# Surgical robots help, but rare procedures lack training data

Markdown copy of https://realalpha.app/s/surgical-robots-help-but-rare-procedures-lack-training-data/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy.

- Speaker: [Fei-Fei Li](https://realalpha.app/builders/fei-fei-li/) · Fei-Fei Li is a professor of computer science at Stanford and AI pioneer. · Co-founded World Labs, whose Marble product generates persistent, high-fidelity 3D worlds from images, video or text.
- Host: [Andrew Huberman](https://realalpha.app/people/andrew-huberman/) · Host, Huberman Lab
- Show: Huberman Lab
- Episode: [Using AI to Increase Your Intelligence & Enrich Humanity | Dr. Fei-Fei Li](https://realalpha.app/v/N5AQFYtqx8Q/), Aug 10, 2026
- Moment: 1:04:34 to 1:07:40 of the episode (3 min), playing on https://realalpha.app/s/surgical-robots-help-but-rare-procedures-lack-training-data/; the episode from there: https://realalpha.app/v/N5AQFYtqx8Q/?t=3874

## Quote

> “Even if you aggregate the world's liver patient surgeries, you might **not have enough data** to train this algorithm.”
> — [Fei-Fei Li](https://realalpha.app/builders/fei-fei-li/) at [1:05:47](https://realalpha.app/v/N5AQFYtqx8Q/?t=3947) · Huberman Lab

## Takeaways

1. Liver surgeries vary, and there may be too few cases to train an AI.
2. A human surgeon controlled the robot during her father's operation.
3. The robotic surgery resulted in ten times less blood loss.

## About this segment

Fei-Fei Li recounts her father's robot-assisted liver surgery and why the surgeon doubted AI could learn the procedure from existing cases. Sparse data makes human-robot collaboration more reliable than autonomy.

From “Using AI to Increase Your Intelligence & Enrich Humanity | Dr. Fei-Fei Li”, Aug 10, 2026. [Watch the full episode](https://realalpha.app/v/N5AQFYtqx8Q/)

## Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

[1:04:38](https://realalpha.app/v/N5AQFYtqx8Q/?t=3878) a very interesting example, you know, that we have to reschedule this, our conversation, because my father was going through a surgery, right, at Stanford with an incredible surgeon. But the surgery was done by a robot, the Da Vinci robot system, because it was a liver surgery, and the surgeon, the incredible surgeon, was driving. the robot. So it was a deep human-machine collaboration. After the surgery, I asked the surgeon, I said, do you imagine if, say you've done a million, which is impossible for a surgeon, but a human surgeon, but let's collect all of human surgeons for this liver, this type of liver surgery data. Can we possibly train an automatic AI to do this? The answer was not clear. So we went a little bit down the rabbit hole because liver is a very complicated organ. It's extremely

[1:05:38](https://realalpha.app/v/N5AQFYtqx8Q/?t=3938) vascular. It has a lot of vessels and everybody's liver is very different. So given the reality of how many patients undergo liver surgery per year. Even if you aggregate the world's liver patient surgeries, you might not have enough data to train this algorithm. So this speaks of a very important fact that AI learns from patterns. When the patterns are not abundant, then we have to be careful. We have to know how to use AI or how not to use AI. You know, in this case, that having a human collaborating with the robot is way better than an under-learned robot doing the surgery by itself. But the same issue might be true for surgeons, because how many surgeries a surgeon can get trained on? So these are opportunities that humans and AI can totally collaborate with and might reveal the best result, right?

[1:06:42](https://realalpha.app/v/N5AQFYtqx8Q/?t=4002) Now, the future remains to be seen. Can we create an artificial simulation of a liver that we can now train infinite possibility? These are all incredibly open scientific possibilities that is waiting ahead of us. But then there are situations like your situation where the vertigo versus low blood pressure probably have been reported so many times that in the database, there's enough of that, that AI has learned that. So we can then now take advantage of that for people who don't have immediate access to doctors. Amazing. Your father's surgery went okay?

[1:07:24](https://realalpha.app/v/N5AQFYtqx8Q/?t=4044) It did. I'm happy to hear that. He lost 10x less blood. than a typical surgery, thanks to the laparoscopic capability of a robot surgery.