Performance Evaluation Of Clustering – A Hybrid Approach [K- Mean- SOM NN] In Health Care
Main Article Content
Abstract
The high multitude of medical records and an array of interventions adopted for treating a specific disease contribute to the inherent sparsity of healthcare data collection. For the effective extraction of valuable information from these vast databases, novel data analytics methodologies are required. This article demonstrates an exploratory data analysis method based on a clustering algorithm for discovering trends in healthcare data. In addition, the clustering algorithm was employed in a multi-dimensional approach to concentrate on a distinct set of data parts and recognize patient groups. One of the unsupervised learning methods, Clustering, was utilized in numerous disciplines. The present research outlines the various clustering methods, specifically current similarity measures determined by distance-based clustering. This article compares K-means, Self-organizing Mapping, and K-means- SOM Hybrid algorithm. The outcomes exhibit that the hybrid algorithm precisely clustered the data. Moreover, comparing the K means and Self-organizing Mapping, the hybrid method performs better. The hybrid model performs faster and with higher clustering accuracy. Therefore, the hybrid model is highly recommended, and it can be employed to discover the patterns in the healthcare data, gain valuable knowledge concerning the early diagnosis of diseases, and identify potentially effective treatment modalities.
Article Details
References
Aggarwal, C.C., Hinneburg, A. and Keim, D.A., 2001. On the surprising behavior of distance metrics in high dimensional space. In Database Theory—ICDT 2001: 8th International Conference London, UK, January 4–6, 2001 Proceedings 8 (pp. 420-434). Springer Berlin Heidelberg. https://doi.org/10.1007/3-540-44503-X_27
Alsayat, A. and El-Sayed, H., 2016, June. Efficient genetic K-Means clustering for health care knowledge discovery. In 2016 IEEE 14th International Conference on Software Engineering Research, Management and Applications (SERA) (pp. 45-52). IEEE. https://doi.org/10.1109/SERA.2016.7516127
Ankerst, M., Breunig, M.M., Kriegel, H.P. and Sander, J., 1999. OPTICS: Ordering points to identify the clustering structure. ACM Sigmod record, 28(2), pp.49-60. https://doi.org/10.1145/304181.304187
Bruno, G., Cerquitelli, T., Chiusano, S. and Xiao, X., 2014, September. A clustering-based approach to analyse examinations for diabetic patients. In 2014 IEEE International Conference on Healthcare Informatics (pp. 45-50). IEEE. https://doi.org/10.1109/ICHI.2014.14.
Chae, Y.M., Kim, H.S., Tark, K.C., Park, H.J. and Ho, S.H., 2003. Analysis of healthcare quality indicator using data mining and decision support system. Expert Systems with Applications, 24(2), pp.167-172. https://doi.org/10.1016/S0957-4174(02)00139-2
Defays, D., 1977. An efficient algorithm for a complete link method. The computer journal, 20(4), pp.364-366. https://doi.org/10.1093/comjnl/20.4.364
Delias, P., Doumpos, M., Grigoroudis, E., Manolitzas, P. and Matsatsinis, N., 2015. Supporting healthcare management decisions via robust clustering of event logs. Knowledge-Based Systems, 84, pp.203-213. https://doi.org/10.1016/j.knosys.2015.04.012
Ester, M., Kriegel, H.P., Sander, J. and Xu, X., 1996, August. A density-based algorithm for discovering clusters in large spatial databases with noise. In Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining (Vol. 96, No. 34, pp. 226-231).
Galluccio, L., Michel, O., Comon, P., Kliger, M. and Hero, A.O., 2013. Clustering with a new distance measure based on a dual-rooted tree. Information Sciences, 251, pp.96-113. https://doi.org/10.1016/j.ins.2013.05.040
Haraty, R.A., Dimishkieh, M. and Masud, M., 2015. An enhanced k-means clustering algorithm for pattern discovery in healthcare data. International Journal of Distributed Sensor Networks, 11(6), p.615740. https://doi.org/10.1155/2015/6157
Hobbs, G.R., 2001. Data mining and healthcare informatics. American journal of health behavior, 25(3), pp.285-289. ttps://doi.org/10.5993/AJHB.25.3.16
Negi, N., and Chawla, G., 2021. Clustering Algorithms in Healthcare, Intelligence Healthcare, pg 211-224.
Niwattanakul, S., Singthongchai, J., Naenudorn, E. and Wanapu, S., 2013, March. Using of Jaccard coefficient for keywords similarity. In Proceedings of the international multiconference of engineers and computer scientists (Vol. 1, No. 6, pp. 380-384).
Ogbuabor, G. and Ugwoke, F.N., 2018. Clustering algorithm for a healthcare dataset using silhouette score value. International Journal of Computer Science and Information Technology, 10(2), pp.27-37.
https://doi.org/10.5121/ijcsit.2018.10203
Radha, R. and Rajendiran, P., 2014, February. Using K-means clustering technique to study of breast cancer. In 2014 World Congress on Computing and Communication Technologies (pp. 211-214). IEEE.
https://doi.org/10.1109/WCCCT.2014.64.
Santhi, P. and Bhaskaran, V.M., 2010. Performance of clustering algorithms in healthcare database. International Journal for Advances in Computer Science, 2(1), pp.26-31.
Singh, A., Yadav, A. and Rana, A., 2013. K-means with Three different Distance Metrics. International Journal of Computer Applications, 67(10).
Zhou, H., Li, G.M. and Zhang, G.Y., 2010. SOM+ K-means two-phase clustering algorithm and its application. Modern Electronics Technique, 16, pp.113-115.