Delphea.
By Aurelia Vitals
Enhancing Wearable-App Integration for Fertility Tracking.
Delphea.
AV
Enhancing Wearable-App Integration for Fertility Tracking
Enhancing Wearable-App Integration for Fertility Tracking
Summary:
Summary:
Summary:
Delphea (under Aurelia Vitals) isn’t just another period app. It’s a wearable earring and mobile experience designed to utilize biomedical data and machine learning to predict fertility windows, with the rigor required for FDA clearance. As a founding product designer, I helped transform a rough CSV-export prototype into a scalable product with clear user flows, a design system, and approachable visuals.
Delphea (under Aurelia Vitals) isn’t just another period app. It’s a wearable earring and mobile experience designed to utilize biomedical data and machine learning to predict fertility windows, with the rigor required for FDA clearance. As a founding product designer, I helped transform a rough CSV-export prototype into a scalable product with clear user flows, a design system, and approachable visuals.
6 months (and counting)
My Role:
Product Designer
1-4 Product Designers
1 Marketer
1 Data Scientist
3 Developers
2 Elec Engineers
7 months
My Role:
Product Designer
1-4 Product Designers
1 Marketer
1 Data Scientist
3 Developers
2 Elec Engineers
1-4 Product Designers
1 Marketer
1 Data Scientist
3 Developers
2 Elec Engineers
Results:
89%
of test users reported Delphea would be useful to guide pregnancy planning/prevention choices
6 months (and counting)
My Role:
Product Designer
1-4 Product Designers
1 Marketer
1 Data Scientist
3 Developers
2 Elec Engineers
Case Study Outline:
The Problem
The Problem
→
The Solution
The Solution
→
The Process
The Process
→
Reflection
Reflection
The Problem
The Problem
→
The Solution
The Solution
→
The Process
The Process
Case Study Outline:
The Problem
The Problem
→
The Solution
The Solution
→
The Process
The Process
The Problem:
The Problem:
The Problem:
The Missing Link in Fertility Support.
The Missing Link in Fertility Support.
The Missing Link in Fertility Support.
For women trying to plan or prevent pregnancy, decisions often hinge on cycle predictions that feel unreliable. Irregular periods, missed logs, and confusing data make it difficult to know when to feel confident and when to be cautious. Existing tools often leave users overwhelmed with input requirements or under-informed with vague insights, which erodes trust.
For women trying to plan or prevent pregnancy, decisions often hinge on cycle predictions that feel unreliable. Irregular periods, missed logs, and confusing data make it difficult to know when to feel confident and when to be cautious. Existing tools often leave users overwhelmed with input requirements or under-informed with vague insights, which erodes trust.
Solution Preview→
Research:
Research:
Research:
No existing menstrual cycle tracking app combined FDA-level accuracy with automatic data collection and a friendly user experience.
No existing menstrual cycle tracking app combined FDA-level accuracy with automatic data collection and a friendly user experience.
No existing menstrual cycle tracking app combined FDA-level accuracy with automatic data collection and a friendly user experience.
User interviews (13) →
My team and I conducted 13 interviews in order to investigate the most significant pain points of our target users. We sourced our participants from the Rice community and conducted all but two interviews in person (some were conducted after we started designing). We found that the top priorities for users were cycle prediction and prep, monitoring sexual health, and symptom tracking.
My team and I conducted 13 interviews in order to investigate the most significant pain points of our target users. We sourced our participants from the Rice community and conducted all but two interviews in person (some were conducted after we started designing). We found that the top priorities for users were cycle prediction and prep, monitoring sexual health, and symptom tracking.
Women interviewees with irregular cycles
"I hate logging every day"
"Existing apps are too playful"
Sexually active women interviewees who are worried about pregnancy
"I need more accurate predictions"
Persona 2: Sexually active women who are worried about pregnancy
Persona 1: Women with irregular cycles
"Daily logging is a chore"
"Privacy is a must"
"Existing apps are too playful"
Persona 1: Women with irregular cycles
"Daily logging is a chore"
"Existing apps are too playful"
Persona 2: Sexually active women who are worried about pregnancy
"Privacy is a must"
54%
of interviewees wanted more accurate cycle predictions
Target Users:
Sexually active women who are worried about pregnancy
Women with irregular cycles (where other apps cannot accurately predict their cycle)
Competitor Analysis →
My team and I analyzed 7 apps in depth and 12 total existing solutions for menstrual tracking. We discovered significant issues that these apps were not sufficiently addressing.
