Ryan Radecki MD MS
FACEP FACEM ABPM-CI. HealthNZ AI & Christchurch EM. Annals of EM Podcast & Journal Club. Columnist ACEPNow. Speaker, writer, dad. Stanford '00. evidencetriage.com 🇺🇸 in 🇳🇿
- More "tissue not time" evidence – but these data are almost certainly weaker than they appear. Unfortunately, I expect they'll simply be piled upon the ever-expanding indications for stroke thrombolysis, along with corresponding indication creep. #medsky www.evidencetriage.com/p/the-option...
- Amazing, thanks LLM helper.
- Trial stopped early for futility. The opposite of the headline I would choose. www.thelancet.com/journals/lan...
- The magic wand stethoscope doesn't reliably measure up – yet. Phonographic and single-lead ECG analysis by AI did not reliably improve diagnosis of atrial fibrillation, heart failure, or valvular heart disease. #medsky #MLsky www.evidencetriage.com/p/not-a-magi...
- Fascinating thoughts and data here from Anthropic – analyses of conversations to determine the rate and extent to which AI may be providing harmful reinforcement or distortion. Spoiler – it's a lot, both in relative frequency and in absolute terms ... #medsky www.anthropic.com/research/dis...
- Reposted by Ryan Radecki MD MSSci-Fi Author: In my book I invented the Torment Nexus as a cautionary tale Tech Company: At long last, we have created the Torment Nexus from classic sci-fi novel Don't Create The Torment Nexus
- All I really want is … gulls. 🎶
- More evidence of there not being much of an additive or synergistic effect between different types of analgesia for moderate acute pain – this example in pediatrics: #medsky www.evidencetriage.com/p/ibuprofen-...
- Reason #2148 medical care in the U.S. is so expensive – zero tolerance for poor outcomes, avoidable or not, leading to over-testing, over-referral, and generally harmful practices focused narrowly on avoiding rare badness. #medsky www.expertinstitute.com/resources/in...
- Yourself, but as a cartoon.
- These sorts of retrospective analyses are always confounded by indication, but it is probably the case hyPERnatremia can be corrected as rapidly the salient clinical context requires. #medsky www.evidencetriage.com/p/does-it-ma...
- Credit to Ed, toughing out the Christchurch "summer" in apparent good humour. Whilst you'd think it would be basic expectations for any professional to do their well-paid "job", not every touring artist displays the same level of resilience. thespinoff.co.nz/pop-culture/...
- Reposted by Ryan Radecki MD MS[Not loaded yet]
- The new reality: if you have a information aggregation/interpretation problem that previously required a team of engineers and data scientists, there's an awfully good chance Claude Code or a tool like it can address it given functional requirements. #medsky medium.com/data-science...
- Example #2914 of telling clinicians there's no bacteria to treat, but clinicians continuing the antibiotics. (in this case, the test is flawed, but I digress) #medsky www.evidencetriage.com/p/no-bacteri...
- Emoji usage is slowly percolating into clinical documentation – and with some rather quirky choices, if I might say. #medsky www.evidencetriage.com/p/emojis-in-...
