Flo is the #1 women's health app worldwide. Over 300 million people around the globe use Flo as their ovulation and period tracker app, fertility calendar, and pregnancy assistant.

The project required close collaboration between various departments, including Product, Medical, Legal, Marketing, and Engineering. The Product team comprised a Product Designer (myself), Content Designer, Product Manager, and UX researcher.

Sexual and reproductive health conditions are common, but hard to diagnose. Endometriosis, uterine fibroids, and polycystic ovary syndrome (PCOS) impact a significant number of women and individuals who menstruate globally, with estimates ranging from 5% to 40% of reproductive-age women. Currently, it can take up to 12 years to diagnose these specific conditions, subsequently contributing to health complications and increased healthcare costs.

For users: they can learn how to manage their risk of common conditions. For business: position Flo as a health partner rather than just a period tracker and tangible new value for users.

During the discovery phase, we explored the topic and created a simplified version of the feature as a proof of concept. This early version became our starting point for further design and research. The design process involved numerous iterations and user testing. Once we had a clear vision, we established priorities for iterative development and tested each increment internally. Finally, when we launched the first public version, we measured metrics and listened to user feedback (spoiler: the result was great!).

Such a project is not an easy thing to do taking into account potential risks when it comes to people's health. So while doing discovery research, and diving deeper into the topic, we created a very simplified (and quite straightforward) first version of the Symptom Checker. The main goal was to prove that we could actually build a product like this and it was possible to implement such an algorithm. And it worked!

Then based on the initial version, its user testing results, and findings from the discovery we started mapping the user journey to find out opportunities for the best experience.

This step included an enormous number of ideas and design iterations for every single piece of experience: first touch and entry points, assessment and its results, symptoms list and statuses, a user needs specific scenarios, etc. And to make sure we were going the right way we were running user testing to validate our hypotheses and ideas.

The Symptom Checker's primary access point is the widget located on the Today screen. It acts as a crucial indicator of the current status, alerting users to potential issues by analyzing and interpreting the data they've submitted related to cycles and symptoms.

The initial version of the Symptom Checker screen featured a list of assessments for users to take. Despite its simplicity, it effectively demonstrated the Symptom Checker's capabilities and provided a comprehensive overview of the status of assessments, including cases where a user could be diagnosed with a specific condition.

On this page, we offer users a self-assessment to understand certain signs and symptoms they may be experiencing, along with guidance and next steps.

So here users can read about conditions in detail (about, causes, and treatment), see the symptom checklist, get education from the Flo library, and connect with others in the Flo community. All of these support users in their awareness, education, and social journeys.

Finally, a promo story was designed to support the launch of the Symptom Checker. We tested several options of storytelling before finding the best way to catch users' attention and explain the value.

After launching the Symptom Checker, we completed our quarter's OKR in just two weeks, confirming the value the feature provides to our users.

A brand new Flo Health study, published in the JMIR mHealth and uHealth journal, has identified solid accuracy levels for Flo’s groundbreaking Symptom Checker feature, signaling an exciting step towards helping reduce time to diagnosis for conditions like polycystic ovary syndrome (PCOS), endometriosis and uterine fibroids by educating users. Symptom Checker feature is not intended to be used for diagnosis or treatment, but only for education and providing information.

To test its Symptom Checker, Flo’s Science team recruited multiple panels of general practitioners, independent from Flo. Separate panels of independent GPs then created clinical case vignettes of simulated patients, classified them for each condition, and entered the symptoms of each case into the Symptom Checker. Finally, the output of the Symptom Checker was compared to the designation from the independent GPs for each vignette case and the results indicated very high levels of agreement at 83–88%, which implies a solid level of accuracy.

Reference: Flo Health blog post