Title :
A comparative study of missing value imputation with multiclass classification for clinical heart failure data
Author :
Zhang, Y. ; Kambhampati, C. ; Davis, D.N. ; Goode, K. ; Cleland, J.G.F.
Author_Institution :
Dept. of Comput. Sci., Univ. of Hull, Hull, UK
Abstract :
Clinical data often contains missing values. Imputation is one of the best known schemes to overcome the drawbacks associated with missing values in data mining tasks. In this work, we compared several imputation methods and analyzed their performance when applied to different classification algorithms. A clinical heart failure data set was used in these experiments. The results showed that there is no universal imputation method that performs best for all classifiers. Some imputation-classification combinations are recommended for the processing of clinical heart failure data.
Keywords :
cardiology; data mining; medical computing; pattern classification; clinical heart failure data; data mining tasks; imputation-classification combinations; missing value imputation; multiclass classification; universal imputation method; Blood; Classification algorithms; Data mining; Decision trees; Electromagnetic interference; Heart; Support vector machines; Classification; Clinical data; Heart failure; Imputation; Missing value;
Conference_Titel :
Fuzzy Systems and Knowledge Discovery (FSKD), 2012 9th International Conference on
Conference_Location :
Sichuan
Print_ISBN :
978-1-4673-0025-4
DOI :
10.1109/FSKD.2012.6233805
