Impact of Automated Transfer of Semi-Automated Segmentation and Structured Report Rule Requirements on Cardiac MRI Report Quality, Standardization, and Efficiency

Presentation Time: 08:00 AM - 08:15 AM

Abstract Keywords: Clinical Decision Support, Informatics Implementation, Machine Learning, Data Mining, Workflow
Primary Track: Applications
Programmatic Theme: Clinical Informatics

Clinical reporting of cardiac magnetic resonance (CMR) imaging exams is commonly performed with a dictation approach which requires great care to capture both consistent and comprehensive data. We sought to transform the reporting process by utilizing a structured report framework for reporting standardization, by incorporating automated transfer of data semi-automated segmentation tools for efficiency, and rule-based reporting requirements to improve quality and standardization. Interfaces between the applications used to schedule and protocol exams and to analyze the acquired images were created to bring the source information directly into the structured reporting environment. The physicians reporting CMR were surveyed to determine satisfaction and improved efficiency with the new process through self-reported reporting time. Quality improvement was assessed by examining the consistency of reported parameters with the inclusion of rule-based requirements. The designed structured reporting process with automated measurements and rule-based requirements resulted in significant improvement in report efficiency and quality.

Speaker(s):
Diane Rizkallah, MD
Cleveland Clinic

Author(s):
Rishabh Khurana, MD - Cleveland Clinic; Deborah Kwon, MD - Cleveland Clinic; Vadivelan Palanisamy, Siemens Medical Solutions USA, Inc. - Siemens Healthineers; Neil Greenberg, PhD - Cleveland Clinic; Ben Alencherry, MD - Cleveland Clinic; Richard Grimm, Staff - Cleveland Clinic; David Chen, PhD - Cleveland Clinic; Christopher Nguyen, PhD - Cleveland Clinic; Robert Geschke, Director, Informatics - Cleveland Clinic; Carl Ammoury, MD - Cleveland Clinic;

Assessing the Impact of a Clinical Decision Support Tool for Pain Management on Guideline-Concordant Decisions in Primary Care: A Cluster Randomized Clinical Trial

Presentation Time: 08:15 AM - 08:30 AM

Abstract Keywords: Clinical Decision Support, Chronic Care Management, Evaluation
Primary Track: Applications
Programmatic Theme: Clinical Informatics

We assessed the effects of Chronic Pain OneSheet on guideline-recommended pain care in a randomized controlled trial across two health systems. OneSheet access caused a significant 0.2 percentage point increase in the rate of goal documentation, a 0.8 percentage point increase in pain and function documentation, and a 1.9 percentage point increase in urine drug screen orders. OneSheet had positive effects on care and is low-cost to adopt, implement, and sustain in electronic health records.

Speaker(s):
Nate Apathy, PhD
University of Maryland

Author(s):
Christopher Harle, PhD - Indiana University; Olena Mazurenko, MD, PhD - Indiana University Fairbanks School of Public Health; Lindsey Sanner, MPH - Indiana University; Emma McCord, MPA - Indiana University Richard M. Fairbanks School of Public Health; Pablo Cuadros; Meredith Adams, MD, MS - Wake Forest School of Medicine; Robert Hurley, MD PhD - Wake Forest Baptist Health; Randall Grout - Indiana University; Burke Mamlin, MD - Regenstrief Institute; Saura Fortin, MD, MBA - Eskenazi Health; Justin Blackburn - Regenstrief Institute; Nir Menachemi, PhD, MPH - Indiana University / Regenstrief Institute; Joshua Vest, PhD - Indiana University; Matthew Gurka, PhD - University of Virginia;

Factors Driving Patient Decisions to Access Electronic Health Records via a Breast Cancer Online Decision Aid linked to the Patient Portal

Presentation Time: 08:30 AM - 08:45 AM

Abstract Keywords: Bioinformatics, Clinical Decision Support, Interoperability and Health Information Exchange, Cancer Prevention, Patient Engagement and Preferences, Human-computer Interaction
Primary Track: Applications
Programmatic Theme: Consumer Health Informatics

A critical strategy in limiting breast cancer (BC) mortality is the early identification of high-risk patients and implementation of risk-reducing measures. RealRisks, an online decision aid constructed by our team to provide education on BC risk and personalized risk assessment, allows users to choose to connect to their electronic health record (EHR) to extract requisite data to calculate BC risk via Fast Healthcare Interoperability Resources (FHIR). Using data from RealRisks user profiles, baseline questionnaires, and interview transcripts, we sought to understand the differences between the groups of patients who opted to download their data via the EHR vs. those who did not. A higher percentage of those who downloaded data (53.8% vs. 42.3%) identified as Hispanic/Latino compared to those who did not download. Thematic analysis suggested that while data security and privacy concerns may lead to hesitation, it is perhaps technological barriers that most significantly limit EHR download.

Speaker(s):
Anna Vaynrub, BA
Columbia University Medical Center

Author(s):
Anna Vaynrub, BA - Columbia University Medical Center; Subiksha Umakanth, MS - Columbia University Irving Medical Center; Harry West, PhD - Columbia University; Alissa Michel, MD - Columbia University; Jill Diamond, PhD - Sassafras Tech Collective; Stephan Constante, BS - Columbia University; Katherine Crew, MD, MS - Columbia University; Rita Kukafka, DrPH, MA, FACMI - Columbia University, Dept Biomedical Informatics;

PRESTO-R: A Novel, Scalable Methodology for Enabling Real-Time, True Randomization in the Electronic Health Record to Facilitate Pragmatic Randomized Controlled Trials

Presentation Time: 08:45 AM - 09:00 AM

Abstract Keywords: Informatics Implementation, Clinical Decision Support, Reproducibility, Real-World Evidence Generation
Primary Track: Foundations
Programmatic Theme: Clinical Research Informatics

Existing methods for enabling randomized trials in electronic health record (EHR) systems have important limitations, such as difficulty randomizing newly enrolled patients in real-time. Here, we describe PRESTO-R, a novel randomization methodology in which the last digits of internal subject identifiers are randomized in real-time to study arms via EHR decision support rules. The method was successfully validated in a multi-site pragmatic randomized trial and could facilitate similar pragmatic trials of informatics interventions at scale.

Speaker(s):
Christian Balbin, PhD Student
University of Utah

Author(s):
Polina Kukhareva, PhD, MPH, FAMIA - University of Utah; Kensaku Kawamoto, MD, PhD, MHS - University of Utah; Christian Balbin, PhD Student - University of Utah;