James Diao @JamesADiao Twitter profile

Pinned Tweet

James Diao

5 months

🧵 1/ What’s at stake with race-based equations for lung function? Clinical, occupational, and financial reclassifications for millions of patients. I’m delighted to share this labor of love, published today in @NEJM and unveiled at #ATS2024 .

11

126

362

Last Seen Profiles

@ThreeCountFADF

@PBezzie

@deevictor411

@tao_ting30143

@AliRafee86

@sebgehr

@cVDJsK5SAcBlzmP

@Tante_Binal69

@Michael_L03

@LunaBital

@ShaneOBrien55

@audreythemental

@stw_pdg

@relyme121

@Kyoto_Aquarium

@kennybenny_8

@saghiirz

@LadyFreethinker

@spindrive_fi

@bokeplokalmalam

@qu_upqn_np

@Diesel336

@TEAnotSUGAR

@yomo_neko

@usman502janjua

@timbaillie

@jason_smith707

@VieiraRival

@radiokerrynews

@Chevalier209

@guirad0

@RNamken57171

@KejesoRT

@DataDonationLab

@hasu323

@TsukieruVT

James Diao

@JamesADiao

4 months

Out in print today!

NEJM

@NEJM

4 months

Special Article: Implications of Race Adjustment in Lung-Function Equations Editorial: Beyond Diagnostics — Removing Race from Lung-Function Test Interpretation #CriticalCare

1

22

59

15

18

435

James Diao

@JamesADiao

3 months

🧵 1/ Statins and BP meds can be lifesaving for patients at risk of heart attack or stroke. But what happens when we redefine who is “at risk”? In today’s @JAMA_current , we explore the potential impact of new @American_Heart PREVENT risk equations. Link:

4

38

132

James Diao

@JamesADiao

7 months

Overjoyed to be joining the @BrighamMedRes family next year! I'm eternally grateful to my family, life partner @gloriajwu , and longtime mentor @arjunmanrai , always my greatest supporters. We matched!! 🥳🎉🥂 @harvardmed @harvardDBMI @mit_hst @pdsoros #Match2024

10

5

123

James Diao

@JamesADiao

2 years

@emollick The authors explicitly deny parity with clinicians, and there are a lot of reasons why. E.g., MedPaLM's responses contained incorrect/inappropriate info 18.7% of the time vs. 1.4% for clinicians. Very impressive/promising results ofc, but still some work to go!

3

121

James Diao

@JamesADiao

3 years

1/ Can a simple thumb trick save thousands from sudden cardiac death? Now out in #AmJCardiology , @arjunmanrai , @GloriaJWu , and I investigate the questionable clinical utility of a newly proposed “digital”😉 biomarker.

5

24

109

James Diao

@JamesADiao

2 years

My brother is coming to @MIT_CSAIL for his PhD!! Could not be prouder of @CD1AO and all the hard work that brought him here. Excited to finally live in the same city again after 9 years!

2

1

76

James Diao

@JamesADiao

3 years

Honored to join @ForbesUnder30 in Healthcare among some familiar (and much-admired) faces!! 🥳 As always, a hearty shoutout to my incredible mentor and friend @arjunmanrai , without whom none of this would've been possible.

Forbes Under 30

@ForbesUnder30

3 years

Meet the #ForbesUnder30 Class of 2022: defying the odds amidst a global pandemic and supply chain breakdowns, these honorees are resilient and destined to change the world.

28

91

409

6

74

James Diao

@JamesADiao

3 years

Collecting expert annotations at scale can be a huge cost sink for medical ML. Check out our (non-technical) editorial in @Nature_NPJ on HALS: a human+AI workflow that increases labeling efficiency by up to 10-fold! With @richardjchen and @jkvedar :

1

15

61

James Diao

@JamesADiao

4 years

Grateful and delighted to join the @PDSoros Fellows community!! A huge thank you to the Fellowship for supporting my education—I can’t wait to meet everyone 😀

PD Soros Fellowships

@PDSoros

4 years

We're thrilled to announce the 2021 Paul & Daisy Soros Fellows: 30 New Americans—immigrants and children of immigrants—pursuing graduate school, who exemplify the extraordinary contributions of immigrants to the United States. 🗽🇺🇸🎓

7

41

161

6

3

62

James Diao

@JamesADiao

5 months

No #22 without #23 ! A huge thank you to Raj, my amazing advisor of eight (!) years and the absolute GOAT of supporting my career 🙏

Arjun (Raj) Manrai

@arjunmanrai

5 months

🧵1/ I’m beyond proud of my student @JamesADiao who today became the 22nd student in the >200-year history of Harvard Medical School to receive his MD Summa Cum Laude. No better way to celebrate this by noting the uncanny similarities between James Diao and … Taylor Swift.

