Arjun (Raj) Manrai @arjunmanrai Twitter profile | Pikagi

Pikagi

Arjun (Raj) Manrai

@arjunmanrai

2,756

Followers

377

Following

181

Media

1,403

Statuses

Assistant Professor of Biomedical Informatics, Harvard Medical School @HarvardDBMI | Founding Deputy Editor, @NEJM_AI | Co-host, NEJM AI Grand Rounds

Boston, MA

https://t.co/ScNs4ykDuK

Joined July 2014

Don't wanna be here? Send us removal request.

Pinned Tweet

@arjunmanrai

Arjun (Raj) Manrai

13 days

In 2020, @JamesADiao and I began studying race adjustment in lung-function equations. With amazing coauthors, today we published the past years of work in @NEJM , estimating the many clinical, financial, and occupational implications. #ATS2024 Full paper:

Tweet media one

9

56

169

Last Seen Profiles

@UKGIHep

@UW

@blank_13tay

@ShinchanToday

@SSansyuwu

@BandarStw

@MueedNader

@Sax7374

@konengbiruh

@Rhodestexas

@Rhodestexas

@cdrsalt

@BandarStw

@SPIASrGirlsECNL

@Pecintastw4050

@DGNB_eV

@DonleySeb

@BenJamminsTV

@ElkevanVeen

@stw_pdg

@mo_bitious

@ILikeCat4gooner

@poulomi_nandi

@ariessbaby__

@AmosMeiri

@SPalayew

@blackgalslivin

@Lampshades14

@BandarStw

@chulacola

@AB2_Gallery

@pontsenni

@TanksAaron

@renkliturkce

@Eddie_Steele97

@MeganeNecoP

@arjunmanrai

Arjun (Raj) Manrai

5 years

Introducing our new course at Harvard, BMI 704: Data Science for Medical Decision Making. If you're interested in data science and machine learning applied to medicine, have a look below. Guest lectures by @VPrasadMDMPH , @MauSantillana ! Data and readings:

Tweet media one

Tweet media two

Tweet media three

Tweet media four

12

72

231

@arjunmanrai

Arjun (Raj) Manrai

7 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

Tweet media one

Tweet media two

7

45

157

@arjunmanrai

Arjun (Raj) Manrai

6 years

Billions of lab tests are performed in the U.S. each year, and most are not stratified by demographic variables (e.g. race, sex, age). Should they be? John Ioannidis, @chiragjp , and I explore some of the thorny challenges in our new @JAMA_current piece:

Tweet media one

Tweet media two

1

73

125

@arjunmanrai

Arjun (Raj) Manrai

1 year

I couldn't be more excited to help launch @NEJM_AI as a Deputy Editor and to be working with @zakkohane , @AndrewLBeam , and the entire team

@NEJM_AI

NEJM AI

1 year

Coming soon: NEJM AI, a new journal from NEJM Group. NEJM AI aims to identify and evaluate state-of-the-art applications of artificial intelligence to clinical medicine. Learn more about the new journal:

12

114

337

7

18

125

@arjunmanrai

Arjun (Raj) Manrai

5 years

Excited to share our new analysis in @NatureGenet led by brilliant colleagues @chiragjp and @cmlakhan of @HarvardDBMI : Repurposing large health insurance claims data to estimate genetic and environmental contributions in 560 phenotypes:

Tweet media one

Tweet media two

Tweet media three

2

50

114

@arjunmanrai

Arjun (Raj) Manrai

5 years

Will new genomics and machine learning applications in medicine yield useful biomarkers or expensive "biomarkup"? Excited to share my new article with @mandl in @JAMA_Current :

Tweet media one

Tweet media two

3

50

109

@arjunmanrai

Arjun (Raj) Manrai

2 years

Excited to announce that I’ve joined the core faculty of @HarvardDBMI and that my lab has moved to @HarvardDBMI @HarvardMed . I’m thrilled to return to where I trained with @zakkohane & to join colleagues transforming medicine w/ computation. We’re hiring!

