabah, M., Al-Shaikhli, T.R. and Kaky, K.M., 2024. A Review of Machine Learning's Role in Cardiovascular Disease Prediction: Recent Advances and Future Challenges. Algorithms, 17(2), p.78.
  7. Parashar, G., Chaudhary, A. and Pandey, D., 2024. Machine learning for prediction of cardiovascular disease and respiratory disease: a review. SN Computer Science, 5(1), p.196.
  8. Dwivedi, Ashok Kumar. "Performance evaluation of different machine learning techniques for prediction of heart disease." Neural Computing and Applications 29 (2018): 685-693.
  9. Mohan, Senthilkumar, Chandrasegar Thirumalai, and Gautam Srivastava. "Effective heart disease prediction using hybrid machine learning techniques." IEEE access 7 (2019): 81542-81554.
  10. Bharti, Rohit, Aditya Khamparia, Mohammad Shabaz, Gaurav Dhiman, Sagar Pande, and Parneet Singh. "Prediction of heart disease using a combination of machine learning and deep learning." Computational intelligence and neuroscience 2021, no. 1 (2021): 8387680.
  11. Ali, Md Mamun, Bikash Kumar Paul, Kawsar Ahmed, Francis M. Bui, Julian MW Quinn, and Mohammad Ali Moni. "Heart disease prediction using supervised machine learning algorithms: Performance analysis and comparison." Computers in Biology and Medicine 136 (2021): 104672.
  12. Haq, Amin Ul, Jian Ping Li, Muhammad Hammad Memon, Shah Nazir, and Ruinan Sun. "A hybrid intelligent system framework for the prediction of heart disease using machine learning algorithms." Mobile information systems 2018, no. 1 (2018): 3860146.
  13. Ali, Farman, Shaker El-Sappagh, SM Riazul Islam, Daehan Kwak, Amjad Ali, Muhammad Imran, and Kyung-Sup Kwak. "A smart healthcare monitoring system for heart disease prediction based on ensemble deep learning and feature fusion." Information Fusion 63 (2020): 208-222.
  14. Krittanawong, Chayakrit, Hafeez Ul Hassan Virk, Sripal Bangalore, Zhen Wang, Kipp W. Johnson, Rachel Pinotti, HongJu Zhang et al. "Machine learning prediction in cardiovascular diseases: a meta-analysis." Scientific reports 10, no. 1 (2020): 16057.
  15. Li, J.P., Haq, A.U., Din, S.U., Khan, J., Khan, A. and Saboor, A., 2020. Heart disease identification method using machine learning classification in e-healthcare. IEEE access, 8, pp.107562-107582.
  16. Ghosh, Pronab, Sami Azam, Mirjam Jonkman, Asif Karim, FM Javed Mehedi Shamrat, Eva Ignatious, Shahana Shultana, Abhijith Reddy Beeravolu, and Friso De Boer. "Efficient prediction of cardiovascular disease using machine learning algorithms with relief and LASSO feature selection techniques." IEEE Access 9 (2021): 19304-19326.
  17. Latha, C. Beulah Christalin, and S. Carolin Jeeva. "Improving the accuracy of prediction of heart disease risk based on ensemble classification techniques." Informatics in Medicine Unlocked 16 (2019): 100203.
  18. Ishaq, Abid, Saima Sadiq, Muhammad Umer, Saleem Ullah, Seyedali Mirjalili, Vaibhav Rupapara, and Michele Nappi. "Improving the prediction of heart failure patients' survival using SMOTE and effective data mining techniques." IEEE access 9 (2021): 39707-39716.
  19. Khan, Mohammad Ayoub. "An IoT framework for heart disease prediction based on MDCNN classifier." Ieee Access 8 (2020): 34717-34727.
  20. Garate-Escamila, Anna Karen, Amir Hajjam El Hassani, and Emmanuel Andres. "Classification models for heart disease prediction using feature selection and PCA." Informatics in Medicine Unlocked 19 (2020): 100330.
  21. Kumar, Priyan Malarvizhi, and Usha Devi Gandhi. "A novel three-tier Internet of Things architecture with machine learning algorithm for early detection of heart diseases." Computers & Electrical Engineering 65 (2018): 222-235.
  22. Abdar, Moloud, Wojciech Ksiazek, U. Rajendra Acharya, Ru-San Tan, Vladimir Makarenkov, and Pawel Plawiak. "A new machine learning technique for an accurate diagnosis of coronary artery disease." Computer methods and programs in biomedicine 179 (2019): 104992.
  23. Chen, Min, Yixue Hao, Kai Hwang, Lu Wang, and Lin Wang. "Disease prediction by machine learning over big data from healthcare communities." Ieee Access 5 (2017): 8869-8879.
  24. Amin, Mohammad Shafenoor, Yin Kia Chiam, and Kasturi Dewi Varathan. "Identification of significant features and data mining techniques in predicting heart disease." Telematics and Informatics 36 (2019): 82-93.
  25. Khan, Mohammad Ayoub, and Fahad Algarni. "A healthcare monitoring system for the diagnosis of heart disease in the IoMT cloud environment using MSSO-ANFIS." IEEE access 8 (2020): 122259-122269.
