0 442

Cited 0 times in

Simultaneous Clustering and Classification of Function Recovery Patterns of Ischemic Stroke

Authors
 Kim, Hyungtai  ;  Lee, Minhee  ;  Sohn, Min Kyun  ;  Lee, Jongmin  ;  Kim, Deog Yung  ;  Lee, Sam-Gyu  ;  Shin, Yong-Il  ;  Oh, Gyung-Jae  ;  Lee, Yang-Soo  ;  Joo, Min Cheol  ;  Lee, So Young  ;  Han, Junhee  ;  Ahn, Jeonghoon  ;  Chang, Won Hyuk  ;  Choi, Ji Yoo  ;  Kang, Sung Hyun  ;  Lee, Dong Han  ;  Kim, Young Taek  ;  Choi, Mun-Taek  ;  Kim, Yun-Hee 
Citation
 JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS, Vol.10(6) : 1401-1407, 2020-06 
Journal Title
JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS
ISSN
 2156-7018 
Issue Date
2020-06
Keywords
Function Recovery ; Ischemic Stroke ; Simultaneous Clustering and Classification ; Unsupervised Learning
Abstract
This paper shows the simultaneous clustering and classification that is done in order to discover internal grouping on an unlabeled data set. Moreover, it simultaneously classifies the data using clusters discovered as class labels. During the simultaneous clustering and classification, silhouette and F 1 scores were calculated for clustering and classification, respectively, according to the number of clusters in order to find an optimal number of clusters that guarantee the desired level of classification performance. In this study, we applied this approach to the data set of Ischemic stroke patients in order to discover function recovery patterns where clear diagnoses do not exist. In addition, we have developed a classifier that predicts the type of function recovery for new patients with early clinical test scores in clinically meaningful levels of accuracy. This classifier can be a helpful tool for clinicians in the rehabilitation field.
Full Text
https://www.ingentaconnect.com/content/asp/jmihi/2020/00000010/00000006/art00023;jsessionid=1t8iluldmvbss.x-ic-live-02
DOI
10.1166/jmihi.2020.3061
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Rehabilitation Medicine (재활의학교실) > 1. Journal Papers
Yonsei Authors
Kim, Deog Young(김덕용) ORCID logo https://orcid.org/0000-0001-7622-6311
URI
https://ir.ymlib.yonsei.ac.kr/handle/22282913/179456
사서에게 알리기
  feedback

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse

Links