Designing AI Assist
A Conversational Care Layer for Patient Families
St. Jude helps families understand if their child qualifies for a trial, what happens next, and who to talk to, without making twenty phone calls to find out.
Team
Product Designer (that's me 👋)
Clinical Stakeholders, Business Analyst, Healthcare Staff, Accessibility Expert
Timeline
12 Weeks
Context
A real engagement with St. Jude's Strategic Communication, Education and Outreach team to redesign how patients and physicians find and qualify for clinical trials.
Goal
Help families and doctors get a clear, trusted answer about trial eligibility without manual cross checking or repeated phone calls.
Impact
AI Assist cuts the time it takes families to find and qualify for a trial, which shortens referral delays and reduces staff workload.
2 hrs → 10 min
Time per referral
93% less
St. Jude treats childhood cancer and pediatric diseases, free for every family. I worked with their Strategic Communication, Education and Outreach team to improve how patients and physicians find and qualify for clinical trials.
I talked to stakeholders, business analysts, an accessibility expert, and parents and healthcare staff recruited through Lyssna, to find out where the process breaks and why.
Why were the Users struggling?
Challenge 1: No Answers, No Guidance
Every unanswered question became a phone call.
The problem
Eligibility criteria were buried in jargon, with no filtering and no guidance. Doctors and parents hit the same walls and ended up calling the referral office, which got the same questions on repeat.
"I read the same page four times and still didn't know if she qualified. I just called and hoped someone could help."
Challenge 2: Eligibility Was a Guessing Game
Doctors were making judgment calls they shouldn't have to.
The problem
Cross-referencing a patient's profile against 50+ open trials meant opening tabs, reading dense paragraphs, and hoping nothing was missed. One overlooked line meant starting the referral over.
"I missed a line about prior treatment history. We had to restart the whole referral."
Challenge 3: The Referral Form Was a Dead End
Unqualified referrals. Missing documents. Every field from scratch.
The problem
Parents were submitting referrals without knowing if their child even qualified, flooding the referral staff with incomplete, unqualified submissions. There was no way to attach medical records. And every field was filled from scratch, even information already provided earlier.
"I submitted the form and waited weeks, only to find out my daughter didn't even qualify for any open trials."
Retrospective Analysis
What This Project Taught Me
Trust matters more than speed in healthcare. Making the AI's reasoning visible is what earned people's trust.
What I learned
Test edge cases earlier, and loop engineering into confidence scoring decisions sooner in the process.
Still Scrolling?
Say hello or keep up the friendly snooping 👀
Open to new positions. Let’s work together!
...✨ Fueled by caffeine, late nights, and lots of music @ 2025