Research article

BMC Medical Informatics and Decision Making

, 12:36

Open Access This content is freely available online to anyone, anywhere at any time.

Recognition of medication information from discharge summaries using ensembles of classifiers

  • Son DoanAffiliated withNational Institute of Informatics, Hitotsubashi Email author 
  • , Nigel CollierAffiliated withNational Institute of Informatics, Hitotsubashi
  • , Hua XuAffiliated withDepartment of Biomedical Informatics, School of Medicine, Vanderbilt University
  • , Pham Hoang DuyAffiliated withDepartment of Computer Science, Posts and Telecommunications Institute of Technology
  • , Tu Minh PhuongAffiliated withDepartment of Computer Science, Posts and Telecommunications Institute of Technology



Extraction of clinical information such as medications or problems from clinical text is an important task of clinical natural language processing (NLP). Rule-based methods are often used in clinical NLP systems because they are easy to adapt and customize. Recently, supervised machine learning methods have proven to be effective in clinical NLP as well. However, combining different classifiers to further improve the performance of clinical entity recognition systems has not been investigated extensively. Combining classifiers into an ensemble classifier presents both challenges and opportunities to improve performance in such NLP tasks.


We investigated ensemble classifiers that used different voting strategies to combine outputs from three individual classifiers: a rule-based system, a support vector machine (SVM) based system, and a conditional random field (CRF) based system. Three voting methods were proposed and evaluated using the annotated data sets from the 2009 i2b2 NLP challenge: simple majority, local SVM-based voting, and local CRF-based voting.


Evaluation on 268 manually annotated discharge summaries from the i2b2 challenge showed that the local CRF-based voting method achieved the best F-score of 90.84% (94.11% Precision, 87.81% Recall) for 10-fold cross-validation. We then compared our systems with the first-ranked system in the challenge by using the same training and test sets. Our system based on majority voting achieved a better F-score of 89.65% (93.91% Precision, 85.76% Recall) than the previously reported F-score of 89.19% (93.78% Precision, 85.03% Recall) by the first-ranked system in the challenge.


Our experimental results using the 2009 i2b2 challenge datasets showed that ensemble classifiers that combine individual classifiers into a voting system could achieve better performance than a single classifier in recognizing medication information from clinical text. It suggests that simple strategies that can be easily implemented such as majority voting could have the potential to significantly improve clinical entity recognition.