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

Medicine's Machine Learning Problem

bostonreview.net

Post reply on HN
Print view View original

81–90 of 112 posts

Re: Medicine's Machine Learning Problem

#81

Post by DoreenMichele »

dontreact wrote: post #80
DoreenMichele wrote: post #77

Earlier quoted context omitted.

I vaguely recall some article about bathtubs being given to poor people in Appalachia who had no running water (in like The Great Depression of the 1930s). They would put them on the front porch and use them to store coal, which got mocked by others as them being "ignorant fools" who didn't understand what a bathtub was for rather than seen as evidence that bathtubs are essentially useless for bathing if you lack run…

Yeah... I was just trying to explain what the challenges are in hopes that you have a better understanding of what it will take to fix it. For example, the requirement that you have a physician explain things I think should be relaxed as much as is feasible. I'm not blaming people who are poor for not having access to healthcare. Also... I'm not white.

I'm just talking. That's it.

Have a good day.

Re: Medicine's Machine Learning Problem

#82

Post by chromatin »

DoreenMichele wrote: post #19

"The first rule of any technology used in a business is that automation applied to an efficient operation will magnify the efficiency. The second is that automation applied to an inefficient operation will magnify the inefficiency." -- Bill Gates In the lifetime of my adult sons the world stopped being predominantly agrarian and rural and hit a point where more than half of all people on the planet live in cities. It…

> Human doctors were historically put on call for up to 24 hours at a time as part of their learning process in part so they would see a patient's condition evolve over time while the doctor was still young and healthy enough to endure this grueling process. Having seen it for a time as part of their training, they retained that knowledge when they were older and could recognize a stage of a moving target.

Closer to 36 hours at a time, I am sad to report

Re: Medicine's Machine Learning Problem

#83

Post by QuercusMax »

matheusmoreira wrote: post #61
gdebel wrote: post #14

I'm an eye surgeon and self-taught machine learning practitioner, I started to learn Python in 2016 when the deep learning hype was at his highest. After 3 years of research, playing with datasets, extracting and cleaning data from EMR and from different machines, I not sure that the biggest problem with the so-called "AI" is the inequalities that it can induce ; it is rather, is it useful at all ? This is a little b…

> I also realized that it is extremely difficult, if not impossible, to use data from EMR out of the box. This is my biggest complaint with the EMR systems I've used and I've always wanted to improve this. I wonder if fellow doctors would be okay with using a simple structured language to describe data in an EMR. For example: Height: 175 cm Weight: 70 kg Ethnicity: white Age: 40 years Creatinine: 0.9 mg/dl An inferen…

There's a lot of effort being put forward to extract data from unstructured reports, with some pretty nice results from what I've seen. Convincing every doc to use this type of format is likely to be impossible.

Re: Medicine's Machine Learning Problem

#84

Post by adolph »

ps2fats wrote: post #79
rahulnair23 wrote: post #38

Earlier quoted context omitted.

Health policy is fraught with counter-intuitive phenomenon - and screening is one of them. Seems like it should help, but in practice leads to over-diagnosis. For example - Cancer rates jumped in Korea after screening with no impact on patient outcomes [1]. There are several others. [1] Lee, J. H., & Shin, S. W. (2014). Overdiagnosis and screening for thyroid cancer in Korea. The Lancet, 384(9957), 1848.

You can hardly conclude that broadly screening populations are ineffective from this study. You have to consider, among other things, the treatments available for the given disease being screened and the cost of that screening program. If treatments for the disease already have a low success rate (what is low?), the timing of detection doesn't really help. Additionally, if the cost of the screening program is negligi…

The current consensus about over-diagnosis (as I understand it) is that when there is a significant false positive rate and the cost of proving the positive false is high (in money, time, effort, worry), the screening program is not helpful. Some go further to say that low cost screening drives some of the high cost to outcome ratio in the US. I'll try to find a cite in my textbooks if you are interested.

Re: Medicine's Machine Learning Problem

#85

Post by JimTheMan »

dnautics wrote: post #21
usrnm wrote: post #18

Earlier quoted context omitted.

Honest question: does it really matter for lung cancer? Is there much difference between races in this particular field?

How would you know without the data? There are plenty of medical conditions with wildly divergent rates and pathophysiologies based on human genetics.

I don't think the burden is on us to prove a negative.

It'd be way better to think of it in terms of genetic markers instead of races. Race in general practice is a social construct based on colour, appearance and culture. It's a level of abstraction away from the actual genetic data that we don't need with our level of technology.

We could dig right into the genes and throw away our outdated notions. That's where the actual useful detail is. Who cares about the color of the person if they have the same amount huntington repeats you know?

Re: Medicine's Machine Learning Problem

#86

Post by BlueTemplar »

sjg007 wrote: post #37
sungam wrote: post #22

Earlier quoted context omitted.

I am a dermatologist, AI researcher and co-founder of an AI startup (skinsmart.ai) and I would agree with you regarding the utility of AI in making an accurate diagnosis of melanoma. I don't think it has a significant role it play in the Dermatology clinic for this application. However, I am very optimistic about the potential for AI to help in the triage of patients referred to dermatology by non-specialists. For th…

If I had a benign lesion referred by my PCP to dermatology, I’d want a dermatologist to take a look at it. It’s never been difficult to get a dermatology appointment.

Maybe for you, I would have needed more than 3 months to get one. Thankfully in my case the issue seems to have been benign and was gone in a month.

