[bdzr]

> I agree. Expecting perfection from humans, even experts, is not reasonable and is frankly counterproductive.

There's a big difference between perfection and "Statistical Literacy Among Doctors Now Lower Than Chance"[1]. I don't think their intentions are bad, but they are woefully incompetent at many basic things.

[1] https://slatestarcodex.com/2013/12/17/statistical-literacy-a...

[bonsai_spool]

> There's a big difference between perfection and "Statistical Literacy Among Doctors Now Lower Than Chance"[1]. I don't think their intentions are bad, but they are woefully incompetent at many basic things.

As it happens, the daily practice of medicine does not require interpretation of p-values. Indeed, medicine existed before the p-value.

The people who create studies that ultimately guide policy decisions are specialized (much like people who write GPU drivers are different from those who run inference)

[bdzr]

> As it happens, the daily practice of medicine does not require interpretation of p-values. Indeed, medicine existed before the p-value.

What are you talking about? Doctors refer people based on test results every single day. From what I've seen, hardly any of them understand the precision/recall of the tests that they then use to refer you (or not) to screening procedures (which are not all harmless).

[bonsai_spool]

> What are you talking about?

What are you talking about? How is a single lab value going to generate a p-value? Why are you presuming that your family med doc should be calculating an ROC for each of her 1,500 patients?

The selection of lab critical values is performed by experts in clinical pathology. Exactly the people who were not included in the paper you cited.

You can find links to support any argument you want on the internet.

To place this in clearer HN terms, you're saying that a front end dev is trash because he didn't write his own web browser in assembly.

[stalfie]

To be fair, being knowledgeable about the pre-test probability of a patient having a certain disease vs the sensitivity/specificity of a test IS part of the ideal practice of medicine, although how important it is in practice varies somewhat between specialities. In rheumatology for instance, it is front and center to how you make diagnoses. I was in primary care for a short while myself, and on more than one occasion regretted deeply ordering certain rheumatological screening panels (which you get without asking for it when looking for certain antibodies).

Explaining to a parent the fact that their child did in fact not have a rare, deadly and incurable multi-system disorder even though an antibody which is 98% specific for it showed up on the antibody assay, that we took for an entirely different reason, is the kind of thing thats hard to explain without understanding it yourself.

[bonsai_spool]

Bayesian thinking isn’t about p-values and doesn’t need to be presented that way.

If you use the centor criteria before resting for strep, is that worse than getting out a piece of paper and researching background population prevalence?

The OP is being dogmatic about doctors needing to know things he does which is obviously silly.

Edit - but yes, I agree that we should think about sensitivity and specificity, I just don’t think you need to be a statistician, just to have a helpful script and resources for patients who wish to know more.