Tweet card media

Arjun (Raj) Manrai

Assistant Professor of Biomedical Informatics, Harvard Medical School

dbmi.hms.harvard.edu

3

5

110

@arjunmanrai

Arjun (Raj) Manrai

5 years

(Thread) The paper by Evangelia et al. in @JClinEpi on 'logistic regression = machine learning' for medicine has generated many reactions. This paper may be misinterpreted by #MachineLearning cynics and enthusiasts alike (). Some thoughts below👇 1/n

Tweet media one

7

66

95

@arjunmanrai

Arjun (Raj) Manrai

5 years

What comes through in the @NatureMedicine article by @EricTopol is that one of the biggest contributions of #ArtificialIntelligence to medicine is highlighting how often physicians disagree with one another. A few examples from the article below.

Tweet media one

Tweet media two

Tweet media three

4

30

97

@arjunmanrai

Arjun (Raj) Manrai

4 years

Excited to announce a new version of our course at Harvard, BMI704: Data Science for Medical Decision Making, and to be teaching with @chiragjp . We'll release lectures, data, and an interactive text of data science methods at link below. Sched + Readings:

Tweet media one

Tweet media two

Tweet media three

Tweet media four

0

29

91

@arjunmanrai

Arjun (Raj) Manrai

5 years

If you're a researcher wondering if you should go to medical school, this advice by @zakkohane is the best I've seen (on his new lab website! ):

Tweet media one

5

23

91

@arjunmanrai

Arjun (Raj) Manrai

4 months

We started @NEJM_AI to publish clinical-grade evidence needed to improve patient care with AI. In our new editorial, we draw inspiration from the first year of the @NEJM_AI Grand Rounds podcast to illustrate what we are eager to publish going forward:

Tweet media one

Tweet media two

4

22

76

@arjunmanrai

Arjun (Raj) Manrai

5 years

Excited to start teaching BMI704: Data Science for Medical Decision Making with @chiragjp today at @HarvardDBMI !

5

9

75

@arjunmanrai

Arjun (Raj) Manrai

5 years

A few years ago, my mom saw her nephrologist for staging her kidney disease. An Indian American woman, she was given test results that *averaged* those of "African Americans" and "Everyone else". Honored that her story is included in this @NPR story:

Tweet card media

Lack Of Diversity In Genetic Databases Hampers Research

Scientists around the world are working to correct a problem with genetic health information — too much of it is currently based on samples of Europeans.

2

39

77

@arjunmanrai

Arjun (Raj) Manrai

5 years

Incredibly concise description (with costs per hour!) of your many options to train #DeepLearning models. From the great folks at @math_rachel @jeremyphoward

Tweet media one

2

16

76

@arjunmanrai

Arjun (Raj) Manrai

9 months

Can synthetic data produced by latent diffusion models improve medical AI? We studied this question using skin disease classifiers in our new preprint led by @luke_sagers @JamesADiao @lukemelas . Takeaways: • Synthetic images can enhance model performance in data-limited

Tweet media one

5

14

75

@arjunmanrai

Arjun (Raj) Manrai

4 years

Huge congratulations to new **Associate Prof** ⁦ @chiragjp ⁩ of @harvardmed ⁦ @HarvardDBMI ⁩⁩. Of course the first thing he wants to do to celebrate is hold group meeting as planned and learn about new research.

Tweet media one

6

8

68

@arjunmanrai

Arjun (Raj) Manrai

9 days

🧵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.

