Thank you for your honesty.
May I ask, what exactly do you do that you feel justifies your 800k per year? It seems to me that your career is ripe for disruption.
May I ask, what exactly do you do that you feel justifies your 800k per year? It seems to me that your career is ripe for disruption.
The only thing I can control is the number of studies I read. If I work harder and read more, I make more. It just so happens that I am very fast, and I have surrounded myself with fast partners. On average we read two or three times what other radiologists read, so we make two or three times more.
As far as disruption is concerned, for now the law is on my side. Of course a doctor working in India could read studies cheaper than I could. Most doctors complain about malpractice, without understanding the benefits. Trial lawyers hold me liable for my reports, and rightly so. If I miss a small treatable cancer, it can turn into a large untreatable cancer. This liability also confers a monopoly. How can a lawyer sue a doctor in India? Consequently, in order to perform a 'final read' on a radiology study in the USA, you must have trained in USA, be credentialed in the USA, and liable in the USA. This makes it very hard to undercut on price.
So, I'm not sure if I deserve what I make. There aren't a lot of people that can do my job, or withstand the training. Anyway, I'm saving everything I earn, because I don't think it will last forever.
I happen to think real AI will not happen in my lifetime, if ever. This is not an uninformed opinion, I have MS in Neuroscience, and I'm a programmer. I'm sure others reading HN will disagree.
It will take nothing less than a full artificial intelligence to do what I do.
If you want to read more about early attempts, there is something called "Computer Aided Detection" that is used when reading mammograms. It is awful, and I'll let you in on a secret. Most places that CAD their mammograms do it so they can charge more, not because it helps.
I know a guy who's working for one of the big CT manufacturers (Toshiba, I think) working on 3D image-registration and partial analysis. In essence, lining up the features from different slides and sewing them into a 3D model.
One of the big features being looked at was automatic labelling of certain gross anatomical features - I seem to remember something about cardiac veins needing to be marked as part of a scan report? By mostly automating this, it saves time for the user so they can just check they're correct, maybe move them if not, rather than having to do all the work themselves.
I can see this sort of work being much more useful, and happening in a much shorter term than any sort of AI "You have cancer" system. I wonder how you feel about that sort of thing?
It sounds like you already understand what it does. It helps me read a study quicker by automatically processing the data, a step I used to do by hand. Many times the processing fails due to an artifact while scanning ( patient moves, ectopic heart beat, poor contrast injection timing, variation in anatomy), and I need to process it manually.
When it works well it is very helpful, but to be clear, it does not interpret the studies. I think many people replying in this thread don't understand the enormous complexity to accurate radiology reporting.
Also, providing a large amount of value in a small amount of time (like accurately interpreting the results of a scan) leads to providing huge amounts of value over the course of a year. Part of the explanation is the sheer volume of individuals he can give a reasonable amount of value to.
A reason this is the case is because the average healthcare consumer is totally removed from the cost of healthcare and the doctor has a perverse incentive to make work for him or herself and other specialists.
It's only a rare skill because of licensing/board requirements. I'm fairly certain if you told other people they could make $250k as a radiologist, they could self-teach.
The same thing could be said of programming if the only people that could practice had to be certified.
This may be possible in some medical fields (I doubt it), but not radiology. There is simply too much to learn. I completed 4 years of medical school followed by a 5 year residency. Some radiologists go through additional sub-specialty training. I've been practicing for 5+ years, and I'm still learning everyday.
I am a doctor's doctor, meaning my customers are doctors from every specialty, who order studies and read my reports looking for answers they can't answer clinically. I can talk to Orthopedic surgeons in their language, Neurologists in theirs, and Gastroenterologists in theirs. I'm familiar with the radiological manifestation of most pathological processes a human can experience.
The notion that someone could self-teach what I know seems impossible.
There are licensing and board requirements, but conspiracy theories aside they are not designed to create artificial scarcity, they're supposed to keep dangerously ignorant doctors from practicing.
But what can you say that about? I did 4 years undergrad in CS, followed by 5 years for a PhD. Followed by more than a decade in industry. And I still learn everyday too.
The notion that someone could self-teach what I know seems impossible.
I should be clear, as the term is ambiguous, they'd likely learn from experts, but not by going to a board approved medical school. But through things like online schools, programs, books, etc... It wouldn't be someone trying to recreate a curriculum from scratch.
There are licensing and board requirements, but conspiracy theories aside they are not designed to create artificial scarcity, they're supposed to keep dangerously ignorant doctors from practicing.
Given the lack of policing after becoming a doctor I'm skeptical of this claim. At the college level I'd like to see a wider swath let in to medical school, and then a more rigorous approach to filterning, based on not only medical proficiency, but ethics. The big problem I see with doctors isn't in expertise or proficiency, but in ethics.
And given the data on sleep deprivation and learning, I think loosening the requirements even a tad would result in less scarcity and better prepared doctors on average.
Radiology is a very difficult field to get into after medical school, something like 2/3 of American grads who apply get turned away. Additionally, for those who get in, up to 1/3 never pass all the board exams. It almost seems like you want to lower the bar, and I'm telling you it needs to be raised.
My guess is that if your system was developed and worked, the intelligence and drive required to complete it, the time spent studying and working to become competent in radiology would end up being no different than the current system. There are no short cuts.
I don't agree with kenjackson that the field can be self-taught, but saying that most people don't get into Radiology residencies tells me only that there aren't enough Radiology residencies to go around. The 1/3 board failure rate notwithstanding, my intuition is that there are far more people capable of practicing radiology than are currently allowed to try to get into the field. The intelligence level of medical students does not exceed that of PhD students in engineering, math, chemistry, etc., but the medical profession puts up much, much higher economic barriers to entry.
