What he's saying applies to research nowadays too, especially biology-related. People in e.g. my lab (neuroscience) come from EE, Bio, Physics, Medicine, Stats, CS ...
It's working, though. Care is getting better than ever. Science is progressing faster than ever. We just need more. More funding, more education, more scientists, more talent. Especially in biology, we need a lot more computer scientists, especially the theoretical kind. A probabilistic pi-calculus would do wonders for dealing with the sorts of errors that cost Duane Smith his digits. We need more mathematicians to help us handle systems of vast and irreducible complexity, and we need more truly excellent experimentalists to pull off what was thought impossible.
That's what will help medicine the most, I think. More and better science, and intelligent people thinking rigorously about process. It costs money. My "one wish" would be to redirect the resources we've wasted in our War on Drugs, and the War on Terrorism / the Middle-East, and throw it all at the War on Human Ignorance. In truth, it's amazing how cheap progress is. The cost of developing a new cancer drug is way less than the cost of invading Iraq. It's actually cheaper to save lives rather than kill people!
This post doesn't really have a point. I just wanted to express my vote of total optimism for science in these days of rampant pessimism. It works, it's actually pretty cheap, and it gives back a thousand times more than what we put in. If you're in college and you're reading this, please become a scientist (or a doctor) :)
I fully agree with you here, I work in your field currently and noticed the wide range of skills that are employed. For example my lab director is a Physicist working in brain imaging research.
All the math I learned in school (I have a BS in math) seemed so small compared to the stuff I see used in the research the folks in my lab are doing. There is a great need of skilled mathematicians and comp sci folks in these bio based fields, as you pointed out. Biologist are smart people but when it comes to comp sci their cs skill sets are not always large enough for their need. That's where p eople like us fill in the blanks.
Malcolm Gladwell covered a great story in Blink about the success of decision trees in diagnosing Chest Pain at Cook County Hospital in Chicago. The doctors were very resistant to using the tools. I wonder if we will just have to wait for the old guard to die off before new innovations in technology can be integrated into medicine.
Imagine a Netflix challenge for catching medication problems using customer case files. "Your patient had his spleen removed but is not receiving medication to compensate." should be displayed along side the case so every reviewer would see these recommendations.
What we need is the francise model they are starting to explore in India. Repeatable processes encoded in easy to follow three-ring binders; checklists and procedures that anyone can follow. This will take care of the basics and free up resources for the gourmet care we all need from time to time.
I find it a bit alarming and surprising that there aren't documented, repeatable processes for how to treat common diagnoses and disorders wholistically. Although my surprise is tempered when I think of the arrogance of almost every doctor I've come into contact with - and that's quite a few: an uncommonly persistent neurologist found my pituitary tumour when I was 12 after several others decided I was probably just making up my headaches because I didn't want to exercise.
I've dealt with many other specialist and GPs since then and there's always that omniscient, arrogant attitude from them, especially when they don't have an easy answer for you. I've also watched a few people go through medical school and seen them gradually become like this as well.
It's a world apart, but IT and software development practices have matured over the last 10+ years and have been forced (sometimes catalysed by business requirements e.g. Sarbanes Oxley) to adopt standards, practices and more thorough documentation than previously.
Personally for me it's a narcissistic thrill thinking that you can invent something brand new or solve some problem that someone else couldn't. For me then, the standardisation, extra documentation and the increasing amount of lego-brick style clicking together of existing pieces of wizardry that someone else has built have made IT less exciting.
Of course I could go build an incredible open source something or other in my own time but narcissism is about _delusions_ of grandeur, not actual grandeur ;)
So the bush I'm beating around is that maybe personal and collective arrogance of medical practitioners has blocked this kind of thing being implemented before?
Eastern cultures are much less individualistic - they seem to rely much less on individuals to creatively and independently figure things out in so many fields and situations, preferring to defer to tradition, or predefined rules, or an authority.
I'm not saying doctors are irresponsibly arrogant, they do amazing work, most are thoughtful, compassionate and insanely dedicated people who commit their entire lives to what they do.
But is the mindset that the rarefied world of medicine and its practitioners being so important and sophisticated that every situation requires years of education and experience to manage holding it back?
I remember reading an article (or mayba was it in a book?) about that; a parallel was made with the checklists in airplanes, after the crash of the B17 prototype in the '30s. If only I could find a link...
This article was extremely interesting. I remeber wired reporting on a system which would allow doctors to give a list of symptoms and have the most likely diagnostics listed by probability. Not sure of the name but technology like that has incredible potential. I also remember the article mentioning the reluctance of doctors to use it.
This kind of problem seems more widespread than only in the medical field. This stuff just reminds me of what Doug Englebart was trying to do with his NLS system. Augmenting Human intelligence. Were reaching the limits of what single humans are cable of retaining and processing in their daily jobs. I think that it's time for stuff Englebart did in the 60s to be rediscovered. While the internet is great, it's potential hasn't been maximised in area like this. Englebart's vision went much further than just google. Wolfram alpha is getting close to this in a way but still not far enough. I'm sure someone is already starting to develop this stuff (post some links if you have any).
I can just imagine an iPad application (preferably android table app ;p) for doctors which implements the system I talked about at the beginning of this post. Giving doctors on the go access to a database of diseases and medical records of the patients and a way for the computer to anylisze the data and return the info right there (powered by a huge hadoop cluster). Typing a few symptoms, getting the list of possible diagnostics and viewing some checklist of things to do. This would in no way replace doctors, I don't believe that we have reached a point where you don't need a human person to judge the validity of the computer guesses. In fact, assessing the symptoms is probably going to require a trained professional for ages but, at the same time I think there is massive potential for this kind of AI in these information intensive fields.
