A Robust Decision Support System for Wireless Healthcare Based on Hybrid Prediction Algorithm
- 68 Downloads
Analysis of healthcare data becomes a tedious task as large volume of unlabelled information is generated. In this article, an algorithm is proposed to reduce the complexity involved in analysis of healthcare data. The proposed algorithm predicts the health status of elderly from the data collected at health centres by utilizing PCA (principle component analysis) and SVM (support vector machine) algorithms. The performance of proposed algorithm is assessed by comparing it with well-known methods like quadratic Discriminant, linear Discriminant, logistic regression, KNN weighted and SVM medium Gaussian using F-measure. At that point, the pre-prepared information is subjected to the dimensionality decrease process by playing out the Feature Selection errand. So, chosen component analysis are investigated by the proposed work SVM-based enhanced recursive element determination, and its precision is assessed and contrasted with the other customary classifiers, for example, quadratic Discriminant, Linear Discriminant, Logistic Regression, KNN Weighted and SVM Medium Gaussian. Here, we built up a shrewd versatile information module for the remote procurement and transmission of EHR (Electronic Health Record) chronicles, together with an online watcher for showing the EHR datasets on a PC, advanced cell or tablet. So as to characterize the highlights required by clients, we demonstrated the elderly checking system in home and healing facility settings. Utilizing this data, we built up a portable information exchange module in light of a Raspberry Pi.
KeywordsMachine learning SVM PCA EHR Healthcare Elderly
Data are collected from medical records department of Thanjavur medical college after approval of institute ethical committee. We Thank Dr. L. Mageshwaran MD., Assistant professor, Department of Pharmacology, Thanjavur Medical college, Tamil Nadu for his continuous support and Guidance.
Compliance with ethical standards
Conflict of Interest. The authors have no conflict of Interest.
(In case animal were involved) ethical approval)
Animal were not involved.
(And/or in case humans were involved) ethical approval)
This article does not contain any studied with human participants performed by any of the author.
This Article does not contain any studies with human participants or animals performed by any of the author.
- 1.Zhou, J., Feature selection in data mining—approaches based on information theory. Saarbrücken: VDM Verlag, 2007.Google Scholar
- 3.Han, J., and Kamber, M., Data mining: concepts and techniques. 1st eddition edition. Burlington: Morgan Kaufmann Publishers, 2011.Google Scholar
- 4.Rahm, R. E., and Do, H. H., Data cleaning: Problems and current approaches. IEEE Data Eng. Bull. 23(4):3–13, 2000.Google Scholar
- 5.Schölkopf, B., and Smola, A. J., Learning with Kernels. Cambridge: MIT Press, 2002.Google Scholar
- 6.Leskovec, J., Rajaraman, A., and David Ullman, J., Mining of Massive Datasets: Second Edition (2014). Cambridge: Cambridge University Press.Google Scholar
- 8.Carlsson, G., and Mémoli, F., Characterization, stability and convergence of hierarchical clustering methods. J. Mach. Learn. Res. 11:1425–1470, 2010.Google Scholar
- 12.Shalvi, D. and DeClaris, N., An unsupervised neural network approach to medical data mining techniques. 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227), Anchorage, 1998, pp. 171–176, vol. 1. https://doi.org/10.1109/IJCNN.1998.682257
- 16.Abidi, S. S. R., and Hoe, K. M., Symbolic exposition of medical data-sets: a data mining workbench to inductively derive data-defining symbolic rules. In: Proceedings of 15th IEEE Symposium on Computer-Based Medical Systems (CBMS 2002), Maribor, Slovenia, pp. 123–128, 2002. doi: https://doi.org/10.1109/CBMS.2002.1011365
- 17.Yu Yu, W., Liu, T., Valdez, R., Gwinn, M., and Khoury, M.J., Application of support vector machine modeling for prediction of common diseases: the case of diabetes and pre-diabetes. BMC Med. Inf. & Decision Making, 2010.Google Scholar