Designing Patient Insights Module for an Incubation Lab
Author
David Kim
Scope
UI/UX Design
Internal Tools
Architecture
Concept
The Patient Feedback module was conceptualized and rapidly prototyped for Eli Lilly and Company to illustrate how an incubation lab might develop a data-driven insights product powered by AI.
Drawing on my experience conducting customer discovery with research labs across a range of industries, I’ve observed that research teams frequently face challenges in managing vast volumes of patient data during clinical trials.
This solution enables researchers to collect, analyze, and act on real-time patient feedback, leveraging AI to automatically gather insights and interact with an extensive database of previous clinical trials and research. As part of the broader Incubation Dashboard, the Patient Feedback module forms the foundation of “CardioTrack,” showcasing how such tools can significantly improve trial outcomes by supporting real-time, data-driven decision-making.
First, let’s briefly explore the architecture of our application.
We’ve offloaded resource-intensive AI/ML processing to the backend, while simpler, real-time analysis is handled by IRIS (the name of our AI assistant) directly on the frontend. This structure allows us to scale efficiently to accommodate larger trials, more participants, and evolving features.
A robust set of data sources is interfaced through a GraphQL API, managed by Apollo Client on the frontend, with Redux for state management and React Query (or alternatives like TanStack Query or HTMX) for optimized data fetching. Additionally, we’ll incorporate modern tools like Vercel’s AI SDK for generative UI, enabling dynamic charts and interfaces from IRIS.
While comprehensive safety protocols and ethical considerations are integral to the system's design, the detailed implementation of these measures falls outside the scope of this case study.
The layout of the module is built on a 12-column grid system to ensure the interface remains both flexible and functional. This grid allowed organization of complex content types—such as interview transcripts, patient insights, and AI-generated summaries—into distinct, easy-to-navigate sections without cluttering the interface.
The design implements a consistent 4px spacing scale (4x) throughout the interface, where spacing values multiply from the base unit: from subtle element spacing (4px, 8px) for tight component relationships, to moderate spacing (16px, 24px) for content separation, up to larger spacing (32px, 48px) for major section divisions. This systematic approach to spacing creates visual rhythm and hierarchy while ensuring consistent component relationships across all viewport sizes.
The color palette centers on subtle blue accents built on Radix UI's color system, layered over warm, parchment-toned neutrals. This combination, paired with Kilm Type Foundry's Martijn Plantijn serif for headings, creates an intentionally intimate interface reminiscent of a journal or research notebook. The design encourages sustained, focused engagement—similar to how one might approach a morning journaling session.
These are considered invocations that are necessary when dealing with the health of patients, where the interface must promote the mindful, attentive state necessary for high-quality patient care and research.
Top Insights
IRIS
Hi Nadia, how can I assist you with the trial insights?
Can you tell me how Linda’s positive outcomes compare with other patients?
Linda has experienced notable improvements, particularly with her cholesterol levels due to the dietary intervention. Compared to other patients, Linda’s outcomes align with those who have adhered well to the diet changes. Patients like James Miller and Sarah Thompson also reported similar improvements in cholesterol and blood pressure.
How effective is this treatment compared to the CardioGuard trials last year?
In comparison to the CardioGuard trials conducted last year, the CardioTrack trial shows similar improvements in cholesterol and blood pressure metrics across participants. However, CardioGuard had a lower overall patient adherence rate, with adherence dropping by nearly 42% due to more severe side effects such as dizziness, fatigue, and nausea. Here’s a visualization of the key data comparing adherence rates and reported side effects between the two trials.
CardioGuard vs CardioTrack Trial Comparison
Adherence Rates
100
75
50
25
0
Within the Insights pane, the blue color palette takes on a more prominent role. High-priority insights are positioned at the top, featuring interactive cards that expand on hover or click to reveal detailed analysis. The card's elevation hierarchy visually reinforces the primary workflow between researcher and IRIS, with progressive disclosure of information through tooltips.
IRIS's capabilities extend beyond basic analysis, offering sophisticated features including automated insight extraction from clinical trial data, hypothesis correlation, and dynamic data visualization through generative UI—enabling direct comparisons with historical trial outcomes.
All Interviews
IRIS proves to be a powerful AI assistant by handling deep, nuanced questions that involve synthesizing patient data across contexts.
For instance, researchers can ask IRIS, “How did patients who initially struggled with exercise adherence eventually adapt, compared to those who didn’t?” IRIS quickly draws connections across individual histories, extracting insights on long-term adherence patterns and uncovering correlations.
This level of comprehensive analysis enables researchers to make more informed decisions, revealing patient trends that might otherwise remain hidden in complex datasets.
IRIS
How did patients who initially struggled with exercise adherence eventually adapt, compared to those who didn’t?
Those who struggled initially but received tailored plans improved adherence by 35% by week 12, while others on standard regimens showed smaller improvements. Personalized coaching reduced reported barriers like joint pain, while those without support continued to struggle. Would you like a demographic breakdown?
Yes, please provide an analysis by age group.
Absolutely. Patients aged 55 and older showed the most significant improvements when provided with tailored exercise routines, with adherence increasing by 45% after the first six weeks. In contrast, younger patients, especially those between 30 and 45, showed only a 20% increase, largely due to factors like work-related time constraints, which were frequently mentioned in their feedback.
Interestingly, those younger participants who received digital reminders and motivational messages adapted nearly as well as the older cohort, suggesting that targeted interventions based on lifestyle can help bridge the gap. Would you like me to explore other factors, such as pre-existing health conditions, that might have influenced these trends?
CardioGuard vs CardioTrack Trial Comparison
Adherence Rates Chart