Analysis of Hospitalized Pathways Using Locally Weighted Learning
Yong Gyu Jung1, Jae Hong Lee2, Young Jin Choi3
1Yong Gyu Jung, Department of Medical Information Technology, Eulji University, Korea.
2Jae Hong Lee, Chief Executive Officer, Ubivelox Co, Ltd., Korea.
3Young Jin Choi, Department of Healthcare Management, Eulji University Korea.
Manuscript received on 05 March 2019 | Revised Manuscript received on 12 March 2019 | Manuscript Published on 20 March 2019 | PP: 1-4 | Volume-8 Issue- 4S2 March 2019 | Retrieval Number: D1S0001028419/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In recent years, data mining and treadmill machines have become an issue in various fields. Data mining is the systematic and automatic discovery of metabolic rules and patterns within large-scale stored data. Among data analysis algorithms in data mining and machine learning, there are bifurcation / clustering algorithms. In this study, we use the LWL algorithm among classification algorithms. Identifying these various admission pathways and finding out the weight of various hospitalization pathways can develop toward the response and quality of medical care. Therefore, it is classified into LWL algorithm to predict various hospitalization routes and specific gravity.
Keywords: LWL, Linear Regression, Locally Weighted Learning, Machine Learning and Hospitalization Pathways.
Scope of the Article: Machine Learning