Re: Medicine's Machine Learning Problem

#87

Post by adolph »

matheusmoreira wrote: post #61
gdebel wrote: post #14

I'm an eye surgeon and self-taught machine learning practitioner, I started to learn Python in 2016 when the deep learning hype was at his highest. After 3 years of research, playing with datasets, extracting and cleaning data from EMR and from different machines, I not sure that the biggest problem with the so-called "AI" is the inequalities that it can induce ; it is rather, is it useful at all ? This is a little b…

> I also realized that it is extremely difficult, if not impossible, to use data from EMR out of the box. This is my biggest complaint with the EMR systems I've used and I've always wanted to improve this. I wonder if fellow doctors would be okay with using a simple structured language to describe data in an EMR. For example: Height: 175 cm Weight: 70 kg Ethnicity: white Age: 40 years Creatinine: 0.9 mg/dl An inferen…

Doctors and technologists of various stripes have been working on this since before the dawn of digital computers. Let's take height as an example. Let's look at metadata needed along with that data point: 1. When was it taken? 2. How was it taken? 3. Who took it? 4. What measurement system does "cm" refer to? 5. How does the concept of height relate to other clinical concepts?

https://www.hl7.org/fhir/observation.html

https://www.hl7.org/fhir/observation-example-body-height.htm...

The simple stuff like BMI, BSA, etc. have been calculated for a long time without anything fancy like an inference engine. The challenge is that the surface area of different calculations needed outstrip the supply of people who can interpret the clinical question, identify the source data and encode them. A better approach is needed and is what folks are working towards.

Re: Medicine's Machine Learning Problem

#88

Post by srean »

adolph wrote: post #84
ps2fats wrote: post #79

Earlier quoted context omitted.

You can hardly conclude that broadly screening populations are ineffective from this study. You have to consider, among other things, the treatments available for the given disease being screened and the cost of that screening program. If treatments for the disease already have a low success rate (what is low?), the timing of detection doesn't really help. Additionally, if the cost of the screening program is negligi…

The current consensus about over-diagnosis (as I understand it) is that when there is a significant false positive rate and the cost of proving the positive false is high (in money, time, effort, worry), the screening program is not helpful. Some go further to say that low cost screening drives some of the high cost to outcome ratio in the US. I'll try to find a cite in my textbooks if you are interested.

I think the issues are deeper than that of false positives. Its possible that transient diseases get detected that would have fixed themselves without any treatment. Insead of a non-treatment one now has to deal with the side-effects of the interventions applied.

Re: Medicine's Machine Learning Problem

#89

Post by BlueTemplar »

refurb wrote: post #29
gdebel wrote: post #14

I'm an eye surgeon and self-taught machine learning practitioner, I started to learn Python in 2016 when the deep learning hype was at his highest. After 3 years of research, playing with datasets, extracting and cleaning data from EMR and from different machines, I not sure that the biggest problem with the so-called "AI" is the inequalities that it can induce ; it is rather, is it useful at all ? This is a little b…

First, it took me a very long time to really, fully get that AI is not fundamentally different from a simple linear regression (infering a rule from data). I had a similar revelation. I sat through an AI for health presentation and basically asked “ok, so you take a data set then try and find a set of rules that accurately describes...like a linear regression?” As you said, it’s more sophisticated than that, but in e…

Also because linear regression is a form of AI. (Anything done by a computer rather than a human is.)

Re: Medicine's Machine Learning Problem

#90

Post by Gatsky »

ps2fats wrote: post #17
gdebel wrote: post #14

I'm an eye surgeon and self-taught machine learning practitioner, I started to learn Python in 2016 when the deep learning hype was at his highest. After 3 years of research, playing with datasets, extracting and cleaning data from EMR and from different machines, I not sure that the biggest problem with the so-called "AI" is the inequalities that it can induce ; it is rather, is it useful at all ? This is a little b…

May I suggest, in response to your sentiment that applications of AI to medicine are lacking, is that you are seeing applications replace current medical practices. An AI diagnosis of a medical image seems redundant indeed, however in this situation a patient has seen a doctor out of complaints and has been sent to the radiologist for further investigation. This medical practice is reactionary, and suspicions are alr…

I would differentiate prevention from screening. Screening is for early detection of a problem (for example, the Pap smear to detect pre-cancerous lesions on the cervix). Prevention prevents the problem in the first place (eg the vaccine against the human papilloma virus which causes cervical cancer).

Truly effective preventative measures are the apex achievement of medical science, and have simply deleted an unimaginable amount of human suffering from our modern lives. Vaccines and sanitation are the best examples. They are astoundingly cost effective measures, and are so good that in many ways they are unimprovable in any significant way. 2020 is yet another example of how important vaccine technology is to every single person on this planet.

Screening is nowhere near as beneficial as actual prevention. It is expensive, labour intensive, requires behavioural modification, definitely harms a significant proportion of people due to false positives, and in controlled trials only modestly improves hard clinical outcomes under the most charitable assumptions of compliance and follow up care.

You are proposing a model of 'high-touch' medicine, where people have a raft of continuously administered screening tests for a long list of conditions. This could only ever be applied to a small proportion of the world's population, and would require highly motivated and well educated patients. In my opinion, spending a day in a primary care medical clinic would disabuse you of the notion that this is a feasible or desirable outcome.

Post reply on HN