Hacker News new | ask | show | jobs
by pcrh 545 days ago
The fundamental idea here is that doctors find it difficult to ensure that their recommendations are actually up-to-date with the latest clinical research.

Further, that by virtue of being at the centre of action in research, doctors in prestige medical centres have an advantage that could be available to all doctors. It's a pretty important point, sometimes referred to as the dissemination of knowledge problem.

Currently, this is best approached by publishing systematic reviews according to the Cochrane Criteria [0]. Such reviews are quite labour-intensive and done all too rarely, but are very valuable when done.

One aspect of such reviews, when done, is how often they discard published studies for reasons such as bias, incomplete datasets, and so forth.

The approach described by Geiger in the link is commendable for its intentions but the outcome will be faced with the same problem that manual systematic reviews face.

I wonder if the author considered included rules-based approaches (e.g. Cochrane guidelines) in addition to machine learning approaches?

[0] https://training.cochrane.org/handbook

3 comments

Hey author here--Cochrane reviews are great.

NCCN guidelines and Cochrane Reviews serve complementary roles in medicine - NCCN provides practical, frequently updated cancer treatment algorithms based on both research and expert consensus, while Cochrane Reviews offer rigorous systematic analyses of research evidence across all medical fields with a stronger focus on randomized controlled trials. The NCCN guidelines tend to be more immediately applicable in clinical practice, while Cochrane Reviews provide a deeper analysis of the underlying evidence quality.

My main goal here was to show what you could do with any set of medical guidelines that was properly structured. You can choose any criteria you want.

It amazes me that AI isnt a borderline requirement for being a doctor. Think of how much info is outdated or just wrong.
There's a lot of outdated and wrong info coming from AI tools as well. It's the natural outcome of training on a large historical dataset.
> doctors find it difficult to ensure that their recommendations are actually up-to-date with the latest clinical research

Doctors care about as much this as software engineers care about the latest computer science research. A few curious ones do. But the general attitude is they already did tough years of school so they don’t have to anymore.

I worked with oncologists and this isn’t true.

Oncology has a rapidly changing treatment landscape and it’s common for oncologists to be discussing the latest paper that has come out.

If you’re an oncologist and not keeping up with the literature you’re going to be out of date in your decisions in about 6 months from graduation.

Funny enough that last paragraph is also said of software engineers too. Neither are true.
Unlike oncologists, people won't die if you don't keep up on the latest programming techniques.
This sounds like it should be true but isn’t. Were oncologists killing people in 2010 because they lacked the research from the last 15 years? A career is only 25-35 years long.

And while we are here it’s always a good reminder that medical malpractice is the 3rd leading cause of death. So yes they are still killing people everyday.

doctors are not a special class of professional. They are guided by intuition, standards, a touch of research, and mostly experience. Most of the time that gets the job done.

> This sounds like it should be true but isn’t.

It absolutely is true, I've seen it myself.

> Were oncologists killing people in 2010 because they lacked the research from the last 15 years? A career is only 25-35 years long.

100% absolutely they were.

Maybe you don't understand just how fast cancer treatments change? Cancers that had 20% 5 years survival rates 15 years ago, now have 60% survival rates.

Thus if a doctor today isn't aware of those new therapies, they are killing patients that would otherwise live.

> And while we are here it’s always a good reminder that medical malpractice is the 3rd leading cause of death. So yes they are still killing people everyday.

How is this relevant to the point?

> doctors are not a special class of professional

I'd say they absolutely are. Unlike most other jobs, their decisions don't directly have an impact on whether people live or die.

Which is why we treat their employment differently requiring not only education, but supervised work experience, standardized exams and licensing. If they don't fulfill those requirements, they don't work as doctors, period. That seems like a special class of professionals to me.

Yeah, non-programmers seem to think everything is changing so quickly all the time yet here I am writing in a 40 year old language against UNIX APIs from the 70s ¯\_(ツ)_/¯