LVIS Corp.

NeuroMatch

EEG Analysis and Detection Software

[AUG 2020 - JUN 2024] [Remote] [UX Design]

What is it?

NeuroMatch is a medical software capitalizing on the cloud, big data, and machine learning to identify neurological patterns in EEG (Electroencephalogram) data to produce models that help physicians diagnose brain diseases.

Why is it needed?

The time-consuming nature of reading EEG creates a significant road block to efficient, accessible neurological care. The NeuroMatch reading interface, detection tools, and trend models help doctors find the needle in the haystack within patient data to support diagnosis faster with greater accuracy.

How did I contribute?

As a junior UX designer while NeuroMatch was in alpha stage I worked under the design lead to help develop the design system and interface during user research and competitor analysis.

• Analyzed user studies to produce profiles that informed design decisions
• Created components, layouts, wireframes, and prototypes in Figma
• Managed and maintained the design library
• Performed user interviews with technicians and physicians
• Worked with product manager, engineers, and science team to develop design requirements
• Provided feature design proposals to project and science teams

Tools:

• Design: Figma, Zeplin
• Image: Photoshop, Illustrator
• Video: AfterEffects, PremierPro, Frame.io
• Project Management: JIRA, Confluence

Case Study: NeuroMatch

Problem Identification

• Delayed diagnoses due to lack of biomarker-based precision
• FDA compliance hurdles preventing modern software/hardware updates
• High cognitive burden from multi-system workflows
• Use of separate software for records, EEG viewing, analysis, and reporting
• Proprietary EEG tools from different hardware vendors with outdated UX
• Custom hospital workarounds resulting in inefficient manual workflows

User Discovery and Role Analysis

• Conducted interviews and observations to understand role-specific workflows
• Mapped overlapping responsibilities, workflow stages, and pain points
• Identified unique user types: Monitor, Technician, Physician

Design Direction and Strategic Focus

• Establish seamless transitions between reading and reporting
• Prioritize clarity of user contributions and work ownership
• Leverage online accessibility for transparency and collaboration
• Built workflow diagrams to align Design, Development, and Science teams

Testing and Iteration

• Created interactive prototypes in Figma based on real user workflows
• Focused on signal visualization, annotation, and report editing flows per role
• Ran validation sessions with hospital staff across multiple iterations

Results and Impact

• Reduced tool-switching across roles
• Increased clarity of roles and user ownership in report flows
• Reduced apprehensions around AI-driven tools through transparency

Reflection

This project taught me how to design within a highly complex technical field under strict regulatory systems while keeping the user experience focused and efficient.