Parallelized text classification algorithm for processing large scale TCM clinical data with MapReduce.
Xianju FeiXiaofang LiChunti ShenPublished in: ICIA (2015)
Keyphrases
- classification algorithm
- clinical data
- traditional chinese medicine
- medical data
- mapreduce framework
- patient data
- naive bayes
- support vector machine
- class labels
- knn
- clinical information
- raw data
- electronic health records
- training set
- k nearest neighbor
- statistical analysis
- accurate classification
- knowledge discovery
- learning algorithm
- cloud computing
- information retrieval
- text mining
- domain experts
- electronic medical record
- clinical decision making
- unsupervised learning
- machine learning
- free text
- data sources
- medical knowledge
- databases
- supervised learning
- domain knowledge
- active learning
- prior knowledge
- bayesian networks
- data mining
- real world