11

6

182

3

4

58

James Diao

@JamesADiao

4 years

🧵 1/ How might removing #race from #eGFR impact patient care? Our study in @JAMA_current quantifies the many implications for Black Americans: with @GloriaJWu @HermanATaylor @JKT0202 @Neil_R_Powe @ZakKohane @ArjunManrai

Clinical Implications of Removing Race From Estimates of Kidney Function

This study uses NHANES data to compare estimated glomerular filtration rate from serum creatinine (eGFRcr) values calculated with vs without race as a variable, and to estimate the number of patients...

jamanetwork.com

6

18

54

James Diao

@JamesADiao

4 years

Now out in @NatureComms : AI-derived image features for interpretable molecular prediction! 🔬🧬 Proud to have led this work at @Path_AI alongside my amazing classmates @jkuwang and @wanfungchui . Tweetorial + press release linked below:

Human-interpretable image features derived from densely mapped cancer pathology slides predict...

Nature Communications - Computational methods have made progress in improving classification accuracy and throughput of pathology workflows, but lack of interpretability remains a barrier to...

www.nature.com

5

7

55

James Diao

@JamesADiao

2 years

✨ Best weekend ever ✨ @GloriaJWu and I won intermediate waltz, foxtrot, and quickstep in the UK nationals at Blackpool! 🏆 Best moment: solo in the Empress Ballroom for the waltz honor dance 💃🏻🕺🏻

4

1

44

James Diao

@JamesADiao

5 months

This fallacy is super common - reminds me of a similar mistake I saw in a global health textbook almost 10 years ago:

Florian Ederer

@florianederer

5 months

This should be required viewing for every class on probability.

138

130

2K

0

4

37

James Diao

@JamesADiao

4 years

The @NEJM Image Challenge has accumulated >40 million responses across 15 years. What can these data tell us about the relationship between skin color and diagnostic accuracy? Check out my latest piece with @AdeAdamson in @JAADjournals !

JAAD Journals

@JAADjournals

4 years

Reduced representation and decreased diagnostic accuracy in dermatologic disorders in dark skin – a retrospective analysis of NEJM Image Challenge responses @AdeAdamson

0

3

8

2

3

37

James Diao

@JamesADiao

2 years

Gave this sleek new clinical tool a spin. The ddx explanations are articulate but hilariously wrong - classic LLM smoke and mirrors. If a med student read this A/P on rounds, they would never live it down 😄

Glass Health

@GlassHealthHQ

2 years

We're proud to announce the launch of Glass AI 🩺 Glass AI can generate a differential diagnosis or clinical plan based on your problem representation. Anyone can try Glass AI for free at . #MedTwitter

40

166

674

3

2

32

James Diao

@JamesADiao

3 years

15/ That's all, thanks for reading! For more on sketchy probabilistic reasoning and the base rate fallacy, check out @arjunmanrai 's aptly-titled study:

Medicine’s Uncomfortable Relationship With Math

In 1978, Casscells et al1 published a small but important study showing that the majority of physicians, house officers, and students overestimated the positive predictive value (PPV) of a laboratory...

jamanetwork.com

4

3

31

James Diao

@JamesADiao

3 years

Race-free #eGFR equation now published and blessed by @NKF - @ASNKidney !! Props to my fellow med students who have led this charge for years - y'all are amazing 😊 HT to @NNkinsi @rohankhaz @jes_cerdena @glass_heff_full @leseija and so many more!

National Kidney Foundation

@nkf

3 years

BREAKING: Today, the @NKF and @ASNKidney Task Force on Reassessing the Inclusion of Race in Diagnosing Kidney Diseases has released its final report, which outlines a new race-free way to diagnose this life-threatening illness. Read more.

1

82

132

1

6

28

James Diao

@JamesADiao

4 years

Thrilled to share our work @Path_AI on interpretable molecular predictions from cancer histology slides! 🧬🔬Tweetorial shared below ⬇️ manuscript here:

PathAI

@Path_AI

4 years

Excited to announce our research study on an interpretable pipeline for predicting molecular phenotypes from cancer pathology images! @amarotaylorw @jamesadiao @jkuwang @wanfungchu Tweetorial to follow ⬇️

2

10

34

0

4

28

James Diao

@JamesADiao

4 years

Proud to have shared my voice to the @NKF @ASNKidney Task Force alongside the always inspiring @rohankhaz @jes_cerdena @glass_heff_full @luiz_sayha and many others. Our unanimous opinion: race-based medicine must end, and race-free eGFR should lead the way 🛤️

0

6

28

James Diao

@JamesADiao

2 years

I don't buy it. If "no answer/not in choices/not enough info" are considered wrong answers, ChatGPT failed every test under every query condition (assuming passing is >60%). Not to mention that the study was severely underpowered: N≈100 and p≈0.5, so CIs ≈ +/- 10%.

