Bringing AI into Surgery

Web • AI • Video Analysis • Live Feed Data • LIfe Changing Results

 

Project

The Overview

Insights from Intuitive Surgical and surgeons
As part of the AI for Product Designers course, I studied research from Intuitive Surgical and spoke with surgeons to learn about real challenges in the operating room. My goal was to see how AI can help, not replace, expert decisions in critical surgeries.

The Challenge:

How do we design AI that supports medical professionals without overstepping boundaries or creating dangerous dependencies?

“The AI should never take over. It should support me, not make decisions for me.”
— Gynecologic Oncology Fellow
 

Project

Problem: Most AI tools in healthcare are either distracting or not built with the surgeon in mind. They interrupt, overstep, or don’t adapt to experience level. Surgeons need a tool that quietly supports them—when it makes sense—not one that takes over.

Goal: Design an AI assistant to support surgeons during procedures and provide post-surgical insights—without disrupting clinical judgment or workflow.

 

Designed with AI (and humans)

ChatGPT
Drafted interview questions and generated interaction ideas
Claude
Summarized insights and refined design concepts
Midjourney
Visualized AR overlay concepts for the operating room
Figma
Prototyped interface flows and visual components
Replit
Explored more advanced, interactive prototypes to simulate logic and behavior
UX Pilot
Used to evaluate usability, clarity, and visual hierarchy of early designs
⚕️
Real surgeon feedback
Grounded interaction timing, trust signals, and suggestion tone in clinical expectations
 

Research & Strategic Constraints

3
Academic Research
Analyzed 3 peer-reviewed papers on AI in surgical environments
3
Expert Interviews
Spoke with 3 surgeons about AI integration preferences and workflow requirements
100%
Regulatory Framework
Researched FDA medical device guidelines and HIPAA compliance requirements
 

Solution Overview: two modes of AI assistance:

Surgical Vision Assist - Mode Comparison
Resident Mode: For Training & Learning
Mentor-like Q&A for newer surgeons
Real-time feedback
Builds confidence
Interaction Style:
Conversational, educational, encouraging learning through gentle prompts
Pro Mode: For Expert Surgeons
Subtle tips for experienced surgeons
No interruptions—just helpful summaries
Improves precision and post-op learning
Interaction Style:
Minimal, data-focused, respects expertise and workflow
 

What I designed

  • An AR overlay concept to highlight key anatomy during surgery

  • A clean dashboard for post-op reports with smart insights

  • A toggle for switching modes or turning off suggestions

  • Privacy-first language and optional feedback controls

Key Design Solutions

  1. AR Surgical Overlay

  1. Post-Op Dashboard

  2. AI Control Panel

 

Results & Takeaways

  • Surgeons appreciated the non-intrusive approach and customizable control

  • Learned how to balance AI suggestions with human expertise

  • Designed with trust, ethics, and usability at the center

  • Gained confidence using AI tools to enhance critical UX decision

 

Final product:

 

How we measured success.

  • We had a successful outcome with this project, which we measured through various metrics. We were able to accommodate a significant number of users, about 380,000, with only a minimal increase in customer care calls, and those were only around 120 requests per week related to the new sales tax feature. Additionally, only 3% of users encountered issues with the flow, which indicates a successful design.

  • Furthermore, our analytics showed that users had the most problems with the tax mapping screen, and during user testing, 38% of users clicked on the help links above. These insights helped us improve the design, and ultimately, we were able to create a product that met the needs of our users.

If you would like to learn more about the project and see additional displays and interactions, please let me know. I'm always happy to chat about design.

 

Credits

Deep thanks to Intuitive Surgical for being my primary source of clinical insight and inspiration throughout this project.

Gratitude to Stanford University for providing the ethical foundation and thoughtful frameworks that shaped how I approached AI in high-stakes environments.

And a heartfelt thank-To the three Surgeonss (who will remain anonymous) for their openness, honesty, and generosity in sharing real-world surgical experiences that made this work possible.