What a godawful ignorant comment you've made. Scientists and their orgs do value their work. The whole system is screwy. We pay scientists jack shit, make them scrounge for research money, then write technical papers that they get paid squat for, charge them for things like public access and color graphs, and make a bunch of other scientists review those papers for free and create more unpaid labor for the writing scientists. Finally it gets published, which you pay thousands of dollars to access either as a member of a society, journal subscriber, or through your institution. Meanwhile, marketing majors and MBAs pull hundreds of thousands of dollars a year in salary, not to mention bonuses. But yeah, that's a problem of the Left, not of unfettered capitalism and a general apathy if not distrust of science in the US. But hey, enjoy reading this comment on your handheld computer through the intertubes. God has willed it.

Please tell that to the clinical scientists I work with.

As a few other (already up-modded) commenters have noted, this test is not necessarily specific, however sensitive it may be. This is about tapping into people's fears about having neurodegenerative problems later in life, when we don't really know for sure what can be done to mitigate them ahead of time, besides living a health lifestyle. So basically it's a moneymaking scheme, since we can't really do anything about it, and it has limited clinical/research use due to its non-specificity vs. more expensive tech (i.e., MRI and PET). I personally think the bar should be set very high by the FDA to approve test likes this because they literally can cause harm by inducing anxiety in people who would otherwise be blissfully unaware of their biomarker status, which in any event is not 100% predictive of outcome at the individual level.

Ubiquiti unifi cameras ftw.

You are really out of your league here. I've published a lot of papers, and I've reviewed a lot of papers (as in the top 10% of reviewers in my field). I am very familiar with how the system works. From your comment here and elsewhere it is clear you do not. But hey, keep insisting you are right while those of us with decades of education, experience, presentations, papers, and peer review look on shaking our heads.

There are opposing views, and then there are bad ideas and bad science. As an active peer reviewer, I reject poorly written manuscripts and poorly conducted science. This is not unusual. There are a lot of armchair scientists rejecting climate change and its causes. But their logic and command of the facts lack the rigor that working scientists have to apply every day. Not everyone's opinions are equally valuable.

Not a huge of enough difference to justify your logical leap that you can "make" the values whatever you want. We are talking temperature measurements here, not the values of properties as reported by Donald Trump.

X-ray is fairly harmonized, the other imaging modalities not at all. Garbage in, garbage out. Additionally, COVID, while new, still has a lot of data out there to train on, and it just isn't cutting the mustard yet. We don't know what a lot of DL algos are running off of, and there doesn't seem to be much interest in figuring it out, only in getting results that we can generate AUCs for, and then say, "Oh look, this number is higher, so it's better, right?" Shades of Spinal Tap abound in Radiology.

It's AI trying to detect COVID (known outcome) from X-ray (same modality). So it's not dissimilar. That margins are what matters, not whether there is something obvious like a broken rib or a pneumothorax.

Hello, I work in radiology. I strongly recommend that you not opt for the AI over the radiologist at this point and time. Especially given the scant detail of this study, whose summaries includes nothing about the population studied, which conditions, etc. We are still struggling to get AI to identify COVID using large databases created with federal dollars in the US. Don't get your hopes up too fast.

YNAB FTW

Make their funding commensurate with their impact.

They develop, set, and maintain various standards. They perform fundamental research. They produce Nobel Prize winners.

They only get a billion a year, and are mostly forgotten by Congress and the lay public. Extremely understaffed and heavily reliant on newly minted PhDs to do the grunt work. They donâ(TM)t hire very many people permanently so there is continuous brain drain. You get what you pay for as the taxpayer.

Why do you say that? Have you peer reviewed before?