The system in this article is not interpreting mammograms, which is something that radiologists do. This is looking at tissue samples on slides, the domain of pathologists.
116 karma · joined September 24, 2011
These exist, google for "mammogram computer aided detection". While the data on their efficacy is equivocal at best, I well tell you that they are useless. I do get to bill more for reading a mammogram if I run it through a CAD machine, which my group owns, so of course I do it.
Strangely enough, patients are reassured when the learn that the computer didn't detect any problems. And, more importantly, ignorant juries can be swayed by this piece of information. "The computer didn't detect anything? Then there is no way the radiologist should be held liable for missing that little tumor!" I'm not joking.
Little do they know.
Yes, exactly. To computer savvy people unfamiliar with radiology it looks like something a computer might be good at, but I suspect the best we can hope for is a computer to aid me in my work, not replace me.
I have been programming computers since I was 5 years old. I have a MS in neuroscience, and I am a board certified radiologist, so I think I'm qualified to understand the problem.
Believe it or not, nothing would make me happier than a magical black box that could spit out accurate radiology reports. Someday I'm going to get sick, and I would benefit from the technology.
If my job was replaced tomorrow I would be OK. I'm smart and hard working, and I'm good at almost everything I try, eventually. Also, I'm saving every last penny I earn, so I can keep things up for a few more years I should be financially secure.
Having said all that, I still think the problem is not solvable. On any given day I read xrays, CT scans, MRIs, ultrasounds, PET scans, mammograms, nuclear medicine studies, or live flouroscopic studies, and using CT or ultrasound guidance I can get a needle into just about any part of your body to take a biopsy. Doctors talk to me and our discussion influences the differential diagnosis, and the interventions planned. I am not just matching patterns, I am thinking and using my hard worn judgement.
Wishful thinking aside, computers cannot do this now, if ever. And if / when we reach the point that computers can do this, my guess is every other job will have fallen, with the exception of plumbing.
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.
See my response below, and look into "CAD" and mammography.
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.
Final interpretations must be performed by a radiologist residency trained in the USA, licensed in the state there are reading from, and credentialed for the facility and the insurance company.
Why? Well, I guess it's supposed to be to ensure quality. In general, it is probably good that every hospital in the USA has an independent credentialing process. You could debate the fact that doctors in the USA are better trained, but in fact that has overwhelmingly been my experience.
Cynically, I believe that the lawyers need someone to sue. Like I said, most doctors complain about malpractice, but not me. The trial lawyers can't sue doctors overseas, but they can sue me. So, in a sense they are my ally, they ensure that no one else ( except people they can sue ) can read the studies.
That being said, there are companies that take USA trained radiologists and station them overseas. Australia and Geneva are both popular. They take advantage of the time difference to read hospital cases that occur overnight, when I am home in bed. They usually provide a preliminary read, something like "no appendicitis." The next day I do a final read, look for mistakes in the preliminary read, and in general do a more thorough job. Sure, there's no appendicitis, but the preliminary read didn't mention the small tumor in your left kidney that kind of looks like a cyst, but isn't.
FYI - overseas reads by USA trained radiologists tend to be more expensive, not less.
Anyway, thanks for jquery.
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.
> increasingly radiology has been outsourced overseas with mostly technicians required stateside (scan during the day, radiologist in India examines at night, results available the next morning).
This is not true. Some "preliminary reads" are read overseas at night, but the doctors reading the studies are trained and certified in the USA. "Final reads", the CT scan report that counts, cannot be read elsewhere.
I should make clear why I'm replying in this thread. The world needs good doctors, and I want bright and ambitious readers of this site to know that there is a potential upside.
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.
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.
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.
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.
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.
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.
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.
For reference, before medical school I worked in IT, and at the age of 23 ( 15 years ago ) I was making six figures. I left that to go back to school, partly because I knew I would be financially rewarded.
Again, see my response below. I don't order the studies I read, and I don't set the reimbursement rates. Additionally, it is Medicare fraud for me to read a study and not charge for it. In short, I have very little say over what I earn.