My Youthspan

Project

My Youthspan

My role

Product Designer & Researcher

Location & year

Remote, USA - 2025

MyYouthspan
Designing trustworthy AI-powered health predictions for everyday users.
Objective

An exercise in predictive healthcare and behavior-driven design | To explore how AI-generated health predictions can be translated into understandable, trustworthy, and actionable guidance by helping users connect everyday habits and recovery patterns to long-term health outcomes and biological aging.

My Role

UX Design

Research

System Design

Prototyping

Tools

Figma

Miro

Photoshop

Illustrator

Duration
Research
8 weeks
Prototyping
4 weeks
The Challenge
Health data is growing. Understanding is not.
As AI-generated health predictions become more accessible, people are gaining access to increasing amounts of personal health data without understanding how to interpret it. Most systems still rely heavily on disconnected scores, complex analytics, and static reports that fail to explain how everyday behaviors influence long-term health outcomes. The growing complexity of AI-driven health data is making it increasingly difficult for users to understand what changes in their health actually mean, what habits matter most, and what actions can positively influence their long-term trajectory.
72% of Users Struggle to Interpret Health Data
Most users can see changes in their health scores but do not understand what behaviors are influencing those changes.
Health Feedback Can Become Emotionally Overwhelming
Risk-heavy messaging, dense analytics, and optimization-focused experiences can create anxiety instead of actionable guidance.
AI Health Platforms Often Lack Explainability
Many predictive health systems surface scores and projections without explaining confidence, contributing factors, or behavioral impact.
Long-Term Health Data Feels Disconnected From Daily Behavior
Users often struggle to connect everyday habits, recovery patterns, and lifestyle decisions to long-term health outcomes and biological aging.
How might we
Help users better understand and take action on long-term health predictions without overwhelming them with complex analytics, disconnected scores, and emotionally discouraging health feedback?
The Solution
A behavioral health guidance system.

MyYouthspan is an AI-powered health intelligence platform focused on helping users better understand how daily behaviors influence long-term health outcomes.

By translating complex health predictions into more understandable and actionable guidance, the platform connects recovery patterns, lifestyle behaviors, and biological aging insights to a calmer and more transparent health experience, helping users make more informed long-term health decisions without feeling overwhelmed by data.

Key Features
Designed around understanding, not optimization.
01
Predictive Health Dashboard
A trajectory-based health dashboard translating long-term health predictions into more understandable daily guidance through behavioral patterns, recovery insights, and biological aging trends.
02
Lifespan & Health Assessment Calculator
An interactive onboarding experience helping users better understand how lifestyle behaviors, recovery habits, and health patterns influence long-term health trajectory and projected biological aging.
03
Explainable Predictions & Behavioral Insights
The platform explains which behaviors are influencing recovery, stress, cardiovascular resilience, and long-term health outcomes — while tracking how daily sleep, movement, and stress patterns are shaping overall health trajectory over time.
04
Confidence-Aware Health Guidance
Prediction confidence is surfaced throughout the experience to help users better understand how health projections are formed and how reliable different health insights are over time.
05
Real-Time Watch Companion
A lightweight Apple Watch companion providing recovery awareness, stress detection, behavioral nudges, and real-time health guidance throughout the day.

Research insights

User interviews revealed that people did not reject AI-generated health predictions. They rejected predictions they could not understand.

Users consistently wanted:

  • visibility into what influenced their results

  • clearer explanations behind recommendations

  • feedback connecting daily behavior with long-term outcomes

Design Principles

From the research, we defined three principles that guided the product experience:

Research & Findings

User interviews revealed three consistent patterns:

People wanted clarity over complexity

Users cared less about technical medical outputs and more about understanding:

  • what influenced their results

  • what actions could improve outcomes

  • whether their habits were making progress

Trust depended on transparency

Users distrusted predictions without explanation.

They wanted visibility into:

  • what data influenced results

  • how recommendations were generated

  • how confident the system was

Long-term health felt emotionally distant

Many users struggled to stay engaged with traditional wellness apps because results felt disconnected from everyday behavior.

Simplifying complex health predictions

We worked closely with engineering, PMs, and medical teams to translate predictive health models into understandable user experiences.

The platform simplified complex outputs into:

  • progress-based health indicators

  • actionable feedback systems

  • explainability patterns

  • behavior-driven recommendations

This helped users better understand how everyday habits could influence long-term health outcomes.

Prototyping, Testing & Iteration

To align the structure with user needs and the technical realities of the AI model, we held several rounds of feedback with the product manager, engineers, and medical advisor. Each iteration refined how data, predictions, and insights connected, creating a clearer and more trustworthy experience.

First round of user testing and iteration

Problem


The original output from the AI model used a Kaplan Meier survival curve a statistically accurate but highly technical visualization. During testing, users described it as “intimidating,” “too scientific,” and “hard to connect to my daily actions.” The linear, probabilistic graph felt abstract and fixed, making users perceive lifespan as a static outcome rather than something they could influence.



Solution


We redesigned the visualization to make predictions feel understandable, dynamic, and empowering. The survival curve was replaced with a progress ring that displayed projected healthspan change and top influencing factors such as sleep, exercise, and stress. Confidence ranges were visualized subtly in the background, turning uncertainty into clarity.


The result transformed a complex statistical model into a human-centered feedback loop, helping users see how small actions could meaningfully extend their healthy years.

Problem


Landing Page — First Impression
Early usability testing revealed that the original landing page (left) felt heavy and marketing-focused. Users struggled to understand what MyYouthspan actually did beyond selling plans. The scientific foundation and simplicity of starting were buried under long scrolls and dense visuals.

Solution

The redesigned version (right) streamlined the structure around clarity and motivation. The hero section now communicates why MyYouthspan exists — “Live longer. Get healthier. Feel better — starting now.” Core benefits and steps to get started appear above the fold, reducing cognitive load.


Users reported stronger trust and comprehension in the first 10 seconds of viewing. Scroll depth increased by 42%, and 60% of users said the platform “felt more credible and science-based.”

Landing Page — A/B & Accessibility Testing

We conducted A/B testing on two landing page layouts to evaluate clarity, engagement, and perceived trust. The updated design performed significantly better, with users reporting that it felt more science-driven and easier to navigate.

In addition, accessibility testing with senior users helped refine font size, color contrast, and visual hierarchy, ensuring readability and ease of interaction across all age groups.

Outcome

MyYouthspan translated complex AI-generated health predictions into more understandable and actionable consumer experiences.

The project established:

  • explainability patterns for predictive health AI

  • clearer systems for uncertainty visualization

  • behavior-driven health tracking experiences

  • stronger trust around AI-generated recommendations

What did users mention in the final user testing?

“It finally feels like an AI that explains itself, not just predicts.”

“This gives me control. It’s not guessing my future, it’s helping me shape it.”

MyYouthspan positioned Mety Technology as a credible player in longevity and health intelligence, bridging advanced predictive modelling with everyday decision-making for healthier living.