←
Max Marsden2,284 posts
Max Marsden avatar

Max Marsden

@MaxMarsden83

General Surgeon | Trauma | Academic Dept of Military Surgery & Trauma / Centre for Trauma Sciences | Decision Making BNs Views my own, not those of my employer

◷ Joined January 2013▧ 210 Photos and videos
ASGBI avatar
⟳ Max Marsden retweeted
ASGBI@asgbi·May 11

Critical decision-making in trauma- Penetrating Thoraco-abdominal injury. Laparotomy or Thoracotomy? Success relies not just on operative skill, but on strategic restraint-knowing that CT scans lie about the diaphragm, chest tubes lie about the source of blood, and that surviving the trauma requires deliberately identifying the true source of instability before making the first incision. @MaxMarsden83 #ASGBI2026

Post attachment
ASGBI avatar
⟳ Max Marsden retweeted
ASGBI@asgbi·May 11

Critical decision-making in trauma- @MaxMarsden83 is back, challenging us to think about blunt thoraco-abdominal trauma decisions. #ASGBI2026

Post attachment
Gabe Wilson MD avatar
⟳ Max Marsden retweeted
Gabe Wilson MD@Gabe__MD·Apr 30

A study published today in Science may be the most important AI paper in clinical medicine this year. And it happened to land on the same day I submitted a letter to JAMA arguing that AI can already deliver clinically adequate care for defined tasks. Researchers at Harvard Medical School and Beth Israel Deaconess Medical Center ran six experiments pitting OpenAI's o1 reasoning model against hundreds of physicians across the full spectrum of clinical reasoning: differential diagnosis, management planning, probabilistic reasoning, and clinical documentation. Then they did something most AI studies don't. They tested it on 76 real, unstructured emergency department cases pulled directly from the medical record at a major academic medical center. The results across all six experiments: the AI outperformed physicians. On the real ER cases — the messiest, most clinically relevant test — the AI identified the correct or very close diagnosis in 67.1% of cases at initial triage, 72.4% at ER physician evaluation, and 81.6% at hospital admission. The two attending physicians scored 55.3% and 50.0% at triage, 61.8% and 52.6% at ER evaluation, and 78.9% and 69.7% at admission. The gap was widest at initial triage. On management reasoning using expert-scored clinical vignettes, the AI scored a median of 89%. Physicians with conventional resources scored 34%. That is not a typo. The physician evaluators were blinded and could not distinguish AI-generated differentials from human ones. One evaluator guessed correctly 15% of the time. The other guessed correctly 3% of the time. I'm an emergency physician. I work in a rural Texas ED. These are my cases. These are my decision points. And I can tell you that the triage finding is the one that matters most. Triage is where the least information meets the highest stakes — where the wrong call means a patient sits in the waiting room while their sepsis progresses or their STEMI evolves. The AI was 12 to 17 percentage points better than experienced attendings at exactly that moment. The authors are careful to note this is text-based reasoning only; the AI doesn't see the patient's distress, doesn't hear breath sounds, doesn't read the room. Those are real limitations today. But the cognitive reasoning component of emergency medicine — pattern recognition under uncertainty with incomplete data — is precisely what this model is demonstrating it can do. This was published in Science. Not a preprint. Not a company blog post. Peer-reviewed, in one of the two most prestigious scientific journals in the world. The profession needs to stop debating whether AI will be good enough. It needs to start planning for the fact that, for an expanding set of clinical reasoning tasks, it already is. And yes, this was written with AI. Sorry!!

Post attachment
Patrick Georgoff, MD avatar
⟳ Max Marsden retweeted
Patrick Georgoff, MD@georgoff·2 Jul 2025

PENETRATING LUNG 🫁 INJURY?! Rule of 👍🏼 ➡️ 1500 cc bloody drainage @ time of chest tube placement or > 200 cc/hr 🟰 OR. In reality, many factors go into this decision 🧠 , including stability, transfusion requirements/trend 📈, concomitant injuries, etc. ✔️ Quickest + safest approach for a TRAUMA patient is an anterolateral thoracotomy. ✔️ Small injuries can often be managed with suture repair alone. ✔️ Treat peripheral injuries with a non-anatomic stapled resection. ✔️ A pulmonary tractotomy can be used to expose deep injuries, allowing for repair. ✔️ Central 🫁 injuries are tough. Control the hilum with fingers, a clamp, or in extreme cases, hilar twist. ✔️ Total pneumonectomy is a last resort ➡️ mortality is ~50% ✔️ Repair the diaphragm primarily ➡️ use permanent suture & whatever technique works best. Be sure to watch the high-yield @BehindTheKnife video in our Trauma Atlas: app.behindtheknife.org/cours…

Post attachmentPost attachment
Gareth Grier avatar
⟳ Max Marsden retweeted
Gareth Grier@gareth_grier·6 Jul 2025

I wasn’t there, but know that the role played by friends. colleagues, and people we don’t know, on 7/7 was extrordimary. There are amazing people in this world, with acts of kindness always outglowing the hate. 🙏🏼 for everyone who was affected, and who played a part to help.

Curiosity avatar
⟳ Max Marsden retweeted
Curiosity@MAstronomers·10 Jun 2025

A woman in West Virginia snapped a one-in-a-million shot of a tree being struck by lightning. Photographed by Donnie Dania.

Post attachment
Bellal Joseph avatar
⟳ Max Marsden retweeted
Bellal Joseph@Topknife·1 Jun 2025

You didn’t just build a trauma system you set off a ripple effect that reshaped trauma care across the globe. Thousands of lives saved thousands of learners taught! A model studied and copied. Legends don’t step down. They leave shockwaves. Respect, Karim 👊

NEJM avatar
⟳ Max Marsden retweeted
NEJM@NEJM·8 Apr 2025

Hey, what do you think? IV or IO? This video in our partnership with @DGlaucomflecken summarizes new research comparing initial attempts at intraosseous or intravenous vascular access in adults who had out-of-hospital cardiac arrest. Full trial: nej.md/DrG14

1:06