Homni Stroke Detector

Improving Human-AI Diagnostic Experience

Project Overview

Problem

Homni is an AI-assist stroke detection tool aims to improve stroke diagnostic efficiency and accuracy for various medical professionals. Upon I join the team, the product is undergoing a pilot testing process for the UX of the product with wizard of oz on the AI part. While AI accuracy is not the concern at this stage, the efficiency of the tool, however, has been questioned by stroke experts.

Solution

My goal is to understand how various medical professionals naturally integrate this tool into their workflows. By gaining this insight, we aim to offer a redesign that assists in reducing the time it takes for medical professionals to assess stroke symptoms.

Impact

- Exam completion time decreased by 10 mins.

- Started a research project that is forming collaboration between cross-universities stroke centers.

How can we make medical professionals feel supported by Homni AI to improve stroke diagnosis efficiency?

Explore The Problems

Interview+Usability Testing: Mismatch between users’ natural workflow and current functions.

  • Methodology: I conducted 6 rounds of combined interviews and usability testing sessions with six stroke-related experts, including neurologists from clinical settings and Emergency Medical Technicians (EMTs) who handle stroke emergencies. We initiated our outreach by sending cold mails through LinkedIn and leveraging our team members' personal networks.

  • Process: During these interviews, we asked about their perspectives on AI-assisted diagnostic tool and presented a brief demonstration of the Homni stroke assessment flow to gain their feedback. Additionally, we inquired about their experiences with assistive technology and their collaboration with other professionals in stroke diagnosis.

==>The users has clearly different type, and we didn’t design toward this. The target user is unclear.

==>Different users have different workflow when it comes to assess stroke symptoms, and the current design did not fit naturally into the real-world workflow.

==>Experts pointed out that in real world not only stroke specialists would deal with the patients, but a lot other medical professionals from other department, and suggest us considering the big hospital picture.

Persona&Lit Review: Refocus The Users

  • After the interview with the stroke experts helped us find the wicked problem, I choose to conduct secondary research to better understand the users.

  • 15 interview/short question data from UCSD hospital and medical campus showed 80% of medical professionals’ stroke related workflow shifting back and forth from urgent and non-urgent. While the current design only provide a fixed workflow.

  • Literature shows that diagnostic decision aids technology better help the less experienced medical professionals. 

  • Notes: While I revisit this procedure, I think we should use field study to observe their natural workflows.

Usability Testing: Go into the details.

  • After we reassure the users of the Homni, I conducted usability testing to see how the current design fits in their workflow and what can be improved.

Experimental Study: Medical Human-AI collaboration pattern across expertise. (Ongoing and became a new project)

  • In our recent usability testing, I observed a trend where users with varying levels of expertise displayed distinct preferences in their interactions with AI. This observation has piqued my curiosity about the specific nature of these patterns. Understanding them could significantly enhance our design of AI-assisted technology. To delve deeper into this matter, we need to develop an experimental study. With this in mind, I have discussed the idea with the team and initiated a new research project.