Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Google Is Training Machines to Predict When a Patient Will Die

bloomberg.com

Post reply on HN
Print view View original

71–80 of 87 posts

Re: Google Is Training Machines to Predict When a Patient Will Die

#71

Post by knuththetruth »

Arnt wrote: post #67
knuththetruth wrote: post #64

Earlier quoted context omitted.

I think a more useful question is how is it that developed countries like the US and UK have widespread unemployment, but no shortage of need of this kind of work? Perhaps the economy is massively misaligned in who and what it serves.

From a quick look the NHS alone appears to employ slightly more health professionals than there are long-term unemployed in the UK, so perhaps the economy is massively misaligned... and perhaps it isn't.

The NHS is well known to be suffering a staff shortage in GPs and other care workers, which will only be worsened in light of the immigration restrictions coming with Brexit.

This of course also ignores that all of the unemployed would never be funneled into healthcare alone, but in other social services and infrastructure work for which there is similar, dire need.

Re: Google Is Training Machines to Predict When a Patient Will Die

#72

Post by muraiki »

itschekkers wrote: post #25

I hate to pour cold water on this, but medical researchers have been predicting mortality for years. For example, here's a paper from the 1980's also predicting when a patient will die, also using a couple of thousands of patients' data: http://europepmc.org/abstract/med/3816253 And, Google's paper wasn't published in Nature, it was in a new open access journal owned by Nature. In academia, that is like the differenc…

From the paper:

"...the novelty of the approach does not lie simply in incremental model performance improvements. Rather, this predictive performance was achieved without hand-selection of variables deemed important by an expert, similar to other applications of deep learning to EHR data. Instead, our model had access to tens of thousands of predictors for each patient, including free-text notes, and identified which data were important for a particular prediction."

So it sounds like the advance here is actually in the following: "a generic data processing pipeline that can take raw EHR data as input, and produce FHIR outputs without manual feature harmonization".

The article doesn't explain this very clearly. Yay!

Re: Google Is Training Machines to Predict When a Patient Will Die

#73

Post by Spivak »

Broken_Hippo wrote: post #39
dapearce wrote: post #14

Earlier quoted context omitted.

>Customer A does not receive full medical support because "he's dying anyway"? Unless the patient consents to stop or reduce care, this would be medical negligence, which is illegal (in the US). Medical providers are required by law to provide medical treatment with all the knowledge and skill they possess.

I wish that were the case. They'll treat you in the ER, but not make sure you can actually purchase antibiotics to cure the thing that brought you to the ER to begin with, nor make sure you can afford the bone specialist you need to see for your surgery. Anything short of an emergency and you can be denied care due to finances. Even if your problem is cancer or they know it will eventually be an emergency or life-thr…

What is the ER going to do about the fact that you can't afford a prescription or treatment/surgery from a specialist? Their job is pretty much to stop you from dying right now and direct you to another doctor when you're stable.

You can also present insurance upfront but same difference I suppose. A world where you didn't have to pay upfront would make care even more expensive because doctor's offices have to essentially become banks.

Re: Google Is Training Machines to Predict When a Patient Will Die

#74

Post by Spivak »

Eridrus wrote: post #65
b34r wrote: post #23

I’m sure insurance companies will be glad to get their hands on this to use it as an excuse to deny coverage.

Insurance is all about pricing risk accurately, so yes, of course, these ideas will be used to price the risk more accurately. The problem isn't that insurers are horrible people, it's that insurance is a bad fit for healthcare.

Why do you say that? Take insurance in its most basic form: a company does its best to determine how much money they're likely going to pay out over the lifetime of a policy and spreads that cost out for their customer who is then insulated from unexpected expenses or non-uniform cost schedules. It seems perfectly suited to medicine.

Insurance doesn't solve the problem of a population where the total cost of care is more then they can collectively afford or when an individual's treatment has known costs higher than what they can afford but nobody has a good answer for that.

Insuring everyone from birth can be a solution for the individual but not the population.

Re: Google Is Training Machines to Predict When a Patient Will Die

#75

Post by knuththetruth »

Spivak wrote: post #73
Broken_Hippo wrote: post #39

Earlier quoted context omitted.

I wish that were the case. They'll treat you in the ER, but not make sure you can actually purchase antibiotics to cure the thing that brought you to the ER to begin with, nor make sure you can afford the bone specialist you need to see for your surgery. Anything short of an emergency and you can be denied care due to finances. Even if your problem is cancer or they know it will eventually be an emergency or life-thr…

What is the ER going to do about the fact that you can't afford a prescription or treatment/surgery from a specialist? Their job is pretty much to stop you from dying right now and direct you to another doctor when you're stable. You can also present insurance upfront but same difference I suppose. A world where you didn't have to pay upfront would make care even more expensive because doctor's offices have to essent…

>A world where you didn't have to pay upfront would make care even more expensive because doctor's offices have to essentially become banks.

