Design and Implementation of PharMe: A Mobile Application to Return Pharmacogenomic Test Results to Patients
Slosarek, T.; Baum, J.; Frost, B.; Genchev, N.; Hermann, L.; Kunst, S.; Meister, C.; Schmidt, M.; Wagner, S.; Mashni, S. M.; Lippert, C.; Böttinger, E. P.; Owusu Obeng, A.
Show abstract
ObjectivePharmacogenomics can optimize therapeutic outcomes while minimizing adverse events. However, barriers like the lack of trained healthcare professionals impede its widespread adoption. To address this challenge, we developed the PharMe app to return pharmacogenomic results to patients, facilitated by Anni, a custom annotation interface. Materials and MethodsAll components were developed user-centered; patient content was created by experts with Anni, based on CPIC and FDA guidelines. PharMes usability was tested in a remote pilot, asking users to perform tasks and give SUS and star ratings. A power user delivered in-depth, qualitative insights. ResultsPharMe is available for iOS and Android in English and includes information for 17 genes and 159 medications. Anni allows the consistent, multi-lingual annotation of guidelines with patient-friendly formulations. PharMe securely loads laboratory results, displays personalized annotated guidelines, and includes phenoconversion. Pilot testers finished most tasks successfully; on average, PharMe received 4.1 stars and a SUS score of 82.86. Feedback collected in all test sessions was incorporated into the current PharMe version. DiscussionWhile the remote pilot testing has limitations like a small sample size and (digitally) literate participants, it showed that PharMe is a valuable, understandable, and easy-to-use system. PharMe is assessed in a clinical validation study in a more diverse population. In the future, PharMe and Anni could support further guidelines and data formats. ConclusionWe developed a novel and user-friendly system to return pharmacogenomic results to patients and scale the clinical adoption of pharmacogenomics, supporting trained clinical experts. PharMe and Anni are designed to use transparent and standardized content based on published guidelines, be agnostic to pharmacogenomic data sources, and be flexibly deployed globally in different settings and institutions.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- A Framework to Assess Clinical Safety and Hallucination Rates of LLMs for Medical Text Summarisation 93%
- The clinician-AI interface: intended use and explainability in FDA-cleared AI devices for medical image interpretation 93%
- How AI is used in FDA-authorized medical devices: a taxonomy across 1,016 authorizations 92%
Similar papers in this journal
- Large Language Models in Real-World Clinical Workflows: A Systematic Review of Applications and Implementation 89%
- An automated Dashboard to improve laboratory COVID-19 diagnostics management 89%
- User Perceptions of Individually-Tailored Health Information in 1 Digital Apps: Development of a Scale 89%
Similar papers in this journal
- Improving Patient Engagement in Phase 2 Clinical Trials with a Trial-specific Patient Decision Aid (tPDA): A Development and Usability Study 93%
- Design and implementation of a system for automated monitoring of adherence to evidenced-based clinical guideline recommendations 92%
- Quantified Flu: an individual-centered approach to gaining sickness-related insights from wearable data 92%
Similar papers in this journal
Similar papers in this journal
- Evaluating the Clinical Feasibility of an Artificial Intelligence-Powered Clinical Decision Support System: A Longitudinal Feasibility Study 90%
- Design and Formative Evaluation of a Voice-based Virtual Coach for Problem-Solving Treatment 90%
- Applications and barriers to use of an mHealth iPhone application for self-management of chronic recurrent medical conditions: A Pilot Study 89%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.