Echo
AI-powered clinical trial matching made transparent and safe, through a workflow-driven system for defining, visualizing, and executing eligibility criteria with cohort-level insight.
- Role
- Lead Product Designer & Front-end Engineer
- Timeline
- 2024–2026
- Focus
- AI explainability · Clinical workflows · Visual analytics
- Outcome
- A clearer way to inspect eligibility logic, compare cohorts, and understand AI-generated decisions.
About this work
Echo is an AI-assisted clinical-trial-matching system developed within biomedical AI research at the Yale School of Medicine, Department of Biomedical Informatics and Data Science. The work has progressed from Cohort Visualization (2024) and Workflow Redesign (2025) to Visual Steering and Study Variable Chart Review (2026). Across these projects I have led interface design, visual encoding decisions, and frontend implementation.
Echo: Cohort Visualization
Exploring large-scale patient cohorts through interactive, data-driven visualizations.
Echo: Workflow Redesign
Redesigning clinical trial matching workflows to make eligibility logic transparent and safe to execute.
Echo: Visual Steering for AI-Assisted Cohort Construction
An interactive visual analytics system for constructing, inspecting, and comparing EHR cohorts through AI-assisted SQL generation and coordinated views.
Echo: Study Variable Chart Review
Optimizing patient-level evidence review across study variables without changing the underlying clinical data.