Your Lung Map Is a Week Old: Evelyn Chang on AI in Medical Robotics, Robotic Bronchoscopy, and Clinical Engineering

A doctor guiding a scope into your lung is often working from a CT scan taken a week earlier. Your body has moved since then. Your breathing moves it again during the procedure. That gap — between the map and the body it claims to describe — is the entire problem AI in medical robotics is trying to close.

Evelyn Chang is a senior clinical engineer at Noah Medical, working on the Galaxy system, a robotic platform built to navigate the outermost edges of the human lung and biopsy nodules early. Her path there ran through Yellowstone fieldwork, a NASA data science role, operations and logistics work in Singapore, and an IEEE conference stage at seventeen. In this episode of Still Human, the biweekly podcast from Oshen Studio, Evelyn and host Perkin Yang talk about what robotics actually fixes, where AI is already doing real work in medicine, and what stays human when the tool gets better than the hand.

Key Themes Covered in This Episode

• Why manual bronchoscopy loses precision and real-time position, and what robotics actually fixes
• How a live fluoroscopy sweep gets reconstructed into 3D to confirm where the scope is right now
• Where AI is already doing real work in medicine, and where a clinician still has to confirm
• What a clinical engineer actually does on a Tuesday — translating physician needs into design inputs
• Why patient trust before and after the procedure may matter more than the procedure itself
• Systems thinking as a career, and why medical devices adopt new technology slowly

Systems Thinking, and a Career Built Sideways

Evelyn's route into medical devices doesn't read like a straight line, and that's the point. Yellowstone fieldwork taught hands-on problem solving. A NASA role during COVID-19 put her in front of massive satellite datasets. Operations and logistics work in Singapore added a different kind of scale. She presented research at an IEEE conference at seventeen. What connects them is a habit of looking at the whole system rather than the component in front of her — which turns out to be most of the job in medtech, where cross-functional teams are the unit of work.

The Galaxy System and the Problem With the Lung

Nodules at the periphery of the lung sit at the end of narrowing, branching airways. Reaching them early is where diagnosis gets hard, and it's the specific problem Noah Medical's Galaxy system is built for. Evelyn walks through why the anatomy makes this difficult and what a robotic platform changes about the reach.

Manual Scope vs. Robotic Precision

The comparison Evelyn draws is concrete: a manual scope loses precision and, more importantly, loses real-time position — the operator is inferring where they are from a picture that predates the procedure. Robotics restores that. A live fluoroscopy sweep is reconstructed into 3D during the case, confirming where the scope actually is at that moment rather than where a week-old scan suggests it should be.

Where AI Works, and Where a Human Confirms

Evelyn is precise about the boundary. Image recognition is already doing real work inside the loop — surfacing and flagging what matters. What it does not do is close the loop alone. A clinician still confirms. She frames that not as a gap waiting to be engineered away but as the correct design for the stakes involved, and part of why medical devices adopt new technology slowly.

A Day in the Life of a Clinical Engineer

It's one of the less legible roles in medtech. Evelyn describes the actual Tuesday: sitting between physicians and engineers, translating clinical needs into design inputs that a team can build against. She makes the case for why clinical engineering is crucial to medical device development, and why the field is growing.

Designing for Human Perception

The last stretch of the conversation turns to interface design — how 3D imaging gets presented so a human can actually read it under pressure. Visual feedback is not a cosmetic layer on top of the robotics; it's where the system either meets human perception or fails to.

The Part That Isn't Technical

Before a procedure and after it, someone talks to the patient. Evelyn suggests that trust may matter more than the procedure itself — and that a team optimizing a robotic platform should treat that conversation as part of the system it's building, not as something outside it.

Show Notes

Evelyn Chang is a senior clinical engineer at Noah Medical working on the Galaxy system, a robotic platform designed to navigate the outermost edges of the lung and biopsy nodules early. Her background spans Yellowstone fieldwork, data science at NASA, operations and logistics work in Singapore, and an operations research degree — a range that shows up in how she reasons about the whole system around a device rather than the device alone. In this conversation she explains what robotics fixes about bronchoscopy, where AI has earned a role inside the procedure, and which steps should stay human.

Tools & Resources

• Noah Medical Galaxy System — The robotic bronchoscopy platform Evelyn works on — noahmed.com
• Live fluoroscopy → 3D reconstruction — The approach that replaces a week-old CT scan with a real-time picture of where the scope actually is
• Human-in-the-loop decision making — The design pattern behind image recognition that assists rather than decides

Related Still Human Episodes

Builders working where technology meets the human body:

• Will AI Replace Doctors? Ewen Huang on Causal AI, CRISPR, and What Medicine Can't Automate — oshenstudio.com/episode/will-ai-replace-doctors-ewen-huang-causal-ai-medicine
• Building AI for Human Connection: Neil Gawande on Belonging, Perception, and Five Companies by 20 — oshenstudio.com/episode/neil-gawande-building-ai-human-connection
• Still Human? The Bioengineer Building the Technology of Tomorrow — Michael Iwashima on Brain-Computer Interfaces — oshenstudio.com/episode/brain-computer-interfaces-michael-iwashima-ai-limits
• William Norden: Building Neural Networks from Scratch in C and What Most AI Engineers Skip — oshenstudio.com/episode/neural-networks-from-scratch-c-william-norden-neuromorphic-computing

About Evelyn Chang

Evelyn Chang is a senior clinical engineer at Noah Medical, where she works on the Galaxy robotic bronchoscopy system. Before medical devices she did fieldwork in Yellowstone, worked with large satellite datasets as a data scientist at NASA, and did operations and logistics work in Singapore; she presented research at an IEEE conference at seventeen. That range is the point: she treats a surgical robot as one component inside a larger system that includes the clinician, the patient, and everything that happens in the room before the procedure starts.

Listen to the Full Episode

Listen to the full conversation on Spotify, Apple Podcasts, or YouTube. Or read the full transcript on Substack.

Connect With Evelyn Chang

• Watch the episode: youtube.com/watch?v=C4pxqtYIC9M

Follow Still Human Podcast

Still Human is a biweekly podcast by Oshen Studio, hosted by Perkin — exploring what it means to stay human in the age of AI. Real conversations with builders, creators, founders, and thinkers doing it in real life. New episodes every two weeks on YouTube, Spotify, Substack, and LinkedIn.

• YouTube: youtube.com/@Oshen.studio
• Instagram: instagram.com/perkin0909
• Listen everywhere: Search Still Human Podcast on Spotify, Apple Podcasts, or wherever you listen

New episodes drop every two weeks. Subscribe so you never miss a conversation.