My team and I analyzed 7 apps in depth and 12 total existing solutions for menstrual tracking. We discovered significant issues that these apps were not sufficiently addressing.
Requires constant user input
Inaccuracies due to monitoring location.
Only FDA-Cleared birth control app, but still requires manual entry.
Requires constant user input
Inaccuracies due to monitoring location.
Only FDA-Cleared birth control app, but still requires manual entry.
Inaccuracies due to monitoring location.
Only FDA-Cleared birth control app, but still requires manual entry.
Inaccuracies due to monitoring location.
Only FDA-Cleared birth control app, but still requires manual entry.
Our Direction →
How might we give users confidence in cycle tracking through a design that balances warmth and scientific rigor?
Our Direction →
How might we give users confidence in cycle tracking through a design that balances warmth and scientific rigor?
Secondary Research →
After reviewing online forums, published papers, and other sources, my team found that while users want menstrual tracking apps to be accurate and educational, they are often frustrated by non-inclusive designs and inaccurate predictions. We identified a significant lack of data privacy and security as the primary barrier to trust, as many apps share sensitive data, creating legal risks. Full research document here
After reviewing online forums, published papers, and other sources, my team found that while users want menstrual tracking apps to be accurate and educational, they are often frustrated by non-inclusive designs and inaccurate predictions. We identified a significant lack of data privacy and security as the primary barrier to trust, as many apps share sensitive data, creating legal risks. Full research document here
Our Direction →
How might we give users confidence in cycle tracking through a design that balances approachability and scientific rigor?
Our Direction →
How might we give users confidence in cycle tracking through a design that balances warmth and scientific rigor?
How might we give users confidence in cycle tracking through a design that balances warmth and scientific rigor?
Our Direction →
Initial MVP Design Journey:
Initial MVP Design Journey:
Initial MVP Design Journey:
From messy exports to meaningful predictions.
From messy exports to meaningful predictions.
From messy exports to meaningful predictions.
Initial Planning and Ideation →
When I joined, the app flow was clunky: pair device → export CSV → AirDrop to computer→ lose your data because the app deleted it. Not exactly user-friendly. So in order to create a functional app, we started by determining the necessary features, information architecture, and user flow (onboarding and other screens have been left out for simplicity):
When I joined, the app flow was clunky: pair device → export CSV → AirDrop to computer→ lose your data because the app deleted it. Not exactly user-friendly. So in order to create a functional app, we started by determining the necessary features, information architecture, and user flow (onboarding and other screens have been left out for simplicity):
Wireframing →
Given our planning of features, information architecture, and user flow, we began creating lo-fis to begin visualizing our product. We wireframed our home track symptoms, calendar, onboarding, settings, daily log, profile, and more screens.
Given our planning of features, information architecture, and user flow, we began creating lo-fis to begin visualizing our product. We wireframed our home track symptoms, calendar, onboarding, settings, daily log, profile, and more screens.
Home screen has relevant information including fertility
Users can manually track flow level
Home Screen
Users can connect to their wearable
Track Symptoms:
Connection Screen:
Track Symptoms:
Home Screen
Users can manually track flow level
Home screen has relevant information including fertility
Home Screen
Users can manually track flow level
Home screen has relevant information including fertility
Track Symptoms:
Home Screen
Users can manually track flow level
Home screen has relevant information including fertility
How might we provide effective at-a-glance summaries for the wearable's data?→
Home Iterations→
Fertility predictions:
Displaying temperature data:
Sliding bar suggests too much confidence
Clear explanation and prediction
Text is too on the nose and insensitive
No trend visible - hard to interpret
Error bars are information overload
Home Screen
Easy to digest information
How might we effectively display predictions and past data for ovulation and menstrual periods?→
Card and "dot" design
Glowing/Gradient Design
Large Pill and Flat Design
Preview of daily log is helpful but cluttered
the dot symbols are unintuitive
Darkness of ovulation indication seems to indicate a definite prediction
Color coding at the top is helpful but is distracting & not accessible
"glowing" indicators are tacky & hard to develop
Months aren't clearly separated
Ovulation and periods are clearly indicated
Interface is decluttered
Months are clearly seperated
Major Pivot Point:
Major Pivot Point:
Major Pivot Point:
Changing the Visual Identity Based on Initial User Feedback.