Tweet media one

11

8

186

@arjunmanrai

Arjun (Raj) Manrai

29 days

Could an AI second opinion service improve medical diagnosis and reduce medical errors **today**? We believe the answer is yes with proper oversight. @AdamRodmanMD and I reflect on the urgency in our new @statnews essay:

Tweet card media

An AI-based second opinion service could improve clinical decision-making today

Safely integrating AI into the clinical workflow could help address some of the limitations of human cognition when it comes to diagnosing medical problems.

www.statnews.com

10

18

63

@arjunmanrai

Arjun (Raj) Manrai

1 year

How will GPT-4 change medicine? I lost sleep after this long and fascinating conversation with @peteratmsr of Microsoft. He took us behind the scenes of the Microsoft/OpenAI partnership and predicted how GPT-4 & beyond will impact healthcare. Listen here:

Tweet card media

NEJM AI Grand Rounds | NEJM Group

NEJM AI Grand Rounds, hosted by Arjun (Raj) Manrai, Ph.D. and Andrew Beam, Ph.D., features informal conversations with a variety of unique experts exploring the deep issues at the intersection of...

ai-podcast.nejm.org

1

22

63

@arjunmanrai

Arjun (Raj) Manrai

6 months

It's a privilege to work alongside this creative & hard-working team. It was a great 2023 for our lab at @HarvardDBMI and we are looking forward to 2024!

Tweet media one

0

9

59

@arjunmanrai

Arjun (Raj) Manrai

5 years

If you're a researcher worried you can't compete with the resources of the big companies, this is a stunning defense of the disruptive power of small team science:

Tweet media one

Tweet media two

Tweet media three

1

28

56

@arjunmanrai

Arjun (Raj) Manrai

2 years

Can synthetic data from large diffusion models improve dermatology classifiers across populations? Hear @luke_sagers and @JamesADiao present our new work (joint w/ @pranavrajpurkar @mattgroh @AdeAdamson ) tmrw at the #NeurIPS22 SyntheticData4ML ws: Paper:

Tweet media one

3

14

53

@arjunmanrai

Arjun (Raj) Manrai

2 months

A warm welcome to an amazing new team of Associate Editors at @NEJM_AI including @EnricoCoiera @RoxanaDaneshjou @IAmSamFin @venkmurthy @royperlis @AdamRodmanMD @EffyVayena @bratogram

Tweet media one

Tweet media two

Tweet media three

3

6

51

@arjunmanrai

Arjun (Raj) Manrai

6 years

Great collection of @awscloud -hosted datasets for #MachineLearning image classification, NLP, and localization by @jeremyphoward and the kind folks at @fastdotai

Tweet media one

Tweet media two

0

9

48

@arjunmanrai

Arjun (Raj) Manrai

5 years

Are you looking for a post-doc position in machine learning applied to fundamental questions in medical diagnosis? @chiragjp and I are recruiting for an exciting new position across our labs at @HarvardDBMI / @Bos_CHIP -- reach out if interested!

2

24

49

@arjunmanrai

Arjun (Raj) Manrai

4 years

Reproducing neural architecture search for some ML models can cost 3 R01 grants, but do most medical applications need this? Our take on the top challenges to reproducibility of machine learning in medicine in the latest @JAMA_current :

Tweet media one

Tweet media two

2

20

49

@arjunmanrai

Arjun (Raj) Manrai

5 years

Honoring @MIT_CSAIL 's Pete Szolovits at @harvardmed , @zakkohane shares 3 articles by Pete that were decades ahead of their time and are being recapitulated today.

Tweet media one

Tweet media two

Tweet media three

0

19

47

@arjunmanrai

Arjun (Raj) Manrai

6 months

We are supporting and encouraging the use of large language models in submissions to @NEJM_AI . Read our rationale in this new editorial led by the inimitable @DaphneKoller : and see the helpful thread by @AndrewLBeam below

@AndrewLBeam

Andrew Beam

6 months

1/n: We're excited to share a new policy on the responsible use of LLMs in drafting manuscripts for @NEJM_AI 🔗: We believe strongly that LLMs provide a net benefit to science writing, so we encourage their use. Rationale and caveats for this policy 👇

Tweet media one

Tweet media two

3

62

180

2

11

49

@arjunmanrai

Arjun (Raj) Manrai

3 years

Medical centers across the US have recently removed race from estimates of kidney function. How might this impact care? In our new @JAMA_Current study led by superstar @harvardmed student @JamesADiao , we quantify the broad impact on Black Americans:

Tweet media one

Tweet media two

3

20

47

@arjunmanrai

Arjun (Raj) Manrai

5 years

It's only t-SNE if it's from the Toulouse region of France; otherwise it's just sparkling PCA.

