Abstract:
The Electronic Health Record (EHR) is a digital record of a patient’s medical history. A feature of the EHR is the Problem List (PL), used by providers to obtain a summary of a patient's health problems. The PL contains all documented conditions of a patient; however, its necessity for manual curation may conflict with a provider's workflow and result in PL inaccuracies. For patients with chronic illness, their PLs can be very long, so identifying significant problems becomes complicated. The goal of this research is to determine the potential of utilizing the Word Cloud (WC) format for the PL to make the information easily interpretable for providers. The WC is a visualization of keywords varying in size, from text data in one image. The terms on a patient’s WC are pulled from the patient’s EHR and the relative size of a term is based on the recurrence of that term in the records. We hypothesize that utilizing the WC will streamline the interaction between PL and provider and decrease the risk of important patient information being overlooked. The WC prototype will be evaluated by selected providers for feedback and to obtain a System Usability Scale (SUS) score. We expect evaluation of the WC will provide insight on intuitive features and areas for further improvement. This research will evaluate the implementation of the WC in providers’ workflow in hopes the WC will better aid in the treatment of patients.

Describe the new knowledge and additional skills the participant will gain after attending your presentation.: This presentation will discuss the issues of consistency and visability of the current patient Problem List and will introduce the prototype word cloud tool that would be added as a feature into the Electronic Health Record (EHR). It provides a word cloud visualization of a patient's problems and pulls the terms directly from the EHR to give a more consistent and thorough patient summary. This presentation will analyze the preliminary results of the word cloud's usability study and discuss improvments for future iterations.

Authors:

Hannah Tan (Presenter)
Lehigh University

Yaa Kumah-Crystal, Vanderbilt
Dario Giuse, Vanderbilt