Posted on 09/25/2026 1:10:11 PM PDT by Red Badger
Remember not too long ago, when you couldn’t generate an image with AI adding 3 extra fingers to the mix? We’ve come a long way, baby… but still, AI gets blamed for a lot these days…
It’s coming for your job, it’s making creepy deepfake videos, kids are cheating on their homework, and most of your social media feed looks like it was uploaded by a robot on a meth bender.
Fair enough, we get it.
But every once in a while, a story comes along that reminds you why this technology could also turn out to be one of the greatest tools humans have ever built. And we have that story for you today, and it’s pretty amazing.
Joseph Coates was 37 years old when doctors basically told him they were out of options, and his life was about to end.
He’d spent months battling POEMS syndrome. It’s a rare blood disorder that had wrecked his body. His kidneys were failing, his heart was enlarged, and doctors were draining liters of fluid from his abdomen on a regular basis.
It was so bad, he couldn’t even receive the stem-cell transplant that might have saved him.
It was the end of the road for Joseph, so conversations shifted from treatment to death.
They were asking him things like, “Where do you want to die? At home or in the hospital?”
His life was essentially over.
But his girlfriend wasn’t ready to let go…
And then one day, her desperate email changed everything.
Tara Theobald remembered a doctor they’d met at a rare-disease summit named David Fajgenbaum.
So she emailed him.
Dr. Fajgenbaum came back with a pretty crazy idea… what if they tried a combination of chemotherapy, immunotherapy, and steroids to treat Coates’s disease? It had never been used for his condition before, and there was no guarantee it’d work. All they had was some suggestion from an AI model and a patient who was running out of options real fast.
And then something remarkable happened.
The New York Times:
A little over a year ago, Joseph Coates was told there was only one thing left to decide. Did he want to die at home, or in the hospital?
Coates, then 37 and living in Renton, Wash., was barely conscious. For months, he had been battling a rare blood disorder called POEMS syndrome, which had left him with numb hands and feet, an enlarged heart and failing kidneys. Every few days, doctors needed to drain liters of fluid from his abdomen. He became too sick to receive a stem cell transplant — one of the only treatments that could have put him into remission.
“I gave up,” he said. “I just thought the end was inevitable.”
But Coates’s girlfriend, Tara Theobald, wasn’t ready to quit. So she sent an email begging for help to a doctor in Philadelphia named David Fajgenbaum, whom the couple met a year earlier at a rare disease summit.
By the next morning, Dr. Fajgenbaum had replied, suggesting an unconventional combination of chemotherapy, immunotherapy and steroids previously untested as a treatment for Coates’s disorder.
Within a week, Coates was responding to treatment. In four months, he was healthy enough for a stem cell transplant. Today, he’s in remission.
The lifesaving drug regimen wasn’t thought up by the doctor, or any person. It had been spit out by an artificial intelligence model.
In labs around the world, scientists are using A.I. to search among existing medicines for treatments that work for rare diseases. Drug repurposing, as it’s called, is not new, but the use of machine learning is speeding up the process — and could expand the treatment possibilities for people with rare diseases and few options.
Thanks to versions of the technology developed by Dr. Fajgenbaum’s team at the University of Pennsylvania and elsewhere, drugs are being quickly repurposed for conditions including rare and aggressive cancers, fatal inflammatory disorders and complex neurological conditions. And often, they’re working.
The cool thing about this story is that AI looked for “connections.”
A human researcher can study a drug and start digging through research to see what else it might do, but AI can look across thousands of drugs and thousands of diseases at the same time, really fast.
That’s a totally different ballgame.
And this doctor, Fajgenbaum, knew this better than most, because he’d almost died. He had a very rare disease called “Castleman” while he was in medical school. The current treatments weren’t working for him. He finally found the answer to his problem in a generic drug being used for something else.
That experience changed the direction of his life.
The New York Times:
“I had this really clear realization that I didn’t have a billion dollars and 10 years to create some new drug from scratch,” he said.