There is definitively lots of startup potential in all this.
I see a lot of startups solving easy problems (for good reasons) but this is worth a 10 twitters in value.
If I wasn't doing stuff in the medical imaging field (Brain imaging specifically) I'd go out and build this.
a system which would allow doctors to give a list of symptoms and have the most likely diagnostics listed by probability
Oh, good. Seems every episode of House I watched would contain a scene that began with, "Differential diagnosis for shoulder pain, go!" And then they'd spend ten minutes listing off all the diseases that could cause it. And I'd spend ten minutes thinking "You people really need a database."
I'm not sure that House is an entirely accurate depiction of how diagnostic medicine works. For instance, I'm pretty sure real diagnosticians have to look something up in a book every now and then.
Indeed. I hoped that something like what I imagined either existed or was actively being built. Until this comment, though, my faith in the medical industry was insufficient to justify the belief.
This article was extremely interesting. I remeber wired reporting on a system which would allow doctors to give a list of symptoms and have the most likely diagnostics listed by probability. Not sure of the name but technology like that has incredible potential. I also remember the article mentioning the reluctance of doctors to use it.
I keep reading comments like this and am wondering if anyone has been to an HMO in the past 5 years. This is part of any GP's office with a full EPIC install. I guess many probably don't use it, unless they are forced to. Just wanted to point out this tech already exists in a commercial product. It's not wonderful, it actually kind of sucks. I also wonder why hackers think software like this is going to have "incredible potential," or even be "good."
Why wouldn't it be "good"? If you can only remember the symptoms of 200 diseases, but the machine can remember 18000, why wouldn't it be net-beneficial to always input the symptoms into the machine, as well as performing whatever deductive diagnosis you do normally? Is it just because the UI of existing implementations is horrible?
I thinks this is the whole point, were not just talking about making a wiki of disease but doing some analysis of the case and narrowing down the range of disease possible to something the doctor can analyse.
To the ../../post can you remember the name of one of these systems? it be interesting to see what it does and how it works. I don't believe what's out there is what I'm imagining.
EDIT: reread your post, I just found the side for that EPIC system (terrible name). http://www.epic.com/ The page doesn't inspire confidence in this system being of any quality or does what I am talking about.
It does exactly what you're talking about. The quality is not good, but I don't know why anyone thinks the situation will improve. Countless careers have been wasted on expert systems, recommendation systems, and the like. The best minds doing this sort of thing will always be poached by wall street, where they still fail most of the time. However if it makes people feel better, most HMOs and managed care systems will start requiring their doctors to use such a system, if they don't already.
The problem is of expectations. We don't expect computers to write books (creativity is a Hard problem), but we do expect writers to use word processors.
Likewise, we shouldn't expect computers to deduce your ailment and prescribe treatment (critical thinking is also a Hard problem), but we should expect doctors to use computers to remember, search, and sort things for them: the things computers are good at.
We don't need the computer to think—we need it to help the doctor think. People should be working on that, not on systems to replace the doctors themselves.
I understand what you are saying but I'm an optimist at heart. I don't think careers were wasted because most of what's out there is not very good. This stuff is hard to solve but after seeing things like wolfram alpha I can't help but wonder if these systems will improve soon. As for startup attempting this, it's a long shot but those are the ones that make money.
One such system was Pathfinder, which (I believe) used a relatively simple Bayes net to diagnose within certain categories of disease.
It was able to outperform pathologists in the area it was designed for because (or so I've been told) it didn't face the cognitive biases that human doctors have (like the inability to reason with probabilities, the accessibility bias, etc).
What incentives are there for engineering a better process? Seems like PPOs and HMOs would both want this. But I guess only HMOs are the only ones who have a chance of making progress here.
Kaiser does seem to be making progress here, but I'm not sure how fast it is.
Incidentally, for the recent "what problems need solving?", this is one.
Interperson coordination. I want it for small team IT project work, they want it for multiteam medicinal work.
We have decent task schedulers in computers at the kernel level, multiple processes, multiple threads, RPC, yet in people terms we're still on email, shared docs, waves, CRUD-dy database frontends with no central driver.
And I don't want to be the central project manager myself, tracking lots of data and sorting it into order - that's machine work.
It's working, though. Care is getting better than ever. Science is progressing faster than ever. We just need more. More funding, more education, more scientists, more talent. Especially in biology, we need a lot more computer scientists, especially the theoretical kind. A probabilistic pi-calculus would do wonders for dealing with the sorts of errors that cost Duane Smith his digits. We need more mathematicians to help us handle systems of vast and irreducible complexity, and we need more truly excellent experimentalists to pull off what was thought impossible.
That's what will help medicine the most, I think. More and better science, and intelligent people thinking rigorously about process. It costs money. My "one wish" would be to redirect the resources we've wasted in our War on Drugs, and the War on Terrorism / the Middle-East, and throw it all at the War on Human Ignorance. In truth, it's amazing how cheap progress is. The cost of developing a new cancer drug is way less than the cost of invading Iraq. It's actually cheaper to save lives rather than kill people!
This post doesn't really have a point. I just wanted to express my vote of total optimism for science in these days of rampant pessimism. It works, it's actually pretty cheap, and it gives back a thousand times more than what we put in. If you're in college and you're reading this, please become a scientist (or a doctor) :)