1

7

45

@arjunmanrai

Arjun (Raj) Manrai

4 years

Congrats to @zakkohane , a scientist and mentor like no other

@AMIAinformatics

AMIA

@AMIAinformatics

4 years

The 2020 Morris F. Collen Award of Excellence to be presented to @zakkohane at the AMIA 2020 Virtual Annual Symposium. #AMIA2020

Tweet media one

12

24

111

4

7

41

@arjunmanrai

Arjun (Raj) Manrai

6 years

Many people believe that 21st century neural networks will soon transform doctors' approaches to medical reasoning; the 18th century Bayes' rule has yet to.

1

19

42

@arjunmanrai

Arjun (Raj) Manrai

6 years

Geoff Hinton pens an equation-free essay on how deep learning works in @JAMA_current : cc @AndrewLBeam @zakkohane

Tweet card media

The Potential of Deep Learning Technology to Transform Health Care

In this Viewpoint, Geoffrey Hinton of Google’s Brain Team discusses the basics of neural networks: their underlying data structures, how they can be trained and combined to process complex health...

jamanetwork.com

0

13

41

@arjunmanrai

Arjun (Raj) Manrai

23 days

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

Tweet media one

Tweet media two

2

4

41

@arjunmanrai

Arjun (Raj) Manrai

3 years

We have long known about statistical reasoning challenges in medicine. But where along the diagnostic pathway should we target efforts and for which patient population? My comments on an important new study by @dr_dmorgan et al. in @JAMA_IM :

Tweet media one

Tweet media two

2

13

40

@arjunmanrai

Arjun (Raj) Manrai

3 years

The best part of being a prof. is working alongside passionate students over years. There is nothing quite as rewarding as when they are recognized for their hard work and contributions. Congrats to @JamesADiao , new @PDSoros Fellow:

Meet the Fellows | James Diao

James Diao grew up amid Chinese restaurants, street signs, and supermarkets in...

www.pdsoros.org

4

1

40

@arjunmanrai

Arjun (Raj) Manrai

1 year

#SAIL2023 last week was one of the best conferences I've attended. Nuanced and in-depth discussions about medical AI with an amazing community, and I'm already missing the energy. Some of my highlights were @JamesADiao giving a spotlight talk on our work on improving

Tweet media one

Tweet media two

Tweet media three

Tweet media four

1

6

40

@arjunmanrai

Arjun (Raj) Manrai

4 years

Thrilled to share new work from my group led by @Bos_CHIP / @HarvardDBMI student Luke Sagers in collab. w/ Luke Melas-Kyriazi and @chiragjp , now out in @AgingJrnl : Prediction of chronological and biological age from laboratory data Full text: Thread👇 1/n

Tweet media one

Tweet media two

3

14

38

@arjunmanrai

Arjun (Raj) Manrai

8 months

We had an amazing conversation with @mcuban about AI, large language models, trust in medicine, and Skip Bayless (not a sentence I ever thought I would say). Out now on the latest @NEJM_AI Grand Rounds:

Tweet card media

Mark Cuban on AI, Trust in Health Care, and Skip Bayless | NEJM AI...

In this episode, we’re joined by business magnate and investor Mark Cuban. Cuban describes his journey from humble beginnings as a self-taught programmer to becoming a successful serial entrepreneur...

ai-podcast.nejm.org

1

9

37

@arjunmanrai

Arjun (Raj) Manrai

5 years

Key line from @EricTopol 's recent review of medical #AI in @NatureMedicine : "the ‘AI chasm’—that is, an algorithm with an AUC of 0.99 is not worth very much if it is not proven to improve clinical outcomes."