Bryan Carmody

@jbcarmody

2 years

Well, looks like ChatGPT can pass the USMLE now. (h/t @RianKMD )

30

114

675

0

2

27

James Diao

@JamesADiao

2 years

Scaling laws strike again!! Med-PaLM = Google's PaLM (540B parameters trained on >6k TPUs) + prompting/tuning strategies The accelerating progress is wild to watch. For better or for worse, it's hard to imagine LLMs not infiltrating clinical practice/consumer use sometime soon.

Alan Karthikesalingam

@alan_karthi

2 years

💡New paper - Large Language Models Encode Clinical Knowledge💡 Our work @GoogleHealth @GoogleAI @DeepMind advances state-of-art in 7 medical question-answering tasks - including achieving 67% on MedQA (USMLE qs) improving prior work by >17% 1/n

23

75

402

2

4

26

James Diao

@JamesADiao

7 months

I was explaining q4 call to a friend and he goes "24h shift sounds terrible but at least you get 3 days off to recover" 💀

1

0

24

James Diao

@JamesADiao

4 years

Mentorship is hard work!! Deeply grateful to my incredible mentors who have written *countless* letters to support me—hoping to pass on the favor someday 😇 @arjunmanrai @zakkohane @rozowsky @markgerstein @andybeck @neugebauerkarla @rachelrau3

Noah Whiteman

@NKWhiteman

4 years

Sending in 70ish letters of recommendation for undergrads applying to grad school this weekend. It is such an honor to write on their behalf. The world truly is in good hands.

3

2

232

2

1

26

James Diao

@JamesADiao

3 years

Sobering thought for physician-(data) scientists in training. A typical MD/PhD cardiologist🫀 doesn't finish clinical training until *checks notes* 8-10 YEARS after defending their thesis. Imagine writing a thesis on AI before AlexNet (2012) and coming back to GPT-3 (2020) ☠️

Roxana Daneshjou MD/PhD

@RoxanaDaneshjou

3 years

@IAmSamFin @timothykeyes @walterfwiggins @AndrewLBeam @beaulieujones @timothykeyes as you know, data science changes at a blistering pace. The world moves on without you during residency.

1

0

5

1

0

25

James Diao

@JamesADiao

11 months

We've seen GPT-4 excel on MC medical challenges, but how do things change now that it can "see"? tl;dr - sometimes better, sometimes worse! It depends on how much informative text is available. Great work led by star @HarvardDBMI summer student @tabuckley_ !

Arjun (Raj) Manrai

@arjunmanrai

11 months

In our new preprint, we evaluated GPT-4V on 934 challenging @NEJM medical image cases and 69 clinicopathological conferences. GPT-4V outperformed human respondents overall and across difficulty levels, skin tones, and image types except radiology, where it matched humans. GPT-4V

7

45

156

1

19

James Diao

@JamesADiao

4 years

No patient should ever be denied appropriate care due to their race. In the case of eGFR, race-free equations can deliver both performance and equity in estimates of kidney function. Check out our latest in @NEJM :

In Search of a Better Equation — Performance and Equity in Estimates of Kidney Function | NEJM

Although many experts agree that we should reconsider the use of race in equations for estimated glomerular filtration rate and in medicine more generally, precisely how eGFR equations should chang...

www.nejm.org

0

2

22

James Diao

@JamesADiao

3 years

@timothykeyes I've always thought the 2-4-2 MD/PhD model was a bit odd. PhD after/late in clinical training seems like a better setup for continuous skill-building. Ex: Atul Butte, Andy Beck, Mia Levy, etc.

0

22

James Diao

@JamesADiao

5 months

2/ Tl;dr: using or removing race reclassifies lung disease for millions of patients and reallocates billions in disability compensation. These shifts result from trade-offs in sensitivity vs. specificity with no overall effect on discriminative accuracy.

1

3

20

James Diao

@JamesADiao

5 months

@Reuters Finally, a huge thank you to all of our coauthors and collaborators, and especially to my longtime mentor and senior author @arjunmanrai (picture below introducing our talk at #ATS2024 ). I learned so much and had an incredible time working with all of you!