Changing the Visual Identity Based on Initial User Feedback.
Changing the Visual Identity Based on Initial User Feedback.
Getting initial feedback →
After the initial high-fidelity prototype was designed, I became the sole UX designer on the project. To validate the work, I tested the designs with users, who consistently described the app as too sterile and, therefore, unlikely to be used regularly. I also found that users consistently did not understand the wearable integration element of the app.
After the initial high-fidelity prototype was designed, I became the sole UX designer on the project. To validate the work, I tested the designs with users, who consistently described the app as too sterile and, therefore, unlikely to be used regularly. I also found that users consistently did not understand the wearable integration element of the app.
80%
Of the 5 test users reported that the app didn't feel welcoming (uh-oh!)
Major visual overhaul →
To address these concerns, I began ideating new ways to show the connected device as well as changing the overall color scheme of the app.
To address these concerns, I began ideating new ways to show the connected device as well as changing the overall color scheme of the app.
Experimented with gradient backgrounds but got feedback that they were too playful.
I added a card for the wearable device in the middle of the screen to make it more obvious.
Experimented with gradient backgrounds but got feedback that they were too playful.
I added a card for the wearable device in the middle of the screen to make it more obvious.
Adapting the Design System →
I changed the color scheme, typography, and components of the design system in addition to changing the layouts of screens like the home screen. I opted for a warmer color palette to adapt to user feedback, straying away from clinical blues while still ensuring that ovulation and period color coding made sense within users' mental models. *Note, these are not the comprehensive design systems
I changed the color scheme, typography, and components of the design system in addition to changing the layouts of screens like the home screen. I opted for a warmer color palette to adapt to user feedback, straying away from clinical blues while still ensuring that ovulation and period color coding made sense within users' mental models. *Note, these are not the comprehensive design systems
Old Design System Preview→
Old Design System Preview→
Old Design System Preview→
Old Design System Preview→
New Design System Preview→
New Design System Preview→
New Design System Preview→
New Design System Preview→
→
80%
Of the 5 test users reported that the app didn't feel welcoming (uh oh!)
Additional Iteration and User Testing:
Additional Iteration and User Testing:
Additional Iteration and User Testing:
Adapting to wearable tech/ML advancements and User testing Feedback.
Adapting to wearable tech/ML advancements and User testing Feedback.
Adapting to wearable tech/ML advancements and User testing Feedback.
User Testing Methodology→
After my initial round of testing (based on feedback from 5 potential users), I conducted an additional 8 user tests, sourced from connections and cold outreach with different users, to validate my redesign.
After my initial round of testing (based on feedback from 5 potential users), I conducted an additional 8 user tests, sourced from connections and cold outreach with different users, to validate my redesign.
Advancements in wearable technology and ML algorithms →
As the wearable’s battery life improved and we learned more about how users should wear the tracker during sleep for accurate predictions, I rethought how the device was represented in the interface. This meant removing a dedicated battery indicator from the home screen and redesigning the flow to support instantaneous data transfer.
As the wearable’s battery life improved and we learned more about how users should wear the tracker during sleep for accurate predictions, I rethought how the device was represented in the interface. This meant removing a dedicated battery indicator from the home screen and redesigning the flow to support instantaneous data transfer.
The Solution:
The Solution:
The Solution:
Tracking temperature for accurate menstrual cycle predictions and other cycle-tracking features.
