Revisiting a healthcare AI concept with stronger visual hierarchy, accessibility, and a design direction better suited for patient-facing experiences.
After completing the initial design for this AI-powered healthcare companion, I revisited the project with a fresh perspective, both visually and strategically.
The original version was created under tight time constraints as part of a group project. It worked functionally, but it lacked the level of visual polish and healthcare-specific clarity I knew it could reach.
Since then, I’ve grown in how I think about accessibility, visual hierarchy, UI consistency, and emotional context. I wanted the project to reflect that growth.
There were three main reasons I came back to this project.
The biggest strategic change was moving from dark mode to light mode.
After more research, I made that shift intentionally. It was not just a visual preference. It was about the user’s environment and emotional context.
Who’s using this, and in what environment? That question now shapes my design decisions much earlier.
Light mode is often better suited for healthcare products because it improves readability for patients and clinicians, aligns more closely with existing medical systems, and reduces the emotional heaviness dark interfaces can sometimes carry in already overwhelming health contexts.
This redesign pushed me to think less about what looked dramatic and more about what felt calm, clear, and usable for real people.
The original version relied on too many colors in the vitals section and across the UI, which made the interface feel visually heavy.
I used the redesign as an opportunity to bring the interface closer to WCAG-friendly contrast and more reliable legibility across the experience.
This was also a reminder that healthcare products cannot rely on aesthetic preference alone. The interface needs to hold up when users are fatigued, stressed, or under pressure.
This project was developed as part of my Human-AI Interaction class at Drexel University. The AI Healthcare Companion is a conceptual design for an intelligent system aimed at improving chronic disease management and emergency response.
It reflects my interest in blending user-centered design principles with AI technologies to solve real-world healthcare challenges.
Managing chronic or terminal conditions often means dealing with medication schedules, frequent doctor visits, and unexpected emergencies.
Many patients struggle with independence because of these challenges, creating a need for a supportive, intelligent system that helps both them and their caregivers.
We conducted research into stakeholder needs and the technology landscape to better understand challenges faced by chronic patients and caregivers.
We ideated several potential solutions and selected the AI Healthcare Companion for its feasibility and potential impact.
Core features included wearable integration, emergency escalation, and AI-driven scheduling for appointments and medication reminders.
We sketched basic wireframes to outline user flows and critical touchpoints, including a vitals dashboard, emergency alert panel, and personalization settings for thresholds and notifications.
I designed more polished interfaces in Figma, focusing on usability and accessibility.
I built a basic AI model using Teachable Machine to classify heart rate data into “Normal” or “Critical” using labeled screenshots.
The system was designed to map those AI classifications directly to interface behaviors, turning model output into meaningful user states.
This project reinforced how important accessibility, emotional context, and system trust are in healthcare experiences.
It also pushed me to think more critically about when design choices are about aesthetics versus when they directly affect comprehension and comfort.