  26. Guo, Chunyan, Jiabing Zhang, Yang Liu, Yaying Xie, Zhiqiang Han, and Jianshe Yu. "Recursion enhanced random forest with an improved linear model (RERF-ILM) for heart disease detection on the internet of medical things platform." Ieee Access 8 (2020): 59247-59256.
  27. Dami, Sina, and Mahtab Yahaghizadeh. "Predicting cardiovascular events with deep learning approach in the context of the internet of things." Neural Computing and Applications 33 (2021): 7979-7996.
  28. Rojek, Izabela, Piotr Kotlarz, Miroslaw Kozielski, Mieczyslaw Jagodzinski, and Zbyszko Krolikowski. "Development of AI-Based Prediction of Heart Attack Risk as an Element of Preventive Medicine." Electronics 13, no. 2 (2024): 272.
  29. Rimal, Yagyanath, and Navneet Sharma. "Hyperparameter optimization: a comparative machine learning model analysis for enhanced heart disease prediction accuracy." Multimedia Tools and Applications 83, no. 18 (2024): 55091-55107.
  30. Wang, Meng, Xinghua Yao, and Yixiang Chen. "An imbalanced-data processing algorithm for the prediction of heart attack in stroke patients." IEEE Access 9 (2021): 25394-25404.
  31. Dubey, Madhuri, Jitendra Tembhurne, and Richa Makhijani. "Improving coronary heart disease prediction with real-life dataset: a stacked generalization framework with maximum clinical attributes and SMOTE balancing for imbalanced data." Multimedia Tools and Applications (2024): 1-30.
  32. Hasan, Mahmudul, Md Abdus Sahid, Md Palash Uddin, Md Abu Marjan, Seifedine Kadry, and Jungeun Kim. "Performance discrepancy mitigation in heart disease prediction for multisensory inter-datasets." PeerJ Computer Science 10 (2024): e1917.
  33. Pitchal, Padmakumari, Shanthi Ponnusamy, and Vidivelli Soundararajan. "Heart disease prediction: Improved quantum convolutional neural network and enhanced features." Expert Systems with Applications 249 (2024): 123534.
  34. Nandy, Sudarshan, Mainak Adhikari, Venki Balasubramanian, Varun G. Menon, Xingwang Li, and Muhammad Zakarya. "An intelligent heart disease prediction system based on swarm-artificial neural network." Neural Computing and Applications 35, no. 20 (2023): 14723-14737.
  35. Dileep, P., Kunjam Nageswara Rao, Prajna Bodapati, Sitaratnam Gokuruboyina, Revathy Peddi, Amit Grover, and Anu Sheetal. "An automatic heart disease prediction using cluster-based bi-directional LSTM (C-BiLSTM) algorithm." Neural Computing and Applications 35, no. 10 (2023): 7253-7266.
  36. Ansari, Gufran Ahmad, Salliah Shafi Bhat, Mohd Dilshad Ansari, Sultan Ahmad, Jabeen Nazeer, and A. E. M. Eljialy. "Performance evaluation of machine learning techniques (MLT) for heart disease prediction." Computational and Mathematical Methods in Medicine 2023, no. 1 (2023): 8191261.
  37. Noroozi, Zeinab, Azam Orooji, and Leila Erfannia. "Analyzing the impact of feature selection methods on machine learning algorithms for heart disease prediction." Scientific Reports 13, no. 1 (2023): 22588.
  38. Almazroi, Abdulwahab Ali, Eman A. Aldhahri, Saba Bashir, and Sufyan Ashfaq. "A clinical decision support system for heart disease prediction using deep learning." IEEE Access 11 (2023): 61646-61659.
  39. Clinical features for predicting heart disease, DB1: https://www.kaggle.com/datasets/fedesoriano/heart-failureprediction [Access date: 12 January, 2024].
  40. Wagner, P., Strodthoff, N., Bousseljot, R., Samek, W. & Schaeffter, T. PTB-XL, a large publicly available electrocardiography dataset. PhysioNet. https://doi.org/10.13026/6sec-a640 (2020).
  41. Yoo, H., Yum, Y., Park, S., Lee, J. M., Jang, M., Kim, Y., Kim, J., Park, H., Han, K. S., Park, J. H., & Joo, H. J. (2021). KURIAS-ECG: a 12-lead electrocardiogram database with standardized diagnosis ontology (version 1.0). PhysioNet. https://doi.org/10.13026/kga0-0270.
  42. Heart Disease Data Set from UCI data repository: DB4 https://www.kaggle.com/datasets/redwankarimsony/heart-diseasedata prediction [Access date: 12 January, 2024].
  43. Wen, Tingxi, and Zhongnan Zhang. "Deep convolution neural network and autoencoders-based unsupervised feature learning of EEG signals." IEEE Access 6 (2018): 25399-25410.
  44. [Zambra, Matteo, Alberto Testolin, and Marco Zorzi. "A developmental approach for training deep belief networks." Cognitive Computation 15, no. 1 (2023): 103-120.