Design Principles and Clinician Preferences for Pharmacogenomic Clinical Decision Support Alerts
January 31, 2020 Β· Declared Dead Β· π arXiv.org
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Timothy M. Herr, Therese A. Nelson, Justin B. Starren
arXiv ID
2002.00044
Category
cs.HC: Human-Computer Interaction
Cross-listed
q-bio.GN
Citations
0
Venue
arXiv.org
Last Checked
5 months ago
Abstract
OBJECTIVE: To better understand clinician needs and preferences for the display of pharmacogenomic (PGx) information in clinical decision support (CDS) tools. MATERIALS AND METHODS: We developed a semi-structured interview to collect feedback and preferences in six key areas of PGx CDS design, from clinicians who had prior experience with live PGx CDS tools. Eight clinicians from Northwestern Medicine's (NM) General Internal Medicine clinic participated in the study. RESULTS: Clinicians expressed preference for interruptive pop-up alerts during order entry, brief descriptions of relevant drug-gene interactions, and a clear and specific recommended alternative course of action when a medication is contraindicated. They did not wish to see detailed genetic data, preferring phenotypic information predicted from the genotype. Nor did they wish to be interrupted when genetic test results do not indicate a change in treatment plan. Clinicians reported little familiarity with Clinical Pharmacogenetic Implementation Consortium prescribing recommendations but reported trusting recommendations of their professional societies and resources like UpToDate. Analysis of unstructured comments concurred with structured results, indicating a general uncertainty among participants around how to interpret and apply PGx information in practice. DISCUSSION: Results point to several underlying principles that can inform future PGx CDS alert designs: Be Specific and Actionable; Be Brief; Display Phenotypes not Genotypes; Rely on Sources Clinicians Already Trust; and, Be Adaptable to Learning Effects. CONCLUSION: This study is part of a broader socio-technical design approach to PGx CDS design underway at NM and provides a baseline for future PGx CDS development. Designs based on these results have the potential to improve clinician education and adherence levels, and to improve patient outcomes.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Human-Computer Interaction
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Improving fairness in machine learning systems: What do industry practitioners need?
R.I.P.
π»
Ghosted
Identifying Stable Patterns over Time for Emotion Recognition from EEG
R.I.P.
π»
Ghosted
Questioning the AI: Informing Design Practices for Explainable AI User Experiences
R.I.P.
π»
Ghosted
Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
R.I.P.
π»
Ghosted
Educational data mining and learning analytics: An updated survey
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted