site banner

Culture War Roundup for the week of April 24, 2023

This weekly roundup thread is intended for all culture war posts. 'Culture war' is vaguely defined, but it basically means controversial issues that fall along set tribal lines. Arguments over culture war issues generate a lot of heat and little light, and few deeply entrenched people ever change their minds. This thread is for voicing opinions and analyzing the state of the discussion while trying to optimize for light over heat.

Optimistically, we think that engaging with people you disagree with is worth your time, and so is being nice! Pessimistically, there are many dynamics that can lead discussions on Culture War topics to become unproductive. There's a human tendency to divide along tribal lines, praising your ingroup and vilifying your outgroup - and if you think you find it easy to criticize your ingroup, then it may be that your outgroup is not who you think it is. Extremists with opposing positions can feed off each other, highlighting each other's worst points to justify their own angry rhetoric, which becomes in turn a new example of bad behavior for the other side to highlight.

We would like to avoid these negative dynamics. Accordingly, we ask that you do not use this thread for waging the Culture War. Examples of waging the Culture War:

  • Shaming.

  • Attempting to 'build consensus' or enforce ideological conformity.

  • Making sweeping generalizations to vilify a group you dislike.

  • Recruiting for a cause.

  • Posting links that could be summarized as 'Boo outgroup!' Basically, if your content is 'Can you believe what Those People did this week?' then you should either refrain from posting, or do some very patient work to contextualize and/or steel-man the relevant viewpoint.

In general, you should argue to understand, not to win. This thread is not territory to be claimed by one group or another; indeed, the aim is to have many different viewpoints represented here. Thus, we also ask that you follow some guidelines:

  • Speak plainly. Avoid sarcasm and mockery. When disagreeing with someone, state your objections explicitly.

  • Be as precise and charitable as you can. Don't paraphrase unflatteringly.

  • Don't imply that someone said something they did not say, even if you think it follows from what they said.

  • Write like everyone is reading and you want them to be included in the discussion.

On an ad hoc basis, the mods will try to compile a list of the best posts/comments from the previous week, posted in Quality Contribution threads and archived at /r/TheThread. You may nominate a comment for this list by clicking on 'report' at the bottom of the post and typing 'Actually a quality contribution' as the report reason.

11
Jump in the discussion.

No email address required.

Dr. GPT will see you now

I've often noted around these parts that GPT-4 is a really good clinician. It would be hard for it not to be one, I'd be bloody amazing too if I had quasi-eidetic memory of most relevant diagnostic criteria and guidelines. That being said, just the guidelines alone are next to useless, you need to have the crystalline intelligence to apply it in a specific context.

I'd go so far as to say that it's a better, more competent doctor than the majority of human ones, even if it isn't outright superhuman (I've seen some ridiculously good human ones). I read with some humor an article about how it was tested by some bigshot hospital in the US (Harvard Med?) as a clinical adjunct, but by the end of it, the Clinical Director was praising its bedside manner, in the sense that it was kind, compassionate, patient and understanding, and outright suggested human doctors try and emulate that(!).

However, I have one resounding advantage over it namely that thanks to decades of regulatory bullshit, I have a certificate saying I can legally prescribe meds and it can't. L Bozo 💅, as the kids these days say haha.

Still, it would be remiss of me not to make use of it to improve my own skills while that's still relevant, so of late, I've tried using it to hone my own clinical skills. I have it write clinical vignettes that I solve, and then it grades me on my performance.

So far, it's done an excellent job, and funnily enough, I feel a tingling of pride when it says I did a good job. Why wouldn't I? It's a smarter and more decent entity than most humans I've had the displeasure of meeting.

Here's an example:

Clinical Vignette: A 42-year-old male patient presents to the emergency department with sudden onset severe, colicky pain in the right flank and lower abdomen that began 6 hours ago. He also reports nausea, vomiting, and an urgent need to urinate. The patient has a history of hypertension, which is controlled with medication. His vital signs are: blood pressure of 145/95 mmHg, pulse rate of 100 bpm, respiratory rate of 20 breaths/min, and temperature of 99.1°F (37.3°C). Upon physical examination, there is tenderness to percussion on the right side of the lower abdomen and right flank, and the patient appears restless, frequently shifting positions.

What is your diagnosis and treatment plan?

My response:

My diagnosis is a case of a stone in the right ureter.

In terms of management, I'll start IV fluids and insert a catheter. IV antibiotics are to be started according to hospital guidelines.

IV morphine should be given as pain control, along with IV antiemetics.

An Xray KUB or USG should be ordered to identify the size of the stone, and then further treatment depends on said size. A wait and watch policy is appropriate for sub 2mm stones, while larger ones might need surgical removal.

Assessment:

Grade: A

Your response demonstrates a strong understanding of the clinical presentation and management of ureteral stones.

Diagnosis: Your diagnosis of a stone in the right ureter is appropriate given the patient's sudden onset severe, colicky pain in the right flank and lower abdomen, nausea, vomiting, and urgency to urinate. The physical examination findings, such as tenderness to percussion and restlessness, also support this diagnosis.

Treatment Plan: Your plan to start IV fluids and insert a catheter is appropriate for initial management, monitoring, and providing relief to the patient. Initiating IV antibiotics may not be necessary unless there are signs of infection or sepsis; however, following hospital guidelines is always a wise choice.

