A cascade of classifiers for extracting medication information from discharge summaries

Abstract

Background: Extracting medication information from clinical records has many potential applications, and recently published research, systems, and competitions reflect an interest therein. Much of the early extraction work involved rules and lexicons, but more recently machine learning has been applied to the task.

Methods: We present a hybrid system consisting of two parts. The first part, field detection, uses a cascade of statistical classifiers to identify medication-related named entities. The second part uses simple heuristics to link those entities into medication events.

Results: The system achieved performance that is comparable to other approaches to the same task. This performance is further improved by adding features that reference external medication name lists.

Conclusions: This study demonstrates that our hybrid approach outperforms purely statistical or rule-based systems. The study also shows that a cascade of classifiers works better than a single classifier in extracting medication information. The system is available as is upon request from the first author.

Figure 1

System performance on the development set with different training set sizes. Key: + represents horizontal F-scores with features in F1-F4b; ○ represents horizontal F-scores with features in F1-F4a.

Figure 2

Cascade vs. find_all for field detection on the development set. Key: + represents horizontal F-scores with the three-module cascade; ○ represents horizontal F-scores with find_all.