1

3

20

James Diao

@JamesADiao

2 years

1/ Last year, NKF-ASN recommended a new race-free eGFR equation for immediate nationwide use. The improved equation is already reshaping recommended care for millions. In what ways? Check out our latest in @JASN ! With @ArjunManrai and many others ⬇️

1

2

19

James Diao

@JamesADiao

3 years

1/ Most chronic health conditions have huge disparities in access and outcomes. Mobile tech promises to help bridge the gap, but what do the data show? @jkvedar and I discuss a new meta-analysis in @Nature_NPJ led by @elainekhoong + @urmimalasarkar

Mobile health technology for diverse populations: challenges and opportunities

npj Digital Medicine - Mobile health technology for diverse populations: challenges and opportunities

www.nature.com

1

3

18

James Diao

@JamesADiao

5 months

6/ The use of race in spirometry is also controversial because of its sordid history. Early studies on race and lung function were used to defend White supremacy and justify slavery.

Race, ethnicity and lung function: A brief history

Spirometry is the most common lung function test and represents the cornerstone diagnostic and management tool for individuals with chronic respiratory diseases. Variability and changing temporal...

www.ncbi.nlm.nih.gov

1

2

17

James Diao

@JamesADiao

3 months

A pleasure and privilege to join Drs. Lundy Braun and Aaron Baugh on the latest @NEJM Intention to Treat podcast!

NEJM

@NEJM

3 months

Dr. @JamesADiao , resident physician @BrighamWomens , discusses the impact of changing lung function equations on Veterans Affairs disability compensation. Learn more on the latest episode of Intention to Treat:

2

8

18

0

2

18

James Diao

@JamesADiao

10 months

An inspiring startup journey! I was such a hater when Glass 1.0 came out, not seeing the tide that would rise with GPT-4, RAG, etc. or the mission-driven resolve of the team. Wishing @GlassHealthHQ the very best in 2024 as you work toward launching Glass 3.0 🌟

Dereck Paul MD

@dereckwpaul

10 months

Happy New Year @GlassHealthHQ 🎉🎇🎊 We have had a remarkable year together. And since Walter Isaacson and Ashlee Vance have yet to take on telling our story, for now, you'll have to settle for me. Glass Health 2023 Year in Review 🖤🎆

3

20

78

1

4

16

James Diao

@JamesADiao

5 months

16/ Our study found that using race did NOT improve discriminative accuracy in predicting respiratory outcomes. Instead, it traded-off sensitivity for specificity, with diverging effects by race.

2

5

17

James Diao

@JamesADiao

2 years

@emollick When evaluating free text responses (e.g., "why take simvastatin"), there's no binary right or wrong. 92.6%/92.9% refers to overall agreement with scientific consensus, not that everything in that response was true!

0

17

James Diao

@JamesADiao

5 months

5/ This means that three otherwise identical people could experience different diagnoses, work eligibility, and disability payments, depending on their assumed or reported race.

1

4

16

James Diao

@JamesADiao

3 years

14/ To me, this exchange indicates the challenge of tackling not just existing instances of low value care, but also the continuing influx. As others have shown, especially difficult to overturn when more screening = more $$$.

Reversals of Established Medical Practices

Ideally, good medical practices are replaced by better ones, based on robust comparative trials in which new interventions outperform older ones and establish new standards of care. Often, however,...

jamanetwork.com

1

15

James Diao

@JamesADiao

3 years

1/ How would switching to cystatin-based race-free eGFR affect patient care? We answer this excellent question posed by van der Burgh et al. in today's issue of @JAMA_current .

Removing Race From Kidney Function Estimates—Reply

In Reply In response to our study on the implications of removing race from eGFR,1 Ms van der Burgh and colleagues describe advantages of eGFRcys, including potentially improved prediction of...

jamanetwork.com

3

2

15

James Diao

@JamesADiao

3 years

Grateful to share my thoughts in @ScienceMagazine on subtracting race from clinical algorithms!

1

13

James Diao

@JamesADiao

3 years

Growing up (and now), I spent quite a few weekends putting off homework to interpret and fix grammar for my dad's business (docs/forms/emails). Even now, the company voicemail is my voice from high school 😄

Melissa Gonzalez

@melissa_gon5

3 years

Being a daughter of immigrants means spending a few hours on a Saturday filing their taxes because English is their second language.... meanwhile I still need to catch up on 8 lectures from this week 😅

0

1

24

1

0

14

James Diao

@JamesADiao

4 years

Love @GoogleAI 's transparency here. Thailand 🇹🇭 user studies show: low-quality images + poor internet ➡️ low throughput ➡️ subpar UX. Needs more user studies, multisite RCTs, and postmarket surveillance like any other practice-transforming intervention.