The drug that saved Dr. Fajgenbaum’s life was a generic medication called sirolimus, typically given to kidney donation recipients to prevent rejection. The medication has kept his Castleman disease in remission for more than a decade.
Dr. Fajgenbaum went on to become a professor at the University of Pennsylvania, and began seeking out other drugs with unknown uses. Existing research, he realized, was full of overlooked clues about potential links between drugs and the diseases they could treat, he said. “If they’re just in the published literature, shouldn’t someone be looking for these all day, every day?”
His lab had some early successes, including finding that a novel cancer drug helped another Castleman patient. But the process was laborious, requiring his team to examine “one drug and one disease at a time,” he said. Dr. Fajgenbaum decided he needed to speed up the project. In 2022, he established a nonprofit called Every Cure, aimed at using machine learning to compare thousands of drugs and diseases all at once.
There was a mountain of medical research just sitting there, but nobody could read and remember all of it and then compare every clue about every drug against thousands of completely different diseases. That would take forever.
But the machine can do it in no time. And now, Fajgenbaum’s platform compares about 4,000 drugs against 18,500 diseases. Then researchers take the info and investigate the best leads, and then doctors decide whether a suggestion makes medical sense.
AI isn’t replacing doctors. It’s helping them sort through the piles of paperwork to get to the life-saving part much faster.
And some of these discoveries sound downright ridiculous until you realize, holy crap, they actually worked.
One AI model suggested inhaling isopropyl alcohol for a teenager suffering from chronic vomiting… that helped. Another told researchers to use ADHD medication for kids with periodic paralysis… that also worked. And a Parkinson’s drug ended up helping people with a neurological disorder to move and speak.
The New York Times:
The model developed by Dr. Might’s institute has successfully predicted other treatments, too: Amphetamines typically used to treat A.D.H.D. relieved periodic paralysis in children with a rare genetic disorder. A Parkinson’s drug helped patients with a neurological condition move and speak. A common blood pressure medicine called guanfacine drastically improved the mobility of a pediatric patient with a different neurological condition.
Many drugs do more than one thing, Dr. Might said. Their additional features sometimes get characterized as side effects. “If you comb through enough drugs, you eventually find the side effect you’re looking for,” he said, “and then that becomes the main effect.”
At the University of Pennsylvania, Dr. Fajgenbaum’s platform compares roughly 4,000 drugs against 18,500 diseases. For each disease, pharmaceuticals get a score based on the likelihood of efficacy. Once the predictions are made, a team of researchers combs through them to find promising ideas, then performs lab tests or connects with doctors willing to try the drugs on patients.
Rare diseases are especially brutal because there often just aren’t enough patients to make a brand-new drug worth developing financially. And even if somebody tries, starting from scratch can take years and cost a bloody fortune.
But AI can search and figure out if there’s medicine that already exists. Who knows, it could’ve been invented years ago to help with arthritis.
In the case of Mr. Coates, his oncologist was actually really nervous about the AI suggestion, because he thought the combo looked so intense that it might kill him even faster.
But at that point, Mr. Coates was headed to hospice anyway, so why not try it?
The New York Times:
When Dr. Fajgenbaum first suggested that Dr. Wayne Gao, a hematologist and oncologist in Washington State, try a novel treatment on one of his patients, Dr. Gao had doubts.
The patient was Coates, the Washington man headed for hospice, and the aggressive drug combination suggested by Dr. Fajgenbaum’s model seemed “a little bit crazy,” Dr. Gao said. In fact, he worried that the treatment might kill Coates faster.
But Coates was a young man, and there were no other treatments to consider. And so, Dr. Gao said, “someone had to be the first to try.”
Last month, just over a year after his brush with death, Coates and his girlfriend visited Dr. Fajgenbaum in Philadelphia to thank him for his help. A smiling Coates was the picture of health; he had put on muscle since the last time he met the doctor.
