Simplifying Healthcare, One Patient at a Time
Epic SmatyChart.ai:
Background
—Designing an AI-powered “Friendly Mode” for the MyChart patient portal to helps patients better understand their own health data—without needing a medical degree.
Role
UX Designer · Product Owner
Scope
4 Months · apprenticeship
TEAM
Team of 5 - 1 UX Designer (Me) · 2 developers · 2 data engineers
Figma
Overview
Client Brief
"In recent years, healthcare has moved toward greater transparency by giving patients access to their medical data through online portals. However, much of this information—like test results and physician notes—is still written for healthcare professionals, making it difficult for patients to fully understand or act on their own health information."
Much of the information in patient portals—like lab results and physician notes—is still written for healthcare professionals, not patients. As a result:
Patients struggled to interpret their own test results and medical records.
Confusion and anxiety increased when information was unclear.
Opportunities for patients to take informed action on their health were missed.
We created SmartChart.ai, an AI-driven “Friendly Mode” plugin embedded into Epic’s MyChart. The pulgin:
Simplified complex medical jargon into plain, patient-friendly language
Added conversational explanations to provide clarity and reassurance
Offered contextual definitions of medical terms without altering the original content
Impact
In just 4 months, we shipped a high-fidelity platform plugin that:
%
reduced cognitive load by
Created a flexible foundation for a scalable AI patient plugin
Received positive feedback from mentors and mychart users alike
Patients couldn’t understand their own medical data in portals like MyChart. We built an AI plugin with a friendly mode that translates jargon into plain language with context.
The result: clearer comprehension, less confusion, and greater patient confidence.
Research Process
Understanding the Problem
We kicked off with qualitative research—interviewing MyChart users to understand where they struggled.
Key insights:
“I don’t understand half of what’s written, so I just Google it.”
“I’m not sure if something’s serious or routine.”
“I wish I could just toggle a simple version of the results.”
Patients didn’t want more data—they wanted clearer meaning and reassurance. Their needs shaped our design focus.
To manage design + dev in parallel, we combined Scrum + Kanban frameworks.
Scrum: Weekly sprints with standups, retros, and rotating Scrum Masters.
Kanban (Jira): Each team member pulled from prioritized tasks. I maintained the product backlog and coordinated between design and development.
As both the UX Designer and Product Owner, I ensured our design decisions reflected real user pain points, and that those insights translated into feasible dev milestones.
I led a collaborative ideation sprint using Figma and Miro, sketching wireframes and user flows based on user scenarios from our interviews.
With time constraints in mind, we scoped three MVP features:
“Friendly Mode” toggle – for simplified test results and doctor’s notes.
Contextual hovers – offering plain-language popups for complex medical terms.
Conversational chatbot – for guided walkthroughs and emotional support.
Wireframes
This user journey map follows Nia, a first-time student entrepreneur, as she navigates the original TEO website. Based on real usability walkthroughs, it highlights key breakdowns—like vague headlines, confusing CTAs, and a lack of entry points. Each step captures her actions, thoughts, and emotional drop-off, showing how poor site structure led her from curiosity to confusion, frustration, and eventually exit.
building the experienece
While the engineering team built the app in React.js, I continued to evolve the UX.
Integrated Gemini AI plugin for summarizing health data
Designed mobile-first, responsive screens
Shifted from web scraping to file-based inputs for quicker implementation
Conducted handoff with detailed design specs and Figma tokens
We combined Scrum and Kanban to keep design and dev moving in parallel, with me driving backlog, sprints, and cross-team coordination. Through rapid ideation, user testing, and iterative wireframing, we translated real patient pain points into feasible MVP features.
Final Design
Results & Impact
In just 4 months, we shipped a high-fidelity prototype that:
Reduced user overwhelm by offering digestible medical summaries
Created a flexible foundation for a scalable AI patient-assistance plugin
Received positive feedback from mentors and healthcare users alike
Reflection