Jonathan Mezrich

@XrayDFS @marcportermagee I would guess that lots of kids want to leave home rather than stay local at their nearby state school - it’s a baby step form of spreading their wings. Others may like the campus aesthetics and nearby skiing. A lot of other state schools have a more industrial feel.

@marcportermagee Why would out of state students go to Vermont?

University of Vermont projects 15% drop in freshman class

@CaptainSteak @marcportermagee Nearby skiing used to be a big draw back in the day.

@marcportermagee Vermont seems like a lovely place. I’d love to own a home there in one of those idyllic New England towns. But going there for college? Hell no. It’s unfortunate because I do think it should have its own top public university. I’m just not sure who would want to go there.

@johhnny2321 @FCademartiri I think being the backstop for liability protects radiologists more than some think. It’s important for surgeons to look at imaging, but unlikely they want liability for everything that appears in a study. If you only look at images 10% of your day you’ll never reach rads levels.

@FCademartiri There’s more work for radiology than ever and radiology is in the top 10 specialties of med mal liability with surgical subspecialties among the top with neurosurgery at number 1. Radiology has an immense medico legal responsibility a lot of clinicians don’t care to understand.

🩻⚠️ Radiology is not dying.
It’s becoming electricity. ✅ Invisible. ✅ Everywhere. ✅ Absolutely essential. And most people won’t notice until it fails. This paper makes a provocative argument: 👉 Radiology may stop being a “specialty.” Not because imaging matters less. But because it may become: the operating system of medicine. Honestly? That’s probably already happening. For decades, radiology worked like this: 👉 image acquired 👉 radiologist reads it 👉 report sent back 👉 everyone pretends the PDF is the actual product Classic. But modern medicine broke the old model. Now: - emergency physicians scan at bedside - intensivists use procedural imaging - cardiologists own advanced cardiac imaging - surgeons navigate in real time - AI pre-triages findings before humans even open the study Meanwhile radiologists are still arguing on LinkedIn about who owns ultrasound. The uncomfortable truth Imaging is no longer a location. It is becoming: infrastructure. - Like electricity. - Like Wi-Fi. - Like cloud computing. Nobody says: 👉 “The electricity department diagnosed my patient.” But try running a hospital without it. The paper’s strongest point Radiologists may evolve from: ❌ image interpreters to: 👉 system architects Meaning: - workflow orchestration - AI governance - quality control - imaging pathways - multimodal integration - diagnostic ecosystems Translation The future radiologist may spend less time: 👉 describing a 4 mm cyst And more time: 👉 designing how an entire healthcare system sees disease. And AI accelerates this dramatically Because once AI handles: - triage - segmentation - measurements - prioritization - preliminary pattern recognition …the bottleneck is no longer image interpretation. It becomes: 👉 integration 👉 accountability 👉 orchestration My provocative take Radiology spent years asking: 👉 “Will AI replace radiologists?” Wrong question. The real question is: 👉 “What happens when imaging belongs to everyone?” Because here’s the irony Radiology may become: ❌ less visible but ✅ more central than ever Final thought The most powerful technologies eventually disappear into the background. Nobody talks about: 👉 electricity 👉 TCP/IP 👉 oxygen in the OR They just become essential infrastructure. ⚡ Imaging may be heading there too. And if that happens: Radiology won’t vanish. It will become the invisible nervous system of medicine. #Radiology #AI #MedicalImaging #Healthcare #DigitalHealth #FutureOfMedicine #PhotonCounting #PrecisionMedicine

@soup_monster_ @MLFootball @RobGronkowski @FitzyGFY @JumboHart @jerrythornton @TitleTalkTCL @FilmstudyRavens @zachbollinger18 @RavensTalkPod @RavensTattooGuy @PatsBuzz He fell down a couple of flights of stairs resulting in a bad head injury. So we’ll never know how good he might have been.