Coates had tweaked his ankle that morning while working out. But otherwise, he said, he felt “just fine.”
A year earlier, this guy was deciding where he wanted to die… he was ready to go into hospice.
Now he’s at the gym working out.
That’s one helluva before-and-after story, right? And this is why AI deserves a bigger place at the conversation table.
We spend so much time worrying about what the technology could destroy that it’s easy to miss what it might build and uncover.
AI can chew through more data than any doctor or research team could ever process alone and spot connections humans might never even think to look for.
And the best part is, it doesn’t replace doctors. This story actually shows why we need both.
David Fajgenbaum.
Thats amouthful.
YHWH helped them out.
I want my AI doctor. I want him now. I’m fed up with doctors following a flow chart that can’t think for themselves. If you confront them with their cherished theory,they stiffen up with you can’t believe everything you read on the internet. Why? He believes everything these drug company compromised government agencies decree. He/she does it without question or reason.
And then there is always the Insurance Company helping out with overview and mandating prior approval....
We ignored AI on Amazon when buiyng canned cat food. AI said that brand didn’t have enough gravy. Most expensive brand with terrific ingredients. When I opened the first can, Daisy jumped up on the counter and started eating it right outy of the can.
The occasional can needs more gravy, so I put a teaspoon of FILTERED water in and mix it in. Nothing but the best for Daisy Jane.
She told me that AI is a stupid idiot.
Cats are ALWAYS right. Mine is.
There must be different levels of ai. I query AI most everyday. I have learned to be skeptical of the answers. Recently I asked chat which journalists lost their WH privileges because of Biden policies. Chat repeatedly denied that any were listed by name. After a Non-AI search I came up with an article from Heritage that listed a Mr. Logan. Today I asked what shirt WNBA coach White wore during a game. Chat went into a long pro-trans diatribe about coach Reeves shirt concerning trans kids. Chat acknowledged the mistakes blaming it on “a program “. Ran out of time and lost the thread to dig deeper. I don’t trust chat but support AI. It has the capability of digging through mounds of data and helping cure diseases or digging through your personal data and putting you on a “list”.
AI heap good medicine
Got bit by a rattlesnake did he?
Try Superpower! I signed up in June and I am absolutely amazed at how useful it is. Proprietary AI that takes in all your lab results and KNOWS your health picture in a way that no doctor has the time or energy to understand. You can ask it any question, any time, and it considers all that it knows about you, the medications and supplements you’re taking, and tells you how the answer applies to you. It is so conversational in its responses, that you have to keep reminding yourself that it is AI. It advises you on what you should discuss with your PCP (though this can get tricky, because you have to be a little diplomatic with your human doctor LOL) This is my first experience using AI of any kind (other that Google searches) and I am really impressed.
Ya gotta love a medical crisis story that has the words: “ and there was no guarantee it’d work”.
My MD told is very smart. I had a Covid test and it was negative. Then I went to see him.
“Do I need a covid shot?”
“You look really healthy to me, com back in six months”
BUT,my big strong handsome son-in-law, head of the Sheriff’s Dept, got a shot to fly to Hawaii. Four months later he was dead. Like her mom, my daughter takes a handful of vitamins every day and never gets sick.
Never is a slight overstatetment. I’ve lived her 17 years, had a cold 10 years ago.
Needed a cattle prod shock I heard. Fixed right up
Amen.
Amen.
My son-in-law got the jab, then got covid, hospitalized and got intubated, checked himself out, went and got a booster jab and died within a couple of weeks.
AN ELECTRONIC HAIL MARY
I am currently taking Biochemistry at our local university. My husband signed us up for a more advanced version of ChatGPT. Wow! Amazing! There is a huge difference between the free and the paid versions.
Worth every penny! ( or should I say “nickel” now?)
AI as a specialized expert system supplementing humans and/or trying to find meta-patterns is useful
Turning it all over to AI and getting rid of people is not the way to use AI.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.