1

2

14

James Diao

@JamesADiao

5 months

8/ These shifts often cut both ways. Consider a 50-year-old Black man seeking firefighting work. Using race-neutral equations may disqualify him from the job. But if he later seeks disability benefits for COPD, the race-neutral equation would justify greater compensation.

1

3

13

James Diao

@JamesADiao

4 years

Very proud to be a part of this dream team collab! @Apple @BrighamWomens @American_Heart

Brigham and Women's Hospital

@BrighamWomens

5 years

Together with @Apple and @American_Heart , we're launching a multi-year longitudinal study of how signals from your heart and mobility signals relate to hospitalizations, falls, heart health & quality of life in order to promote healthy movement and improved cardiovascular health.

2

5

14

0

14

James Diao

@JamesADiao

4 years

omg "Daio et all" love it 😂

JAMA

@JAMA_current

4 years

The report by Daio et all in this issue of JAMA represents an example of the importance of adding data and evidence to inform challenging issues

0

3

6

0

13

James Diao

@JamesADiao

5 months

@he_yix @rohankhaz @maxjordan_n @2plus2make5 @pranavrajpurkar @lukemelas @genetisaur @mahafarhat @luisaborrell @estebanburchard

3

0

11

James Diao

@JamesADiao

5 months

19/ We also hope that lung function assessment can incorporate personalized baselines and more comprehensive measures that continue to move away from crude heuristics like race and toward the shared ideal of precision medicine.

1

10

James Diao

@JamesADiao

5 months

Taking every opportunity to reshare this gem from match day:

0

11

James Diao

@JamesADiao

2 years

ChatGPT scored ~40-60% across the USMLEs. N is low (~100), so CIs are large (+/- 10%). While promising, an LLM that underperforms 99% of med students under ideal conditions (answer choices given, complete info, and text only) has much room to grow.

0

2

9

James Diao

@JamesADiao

4 years

Evidence of stronger effect size & dose-response for the most commonly-prescribed and cost-effective intervention in medicine 🏃🏻‍♂️, analyzed from nearly 100,000 subjects wearing wrist-based sensors ⌚️ #ExerciseIsMedicine

Eric Topol

@EricTopol

4 years

This commentary is too good to sit behind a paywall.

15

154

571

1

2

12

James Diao

@JamesADiao

4 years

@jflier As a @harvardmed student, I am saddened that you have chosen to use your platform this way. It is a mistake and a distraction to focus on verbal generalizations ("all cops.../white people...") over ongoing and life-threatening anti-Blackness in our communities.

0

12

James Diao

@JamesADiao

3 years

7/ Our data find that, for every true positive, you’d find over 1000 false positives, the vast majority of whom will never develop ascending aortic aneurysm anytime in the future. This is because (surprise!) ascending aortic aneurysms are quite rare.

1

0

11

James Diao

@JamesADiao

3 years

11/ Some of my favorites: (1) that we are not doctors and therefore don’t understand physical exams, and (2) that many common exam maneuvers are similarly low value (we quite agree with this!)

2

0

11

James Diao

@JamesADiao

3 years

#SIBMI at @HarvardDBMI gave me two of my favorite summers, my longtime mentor @arjunmanrai , and some of my very best friends in Boston @insachiable @he_yix @ElianaMarostica . Could not recommend more highly!

DBMI at Harvard Med

@HarvardDBMI

3 years

As the cold of December sets in, a reminder that another sublime summer will come to Boston in 2022... along with the 18th year of the Summer Institute in Biomedical Informatics #SIBMI for undergrad quants! Applications close January 31.

0

19

29

0

2

12

James Diao

@JamesADiao

4 years

My first two research experiences were supervised by brilliant female mentors and PIs @Goodell_Lab @SteitzLab . Similar for my work @Apple . I hope no one shies from female mentorship due to the @NatureComms paper 😣

1

12

James Diao

@JamesADiao

5 months

11/ Occupational Implications: 2.3 million with eligibility changes for firefighting work. Similar eligibility changes are expected for jobs in construction, mining, and textile industries.

1

11

James Diao

@JamesADiao

5 months

7/ In 2022, US and European respiratory societies recommended a new race-neutral equation, but we still knew little about the expected downstream effects on patients (or equivalently, the effects of adding race in the first place).

