Title :
Clinical data preprocessing and case studies of POMDP for TCM treatment knowledge discovery
Author :
Liu, Kai ; Zhou, Xuezhong ; Feng, Yan ; Liu, Jie
Author_Institution :
Coll. of Comput. & Inf. Technol., Beijing Jiaotong Univ., Beijing, China
Abstract :
Partially Observable Markov Decision Processes (POMDP) has been applied to induce sequential treatment scheme from Traditional Chinese Medicinal (TCM) clinical data. The data required by POMDP should be of rich structure and with heterogeneous variables. But sometimes there is large number of missing values in the real-world TCM clinical data set. This makes it difficult for data preprocessing. This paper designs a data preprocessing framework of TCM clinical data for POMDP applications. It significantly facilitates the process of sequential treatment scheme discovery through POMDP when applying the framework on TCM clinical cases of coronary heart disease and lung cancer. We also systematically analyze the sequential treatment scheme.
Keywords :
Markov processes; cancer; cardiology; data mining; lung; medical information systems; POMDP; TCM sequential treatment knowledge discovery; clinical data preprocessing framework; coronary heart disease; heterogeneous variables; lung cancer; partially observable Markov decision processes; traditional Chinese medicinal clinical data; Data models; Data preprocessing; Diseases; Heart; Markov processes; Medical diagnostic imaging; Noise measurement; Partially Observable Markov Decision Processes; Traditional Chinese Medicine; case studies; clinical data mining; data preprocessing; framework;
Conference_Titel :
e-Health Networking, Applications and Services (Healthcom), 2012 IEEE 14th International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4577-2039-0
Electronic_ISBN :
978-1-4577-2038-3
DOI :
10.1109/HealthCom.2012.6380056
