Enhancing information retrieval in electronic health records through collaborative filtering

Project Description

Major Research Products

Ziwei Fan, Evan Burgun, Douglas Martin, Titus Schleyer and Xia Ning. Improving information retrieval from electronic health records using dynamic and multi-collaborative filtering. Under review. 2018

Abstract:  Due to the rapid growth of information available about individual patients, most physicians suffer from information overload when they review patient information in health information technology systems. In this manuscript, we present a novel hybrid dynamic and multi-collaborative filtering method to improve information retrieval from electronic health records. This method recommends relevant information from electronic health records for physicians during patient visits. It models information search dynamics using a Markov model. It also leverages the key idea of collaborative filtering, originating from Recommender Systems, to prioritize information based on various similarities among physicians, patients and information items. We tested this new method using real electronic health record data from the Indiana Network for Patient Care. Our experimental results demonstrated that for 46.7% of testing cases, this new method is able to correctly prioritize relevant information among top-5 recommendations that physicians are truly interested in.