1

2

11

James Diao

@JamesADiao

2 years

Congrats @CD1AO on being offered the @NSF #GRFP and @DOECSGF fellowships for PhD study!! Strong start before stepping foot in Cambridge 😎

0

12

James Diao

@JamesADiao

5 months

4/ For over a century, an individual’s spirometry test was interpreted by comparison to a predicted “normal” based on age, sex, height, and race.

1

12

James Diao

@JamesADiao

5 months

3/ Spirometry is a test of lung function that measures the volume of air someone can breathe out in one second or in one full breath. It’s used to diagnose common diseases like asthma and COPD, and to measure respiratory health.

1

11

James Diao

@JamesADiao

2 years

@DrHughHarvey Pretty sure most clinical LLMs will fly under the radar as non-device CDS. Strong need for updated FDA guidance.

2

4

11

James Diao

@JamesADiao

5 months

From @harvardmed :

Measuring Lung Function More Accurately and More Equitably

New analysis estimates the effects of race-neutral lung function testing

hms.harvard.edu

1

11

James Diao

@JamesADiao

4 years

NKF-ASN task force interim report on #race and #eGFR forthcoming!! "1) race modifiers should not be included in equations to estimate kidney function and 2) current race-based equations should be replaced by a suitable approach that is accurate, inclusive, and standardized"

Screaming Pectoriloquy (𝕖𝕩𝕖𝕔𝕦𝕥𝕖𝕕)

@Caulimovirus

4 years

about time

5

17

104

0

4

11

James Diao

@JamesADiao

3 years

My recent work followed a similar trajectory! Simple methods can be just as much work—they just move the heavy lifting from tuning to interpretation.

1

0

11

James Diao

@JamesADiao

5 months

13/ Transplant Implications: rearrangement of 90% of patients on the 2020 US lung transplant waitlist, with Asian and Black patients moving forward 21 positions on average and Hispanic and White patients moving back 4 positions on average.

2

3

10

James Diao

@JamesADiao

3 years

Cool article by Jorge et al—accurate HR/RR monitoring via video camera. Works while sitting, laying in bed, at night, tucked in, on a ventilator, etc. What else could video tech measure? Where else can it add value? Check out our editorial for more😀 w/ @jayson_marwaha @jkvedar

npj Digital Medicine

@npjDigitalMed

3 years

New article! Read Video-based physiologic monitoring: promising applications for the ICU and beyond in npj Digital Med

0

3

13

0

3

10

James Diao

@JamesADiao

5 months

14/ Amid all these trade-offs, we asked the question: does using race make the equation more accurate? Accuracy is less meaningful for lung function than for kidney function because there is no “gold-standard” like measured GFR.

1

9

James Diao

@JamesADiao

5 months

10/ Clinical Implications: 12.5 million Americans with reclassified ventilatory impairment and 2 million with reclassified COPD severity. This has major implications for diagnoses and follow-up testing, treatment, insurance coverage, and trial enrollment.

1

2

10

James Diao

@JamesADiao

3 months

17/ Also grateful for an incisive editorial by @JelaniGrantMD @ChiadiNdumele @SethShayMartin : “the key message is that the establishment of optimal PREVENT-ASCVD risk thresholds for guiding therapy is critical in the development of future guidelines”

The Evolving Landscape of Cardiovascular Risk Assessment

Cardiovascular disease (CVD) remains the leading cause of death1 in the US and globally and risk estimation is a cornerstone approach to guiding CVD prevention. Over the past 2 decades, various tools...

jamanetwork.com

1

4

11

James Diao

@JamesADiao

4 years

The work of undoing implicit racial bias in #meded begins with precise language and appropriate context. Racism, not race. Race-conscious, not race-based. Check out this must-read @NEJM article from an all-star cast 👇

Jenny Tsai, MD, M.Ed

@tsaiduck77

4 years

It really does matter that medicine starts getting its definitions and uses of race correct. What an exciting honor to work with this team, and to see my name in @nejm next to @dorothyeroberts .

15

161

791

1

2

11

James Diao

@JamesADiao

5 months

12/ Financial Implications: $2B reallocated in disability compensation among 413,000 U.S. veterans, including $1B more among Black veterans and $0.5B less among White veterans.

1

3

10

James Diao

@JamesADiao

4 years

Motion health unveils new metrics for the Apple watch⌚️!! In the age of COVID, remote monitoring of mobility stats like walking/stair speed, asymmetry, and VO2 max has never been more important (esp. in post-op and aging patients!) Movement 👣= medicine 🩺

Adeeti Ullal-Reiter

@AdeetiU

4 years

So proud of the incredible team that made a whole new Mobility room in the Health App.

