Submitted 8 months ago by Pro@programming.dev to technology@lemmy.world
https://hub.jhu.edu/2025/07/09/robot-performs-first-realistic-surgery-without-human-help/
A robot trained on videos of surgeries performed a lengthy phase of a gallbladder removal without human help. The robot operated for the first time on a lifelike patient, and during the operation, responded to and learned from voice commands from the team—like a novice surgeon working with a mentor.
The robot performed unflappably across trials and with the expertise of a skilled human surgeon, even during unexpected scenarios typical in real life medical emergencies.
you could not pay me enough to have my surgery done by a robot
I trust a good machine much more than any human.
Have you considered that the machine is made by a collection of humans?
They obviously don’t feel comfortable with the robot doing surgery on humans just yet either which is why they’re not actually suggesting doing that yet. It will have to go through years and years of certification before that’s even considered.
I’m sure most surgeries will still be conducted by humans but there are situations where one of these would be extremely helpful. Any situation where a surgeon isn’t currently accessible and can’t quickly get there. Remote communities, Disaster relief, Arctic research facilities, Starships trapped in the Delta quadrant, War zones, Ships at sea.
Do you think a 5 bed hospital will have the money to afford a robotic surgeon?
yeah, it’s much better to have a towel left inside of you by a real human.
If it were the only option, I’d gladly take it.
I rely on robots to do a lot of other things in my life, directly and indirectly.
Well, not many directly. But machines, definitely.
Yeah it’s not like I refuse to drive my car because it wasn’t handcrafted by a human.
It is an electrical fault on four wheels, but that’s just because it’s old.
Not fair. A robot can watch videos and perform surgery but when I do it I’m called a “monster” and “quack”.
But seriously, this robot surgeon still needs a surgeon to chaperone so what’s being gained or saved? It’s just surgery with extra steps. This has the same execution as RoboTaxis (which also have a human onboard for emergencies) and those things are rightly being called a nightmare. What separates this from that?
Human flaw. A surgeon doesnt require steady hands. So if they were in any way damaged they could still continue being a surgeon.
It can’t sneeze
So… Judging by recent trends in AI, this will be used to devalue the labor of surgeons and be provided as the only option available to people who are not rich. People will die from what would get a human charged with neglegent homicide but, it will be covered up and, when it comes to light just how dangerous it is, nothing will happen because all of the regulatory agencies have been dismantled.
Outside of the US there are pretty stringent rules about what can and cannot be used in the medical profession. Typically it will take at least a decade for a drug to be approved, which is actually a problem in and of itself, but you’re not concerned about that, you’re concerned about technology being used before it’s ready.
As for “devaluing the work of surgeons”, surgeons are overworked as it is, there is nowhere near enough of them. If they don’t have to do simple procedures then they are available to do the more complex surgeries that actually require skill. They’ll be fine. Wealth isn’t really a factor in countries where healthcare isn’t profit motivated.
OR maybe everyone — including the poor — will eventually have access to robotic surgeons with the equivalent of like 500 human years of experience, but with the latest surgical best practices that have only existed in recent years. The experience gained by a single surgery could be shared across all of them.
We’re talking about surgery. If some technology can provide significantly more valuable labor than its human counterpart (which, in this case, could mean more lives saved), then it might actually be worth exploring.
That would be wonderful. The current way that the world has been “working” for a good while now makes me think it unlikely, unfortunately. The vast majority of technological innovation in the last half-century has been used to extract wealth and replace options available to the non-ultra-wealthy with inferior substitutes that are cheaper to make, often for the same effective cost.
I would rather get surgery done by a robot than not get it done at all. I’m not gonna be picky about “devaluing surgeons” if my life is on the line, but if that’s the hill you wanna die on then good on ya, mate.
Who’s dying on what hill now?
so theoretically they could make sex bots and train them on… so they perform ‘unflappably’!
You can already get AI strokers that apparently sync to videos.
This was a new word for me, so I had to look it up: It’s an… interesting choice of words to describe the success of a robot.
