msjoding's profile picture. Pulmonary Critical Care, data-science, machine-learning, and AI in critical care, health services research, University of Michigan

Michael Sjoding

@msjoding

Pulmonary Critical Care, data-science, machine-learning, and AI in critical care, health services research, University of Michigan

Pinned

1/ Our research letter on racial bias in pulse oximetry measurement, out today in NEJM nejm.org/doi/full/10.10…

msjoding's tweet image. 1/ Our research letter on racial bias in pulse oximetry measurement, out today in NEJM nejm.org/doi/full/10.10…

Michael Sjoding reposted

.@AnnalsATS study making national news: “Latino patients with respiratory illnesses are 5 times more likely to be oversedated” nbcnews.com/news/latino/la…


Michael Sjoding reposted

A recent @JAMA_current study co-authored by MIDAS affiliate faculty member @umichmedicine's Dr. Michael Sjoding cautions the use of AI tools with baked-in systemic bias to help diagnose patients. Read more from @axios. axios.com/2023/12/20/ai-…


JAMA produced a video on our just published study!

Although standard AI models improve diagnostic accuracy, systematically biased AI models reduced diagnostic accuracy, and commonly used image-based AI model explanations did not mitigate this harmful effect. ja.ma/3ROAuPf



Michael Sjoding reposted

In #AI for medicine, we often hear, "Oh, this tool just assists clinicians - they decide care" In @JAMA_current, @SarahJabbour_ et al's randomized study finds potential harm from decision support w assistive AI We cover "Automation Bias" in an editorial jamanetwork.com/journals/jama/…

rohan_khera's tweet image. In #AI for medicine, we often hear, "Oh, this tool just assists clinicians - they decide care"

In @JAMA_current, @SarahJabbour_ et al's randomized study finds potential harm from decision support w assistive AI

We cover "Automation Bias" in an editorial

jamanetwork.com/journals/jama/…

Michael Sjoding reposted

Of 4 collaboration strategies to deploy #AI for the diagnosis of ARDS from chest XR, the most accurate is to allow AI review the XR first & defer to the physician if uncertain. 79% of cases were decided by AI - significantly reducing physician workload. nature.com/articles/s4174…

npjDigitalMed's tweet image. Of 4 collaboration strategies to deploy #AI for the diagnosis of ARDS from chest XR, the most accurate is to allow AI review the XR first & defer to the physician if uncertain. 79% of cases were decided by AI - significantly reducing physician workload.

nature.com/articles/s4174…

On this day when a mentee has a great paper accepted, I'm grateful to have learned how to generously and effectively respond to manuscript reviewers from @ColinRCooke @iwashyna and now can model this with my mentees


Michael Sjoding reposted

I've been accused of "relentlessly" covering the pulse oximeter issue. Guilty as charged. I find this issue critical. It's a microcosm of the painful, historical, scientific & nuanced ways race interests with medicine. Here's a🧵of our coverage. statnews.com/2022/11/01/pul…


Michael Sjoding reposted

Ahead of an 11/1 @US_FDA mtg on pulse oximeters, #UMPrecisionHealth members @tsvalley, @iwashyna, @msjoding authored a piece in @ATSBlueEditor proposing actions that FDA, senators, clinicians, manufacturers can take to ensure they work accurately for all linkedin.com/feed/update/ur…


Michael Sjoding reposted

NEW: @msjoding & colleagues have spent 2+ years looking at the accuracy of #pulseox devices in hospital patients with darker skin, and finding major issues. Read our new brief summarizing their work, in advance of an @US_FDA hearing on the topic this fall: ihpi.umich.edu/news/pulse-oxi…

UM_IHPI's tweet image. NEW: @msjoding & colleagues have spent 2+ years looking at the accuracy of #pulseox devices in hospital patients with darker skin, and finding major issues.
Read our new brief summarizing their work, in advance of an @US_FDA hearing on the topic this fall: ihpi.umich.edu/news/pulse-oxi…

Michael Sjoding reposted

1/ Excited to announce our new work at @MLHC2022! Many patient risk-stratification ML models are trained using lab test results as labels. But testing disparities are known to exist across patient groups. (w/ @msjoding, Jenna Wiens) @MichiganAI (arxiv.org/abs/2208.01127)


Michael Sjoding reposted

Hi, here’s my (@shanestorks) next Michigan AI #StudentTakeover Spotlight with Trenton Chang (@chang_trenton)! We discussed equity in healthcare and diagnostic testing, the role of AI, and overcoming imposter syndrome. #AcademicChatter youtube.com/watch?v=KpnmyC…

michigan_AI's tweet card. AI, Healthcare, and Humanities with Trenton Chang (Michigan AI...

youtube.com

YouTube

AI, Healthcare, and Humanities with Trenton Chang (Michigan AI...


Distillation of complex figure/nuanced thread on pulse ox accuracy/reliability. If pulse ox and ABG are way off, additional pulse ox readings likely unreliable for all. If pulse ox and ABG align, additional pulse ox readings likely accurate for White but less so for Black pts.

Although standard AI models improve diagnostic accuracy, systematically biased AI models reduced diagnostic accuracy, and commonly used image-based AI model explanations did not mitigate this harmful effect. ja.ma/3ROAuPf



Our Kindergartener: "I do not like zoom school. I'm having a terrible day." @A2schools @A2Return @A2SchoolsSuper


Michael Sjoding reposted

There are much harder crosses to bear in life, but @A2schools abject failure to make evidence-based decisions or prioritize our kids’ education is deplorable. Where do they think kids go when they are not in school?!? In to negative pressure rooms?!?. No excuses and no words.


Michael Sjoding reposted

Highest child vaccination rate in the state and @A2SchoolsSuper still closing schools against @SecCardona and @GovWhitmer’s advice. An embarrassment.

Although standard AI models improve diagnostic accuracy, systematically biased AI models reduced diagnostic accuracy, and commonly used image-based AI model explanations did not mitigate this harmful effect. ja.ma/3ROAuPf



Loading...

Something went wrong.


Something went wrong.