Sabitlenmiş Tweet
Carolyn Kaufman, MD, PhD
801 posts

Carolyn Kaufman, MD, PhD
@Carkauf23
Internal Medicine PGY-2 @StanfordMed via @kumcMSTP '23 via @Tulane '13 KC native #DoubleDocs #MDPhD
Menlo Park, CA Katılım Kasım 2018
2.5K Takip Edilen1.6K Takipçiler

@dereckwpaul This is one of the best potential applications for AI in medicine. Looking forward to solutions from your team
English

AI is about to fix one of medicine's most well-intentioned but potentially dangerous practices. The chart biopsy.
Before seeing a patient, a doctor is going to do their best to review the chart so that they have the context needed to handle whatever the patient's chief complaint is at the time effectively. Oftentimes, doctors do not have time to review the entire chart or review the chart at all, secondary to the ongoing pressures to see more and more patients.
The very best doctors I've known have, at the very least, tried to do a chart biopsy. They scan through the available previous documentation in the chart and try to intelligently choose pieces of documentation that are likely to provide them with a good overall picture of the patient. For example, a previous specialist note.
The reality is that they can only choose one or two notes to read—hence the term chart biopsy. Just like a real tissue biopsy, it is only taking a tiny sample of what is going on. A good chart biopsy is better than no chart review, but it leaves a tremendous amount of unreviewed context.
In the course of an inpatient hospitalization, as the hospitalization plays out, a great doctor will review more of the chart through those days and learn more about the patient. They accumulate previous context and present context through their conversations with the patient over time.
But at the time when they are seeing the patient and admitting the patient and making the most critical decisions, they often have the lowest context.
Growing context windows mean that an AI can actually process more text than the average human can. A million token context window is the equivalent of about ten novels. For patient records that are even bigger than this, they can be represented and searched using techniques including context compaction, summarization, and vector embedding.
AI is going to make it so that the chart biopsy is not necessary. We are going to have considered all the available context early on in patient encounters, at the point of care when it really matters. This is going to help doctors be more effective at their job of diagnosis and treatment planning, and lead to downstream positive impacts for patients.
English
Carolyn Kaufman, MD, PhD retweetledi

🥳 Grand Rounds 2.0 kickoff with the one and only @DGlaucomflecken at @StanfordDeptMed. Such a great combination of humor & substance. Overflowing crowd with great turnout from faculty and @StanfordMedRes. The best part of #grandrounds is bringing the community together. 🙂




English
Carolyn Kaufman, MD, PhD retweetledi

“It’s called a header, not a headbutt” 💀
We mic’d up @Chiefs rookies at their first KC Current match 😂
English
Carolyn Kaufman, MD, PhD retweetledi

Thrilled to share @JA_Palmer_ former #postdoc in #REACHLab, published her latest paper in @alzdemjournals! Even more special, every co-author is a former trainee. True testament to #collaboration & #teamwork. #proudmentor @Carkauf23 @alicen_whitaker
#APOE4 #cerebrovascular
English
Carolyn Kaufman, MD, PhD retweetledi

(3/x) The reason why the IVC can't answer 'volume status' when you divide the term into its sub-components is that...
1. IVC does not assess left sided filling
2. IVC has some utility for right sided congestion, but not perfect as some patients have dilated IVC without organ level congestion.
3. IVC does not correlate with stroke volume --> you can have a collapsed IVC in distributive shock with high VTI (stroke volume surrogate) or low VTI
4. A collapsed IVC is NORMAL for healthy people --> without abnormal perfusion it doesn't need intervention.
5. IVC collapsibility has very poor accuracy to predict fluid responsiveness
6. IVC can tell us a little bit about fluid tolerance, but only so far as congestion is confirmed.

English

New preprint alert!
Jackie Palmer@JA_Palmer_
During movement involving hemodynamic challenge, APOE4 carriers presented distinct phenotypes of cerebral vascular dysfunction, neurovascular compensation, & changes over the AD progression. medrxiv.org/content/10.110… New preprint w @Sandy_REACHLab @Carkauf23 @alicen_whitaker !
English

What are the chances that today’s reading assignment for the @StanfordMedRes Med Ed elective (led by @Sharminzi) would start with a throwback to the @Royals World Series run - excellent omen for the rest of the series & elective 👏
(Throwback photo from 2014 at the K)



English
Carolyn Kaufman, MD, PhD retweetledi
Carolyn Kaufman, MD, PhD retweetledi

(1/x) Treating patients who are fluid responsive with IV fluids is kind of like using a credit card 💳
It definitely works (in the short term), but be careful.
The debt that accumulates eventually needs to be paid off.
A 🧵
#medtwitter #foamed

English
Carolyn Kaufman, MD, PhD retweetledi

Look who's here! Our 2024-2025 interns officially start residency tomorrow! We're excited to spend the next few years together! 🤩🎉
@StanfordDeptMed

English

@aztezcan @olsonplanner The cost of living is absurd! But it is a beautiful place to live.
English

@Carkauf23 @olsonplanner My husband was considering a hemonc fellowship there in early 90s. They knew the cost of living in palo alto was unaffordable with the salary stanford paid so they had a list of places where others did moonlighting to supplement; we decided to pass.
English

@Carkauf23 Maybe I was told (or I heard) incorrectly?
I’m was teaching a session to a group of residents a couple of weeks ago and they said they top out at $150k, but then corrected themselves and said $130k 🤷🏼♂️
Not at all trying to share wrong info, so if I’m wrong, I’ll take it down.
English

@drcharlieh @olsonplanner Not to mention, Stanford residents are not making this amount. With the union negotiations, a few residents may hit $130k in 2025… if they are PGY-7 or greater 😳
English

Still in shock that this is for real but I am SO excited and thrilled and grateful to match into the internal medicine/global health residency program at Stanford ❤️ I CANNOT WAIT! #match2024 @EmoryMedicine @EmoryMSTP @StanfordMed

English
Carolyn Kaufman, MD, PhD retweetledi

Elated to welcome an incredible group of physicians & physican-scientists to @StanfordMedRes -- the 2024-2025 intern class! We can't wait to welcome you to the @StanfordDeptMed family in 3 short months!🍾🎉#Match2024 @StanfordChiefs @trepraja04 @KarinaSDelgadoC @PoonamHosamani




English

@Harmony_S_ @joeskc @Chiefs @QuintonLucasKC @KCBBQSOCIETY @StanfordChiefs Thanks @Harmony_S. You know @DocHolliday22x and I won’t be subtle today 😂

Menlo Park, CA 🇺🇸 English

Bringing a taste of KC to a 49ers watch party today. @joeskc guaranteed to convert at least a few SF fans!
@Chiefs @QuintonLucasKC @KCBBQSOCIETY #SBLVIII @StanfordChiefs #KCBBQ

Menlo Park, CA 🇺🇸 English

Last Red Friday of the season,
First Red Friday in enemy territory!
@Chiefs #RedFriday #SBLVIII @tkelce @PatrickMahomes @PSchroeppel

Palo Alto, CA 🇺🇸 English



