article thumbnail

ChatGPT triumphs over academic physicians in diagnostic reasoning challenge

PulmCCM

ChatGPT crushed 50 academic attendings and residents in a diagnostic reasoning contest. The big finding was in the secondary outcome of ChatGPT’s performance alone: the LLM scored 92% of the available points, 16 percentage points higher than physicians using human reasoning supported by either AI or decision support tools.

article thumbnail

Mandrola Chooses a Favorite Academic Article

Sensible Medicine

Words that pop into my head when thinking about the academic literature: vast, insipid, repetitive, Sisyphus. He had grown the once small Circulation--Cardiovascular Quality and Outcomes into a prominent journal in the academic cardiology space. This sentence came seven years before social media and a virus shredded our norms.

article thumbnail

Fear and Opioids in Academic Medicine

Sensible Medicine

From these reductions, whether they proceeded quickly or slowly, I saw terrible outcomes. To be clear, a substantial number of patients who reduce doses obtain good outcomes. Respect for the standards by which one is judged is adaptive in academic medicine. Later papers substantiated these warnings.

article thumbnail

Three Academics Speak Out on Bad Medical Studies

Stop and Think

You should first know Dan is one of the smartest and kindest academics I have met. It’s quite an honor to have legit academics comment on my Substack. My response: While I believe that academics have--as one goal—the discovery of answers to help our patients. Regarding outsized conclusions, I could not agree more.

article thumbnail

Can acetaminophen improve outcomes in sepsis?

PulmCCM

The ASTER Trial Ware et al conducted a phase 2b randomized trial from 2021 to 2023 among 447 patients admitted with sepsis and organ failure at 40 US academic hospitals. Patients received either 1 g of acetaminophen IV every six hours or placebo for five days.

Sepsis 52
article thumbnail

Early clinical outcome prediction based on the initial National Early Warning Score + Lactate (News+L) Score among adult emergency department patients

Emergency Medicine Journal

We validated the score in a large patient data set and constructed a model that allows early prediction of the probability of clinical outcomes based on the individual’s NEWS+L Score. The outcomes were hospital death or a composite of hospital death and intensive care unit admission at 24 hours, 48 hours and 72 hours.

article thumbnail

SGEM#460: Why Do I Feel Like, Somebody’s Watching Me – CHARTWatch to Predict Clinical Deterioration

The Skeptics' Guide to EM

He leads an AI team intending to improve patient outcomes and healthcare system efficiency. In healthcare, AI is being leveraged to enhance clinical decision-making, streamline administrative processes, and improve patient outcomes. Despite the potential benefits, integrating AI into clinical workflows presents challenges.