Chronic Conjecture and Uncertainty Detection by Machine Learning

  • Authors

    • J. Jegan Amarnath
    • Pradeep Kumar Sahoo
    • Suresh Anand.M
    • A. Mamutha Nisha
    • B. Priyadharshini
    • V. Sumitha
    2018-12-13
    https://doi.org/10.14419/ijet.v7i4.39.25670
  • chronic, observable variable, decision, convolution, multimodal, big data
  • The early disease risk detection and appropriate diagnosis for the chronic disease is possible with the help of analysis of the medical data.  The analysis accuracy was reduced due to the incompleteness of medical data. Different areas or regions manifest different chronic outbreak which leads to loss of many lives. In this project, we converge machine-learning algorithms for the effective risk prediction of the chronic heart disease and provide early treatment for the disease in disease-frequent communities. The electronic health record collected from the hospital is categorized based on the clinical attributes of the patient and by using the statistical analysis, the overall risk for the heart disease is found .So for reduce the risk of incomplete datas can be use an observable variable to rebuild the absent data which improves the pre-processing effectively. This project uses a new ConvolutionNeuralNetwork (CNN) supported multi-modal disease-risk prediction procedure for the un-structured data, Decision tree algorithm for structured data to find the risk of the chronic disease. Based on the level of the risk, the treatment plan is provided automatically. In the domain of medical big data-analytics, very few existing works focused on both data types.The accuracy of the proposed prediction algorithm will reach more than 94.8% with convergence speed when compared with many other prediction algorithms. This is faster than the convolution neural network (CNN) based uni-modal and existing multimodal disease-risk-prediction method.

     

  • References

    1. [1] M.|Chen, S.Mao, and YLiu,“Big-data:A survey,â€Mobile Networks and Applications, 19, no. 2] pp.

      [2] PBJensen, LJJensen and SBrunak,“Mining electronic-health records: towards better research applications and clinical care

      [3] MChen, YMa, YLi, DWu, YZhang,“Wearable 2.O:Enable Human-Cloud Integration in Next-Generation Heallthcare System,†IEEE Communications, Vol. 55, No. 1, pp. 54–61, Jan. 2017

      [4] WYin and HSch¨utze, “Convolutional neural-network for paraphrase identification.†in HLT-NAACL, 2015, pp. 901–911

      [5] JJWang, MQiu, and BGuo,“Enabling real-time information service on tele-health system over cloud-based big-data platform,†Journal of Systems Architecture, vol. 72, pp. 69–79, 2017

      [6] D. W. Bates, SSaria, LK.Ohno-Machado, A. Escobar, “Big data in health care: using analytics to identify and manage high-risk and high-cost patients,†Health Affairs, vol. 33, no. 7, pp. 1123–1131, 2014

      [7] Y. Zhang, MQiu, C.-W. Tsai, Hassan, and Alamri, “Healthcps: Healthcare cyber-physical system assisted by cloud and big data

      [8] K. Lain, J. Luo, M. S. Hossain, and A. Ghoneim, “Localization based on social big data analysis in the vehicular networks,†IEEE Transactions on Industrial Informatics, 2016

      [9] D. Oliver, FDaly, FCMartin, and MEMurdo,“Risk factors and risk assessment tools for falls in hospital in-patients: a systematic review,†Age and ageing, vol. 33, no. 2, pp. 122–130, 2004

      [10] S Zhai, KChang, Zhang, and Z Zhang, “Deep intent: Learning attentions for online advertising with recurrent neural networks

  • Downloads

  • How to Cite

    Jegan Amarnath, J., Kumar Sahoo, P., Anand.M, S., Mamutha Nisha, A., Priyadharshini, B., & Sumitha, V. (2018). Chronic Conjecture and Uncertainty Detection by Machine Learning. International Journal of Engineering & Technology, 7(4.39), 633-636. https://doi.org/10.14419/ijet.v7i4.39.25670