0

1

11

0

1

10

James Diao

@JamesADiao

1 year

CONGRATS to all!! What an incredible cohort. Every year, I'm reminded how lucky I am to be part of this incredible community ☺️

PD Soros Fellowships

@PDSoros

1 year

❗IT’S ANNOUNCEMENT DAY❗ We're proud to announce the 2023 #PDSoros Fellows! From nearly 2,000 applicants, these 30 graduate school students are immigrants or children of immigrants who will each receive up to $90,000 in funding. Meet the Fellows here ➡️

4

46

191

1

0

10

James Diao

@JamesADiao

3 years

8/ Let's do some math. If you screened 300M in the US, you’d get ~10M positives (sensitivity=3.3%). 10M transesophageal echos = $10-20 billion. That’s more than the CDC’s annual budget. It also ignores all clinic fees, surgical/procedural costs, and follow-up imaging.

2

0

9

James Diao

@JamesADiao

2 years

Prompt injection shows a fairly simple set of instructions, perhaps OpenAI API + a wrapper? The barrier to deploying LLMs (ready or not) has truly never been lower.

1

2

10

James Diao

@JamesADiao

2 years

@ElliotHershberg How about self-healing Roman concrete?

1

0

10

James Diao

@JamesADiao

4 years

"Symphony can compress a 500k-cell reference from 8.9 GB to 1.3 MB, and map a new 10k-cell query in <1 second" 🤯 Congrats @joycebkang and @aparnanathan !!

Joyce Kang, PhD

@joycebkang

4 years

I’m very excited to share Symphony, our new tool for efficient single-cell reference mapping: . Enables accurate mapping of single-cell datasets in seconds! With @soumya_boston , @ilyakorsunsky , @aparnanathan , and other awesome folks. Tweetorial 👇

8

50

252

1

0

10

James Diao

@JamesADiao

4 months

CONGRATS @richardjchen and @AI4Pathology ! Excited to follow the next steps of your amazing work 🔥

Faisal Mahmood

@AI4Pathology

4 months

⚡️📣Today we are tremendously excited to announce @modella_ai the first startup from Mahmood Lab, based on an array of foundation models and generative AI tools including our recent PathChat article in @Nature () @modella_ai will actualize these exciting

14

27

213

0

10

James Diao

@JamesADiao

2 months

Delighted to see promising data for AI outcome assessment in MASH - congrats to @AndyBeck @IWapinski @AmaroTaylorW and teams at @Path_AI !

AI-based automation of enrollment criteria and endpoint assessment in clinical trials in liver...

Nature Medicine - Using data from MASH clinical trials, an AI model shows comparable performance with respect to individual pathologists in assessing histologic scoring for enrollment criteria and...

www.nature.com

0

11

James Diao

@JamesADiao

5 months

17/ For over a century, race adjustment was supported by the assumption that racial differences in lung function are natural and benign. The new GLI-Global equations, though imperfect, offer an important opportunity to move beyond this.

1

8

James Diao

@JamesADiao

5 months

18/ We hope that quantifying the implications of race-based spirometry can inform interventions to redress its harms, preparations for expected changes to care, and improvements to future equations.

1

7

James Diao

@JamesADiao

5 months

20/ Thanks for reading! For more perspectives on this topic, check out the following news on our work:

1

9

James Diao

@JamesADiao

5 months

Congratulations Dr. @luke_sagers on an amazing dissertation!! 🔥🔥🔥

Arjun (Raj) Manrai

@arjunmanrai

5 months

Congrats to **Dr.** @luke_sagers who brilliantly defended his PhD dissertation! Luke rigorously evaluated whether synthetic data can improve medical image classifiers across populations. It's been a privilege to work w/ Luke from when he was a summer undergrad at @HarvardDBMI

2

4

42

1

9

James Diao

@JamesADiao

2 years

@noor_siddiqui_

James Diao

@JamesADiao

2 years

I don't buy it. If "no answer/not in choices/not enough info" are considered wrong answers, ChatGPT failed every test under every query condition (assuming passing is >60%). Not to mention that the study was severely underpowered: N≈100 and p≈0.5, so CIs ≈ +/- 10%.

0

2

27

1

0

9

James Diao

@JamesADiao

3 years

TI BASIC was my baby steps into computing! My middle school teachers would snatch up my calculator thinking I was playing games, but my dork ass was just writing code 🤓

Science 2.0

@science2_0

3 years

Today in 1964 BASIC made its debut, in an effort to take programming out of the world of machine language. Share if you're old enough to have gotten your start with it.