Of course a robot would perform the job unflappably, it is emotionless by design. I’m pretty sure it would go right ahead and murder the patient unflappably as well. The robot “keeping its cool” is not even a question.
That said, this does sound very impressive, even if I think there’s some pretty crazy risks involved. Hopefully they have more respect for the problem then self-driving car companies.
I, too, think they weirdly personified
It does until it doesn’t
“OMG it was supposed to take out my LEFT kidney! I’m gonna die!!!”
“Sorry, in the training video it was the Right kidney.”
so this helps with costs right? right? 🥺🤔🤨
AI and robotics are coming for the highest paid jobs first. The attack on education is much more sinister than you think. We are approaching an era where many thinking and high cost labor fields will be eliminated. This attack on education is because the plan is to replace it all with AI.
It is pretty sickening really to think of a world where your AI teacher supplied by Zombie Twitter will teach history lessons to young pupils about whether or not the Holocaust is real. I am not making this shit up.
This is no longer about wars against nations. This has become the war for the human mind and billionaires just found the cheat code.
It helps the capitalists’ profit margins 😊😊😊
I know, I’m over here trying to light little fires LoL JK but yeah for sure never see reduced costs
Okay but why? No thank you.
without human help
…
responded to and learned from voice commands from the team
🤨🤔
You underestimate the demands on a surgeon’s body to perform surgery. This makes it much less prone to tiredness, mistakes, or even if the surgeon is physically incapable in any way of continuing life saving surgery
That’s absolutely not the point. I was criticizing the journalism, not technology. 🙄
I have seen enough ER to know that operating theatre staff work as a team. So I consider this would be a good thing.
They should have specified “without physical human help.”
So are we fully abandoning reason based robots?
Is the future gonna just be things that guess but just keep getting better at guessing?
I’m disappointed in the future.
reason based robots
What’s that?
That’s all people are too, though.
Naturally as this kind of thing moves into use on actual people it will be used on the wealthiest and most connected among us in equal measure to us lowly plebs right…right?
Are you kidding!? It’ll be rolled out to poor people first! (gotta iron out the last of the bugs somehow)
You really don’t understand modern medical bullshit. The rich will be all over this, just like AI, Just like NFTs just like every bullshit thing that comes up they get roped into by a flashy salesman
I want that thing where a light “paints” over wounds and they heal.
Hold on 3P0…you gotta little piece of human stuff stuck on your right end effector clamp top hinge pin. There, all good! Continue!
Just like how we jail every surgeon that does something wrong
Inb4 someone added Texas Chainsaw Massacre and Saw to the training data.
Then it’s all in a space and invented nanobots. So you win some, you lose some.
Nah, just a thorough reproduction of the consequences of that wrong.
know what? let’s just skip the middleman and have the CEO undergo the same operation. you know like the taser company that tasers their employees.
can’t have trust in a product unless you use the product.
Hey boss ready for your unnecessary heart transplant just to please some random guy on the internet?
Yeah so let’s get this done I’ve got a meeting in 2 hours.
TASER uses their products on their employees? Lol that’s wild
I understand what you are saying is intended as „if they trust their product they should use it themselves“ and I agree with that
I do think that undergoing an operation that a person doesnt need isnt ethical however
Really hope they tried it on a grape first at least.
thank you for removing my gallbladder robot, but i had a brain tumor
That’s ridiculous. Everyone knows that for a robot to perform an operation like this safely, it needs human-written code and a LiDAR.
My son surgeon told me about the evolution of one particular cardiac procedure. Most of the “good” doctors where laying many stitches in a tight fashion while the “lazy” doctors laid down fewer stitches a bit looser. Turns out that the patients of the “lazy” doctors had a better recovery rate so now that’s the standard procedure.
Sometimes divergent behaviors can actually lead to better behavior. An AI surgeon that is “lazy” probably wouldn’t exist and engineers would probably stamp out that behavior before it even got to the OR.
That’s just one case of professional laziness in an entire ocean of medical horror stories caused by the same.
Or more likely they weren’t actually being lastly, and knew they needed to leave room for swelling and healing. The surgeons that did tight stitches thought theirs was better because it looked better immediately after the surgery.
