Exploiting the rich information found in electronic health records (EHRs) can facilitate better medical research and improve the quality of medical practice. Until now, a trivial amount of research has been published on the challenges of leveraging this information. Addressing these challenges, Information Discovery on Electronic Health Records explores the technology to unleash the data stored in EHRs.

Assembling a truly interdisciplinary team of experts, the book tackles medical privacy concerns, the lack of standardization for the representation of EHRs, missing or incorrect values, and the availability of multiple rich health ontologies. It looks at how to search the EHR collection given a user query and return relevant fragments from the EHRs. It also explains how to mine the EHR collection to extract interesting patterns, group entities to various classes, or decide whether an EHR satisfies a given property. Most of the book focuses on textual or numeric data of EHRs, where more searching and mining progress has occurred. A chapter on the processing of medical images is also included.

Maintaining a uniform style across chapters and minimizing technical jargon, this book presents the various ways to extract useful knowledge from EHRs. It skillfully discusses how EHR data can be effectively searched and mined.