If the government decided to tax radiology providers and use the profits to increase the number of radiology residencies by 10 or 100-fold, I find it hard to believe that the lucrative profit margins of your industry wouldn't decline. Medicare reimbursement rates would go down as the number of providers increased.
All you've said is that some tests aren't being passed. Can you correlate them with improved medical care? Again, in my alternate world, I can construct a CS test that 90% of those w/ undergrad CS degrees would fail. That's not hard to do. The question is "does my ability to pass such a test correlate with my ability to do a website?"
You're pointing to scarcity and arguing that this is proof that we require scarcity. I'm saying that if you dropped the bar on these tests, but increased other policing practices that yielded a net increase in the number of doctors, I think you'd see an increase in medical care. My thesis is purely speculative, I grant you that.
I suspect we're likely to find out if this does work out in non-US countries once as medical information and training becomes more prevalent on the web.
Of course, I cannot prove that the tests insure quality. In fact, this is not what the radiology board exam does.
The board exam is designed to weed out dangerous doctors, which is probably the best we can hope for. So, I guess you can take my word for it or not, but dropping the bar at all would let dangerous people practice, which I see as a mistake. The people that I know who failed the exam should not be working in Radiology.
Thanks for the comments in this thread, they've been very informative.
I'm happy there are certifications, and I believe you that the bar should be raised, but given the huge demand for doctors, why aren't we increasing the number of medical schools?
If we have a supply problem, and we don't want to lower the bar, it seems like the answer is to let more people in at the front end, and let the filter do its job.
Doctors have the ability and incentive to increase demand, and I remember seeing data that this is what actually happens historically when you increase doctor supply.
I'm sure that there a many areas where a GP would like to schedule a follow-up, but can't justify it on the current evidence, and lets it slide.
Because there's this level of subjectivity in medicine, any increase in supply can easily be countered by the suppliers pumping up demand, keeping D/S exactly the same.
(I'm not a doctor, although I'm friends with a few)
And then separately, how many people would trust a self-taught diagnostician?
Most people don't have to be able to do it, just more than are allowed to do it now, but a factor of say 10.
Furthermore, I don't think people would necessarily need to go through med school and residency.
It's like building a website. There's probably some parallel universe where programming requires certification and only a handful of schools have it. It requires doing MITs SICP as the intro course. Requires compiler construction courses, algorithms, theory of computation and complexity, etc... And then a 4 year apprenticeship with other programmers. And then you can start building webpages, if that's what you want to do.
But we live in a world where it is open and so there's instruction available at many different levels. Would you let someone without a PhD in CS build your website? Of course you would.
And then separately, how many people would trust a self-taught diagnostician?
I trust my car mechanics diagnosis despite the fact I have no idea what level of education he has. But I'm fairly certain he's not an ME from MIT or Berkeley. With good self-study tools, I think that one can self-teach in specialized areas and achieve good mastery rather efficiently. I could imagine Khan Academy for Radiology taught by JHU and Harvard professors to be quite good.
You have got to be kidding me. How would this work for surgery? There are no short cuts to medical competency.
Sure, some of what I do is self-taught, I read books and articles, attend conferences, and complete Continuing Medical Education requirements. But I am able to do this because I attended medical school, then spent five years sitting less than a foot from experienced radiologists while they worked and answered every question I had.
The argument here is that medical boards are too rigorous, and test things that do not matter practically.
To give a ridiculous example, if a medical school required you to climb Mount Everest before becoming a doctor that might result in only 1 person becoming a doctor per year. However that scarcity isn't proof that climbing Mount Everest is needed to become a doctor. Nor is it proof that cutting out that requirement will provide significantly worse doctors than previous.
Additionally, in many things we need quantity more than we need extreme compentancy. For example when cut, its better to have some kind of treatment (e.g. first aid, stitching) rather than waiting for a surgical specialist.
Bright and determined baby-boomers became doctors and lawyers and accountants. Today smart and determined people aren't even going to college. The HN demographic is a perfect example of this.
I might argue that going to college is no longer necessary for the purpose of learning, because the material is so widely available. Even though I think that's true (for some fields), I still wouldn't advise people not to go to college because of the signaling problem (which one then has to sidestep by starting their own business or by contributing impressively in open source, etc).
I get hyperbole for the purpose of making a point, but if you go too far, you come off sounding a bit incredible.
Of course you don't need to have gone to MIT, etc to build a website. The room for error is just many many orders of magnitude different between that and radiology. There's a reason you don't generally hire self taught code monkeys to build software with real-time or life-ensuring requirements.
I don't have first hand knowledge of this; I am a programmer. I hear about this from a family member who is a radiologist. roentgen may obviously speak with more authority about his situation.
If we can read pediatric brain MRIs more accurately from across the country than the local small group, why shouldn't we?
One additional note. My 'customers' are not really the patients, my customers are the physicians who order the studies. Most hospitals and referring physicians demand that I be available to speak with face-to-face, so there are parts of radiology that cannot be performed remotely.
See my other answers. For each scan or xray performed, two fees are billed. The reimbursements are generally set in stone, and non-negotiable. Additionally, "fee-splitting" is Medicaire fraud. Meaning, if you as an independent businessperson own an imaging center and I read cases for you, you cannot keep any of my "professional fee" for reading the case. So there is no way for another radiologist to compete on price with me, it is simply illegal to offer to read the cases for less.
If you work for a hospital they keep the technical fee, and you get whatever professional fees you can collect. Insurance companies hate paying, so they will find any reason to deny. Collection rates range between 60% and 80%.
My partners and I own imaging centers, we collect both fees. So we are running a business, and I don't consider it small anymore.