@MLFootball @RobGronkowski @FitzyGFY @JumboHart @jerrythornton @TitleTalkTCL @FilmstudyRavens @zachbollinger18 @RavensTalkPod @RavensTattooGuy @PatsBuzz Kindle was a freak and a generational prospect don’t understand how he didn’t pan out

THE WORST MOVES IN BALTIMORE #RAVENS DRAFT HISTORY: The #Ravens intended to draft Hall of Fame tight end Rob Gronkowski in the 2010 #NFL Draft at picks 25 and 43. Baltimore originally held the 25th pick and aimed to draft Gronkowski there, but ended up trading back to Denver, which selected Tim Tebow. Bill Belichick got word that Baltimore was targeting Gronkowski again with the 43rd pick and traded up to secure him with the 42nd pick. Instead, the Ravens drafted linebacker Sergio Kindle, who was out of the league after just three seasons, and had one total career tackle. Gronkowski became the greatest tight end of all time in New England, winning three Super Bowls, being a 5x Pro Bowler, and a 4x All-Pro. Gronk was a major part of multiple NE playoff victories over Baltimore. If Baltimore had drafted Gronkowski… they would have potentially won multiple more Super Bowls and the New England Dynasty could look completely different today. 🤯

@BUYSCHG @Gabe__MD Pundits said that over a decade ago. Yet AI has yet to result in any loss of radiology jobs. I believe it will happen “eventually” but eventually may be decades further out than AI developers are currently hyping to their investors.

@Gabe__MD I’d say in a decade, Rads will becoming the least competitive specialty

AI won't take over radiology... until it takes over radiology. Despite the hype or the protest, evidence is slowly mounting that that day will eventually come. The latest study in BMJ Gut is compelling. A Mayo Clinic team built REDMOD, an AI framework designed to detect pancreatic ductal adenocarcinoma at stage 0 — before any visible mass appears on CT. Before any radiologist, no matter how experienced, could possibly identify it. They tested it on 1,462 patients in a multi-institutional cohort designed to simulate real-world low-prevalence screening (6:1 control-to-case ratio). The results: AI detected visually occult pancreatic cancer with 73% sensitivity. The radiologists achieved 38.9%. That's nearly double. At lead times beyond 24 months — meaning more than two years before clinical diagnosis — the gap widened to nearly threefold: 68% vs 23%. Overall AUC: 0.82 for the AI vs 0.69 for the radiologists (p<0.001). This isn't an AI reading the same images faster. This is an AI seeing what human eyes structurally cannot. The cancers in this study were confirmed as imaging-occult prospectively read as negative by board-certified radiologists, then independently re-reviewed and confirmed negative again. There was nothing to see. REDMOD found the signal anyway, embedded in subvisual textural patterns across the pancreatic parenchyma. And the signal was stable. Test-retest concordance hit 90-92% across serial scans, with one patient correctly flagged 1.8 years before diagnosis and tracked through an evolving radiomic signature that preceded any visible tumor. The interobserver agreement between the two radiologists? Kappa of 0.22. The AI was not only more accurate, it was more consistent than the humans by an order of magnitude. Pancreatic cancer kills 85% of patients at current detection timelines. Modeling studies suggest that shifting even a fraction of diagnoses from late to localized stage would more than double survival rates. REDMOD offers a median 475-day detection window. That is the difference between palliative care and curative surgery. The profession's instinct is to frame AI as a tool that augments the radiologist. And for most imaging tasks today, that framing holds. But studies like this reveal a different trajectory, one where the most consequential diagnostic capability isn't augmentation. It's perception beyond the human visual threshold. Radiology will look very different in well under ten years. The profession can lead that transformation or get restructured by it.

@NorthSideCapper You could make the same argument that your favorite NFL team is made up of mostly future podcasters and small business owners. People joke that NFL stands for not for long. At some point you just have to live in the moment and enjoy the game.