226

3K

5K

1

0

9

James Diao

@JamesADiao

4 years

Nothing would've been possible without my greatest supporters: mom, dad, @cd1ao , @gloriajwu and my incredible mentors, advisors, and role models: @arjunmanrai @zakkohane @markgerstein @karlaneugebauer @rachelrau3 @goodell_lab @andybeck @adeetiu (+more off twitter) Thank you 😌

2

9

James Diao

@JamesADiao

4 years

Very cool study by @he_yix !! Environmental exposures > genetics (alone +/- clinical inputs) for predicting diabetes risk

Yixuan He

@he_yix

4 years

How do environmental exposures and lifestyle factors compare to genetics and clinical factors for predicting risk of type 2 diabetes? Our paper just out in Diabetes Care introduces the polyexposure risk score ( #PXS ) to investigate this question: 1/n

4

13

51

1

0

9

James Diao

@JamesADiao

5 months

9/ Our study used data from 370,000 participants in the U.S. and U.K. to compare race-based and race-neutral equations for interpreting lung function. We looked at clinical, occupational, financial, and statistical implications.

1

8

James Diao

@JamesADiao

5 months

15/ We therefore evaluated discriminative accuracy, which measures how well a lung function index can rank order individuals with respect to a clinical endpoint like new-onset disease or mortality.

1

8

James Diao

@JamesADiao

2 years

Does @US_FDA have oversight over clinical LLMs? For many cases, likely not. Requirements for exemption: ✅ Provides basis for recs ⛔️ No probabilities (ranked ddx is grey area) Most LLMs can comply and would be classified as non-device CDS. It's the wild west out here y'all 🤠

Hugh Harvey

@DrHughHarvey

2 years

@dereckwpaul @GlassHealthHQ Clinical decision support counts as a medical device. @FDADeviceInfo might want a word.

1

0

3

0

2

9

James Diao

@JamesADiao

2 years

Just tried a simpler example without any medical history. The AI gave her new medical conditions to justify its differential: - "History of abdominal surgery" - "History of diverticulosis" Could easily be missed in a more complex patient & contribute to chart lore.

James Diao

@JamesADiao

2 years

Gave this sleek new clinical tool a spin. The ddx explanations are articulate but hilariously wrong - classic LLM smoke and mirrors. If a med student read this A/P on rounds, they would never live it down 😄

3

2

32

1

8

James Diao

@JamesADiao

3 months

16/ Thanks for reading, and shoutout to our phenomenal team! @venkmurthy @chiragjp @2plus2make5 @rwyeh @kardiologykazi @rkwadhera (+ others not on twitter), and of course, my amazing mentor + senior author @arjunmanrai . I’ve learned so much from all of you 😊

1

0

8

James Diao

@JamesADiao

4 years

"First, Do No Harm" - must-read editorial in @JAMA_current that provides essential context for our study on #race and #eGFR . See thread from the one and only @AmakaEMD here 👇

Amaka Eneanya, MD, MPH

@AmakaEMD

4 years

I teamed up with @kcnorris_ucla and @EbonyBoulware to write this @JAMA_current editorial on a study that focuses on the removal of #race in #eGFR equations. We reaffirm that in medicine, we must first do no #harm . A thread🤓⬇️

8

74

223

0

2

8

James Diao

@JamesADiao

3 months

19/ Finally, please see also these excellent articles led by @TimAndersonMD @JAMAinternalmed and @MuntnerPaul @HyperAHA , who also explored changes in predicted risk and medication eligibility with PREVENT:

Predicted Cardiovascular Risk by the PREVENT Equations in US Adults With Stage 1 Hypertension |...

BACKGROUND: The 2017 American College of Cardiology/American Heart Association blood pressure guideline recommends initiation of antihypertensive medication for adults with stage 1 hypertension...

www.ahajournals.org

1

0

8

James Diao

@JamesADiao

2 years

@AlecStapp Maybe the difference lies in expected reward? The chance to test into college and out of a lifetime of manual labor is one hell of an incentive.

1

8

James Diao

@JamesADiao

2 months

Loved this commentary from @drjohnm framing our @JAMA_current study around longstanding questions in CVD risk prediction! #ThisWeekinCardiology

Aug 02 2024 This Week in Cardiology

Two downsides of PFA including autonomic tone and hemolysis, a bad surrogate in AF care, and controversies in defining cardiac risk are the topics John Mandr...

www.youtube.com

1

8

James Diao

@JamesADiao

5 months

From @statnews :