Tracking temperature for accurate menstrual cycle predictions and other cycle-tracking features.
Tracking temperature for accurate menstrual cycle predictions and other cycle-tracking features.
1
1
1
1
1
Biometric wearable integration →
The app syncs with the new biometric wearable to reduce data entry.
Pending approval to be the only FDA-approved wearable integrated birth control app.
The app syncs with the new biometric wearable to reduce data entry.
Pending approval to be the only FDA-approved wearable integrated birth control app.
Machine Learning Predictions→
The app uses temperature data and other inputs from the wearable to predict fertility levels in users using a machine learning model.
The app uses temperature data and other inputs from the wearable to predict fertility levels in users using a machine learning model.
2
2
2
2
2
3
3
3
3
3
Retained User Input & Logging→
In order to track other factors, such as pregnancy tests or period flow levels, the app also has functionality to input symptoms.
In order to track other factors, such as pregnancy tests or period flow levels, the app also has functionality to input symptoms.
The Result →
of 9 test users reported trust in the app to make fertility decisions.
of 9 test users reported trust in the app to make fertility decisions.
89%
89%
of 9 test users reported trust in the app to make fertility decisions.
89%
Of 9 test users reported trust in the app to make fertility decisions.
89%
of 9 test users reported trust in the app to make fertility decisions.
Reflection and Next Steps:
Reflection and Next Steps:
Machine learning may power products, but design is what makes it usable, credible, and human.
Machine learning may power products, but design is what makes it usable, credible, and human.
Big thanks to my amazing team!
What I learned→
This project reinforced that designing for AI in healthcare tracking is about trust as much as accuracy.
I learned to translate messy biomedical predictions into approachable guidance.
I discovered that designing for new hardware is never “done,” it’s about building for the long term, as hardware constraints are discovered or solved.
What I learned→
This project reinforced that designing for AI in healthcare tracking is about trust as much as accuracy.
I learned to translate messy biomedical predictions into approachable guidance.
I discovered that designing for new hardware is never “done,” it’s about building for the long term, as hardware constraints are discovered or solved.
What I learned→
This project reinforced that designing for AI in healthcare tracking is about trust as much as accuracy.
I learned to translate messy biomedical predictions into approachable guidance.
I discovered that designing for new hardware is never “done,” it’s about building for the long term, as hardware constraints are discovered or solved.
Next Steps →
Next, we plan to conduct user testing with updated machine learning predictions integrated into the interface, allowing us to more holistically evaluate the app’s predictive capabilities. As the wearable evolves beyond temperature tracking, we will also introduce additional health data to broaden insights. Finally, the product will undergo FDA testing as we work toward official approval.
Next, we plan to conduct user testing with updated machine learning predictions integrated into the interface, allowing us to more holistically evaluate the app’s predictive capabilities. As the wearable evolves beyond temperature tracking, we will also introduce additional health data to broaden insights. Finally, the product will undergo FDA testing as we work toward official approval.
Adding more vitals features like heart rate and blood oxygen
Adding more vitals features like heart rate and blood oxygen
Going through the FDA testing process
Going through the FDA testing process
Finishing up development and launching the product!
Finishing up development and launching the product!
Thanks for visiting! You can look through more of my case studies below or reach out to me here.
But Wait, There's More!
But Wait, There's More!
Reflection and Next Steps:
What did this teach me?
What I learned→
This project reinforced that designing for AI in healthcare tracking is about trust as much as accuracy.
I learned to translate messy biomedical predictions into approachable guidance.
I discovered that designing for new hardware is never “done,” it’s about building for the long term, as hardware constraints are discovered or solved.
Next Steps →
Next, we plan to conduct user testing with updated machine learning predictions integrated into the interface, allowing us to more holistically evaluate the app’s predictive capabilities. As the wearable evolves beyond temperature tracking, we will also introduce additional health data to broaden insights. Finally, the product will undergo FDA testing as we work toward official approval.
About Me
@Will Ingersoll 2025
About Me
@Will Ingersoll 2025
About Me
@Will Ingersoll 2025
