A decision support tool for physicians

Built on a knowledge graph connected to a medical database, a tool that helps doctors diagnose their patient based on symptoms.

Client
RecoverX
Sector
Healthcare, clinical decision support
Role
UX UI, User Research, Design System
Focus
EMR companion tool, Usability testing, Dark and light themes
Year
2021
ServicesProduct redesignDesign systemsDashboard design

Diagnostic Glass

Diagnostic Glass is a decision support tool for physicians. It helps doctors diagnose a patient from the symptoms captured during a visit.

It's built on a knowledge graph connected to a medical database, and it works alongside the clinician's EMR (electronic medical record).

RecoverX Diagnostic Glass shown on a laptop over an electronic medical record
3
Personas
Specialist, general practitioner and telehealth-only doctors
2
Themes
Dark and light, A/B tested with clinicians
AA
Accessible colors
The focus of the new design system's palette

Diagnostic errors are the most common, costly and catastrophic of medical errors

RecoverX wanted to change this by giving clinicians a decision support tool that works with their EMR.

Information overload

It's hard for clinicians to stay up to date on diseases they don't often treat (there are 100k identified human diseases), and on the latest tests and treatments.

Limited time

Clinicians are often overbooked and have limited time with each patient. They're usually late to a visit and rushing to get to the next one.

Complex UI

The EMR has a very cluttered UI and complex navigation, and often frustrates clinicians.

UX isn't linear, and neither is our process

Research and validation are critical, but they can happen at different points. For this project, we started by combining user interviews with usability testing of the existing application. From what we heard, we created personas and user flows, and proposed the most serious usability issues to address.

We studied EMRs and what physicians expect when working with one, as well as competitor tools. We then designed wireframes and A/B tested prototypes with different variations: the UI on the right and at the bottom, in light and dark themes.

RecoverX didn't have a visual language or a design system, so we created both.

  1. EmpathizeCombined user interviews with usability testing of the existing app.
  2. PrioritizeBased on the usability testing feedback, helped the client prioritize the issues to fix.
  3. Document and ideateCreated personas and user flows based on the sessions.
  4. Competitor researchResearched similar apps: what they do well and badly, and what users complain about.
  5. DesignCreated wireframes and visual design to address usability issues and roadmap features.
  6. PrototypeCreated workable prototypes based on the users' needs and documented use cases.
  7. ValidateA/B usability testing to gather feedback and iterate on the designs.
  8. Rinse and repeatIterated on the design, created high-fidelity visual designs, and tested again.

Three kinds of doctor, three sets of expectations

We found that a specialist, a general practitioner and a telehealth-only doctor all expect different things when diagnosing a patient.

The most common user type was the general practitioner. The one with the highest risk of getting a diagnosis wrong was the specialist.

Persona photo for Dr. Shiv
Physician
Dr. Shiv
Cardiologist, works in a clinic

Dr. Shiv is a specialist who works in a clinic. He wishes it was easier to research differentials during and after patient visits. He typically uses UpToDate, but it's very text heavy, and he wishes there was a resource with brief overviews or criteria tables. He'd also like to know whether a treatment, medication or test is the gold standard and reflects the most recent research.

“I want to search for differentials more easily.”
“Right now, if I type something in, it might give me something, but more likely it'll show me this big list of things and I'll need to go through it to find what I'm looking for.”

Motivations

Diagnosing correctlyOrdering tests quicklyEnough time with patientsCompleting notes on time

Goals

  • An easy-to-read resource
  • Brief overviews of differentials and treatments
  • An easier search process
  • Ability to filter by body systems
  • Recommendations based on gold standards and new research

Frustrations

  • Struggles to read text-heavy resources during a patient visit
  • Mental load: sometimes has to dig deep in the search results to find what he's looking for
  • Finding system-specific differentials can be challenging
  • Can't currently search by symptoms
  • Difficult to learn of new methods, treatments and tests

A dark theme, so the tool stands apart from the EMR

Most EMRs come only in light mode. The original Diagnostic Glass was light as well, and there wasn't enough contrast between the two, which made it hard for a clinician to tell them apart. We proposed a dark theme, and updated the light theme too.

The app follows the default setting on the clinician's computer, with the option to change themes in settings.

Before
The original Diagnostic Glass design, in light mode over a light EMR
OriginalLight on a light EMR. Not enough contrast to tell the two apart.
After
The updated Diagnostic Glass design in the dark theme
Dark themeStands apart from the EMR behind it.
The updated Diagnostic Glass design in the light theme
Light themeUpdated too, for clinicians whose computers are set to light.

Design system

Building consistency through components. RecoverX did not have a design system, so we created a modest one to start with. The focus of the colors was to be AA accessible.

RecoverX design system components in dark and light

Dense on purpose

After usability testing the original version and applying usability heuristics, we designed the next version in dark theme, to increase the contrast between the EMR and the UI.

The designs carry a lot of information, because clinicians are not typical consumers. They're power users who want as much information as possible without having to interact with the UI. They're multitasking: talking with the patient, processing what they say, asking questions, writing the note in the EMR, and thinking about what the diagnosis could be.

Each screen answers the questions a doctor like Dr. Michelle, a cardiologist, has at that point in the visit.

Differentials and vitals

  • What could these symptoms together mean for this patient?
  • What else do I need to ask the patient in order to provide a more confident diagnosis?
  • How have this patient’s vitals changed over time? Can this be related to the symptoms that brought them in today?
Dr. MichelleCardiologist
RecoverX differentials and vitals screen in dark theme

Differential, expanded view

  • I’m not familiar with this differential. Tell me what I need to know.
  • What are the non-negotiables (criteria) for this differential to be the right one?
  • What is the recommended treatment?
  • Why does the system think the patient has this disease?
Dr. MichelleCardiologist
RecoverX expanded differential view in dark theme

Order tests

  • What tests do I need to order to confirm this differential is the right one?
  • I’d like to order tests easily. The EMR can make it really difficult to do so.
Dr. MichelleCardiologist
RecoverX order tests screen in dark theme

Read another case study

More selected work across enterprise AI, complex internal systems, and consumer fintech.

↑ Back to top