Scientists Use AI To Create Drug Regime For Rare Form of Brain Cancer In Children (theguardian.com) 21
Scientists have successfully used artificial intelligence to create a new drug regime for children with a deadly form of brain cancer that has not seen survival rates improve for more than half a century. The Guardian reports: The breakthrough, revealed in the journal Cancer Discovery, is set to usher in an "exciting" new era where AI can be harnessed to invent and develop new treatments for all types of cancer, experts say. Computer scientists and cancer specialists at the ICR and the Royal Marsden NHS Foundation Trust used AI to work out that combining the drug everolimus with another called vandetanib could treat diffuse intrinsic pontine glioma (DIPG), a rare and fast-growing type of brain tumor in children. Currently, DIPG and other similar types of tumors are incredibly difficult to remove surgically from children because they are diffuse, which means they do not have well-defined borders suitable for operations. But after crunching data on existing drugs, the team found everolimus could enhance vandetanib's capacity to "sneak" through the blood-brain barrier and treat the cancer.
The combination has proved effective in mice and has now been tested in children. Experts now hope to test it on a much larger group of children in major clinical trials. The research found that combining the two drugs extended survival in mice by 14% compared with those receiving a standard control treatment. Both the drugs in the research, which was funded by Brain Research UK, the DIPG Collaborative, Children with Cancer UK and the Royal Marsden Cancer Charity, among others, are already approved to treat other types of cancer. "The AI system suggested using a combination of two existing drugs to treat some children with DIPG -- one to target the ACVR1 mutation, and the other to sneak the first past the blood brain barrier," said Chris Jones, professor of paediatric brain tumor biology at the ICR. "The treatment extended survival when we tested it in a mouse model, and we have already started testing it out in a small number of children. We still need a full-scale clinical trial to assess whether the treatment can benefit children, but we've moved to this stage much more quickly than would ever have been possible without the help of AI."
The combination has proved effective in mice and has now been tested in children. Experts now hope to test it on a much larger group of children in major clinical trials. The research found that combining the two drugs extended survival in mice by 14% compared with those receiving a standard control treatment. Both the drugs in the research, which was funded by Brain Research UK, the DIPG Collaborative, Children with Cancer UK and the Royal Marsden Cancer Charity, among others, are already approved to treat other types of cancer. "The AI system suggested using a combination of two existing drugs to treat some children with DIPG -- one to target the ACVR1 mutation, and the other to sneak the first past the blood brain barrier," said Chris Jones, professor of paediatric brain tumor biology at the ICR. "The treatment extended survival when we tested it in a mouse model, and we have already started testing it out in a small number of children. We still need a full-scale clinical trial to assess whether the treatment can benefit children, but we've moved to this stage much more quickly than would ever have been possible without the help of AI."
more "AI" marketing (Score:2, Insightful)
The combination of everolimus and vandetanib has been subject of studies for more than a decade, they're still ongoing. Look it up.
"AI" is largely smoke and mirrors, marketing gimmick.
Re: (Score:3)
Re: (Score:1)
Re: YEA! New mind altering drugs FTW!! (Score:1)
Are you on drugs?
If a vaccine against cancer existed I'd do it right away, even every 6 months of that's the case. My grandfathers and my dad died from cancer at around 50 when my brother was just 12, and it wasn't pretty.
You are free to die from cancer if you so prefer.
Re: (Score:2)
Re: (Score:2)
Blaming the wrong party, incidence of childhood cancer UP over the 20th century, we're doing something wrong.
https://www.ncbi.nlm.nih.gov/p... [nih.gov]
Re: (Score:2)
and the 2nd most common type of pediatric cancer, brain tumors, also took sharp upturn in latter 20th century then stabilized, couldn't find stats for incidence before that. definitely we're doing something wrong
https://www.ncbi.nlm.nih.gov/p... [nih.gov]
Re: (Score:1)
Polyomaviruses, lurking dormant in your body are infected cells waiting to emerge from latency and wreck your body.
The SV40 polyomavirus was spread throughout the country via contaminated polio vaccine.