Those are called nationalized healthcare systems and are almost all cheaper than the US’ privatized system?

Re: Google Is Training Machines to Predict When a Patient Will Die

#76

Post by Eridrus »

Spivak wrote: post #74
Eridrus wrote: post #65

Earlier quoted context omitted.

Insurance is all about pricing risk accurately, so yes, of course, these ideas will be used to price the risk more accurately. The problem isn't that insurers are horrible people, it's that insurance is a bad fit for healthcare.

Why do you say that? Take insurance in its most basic form: a company does its best to determine how much money they're likely going to pay out over the lifetime of a policy and spreads that cost out for their customer who is then insulated from unexpected expenses or non-uniform cost schedules. It seems perfectly suited to medicine. Insurance doesn't solve the problem of a population where the total cost of care is…

Insurance works when you incur a lot of one time costs, it works much worse when you start incurring a lot of expenses over a long period of time. Ideally you could buy insurance that would cover all of your long term costs once you contracted some disease, but this doesn't exist in the US. And doubly doesn't exist when you realise that there are a bunch of forces incentivizing people to get their insurance from an employer.

Re: Google Is Training Machines to Predict When a Patient Will Die

#77

Post by evandijk70 »

neurobashing wrote: post #20

I'm sure it's an interesting technical challenge with huge amounts of complex, nuanced debate involved, and it could have a huge impact on health care. That said, my wife is an oncology nurse, and I will bet everything that no machine will ever get better at predicting than an experienced, skilled nurse. Humans are built to read humans.

I would be very willing to take that bet on a 30 year horizon

Just think about the machines/algorithms your wife already (indirectly) uses to predict outcome for patients.

- An MRI scan, which is created from physical laws (Maxwell's law together with a quantum mechanical understanding of hydrogen atoms) and reconstructs a 3D-image of the different tumors. Knowing if and where metastasis are present have an enormous impact on the prognosis.

- The algorithms used to align sequencing reads from biopsies to determine the mutation status, which are critical to determine the prognosis of some tumors.

In fact, I'd wager that if your wife did not have access to these algorithms, she would already perform worse. And, in my opinion, the distinction between machine learning and the algorithms used to reconstruct 3D-images or align sequences is somewhat arbitrary.

Re: Google Is Training Machines to Predict When a Patient Will Die

#78

Post by Spivak »

knuththetruth wrote: post #75
Spivak wrote: post #73

Earlier quoted context omitted.

What is the ER going to do about the fact that you can't afford a prescription or treatment/surgery from a specialist? Their job is pretty much to stop you from dying right now and direct you to another doctor when you're stable. You can also present insurance upfront but same difference I suppose. A world where you didn't have to pay upfront would make care even more expensive because doctor's offices have to essent…

>A world where you didn't have to pay upfront would make care even more expensive because doctor's offices have to essentially become banks. Those are called nationalized healthcare systems and are almost all cheaper than the US’ privatized system?

Huh? The doctor is still getting guaranteed payment but by your government instead of you. I mean the world in which doctors had to accept patients regardless of their ability to pay and have to try and recover later.

Re: Google Is Training Machines to Predict When a Patient Will Die

#79

Post by evandijk70 »

Eridrus wrote: post #65
b34r wrote: post #23

I’m sure insurance companies will be glad to get their hands on this to use it as an excuse to deny coverage.

Insurance is all about pricing risk accurately, so yes, of course, these ideas will be used to price the risk more accurately. The problem isn't that insurers are horrible people, it's that insurance is a bad fit for healthcare.

You just need regulation in place to prevent this. In the Netherlands, it's illegal to deny someone healthcare. It's also illegal not to have health insurance. The system works, Insurance is around ~100 euro per month, covers almost all treatments and deductibles are between 350 and 850 euro's per month.

Re: Google Is Training Machines to Predict When a Patient Will Die

#80

Post by Spivak »

Eridrus wrote: post #76
Spivak wrote: post #74

Earlier quoted context omitted.

Why do you say that? Take insurance in its most basic form: a company does its best to determine how much money they're likely going to pay out over the lifetime of a policy and spreads that cost out for their customer who is then insulated from unexpected expenses or non-uniform cost schedules. It seems perfectly suited to medicine. Insurance doesn't solve the problem of a population where the total cost of care is…

Insurance works when you incur a lot of one time costs, it works much worse when you start incurring a lot of expenses over a long period of time. Ideally you could buy insurance that would cover all of your long term costs once you contracted some disease, but this doesn't exist in the US. And doubly doesn't exist when you realise that there are a bunch of forces incentivizing people to get their insurance from an e…

> you could buy insurance that would cover all of your long term costs once you contracted some disease

Kind of defeats the point if you're using it to cover known future costs. Insurance can really only insulate you against risk, it's not free money.

Post reply on HN