@NFL_DovKleiman This is kinda why I don’t watch the NCAA.. literally sitting there watching math students who will never go beyond the collegiate level.. it’s just weird to me (unless you have a connection to the school/athlete)

Making the NFL is virtually impossible. The numbers are mind-boggling. 🤯🤯🤯

@TheFreakyGent @OnlyTheRavens I believe you can only get a maximum of 4 comp picks. And the ravens traded a pick next year to move up for one of the TEs

@OnlyTheRavens How? They lost 5 starters! Linderbaum Likely Kolar Ricard Stout It should be at least 5 Compensatory Picks… plus their 7 standard allotment. That’s 12… 🤷🏽‍♂️

@SigmundBloom @igglesnut On the flip side it’s going to be almost impossible for this player to not make the final roster.

@igglesnut that is what is called "shifting the heat" in politics if Randall busts, it's on the record whose call it was

Bisciotti was known as one of the most hands-off owners until this offseason

@IESR_DMV Unlikely the Raiders will do the Ravens any favors after Crosby

@ColeJacksonFB Wonder if we could convince the Raiders to do 115, 173, and 253 for 102 and 208. I’m sure that’s not one for one pick value but those are the types of trades we’ve been seeing so who knows

If the #Ravens want to secure a C with their 4th round pick, the cost becomes pretty simple to do so. 115 - 64 173 - 22.2 = 86.2 Pick 104 - Arizona Throw in one of your back to back 5th round comps and go get Sam Hecht. #RavensFlock

New case law could put radiologists on hook for imaging-order appropriateness. @AJR_Radiology @RadiologyACR @JonathanMezrich @YaleRadiology ow.ly/YOJJ50YPurp

Recent case law suggests a shifting legal status for ACR Appropriateness Criteria. Discover why radiologists must remain vigilant in reviewing imaging requests to mitigate potential liability risks. ajronline.org/doi/10.2214/AJ…

In a recent medical malpractice case, the American College of Radiology Appropriateness Criteria was allowed to be introduced to support the defense expert opinion that it is reasonable to request a non-contrast brain MRI for evaluation of chronic headache with new features.

New @AJR_Radiology Accepted Manuscript: "The American College of Radiology Appropriateness Criteria and the Standard of Care: Concerns Resulting From Recent Case Law" By Dr @JonathanMezrich @YaleRadiology ajronline.org/doi/10.2214/AJ…

Check out my latest article on potential legal concerns for radiologists when using EMR messaging, just published in Clinical Imaging! authors.elsevier.com/a/1mx3E3CaTZfQ… @YaleRadiology

Legendary radiologists know how to use their words to drive patient outcomes

Excellent session on How to Write a Quality Radiology Report. Structured reports and proper documentation are highly impactful @francisdeng @JonathanMezrich @ARRS_Radiology #ARRS26

If an AI identifies a nodule that a radiologist misses, or vice versa, who is at fault? The legal landscape for medical imaging is shifting beneath our feet. 🗣️ Join Michael Bernstein, PhD, MA; Jonathan Mezrich, MD, JD, MBA; Gerry Stegmaier; and Bardia Khosravi, MD, MPH, MHPE for SIIM’s presentation of "AI on Trial." We're moving past the "how-to" of AI and diving into the "what-if" of legal liability. 📆 4/27/26 1:00pm ET 🔗 Register: vist.ly/4x2wu #ImagingInformatics #RadiologyAI #MedLaw

@Whit_Cream44 @hoodiestarks Oweh was very good under Minter.

@hoodiestarks Have we not learned about PSU edge guys? Oweh and Issac…….

@GrantDRasch @JFowlerESPN Not really. Minter was part of the team that traded him away to the Ravens in the first place.

@JFowlerESPN Everybody wondering why and how the Ravens let this one go..

Safety Alohi Gilman is headed to the Chiefs for three years at $24.75M including $15M guaranteed, per source.

@brothawils @jamisonhensley No - he will be a 2027 comp.

@jamisonhensley That includes Linderbaum??

With four comp picks awarded, the Ravens now have 10 picks in the 2026 draft: 2nd round: No. 45 overall 3rd round: No. 80 4th round: No. 115 5th round: Nos. 153, 161 (via LAC), 173* and 174* 6th round: No. 211 (via PHI) 7th round: Nos. 250* and 253* *-Comp picks