So go get your covid jab. Hopefully it doesn't have the BK virus
or the John Cunningham virus
or the Merkel cell virus...
Its likely a contributing cause of lymphoma and many other cancers.
It evades immune system surveillance by being dormant. Hard to kill the sleeping virus.
Medical community has largely ignored
Re: (Score:1)
oops guess my SV40 infection is affecting my reading... what I quoted from the study says that the SV40 inactivates the retinoblastoma protein but not P53 tho it is frequently mutated.
I am a little confused also that the study says that polyomavirus is a close relative of SV40. From what I've read, SV40 is one of 14 polyomaviruses found so far to affect humans (and they share similarities and something like 75% genome)
Re: (Score:2)
Nope, you're having multiple brain farts connecting unrelated things.
oral polio vaccines *perhaps* contaminated with SV40 in 1955 through 1963 means nothing, has no correlations, in the stats and timeframes I quoted, and is irrelevant to the vaccines given now.
you need to uncrank your tinfoil hat a few notches, it's on too tight
Heathens (Score:2)
Re: (Score:2)
I fully expect to see anti-vaxxers and their ilk demonstrating at the bedside of dying children.
We’re living in an age of Star Trek Medicine (Score:5, Interesting)
I studied Medical Information Sciences in the late nineties. And if I look back and forward again then I realise: we are doing things that back then would have been seen as only possible as part of a dialogue between dr. Crusher and captain Picard.
I did my theses on using artificial intelligence for offering decision support in therapeutic choices for lung cancer. Getting a proper dataset on which your models could be trained was actually the primary challenge. And medically, the options were way more limited; back then metastatic cancer was often an automatic death-sentence. It would be seen as futile to try to treat and focus would be on palliative care.
Flash forward. For a few years I suffered chronic problems with my retina that ultimately resulted in the detachment of a part of my retina. I was immediately treated by microscopic surgery. A retina surgeon removed the vitreous matter in my eye, removed a membrane only a few cells thick. By inserting a silicon oil into the eye the retina was put back in its place and finally they used a laser to repair a hole in the retina. Following that I needed to have a lens replaced which was significantly less burdensome and about as routine as having a tooth cavity filled.
For cancers we are now able to train the immune system to attack the cancers, we’re on the cusp of using gene editing to “fix” the DNA of people that are unable to process or build various proteins. People can swallow camera pills and we use various neuro-stimulators to intervene in various abnormal neurological processes. We’re using mRNA to build a new generation of vaccine’s and since we are building “big data”-sets we are able to use AI to create new insights.
I have various family members and friends that should have been blind, dead, disabled and unable to work or a combination of the above by the standards of a few decades ago. A few of my family members have various forms of cancers that have become manageble as a chronic disease. We have actually progressed way more than I would have expected when I was studying. The advances just have been gradual and incremental so people don’t actually notice. Great to see just another example. It might not be a survival cure as some commenters have pointed out, but it will be analyzed, expanded upon and ultimately used in a much more impactful way in the not to far future, I am sure.
Re: (Score:2)
It's actually incredible how much medicine has progressed in the last 30 years. Not even just in technologies, but also in techniques.
Re: (Score:2)
It's also amazing how few of us can enjoy access to any medical care at all while all these miracle level medical discovers are going on. At least the rich will have options going forward.
Re: (Score:2)
It's also amazing how few of us can enjoy access to any medical care at all
OK, you're an ignoramus.
mRNA treatments are seriously needed (Score:2)
Regime, regimen, regiment (Score:2)
14%. Um, good? (Score:2)
the two drugs extended survival in mice by 14% compared with those receiving a standard control treatment.
I hate, hate, hate people that use percentages with absolutely zero context. If the standard survival time is 20 years, then the kids will get an extra 2-3 years of life. Great.
If the standard survival time is six months, then this new AI drug combo (not even a new drug) will add... not even one more month of survival. Yes, it is an improvement, but this is hardly revolutionary, and barely worth reporting. And remember, this is only in MICE, not even actual children, so we don't even know if it will ha