Administering IV morphine for pain control and IV antiemetics for nausea and vomiting are essential parts of the treatment plan.

Ordering an X-ray KUB (kidneys, ureters, and bladder) or ultrasound (USG) is appropriate to confirm the diagnosis and determine the size of the stone, which will guide further management. As you mentioned, a conservative approach of observation and pain management may be suitable for small stones (less than 5 mm) that are likely to pass spontaneously, while larger stones may require surgical removal or other intervention, such as extracorporeal shock wave lithotripsy (ESWL) or ureteroscopy.

Overall, your response demonstrates excellent clinical knowledge in identifying and managing a patient with suspected ureteral stone. Well done!

Honestly, as a pedagogical tool for medical education, it's unparalleled. I paid a great deal less attention in med school than I should have, from the month of anatomy classes I can't remember because I was getting frisky under the bench, to the period where I was severely depressed and barely dragging myself to class. I used to be very insecure about my knowledge base, but I did pull together and single-handedly teach myself most of the things I'd glossed over while preparing for the PLAB.

I've tried a similar method on GPT-3.5, and it was inadequate to the task. It made a lot more errors, and ended up confused often enough to be annoying. Till date, I haven't seen 4 fumble the bag once. I'd put their competency around the marks of a decent final year student versus a competent postgraduate resident

Note - GPT4 is handicapped when it comes to performing on 'exam recall' style questions. It still performs admirably, but 2 changes will immediately make it perform better with no extra "innovation" required.

1. Using medical reports in the pre-training dataset.

Presently, most medical reports are privately held, and not available on the open internet. Unlike law, where a majority of cases have at least semi-redacted public documents, medical documents are not available to GPT-4 for training. GPT-4 went from 40th percentile to 88th percentile on the LSAT BAR, by simply adding legal data to the pre-training set. This would be equally easy to do with medicine if HIPAA didn't exist.

2. Retrieval + generate instead of next-word-prediction

GPT models have no sense of truth. This means, that they will confidently blabber about anything you throw at them, even if it is complete lies. Second, even if the model has read everything on the internet, it does not mean it can recall which bits it should be reading with ease. Retrieval style work workflows allow the model to first go search for the right answer or correct reference document on the internet. It looks for the page with the answer on it. Then, it uses its 1600 SAT verbal IQ to interpret it in a manner that GPT-4 is famous for.

Both are relatively easy (as in doesn't need any major innovation to do) changes, and should immediately make the lives of every doctor a LOT LOT better. Y'all are doing 80 hr weeks anyway. Maybe this will help secure so WLB. Ofc, it won't actually happen because Doctors are Evil.

I don't really see why you'd think doctors are evil really, though of course it's hard to make a man understand something when his salary hinges on him not understanding it.

US doctors are far more professionally organized and cartel-like than their peers abroad, they command significantly higher wages and have more to lose. Even then, the medical system is no insanely sclerotic and dysfunctional there that I doubt it's doctors sucking the surplus out of it.

In contrast, Indian and British doctors, the two nations I'm most familiar with, are far less militant in their self protection. The former are barely fending off PAs and NPs, and in India there's a tide of homeopathic and ayurvedic quacks lovingly recognized by our governments under AYUSH.

The Brits have shit salaries, thanks to being employed by a monopsony in the NHS. Indian doctors make poor salaries because the country itself is poor. Neither are ripping off the locals.

What the US does suffer from is a sense that nothing but the best will do. Barring a new midlevels of their own, often sneakily employed unless the patient asks for a doctor instead, there's a sense of sacrilege in accepting care of 80% the quality for 50% the price.

Of course, in India, it's accepting hired monkeys in lab coats that know enough to dole out paracetamol, so something like 30% the quality for 50% the price. But it works, since the typical Indian isn't very discerning.

Consultants make that much about 7-8 years into training, after 4 years of med school and 2 years in the Foundation program. From my understanding, hanging around on subs for British doctors for several years, people feel shafted when they can quite easily emigrate to other Commonwealth countries and make a great deal more, while also dealing with less antisocial hours, more time off, and coverage of the thousands of pounds in fees for mandatory exams needed for career progression. No faffing about being chucked from one end of the deanery to another to boot.

In addition, the perception is that they could have made far more money at the entry level and above by going into something like finance instead of medicine, which I'm given to understand is the one domain in the UK that makes a decent chunk of dough.

In addition, the Government as a monopsony employer has enforced sub-inflation pay raises for over a decade, while resisting pay restoration efforts, leading to the recent strikes. Further, doctors can make a great deal more outside the NHS working for private hospitals, with the only reason to work in the NHS being that your career progression hinges on it. Once again, the monopsony employer suppressing wages..

And of course, wages for entry level doctors in the UK are abysmal, especially given the amount of time spent in training and their responsibilites. A PA can make 45-50k while having fewer responsibilities than an FY2, the latter making around 35k. They can't even prescribe!

As such, a great number of the locals are fleeing to fairer shores, and being replaced by IMGs like yours truly.

And a software developer in UK makes less about 40k after 3-5 years of uni and a couple of years of work. A senior developer with who knows how many years of additional training makes about 50.

Doctors are extremely well compensated and have unparalleled employment security.

It's probably true that people can emigrate to get higher salaries but that is even more true of other professions.