Surgeons are actually pretty well known for being arrogant, and claiming anyone who doesn’t do their neat and tight stitching is lazy is completely on brand for people like that.
Eliminating room for error, not to say AI is flawless but that is the goal in most cases, is a good way to never learn anything new. I don’t completely dislike this idea but I’m sure it will be driven towards cutting costs, not saving lives.
i mean, you could just as easily say professors and university would stamp those habits out of human doctors, but, as we can see… they don’t.
just because an intelligence was engineered doesn’t mean it’s incapable of divergent behaviors, nor does it mean the ones it displays are of intrinsically lesser quality than those a human in the same scenario might exhibit. i don’t understand this POV you have because it’s the direct opposite of what most people complain about with machine learning tools… first they’re too non-deterministic to such a degree as to be useless, but now they’re so deterministic as to be entirely incapable of diverging their habits?
digressing over how i just kind of disagree with your overall premise (that’s okay that’s allowed on the internet and we can continue not hating each other!), i just kind of find this “contradiction,” if you can even call it that, pretty funny to see pop up out in the wild.
thanks for sharing the anecdote about the cardiac procedure, that’s quite interesting. if it isn’t too personal to ask, would you happen to know the specific procedure implicated here?
Not specifically but I think the guidance is applicable to most incisions of the heart. I think the fact that it’s a muscular and constantly moving organ makes it differently than something like an epidermal stitch.
And my post isn’t to say “all mistakes are good” but that invariablity can lead to stagnation. AI doesn’t do things the same way every single time but it also doesn’t aim to “experiment” as a way to grow or to self-reflect on its own efficacy (which could lead to model collapse). That’s almost at the level of sentience.
If we go by that logic, some worker from your supermarket should be able to do surgeries
Doctors have to learns this much so they can handle most really unusual stuff, not because they have to know this for a standard surgery.
How does the success rate compare
SurgeonGPT?
Oh good it’s voice controlled. Because that technology works amazingly all the time.
And then you‘re lying on the table. Unfortunately, your case is a little different than the standard surgery. Good luck.
I assume my insides are pretty much like everyone else’s. I feel like if there was that much of a complication it would have been pretty obvious before the procedure started.
“Hey this guy had two heads, I’m sure the AI will work it out.”
What if I’m on the table telling the truth?
That’s a different thing indeed. In your case the AI 🤖 is goes wild, will strip dance and tell poor jokes (while flirting with the ventilation machine)
finitebanjo@lemmy.world 8 months ago
See the part that I dont like is that this is a learning algorithm trained on videos of surgeries.
That’s such a fucking stupid idea. Thats literally so much worse than letting surgeons use robot arms to do surgeries as your primary source of data and making fine tuned adjustments based on visual data.
Zacryon@feddit.org 8 months ago
Care to elaborate why?
From my point of view I don’t see a problem with that. Or let’s say: the potential risks highly depend on the specific setup.
JustARaccoon@lemmy.world 8 months ago
Unless the videos have proper depth maps and identifiers for objects and actions they’re not going to be as effective as, say, robot arm surgery data, or vr captured movement and tracking. You’re basically adding a layer to the learning to first process the video correctly into something usable and then learn from that. Not very efficient and highly dependant on cameras and angles.
finitebanjo@lemmy.world 8 months ago
Imagine if the Tesla autopilot without lidar that crashed into things and drove on the sidewalk was actually a scalpel navigating your spleen.
Showroom7561@lemmy.ca 8 months ago
Being trained on videos means it has no ability to adapt, improvise, or use knowledge during the surgery.
echodot@feddit.uk 8 months ago
Yeah but the training set of videos is probably infinitely larger, and the thing about AI is that if the training set is too small they don’t really work at all. Once you get above a certain data set size they start to become competent.
After all I assume the people doing this research have already considered that. I doubt they’re reading your comment right now and slapping their foreheads and going damn this random guy on the internet is right, he’s so much more intelligent than us scientists.
finitebanjo@lemmy.world 8 months ago
Theres no evidence they will ever reach quality output with infinite data, either. In that case, quality matters.