banner
Home > Open Journal Systems

Stroke risk prediction with 5G infrastructure based learning framework

A. Revathi, K. Santhi, R. Swathi, P.V.R.D. Prasad Rao

Abstract


Due to the lack of an effective remedy, stroke becomes worldwide cause of death and long-term impairment. Despite the need for deep learning-based approaches on extensive and well labeled data, they possess the potential to outperform existing algorithms for predicting stroke risk. Moreover, there exists a significant disparity between the instances of favorable and unfavorable occurrences within this dataset. By using the specialized knowledge of a related field, transferable knowledge aids in resolving minor data difficulties, especially when many data sources are available. This paper introduces a novel stroke risk assessment system dubbed HDTL-SRP, which utilizes a hybrid deep transfer learning approach to leverage information from several associated resources, such as external stock data and data on chronic conditions like hypertension and diabetes. After undergoing rigorous testing in both simulated and actual scenarios, the recommended framework outperforms the most powerful stroke prediction algorithms. Additionally, it showcases the feasibility of utilizing 5G/B5G infrastructures to provide assistance for several hospitals in real-world scenarios.


Keywords


deep learning; framework; risk prediction; 5G systems

Full Text:

PDF

References


1. Koton S, Schneider ALC, Rosamond WD, et al. Stroke Incidence and Mortality Trends in US Communities, 1987 to 2011. JAMA. 2014; 312(3): 259. doi: 10.1001/jama.2014.7692

2. Benjamin EJ, Muntner P, Alonso A, et al. Heart Disease and Stroke Statistics—2019 Update: A Report From the American Heart Association. Circulation. 2019; 139(10). doi: 10.1161/cir.0000000000000659

3. Cheon S, Kim J, Lim J. The use of deep learning to predict stroke patient mortality. International Journal of Environmental Research and Public Health. 2019; 16(11): 1876. doi: 10.3390/ijerph16111876

4. Sun C, Shrivastava A, Singh S, et al. Revisiting unreasonable effectiveness of data in deep learning era. In: Proceedings of the IEEE International Conference on Computer Vision; 2017. pp. 843-852.

5. O’Brien AA, Rajkumar C, Bulpitt CJ. Blood pressure lowering for the primary and secondary prevention of stroke: treatment of hyper tension reduces the risk of stroke. Journal of Cardiovascular Risk. 1999; 6(4): 203-205. doi: 10.1177/204748739900600402

6. Manson JE, Colditz GA, Stampfer MJ, et al. A prospective study of maturity-onset diabetes mellitus and risk of coronary heart disease and stroke in women. Archives of Internal Medicine. 1991; 151(6): 1141. doi: 10.1001/archinte.1991.00400060077013

7. Yosinski J, Clune J, Bengio Y, et al. How transferable are features in deep neural networks? Advances in Neural Information Processing Systems. 2014; 27: 3320-3328.

8. Huang JT, Li J, Yu D, et al. Cross language knowledge transfer using multilingual deep neural network with shared hidden layers. In: Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing; 2013. pp. 7304-7308.

9. Raina R, Battle A, Lee H, et al. Self-taught learning: transfer learning from unlabeled data. In: Proceedings of the 24th International Conference on Machine Learning; 2007. pp. 759-766.

10. Dai W, Xue GR, Yang Q, et al. Co-clustering based classification for out-of-domain documents. In: Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2007. pp. 210-219.

11. Cheplygina V, Pena IP, Pedersen JH, et al. Transfer learning for multicenter classification of chronic obstructive pulmonary disease. IEEE Journal of Biomedical and Health Informatics. 2018; 22(5): 1486-1496. doi: 10.1109/jbhi.2017.2769800

12. Xu Y, Pan SJ, Xiong H, et al. A unified framework for metric transfer learning. IEEE Transactions on Knowledge and Data Engineering. 2017; 29(6): 1158-1171. doi: 10.1109/tkde.2017.2669193

13. Wan C, Pan R, Li J. Bi-weighting domain adaptation for cross-language text classification. In: Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence; 2011. pp. 1535-1540.

14. Scott T, Ridgeway K, Mozer MC. Adapted deep embeddings: A synthesis of methods for k-shot inductive transfer learning. In: Proceedings of the 32nd Conference on Neural Information Processing Systems (NeurIPS 2018); 2018; Montréal, Canada. pp. 76-85.

15. Lim G, Lim ZW, Xu D, et al. Feature isolation for hypo thesis testing in retinal imaging: an ischemic stroke prediction case study. Proceedings of the AAAI Conference on Artificial Intelligence. 2019; 33(1): 9510-9515. 10.1609/aaai. v33i01.33019510.

16. Pereira DR, Reboucas Filho PP, de Rosa GH, et al. Stroke lesion detection using convolutional neural networks. In: Proceedings of the 2018 International Joint Conference on Neural Networks (IJCNN); 2018. pp. 1-6.

17. Teoh D. Towards stroke prediction using electronic health records. BMC Medical Informatics and Decision Making. 2018; 18(1). doi: 10.1186/s12911-018-0702-y

18. Liu T, Fan W, Wu C. A hybrid machine learning approach to cerebral stroke prediction based on imbalanced medical dataset. Artificial Intelligence in Medicine. 2019; 101: 101723. doi: 10.1016/j.artmed.2019.101723

19. Wang F, Casalino LP, Khullar D. Deep learning in medicine—promise, progress, and challenges. JAMA Internal Medicine. 2019; 179(3): 293. doi: 10.1001/jamainternmed.2018.7117

20. Lee J, Sattigeri P, Wornell G. Learning newtricks from old dogs: Multi-source transfer learning from pre-trained networks. Advances in Neural Information Processing Systems. 2019; 32: 4372-4382.

21. Chen H, Ni D, Qin J, et al. Standard plane localization in fetal ultrasound via domain transferred deep neural networks. IEEE Journal of Biomedical and Health Informatics. 2015; 19(5): 1627-1636. doi: 10.1109/jbhi.2015.2425041

22. Benjamin EJ, Blaha, MJ, Chiuve, SE, et al. Heart disease and stroke statistics—2017 update: A report from the American Heart Association. Circulation. 2017; 135(10): e146-e603.

23. Khosla A, Cao Y, Lin CCY, et al. An integrated machine learning approach to stroke prediction. In: Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining; 2010. pp. 183-192.

24. Monteiro M, Fonseca AC, Freitas AT, et al. Using machine learning to improve the prediction of functional outcome in ischemic stroke patients. IEEE/ACM Transactions on Computational Biology and Bioinformatics. 2018; 15(6): 1953-1959. doi: 10.1109/tcbb.2018.2811471

25. Sung SF, Lin CY, Hu YH. Emr-based phenotyping of is chemic stroke using supervised machine learning and text mining techniques. IEEE Journal of Biomedical and Health Informatics. 2020; 24(10): 2922-2931. doi: 10.1109/jbhi.2020.2976931




DOI: https://doi.org/10.32629/jai.v7i5.1667

Refbacks

  • There are currently no refbacks.


Copyright (c) 2024 A. Revathi, K. Santhi, R. Swathi, P.V.R.D. Prasad Rao

License URL: https://creativecommons.org/licenses/by-nc/4.0/