Slashdot Mirror
MIT Developing AI To Better Diagnose Cancer
stowie writes: Working with Massachusetts General Hospital, MIT has developed a computational model that aims to automatically suggest cancer diagnoses by learning from thousands of data points from past pathology reports. The core idea is a technique called Subgraph Augmented Non-negative Tensor Factorization (SANTF). In SANTF, data from 800-plus medical cases are organized as a 3D table where the dimensions correspond to the set of patients, the set of frequent subgraphs, and the collection of words appearing in and near each data element mentioned in the reports. This scheme clusters each of these dimensions simultaneously, using the relationships in each dimension to constrain those in the others. Researchers can then link test results to lymphoma subtypes.
for steaks, chicken and french fries.
It's been proven that a cat can detect all forms of cancer before any test or machine. Cheap this is so don't hold out much hope in seeing it used as it should.
I don't need an AI to tell me I have cancer that's what WebMd does already!
But how do we bribe -- err I mean buy lunch for -- it so it will suggest prescribing my company's drugs?
"... that aims to automatically suggest cancer diagnoses..." even if you don't actually have cancer.
I think this may contribute to an already existing problem with the high cancer rate: high detection. How many people who are diagnosed with cancer would have lived just fine and ended up dying from something else? We do find cancer in autopsies where the person didn't know they had cancer. Is the current trend of high cancer rates partly due to better means of detection, and it's just that lots of people have had asymptomatic cancer all this time? Does every form of cancer require massive amounts of chemo? My wife passed away from stage 4 colon cancer last year. It had spread to her lungs, adrenal gland, and liver. She had surgery for the original tumor, and underwent 3 years of aggressive chemo to remove the very tiny filaments elsewhere in her body. I can only wonder if, without the chemo, she would have had the same fate. There are people who forego chemo and survive. And obviously chemo is necessary for many people to beat cancer. But I have to wonder if getting better at detecting cancer will bring more good than harm.
Tic-Tac-Toe, Global Thermonuclear War, and relationships all have the same winning move.
by learning from thousands of data points from past pathology reports.
I'd be worried if my future surgeon had only 1000 bullet point takeaways from college, and no experience, I'd be a little worried.
What does the term 'data point' mean?
Only beaten to the punch by... pretty much every new and shiny (in its day) AI/machine learning/neural net. Ever.
And fwiw 800 is a pretty puny size dataset. Usable, but hardly exceptional.
"...technique called Subgraph Augmented Non-negative Tensor Factorization (SANTF)"
Obviously nobody speaks french there or they would have used a last word beginning with 'e' so that it spells SANTE which means 'health' in french.
Nice try MIT, but try again.
So the news is that MIT are making an expert system?
It is unclear where in the diagnostic chain this idea fits. Is it someone that already carries a diagnosis of lymphoma, but there is a question the diagnosis is wrong? Is it using lab data to make a primary diagnosis (or suggestion of diagnoses) based on a clinic visit? Are they suggesting that this data fits an ancillary role in primary diagnosis in terms of resolving subtle discrepancies between diagnoses?
Pretty much all hematopoietic malignancy diagnoses do not come from the docs you see in the clinic. They come from the docs in the back rooms with microscopes, lasers, antibodies, sequencers, and computers. Is the user of this information the person in the front whom you talk to, or the person in the back making the actual diagnosis?
Also, FTA
To paraphrase Yet Another Famous Movie Quote: Getting something into the WHO guidelines ain't like dusting crops, boy.
-- The Genesis project? What's that?
"I'm sorry Dave, I'm afraid you have testicular cancer."
The last word needs to be something like "Analysis". I'll admit, my goal here has nothing to do with helping people or better representing the technology. I just want people to be able to say "SANTA told me I have cancer."
Take it to the limit, everybody to the limit, come on, everybody fhqwhgads.
FFS, it's not AI. It's a mindless program. Unthinking software. Data analysis software. Innovative to some degree perhaps, but AI? Hardly. No better than me stumbling in here and calling some DSP code I'd written "AI." Well, except I wouldn't do that. :/
When AI gets here, we'll have to call it something else what with all this crying wolf going on.
I've fallen off your lawn, and I can't get up.
I would suggest that they're limiting themselves by using only three dimensions and using only three because that's all their minds can understand. Get a real mathematician on mathematical physicist in on this so you can ramp up the dimensions and make some better correlations
So they've written Eliza for Cancer....
https://en.wikipedia.org/wiki/ELIZA
That word 'better', I don't think it means what they think it means.
MIT Developing AI To Better Diagnose Cancer
All right. Congratulations to Allen Iverson! Hopefully it won't require too much practice.
They are using a very complicated technique on a small data set. They picked "cancer" only because it gets them published, gets research grants, and gets them press coverage. The whole thing is a bit of decent math with a great deal of pseudo-science. It will do nothing to help cure cancer.
When I was at University I developed an Expert System to diagnose all kinds of illnesses. It was a a fantastic piece of software. The computer spat out "DEGENERATIVE CHANGE" for every set of symptoms I entered.
OP Success.
Sounds like data mining
It will cheat by giving you cancer so it is always right!