TY - GEN
T1 - Arresting treatment patterns for individual patients in clinical big data
T2 - 2014 AAAI Spring Symposium
AU - Morita, Mizuki
AU - Shiro, Masanori
AU - Akaho, Shotaro
AU - Kamishima, Toshihiro
AU - Asoh, Hideki
AU - Aramaki, Eiji
AU - Hasida, Koiti
AU - Kohro, Takahide
PY - 2014/1/1
Y1 - 2014/1/1
N2 - Data mining of clinical data that are stored continually in the course of daily medical practice will contribute to the advancement of healthcare. However, real-world clinical data are characteristically noisy, sparse, irregular, and biased, which makes it difficult to perform data mining. This study assesses an exploratory approach to ascertain how physicians tackle the worsening of a patient's condition using clinical data from a hospital. It yielded reasonable results.
AB - Data mining of clinical data that are stored continually in the course of daily medical practice will contribute to the advancement of healthcare. However, real-world clinical data are characteristically noisy, sparse, irregular, and biased, which makes it difficult to perform data mining. This study assesses an exploratory approach to ascertain how physicians tackle the worsening of a patient's condition using clinical data from a hospital. It yielded reasonable results.
UR - http://www.scopus.com/inward/record.url?scp=84904891991&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84904891991&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84904891991
SN - 9781577356547
T3 - AAAI Spring Symposium - Technical Report
SP - 98
EP - 99
BT - Big Data Becomes Personal
PB - AI Access Foundation
Y2 - 24 March 2014 through 26 March 2014
ER -