Domain

Clinical Informatics

Type

Conceptual or Process Model/Framework

Theme

population; operations

Start Date

7-6-2014 10:25 AM

End Date

7-6-2014 11:45 AM

Structured Abstract

Introduction: Long and resource intensive update cycles from vendors hinder the availability of new features requested by clinicians, limiting potential contributions of the electronic health record (EHR) to optimize healthcare. We hypothesize that existing clinical data and application programming interfaces (APIs) within the EHR can be leveraged to enhance healthcare delivery by providing those features and extending EHR functionalities. We aim to study the feasibility of delivering personalized and real-time data-driven tools to clinicians by leveraging commercial EHR’s APIs, ultimately aiming to enhance high-value care delivery.

Context: We present model formulation and development of a customizable EHR-embedded web-based tool, describing one of many potential applications: a point-of-care interactive risk profiling and visualization module. Based on user centered design, we developed the module to have minimum clinical workflow impact by focusing on three features: 1) availability on-demand via a non-disruptive ‘best practice alert’, 2) automatic patient-data retrieval for calculations and visualizations, and 3) a non-intrusive view, rendering on a lateral panel which allows concurrent EHR navigation. The prototype was developed for outpatient care providers using a commercial EHR (Epic ®) at The Ohio State University Wexner Medical Center, providing a risk profiling and visualization tool during encounters with female patients >65 years old.

Innovation: Our prototype was able to accurately retrieve and render the corresponding risk profile for a given patient during the encounter. When the alert is clicked, it triggers existing APIs which collect current encounter parameters for the patient from the vendor’s live database, and delivers them to our web app via a secure POST http request. The app then retrieves historical data from our Enterprise Data Warehouse (EDW), and renders the resulting risk profiling and visualization on an embedded instance of a web browser engine. Challenges encountered included browser engine rendering issues (internet explorer 8.0), and recall for parameters from the EDW (compilation of data from multiple sources). Clinical impact might vary depending on the specific tools implemented using this approach, and should be studied individually.

Lessons learned: Our concept demonstrates the feasibility to deliver real-time data-driven tools for clinicians, extending EHRs contribution to augment healthcare beyond their native functionalities, maximizing the use of available data. Besides clinical uses, the model could support new pragmatic point-of-care research paradigms. Given that Epic® is one of the largest EHR providers across the nation, our concept is applicable to a vast population and use cases.

Conclusion: We present our prototype for a customizable EHR-embedded web-based application intended to deliver real-time data-driven tools for clinicians, created by leveraging APIs and the web-browser rendering engine available within a commercial EHR. Our initial findings open an expanded range of potential applications for this concept, extending EHR functionalities and finally enhancing high-value care delivery.

Acknowledgements

This project was partially funded by Pfizer.

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License.

Share

COinS
 
Jun 7th, 10:25 AM Jun 7th, 11:45 AM

Real-time data-driven tools for clinicians: a model for extending functionalities within the electronic health record

Introduction: Long and resource intensive update cycles from vendors hinder the availability of new features requested by clinicians, limiting potential contributions of the electronic health record (EHR) to optimize healthcare. We hypothesize that existing clinical data and application programming interfaces (APIs) within the EHR can be leveraged to enhance healthcare delivery by providing those features and extending EHR functionalities. We aim to study the feasibility of delivering personalized and real-time data-driven tools to clinicians by leveraging commercial EHR’s APIs, ultimately aiming to enhance high-value care delivery.

Context: We present model formulation and development of a customizable EHR-embedded web-based tool, describing one of many potential applications: a point-of-care interactive risk profiling and visualization module. Based on user centered design, we developed the module to have minimum clinical workflow impact by focusing on three features: 1) availability on-demand via a non-disruptive ‘best practice alert’, 2) automatic patient-data retrieval for calculations and visualizations, and 3) a non-intrusive view, rendering on a lateral panel which allows concurrent EHR navigation. The prototype was developed for outpatient care providers using a commercial EHR (Epic ®) at The Ohio State University Wexner Medical Center, providing a risk profiling and visualization tool during encounters with female patients >65 years old.

Innovation: Our prototype was able to accurately retrieve and render the corresponding risk profile for a given patient during the encounter. When the alert is clicked, it triggers existing APIs which collect current encounter parameters for the patient from the vendor’s live database, and delivers them to our web app via a secure POST http request. The app then retrieves historical data from our Enterprise Data Warehouse (EDW), and renders the resulting risk profiling and visualization on an embedded instance of a web browser engine. Challenges encountered included browser engine rendering issues (internet explorer 8.0), and recall for parameters from the EDW (compilation of data from multiple sources). Clinical impact might vary depending on the specific tools implemented using this approach, and should be studied individually.

Lessons learned: Our concept demonstrates the feasibility to deliver real-time data-driven tools for clinicians, extending EHRs contribution to augment healthcare beyond their native functionalities, maximizing the use of available data. Besides clinical uses, the model could support new pragmatic point-of-care research paradigms. Given that Epic® is one of the largest EHR providers across the nation, our concept is applicable to a vast population and use cases.

Conclusion: We present our prototype for a customizable EHR-embedded web-based application intended to deliver real-time data-driven tools for clinicians, created by leveraging APIs and the web-browser rendering engine available within a commercial EHR. Our initial findings open an expanded range of potential applications for this concept, extending EHR functionalities and finally enhancing high-value care delivery.