Ben White, MD

Privademic neuroradiologist. Independent blogger. Author of the definitive books on #studentloans. Program Director of @BUMCRadiology (opinions 100% mine).

[Ben White, MD @benwhitemd]

Post-match fourth-year medical students: I cannot stress enough how important it is to build a foundation in personal finance and make a student loan plan.

I wrote this book just for you, and every word is available online ad-free. Now is the time.
https://t.co/GPW1fBJf2d

[Ben White, MD @benwhitemd]

One of the markers of quality, such as it’s commonly understood in medicine, is reducing variability. This is why we have best practices that are often not really the “best” in truth but are, essentially, a reasonable consensus approach.

https://t.co/YgtBRFsFEw

[Ben White, MD @benwhitemd]

@francisdeng @patrocity428 @morrisonMSK @WillyRontgen @northwoods1980 @heacockmd @drsxr This is true but the problem is Torcula sounds better than Torcular.

[AJR @AJR_Radiology]

Forecasting the radiology workforce decades into the future is nearly impossible. In his latest column, @benwhitemd suggests a more practical approach.

https://t.co/Ij4Jk0DlQ6

[Ben White, MD @benwhitemd]

@francisdeng @SMomtazmanesh @mona_gad_ @shailinthomas A lot of work left!

[Andrew Rosenkrantz @arosenkrantzmd]

New @AJR_Radiology Accepted Manuscript:

"The (Un)Knowable Future"

By @benwhitemd

https://t.co/oRLmckttfI

[Ash Paul @pash22]

“The Real Radiologist Rejects the Role of Robot” via @benwhitemd
https://t.co/my5LQqEk3I

[Ben White, MD @benwhitemd]

Some choice quotes from and thoughts on “The Radiologist Faces Automation,” a lecture given by Dr. Laurence L. Robbins 70(!) years ago in **1956**

https://t.co/KU8WwA0gO8

(h/t @joejanizek)

[Rajesh Bhayana @RajeshBhayana_]

I built NavRad Anatomy, a free tool with an AI Guide that makes it simpler to learn clinically important imaging anatomy.

To read scans, you need to know the anatomy. But there’s a lot to learn, and it’s hard to know what matters.

With this app, you can scroll through real scans with labels and colour-coded overlays, filter the structures you want to see, learn essential anatomy with key clinical pointers, or ask the AI Guide:

“Walk me through the liver segments” (see video)
“Teach me the segments of the internal carotid artery”
Or even: “Just show me the basics”

Then test yourself by asking it to quiz you.

Works on your phone or computer, so you can learn on the go.

See it in action 👇
Try it at https://t.co/ithILGSeYc, or click "Anatomy" in Navigating Radiology.

[Ben White, MD @benwhitemd]

My second workforce column for AJR, "The (Un)Knowable Future," is out:

"Get enough opinions covering enough ground, and someone will always be right: That’s the beauty and frustration of survivorship bias."

https://t.co/oByB14eais

[Ben White, MD @benwhitemd]

@leotrap819 You can just email support for account creation if issues; it's limited to .org and .edu email addresses I'm told.

[Ben White, MD @benwhitemd]

There is a new community-supported free question bank for radiology out. It's still early, but it's exactly the kind of thing I wanted to make back when I was a resident.

I'm not involved, but I think it would be neat to have a Radiopaedia of test prep. https://t.co/9V8sNtcyAA

[Ben White, MD @benwhitemd]

@leotrap819 Shared your tweet with the admin.

[Ben White, MD @benwhitemd]

@InvestingDoc Reimbursement is much higher in the US. But also if tele elsewhere is at all like here, many of those rads could be contractors. A big part of the value here is also probably the contracts and those anchoring relationships across multiple geographies more than just the humans.

[Ben White, MD @benwhitemd]

In case you were wondering, the reported purchase price was $715 million.

[Radiology Business @RadiologyBiz]

Radiology Partners seeks $485M term loan to fuel teleradiology acquisition https://t.co/JqATOJK0qU

[Ben White, MD @benwhitemd]

@about_medicine Thanks! I do try to be fair. I may be loathed by RP, but I'm mostly interested in giving folks some info and providing a thoughtful/reasonable perspective + an excuse to step back, give the big issues some thought, and hopefully have some good conversations.

[Ben White, MD @benwhitemd]

It's Q4 now, and Radiology Partners will be further "sharing the efficiency gains" from its new AI drafting product.

When tech brings the possibility of increased productivity, the logical thing for an employer is to take as much as the market allows.
https://t.co/MNzx4YaJGU

[Ben White, MD @benwhitemd]

@TheTo24611 Interesting, I didn't realize that, but that would certainly juice the numbers. Do you have any insight into how the model decides when a case is too complicated?

[Ben White, MD @benwhitemd]

@DrJgps @WillyRontgen For anyone wanting some more detail about that:

https://t.co/iFAVbX8qoR

https://t.co/HY1wgRcGZV

[Ben White, MD @benwhitemd]

@drmoneymatters @WillyRontgen @radiology_one I also have my biases to be sure. But with regard to the technology, no, I really don't.

[Ben White, MD @benwhitemd]

@DrJgps @WillyRontgen They refinanced their massive debt in 2024. They have some more time to make magic happen.

[Laura Heacock, MD @heacockmd]

Getting ahead of the reposts on this one.

A Swedish health system has decided, based on the ScreenTrust trial, that one radiologist + AI is as good as two radiologists reading a mammogram. The MASAI trial had similar results. They’re now officially doing this outside of the trial.

This will allow the radiologists more time to read other studies and reduce backlogs. No radiologists are being replaced. It is a very logical and expected conclusion to these excellent trials

The US standard of care is a single reader plus CAD (now often AI CAD). We do not use double reads for mammograms, so these study results have interesting implications but do not directly apply to the breast imaging pipeline here.

Is there room for discussion of autonomous reads of low-scoring mammograms? Sure. But they are still discussions, with no clear pathway in the US at this time. Screening mammograms are a part of my job but only a small fraction.

In short: everyone expected this after the study results. Mammography was the one time that two radiologists read the same study, and now everyone is moving to a single reader system (here augmented by AI).

Please note Radiology Business did not make any wrong assumptions; I just expect this will get reposted missing all the context.