Application of Natural Language Processing to Learn Insights on the Clinician's Lived Experience of Electronic Health Records.

We interviewed six clinicians to learn about their lived experience using electronic health records (EHR, Allscripts users) using a semi-structured interview guide in an academic medical center in New York City from October to November 2016. Each participant interview lasted approximately one to two hours. We applied a clustering algorithm to the interview transcript to detect topics, applying natural language processing (NLP). We visualized eight themes using network diagrams (Louvain modularity 0.70). Novel findings include the need for a concise and organized display and data entry page, the user controlling functions for orders, medications, radiology reports, and missing signals of indentation or filtering functions in the order page and lab results. Application of topic modeling to qualitative interview data provides far-reaching research insights into the clinicians' lived experience of EHR and future optimal EHR design to address human-computer interaction issues in an acute care setting.

Characterizing and Visualizing Display and Task Fragmentation in the Electronic Health Record: Mixed Methods Design.

BACKGROUND: The complexity of health care data and workflow presents challenges to the study of usability in electronic health records (EHRs). Display fragmentation refers to the distribution of relevant data across different screens or otherwise far apart, requiring complex navigation for the user's workflow. Task and information fragmentation also contribute to cognitive burden. OBJECTIVE: This study aims to define and analyze some of the main sources of fragmentation in EHR user interfaces (UIs); discuss relevant theoretical, historical, and practical considerations; and use granular microanalytic methods and visualization techniques to help us understand the nature of fragmentation and opportunities for EHR optimization or redesign. METHODS: Sunburst visualizations capture the EHR navigation structure, showing levels and sublevels of the navigation tree, allowing calculation of a new measure, the Display Fragmentation Index. Time belt visualizations present the sequences of subtasks and allow calculation of proportion per instance, a measure that quantifies task fragmentation. These measures can be used separately or in conjunction to compare EHRs as well as tasks and subtasks in workflows and identify opportunities for reductions in steps and fragmentation. We present an example use of the methods for comparison of 2 different EHR interfaces (commercial and composable) in which subjects apprehend the same patient case. RESULTS: Screen transitions were substantially reduced for the composable interface (from 43 to 14), whereas clicks (including scrolling) remained similar. CONCLUSIONS: These methods can aid in our understanding of UI needs under complex conditions and tasks to optimize EHR workflows and redesign.

MyVA Access: An Evaluation of Changes in Access for a System-Wide Program Implemented in the Veterans Health Administration.

The current study evaluates changes in access as a result of the MyVA Access program-a system-wide effort to improve patient access in the Veterans Health Administration. Data on 20 different measures were collected, and changes were analyzed using t tests and Chow tests. Additionally, organizational health-how able a system is to create health care practice change-was evaluated for a sample of medical centers (n = 36) via phone interviews and surveys conducted with facility staff and technical assistance providers. An organizational health variable was created and correlated with the access measures. Results showed that, nationally, average wait times for urgent consults, new patient wait times for mental health and specialty care, and slot utilization for primary and specialty care patients improved. Patient satisfaction measures also improved, and patient complaints decreased. Better organizational health was associated with improvements in patient access.

The pharmacist's role in overdose: Using mapping technologies to analyze naloxone and pharmacy distribution.

OBJECTIVES: To present preliminary research using geographic information system (GIS) mapping as a tool that can be integrated into pharmacy practice to increase access to and utilization of pharmacy-based interventions, including the distribution of naloxone. METHODS: Overdose death data was collected from medical examiner reports in an online database, and pharmacies carrying and distributing naloxone were determined by ZIP Code Tabulation Areas (ZCTAs) in Allegheny County, PA. The distribution of overdose death rates was analyzed in relation to naloxone-carrying pharmacies and all licensed pharmacies in the county with the use of GIS mapping. RESULTS: Eighty-seven ZCTAs were included. Of 322 active licensed pharmacies, 28 pharmacies were confirmed to carry and distribute naloxone. The number of overdose deaths in ZCTAs that have naloxone-distributing pharmacies was significantly higher than the average number of deaths in all ZCTAs in Allegheny County: 7.38 deaths versus 4.84 deaths, respectively (P = 0.021). CONCLUSION: This report illustrates the value of GIS mapping in monitoring the impact of overdose death prevention efforts, including the availability of naloxone in pharmacies. Analysis of these data over the next 5 years will provide valuable information on the potential impact of naloxone-distributing pharmacies on overdose rates, which, in turn, will inform pharmacists and pharmacy organizations on the value of carrying naloxone in pharmacies and inform local communities of its availability.