High-performance medicine: the convergence of human and artificial intelligence

Nature Medicine - Artificial intelligence is beginning to be applied in the medical setting and has potential to improve workflows and errors, impacting patients and clinicians alike.

0

18

37

@arjunmanrai

Arjun (Raj) Manrai

6 years

How can machine learning improve clinical genomics? @zakkohane , @JamesADiao , and I discuss in our new @OxfordJournals Human Molecular Genetics article:

Tweet media one

Tweet media two

0

18

37

@arjunmanrai

Arjun (Raj) Manrai

5 years

The most cited @JAMA_current in the past 3 years is a #DeepLearning paper.

Tweet media one

1

9

35

@arjunmanrai

Arjun (Raj) Manrai

5 years

So U.S. News just released their ranking of "2019 Best Diets Overall" () - it's a GREAT time to reread this @JAMA_current article by John Ioannidis.

Tweet media one

Tweet media two

1

20

33

@arjunmanrai

Arjun (Raj) Manrai

5 years

A seminal 1978 paper by Szolovits and Pauker described two extremes of medical reasoning: purely categorical & purely probabilistic. Explore the "voracious demand for data" of pure probabilistic reasoning below. Created by James Diao for Harvard BMI 704:

Tweet media one

Tweet media two

2

11

36

@arjunmanrai

Arjun (Raj) Manrai

3 years

Deep learning approaches for semantic image segmentation are often data hungry or difficult to train. Thrilled to share our new approach called PixMatch, our #CVPR21 paper now on arXiv. Led by the singular @lukemelas : Paper: Code:

Tweet media one

Tweet media two

Tweet media three

2

11

34

@arjunmanrai

Arjun (Raj) Manrai

9 months

Standing room only for @james_y_zou ’s talk on generative AI at @HarvardDBMI

Tweet media one

0

3

34

@arjunmanrai

Arjun (Raj) Manrai

10 months

Had a blast chatting about healthcare and AI (and basketball!) with @mcuban today for the @NEJM_AI Grand Rounds podcast. Episode coming soon!

Tweet media one

2

5

34

@arjunmanrai

Arjun (Raj) Manrai

6 months

Thrilled to be joining @RoxanaDaneshjou and team at this @StanfordHAI event to discuss the use of generative AI in medical diagnosis and reasoning

@RoxanaDaneshjou

Roxana Daneshjou MD/PhD

@RoxanaDaneshjou

6 months

Excited to be co-moderating with @cyrilzakka for @StanfordHAI @StanfordAIMI 's Health+AI conference. Our session, "Generative AI in Medicine: Potentials and Pitfalls" has an exciting lineup of speakers: @AziziShekoofeh @katieelink @arjunmanrai .

Tweet media one

0

7

43

1

5

34

@arjunmanrai

Arjun (Raj) Manrai

10 months

What a pleasure to chat with the inimitable @atulbutte today for @NEJM_AI Grand Rounds. Sneak preview below with Atul holding a quote with his attitude towards credit assignment; episode coming soon!

Tweet media one

3

8

34

@arjunmanrai

Arjun (Raj) Manrai

5 months

It was great to chat with @RoxanaDaneshjou for @NEJM_AI Grand Rounds — episode out now!

@NEJM_AI

NEJM AI

5 months

🗣️ New episode of AI Grand Rounds!  Dr. @RoxanaDaneshjou shares her journey from a childhood influenced by early exposure to science to her current role as an assistant professor @StanfordMed .  Listen to the full episode now:

Tweet media one

1

15

49

0

5

32

@arjunmanrai

Arjun (Raj) Manrai

2 years

Great to be teaching in person with this guy for the first time in two years! ⁦ @chiragjp ⁩ ⁦ @HarvardDBMI ⁩

Tweet media one

1

3

31

@arjunmanrai

Arjun (Raj) Manrai

9 months

Our conversation with the extraordinary @atulbutte is out now on @NEJM_AI Grand Rounds! Atul shares his career journey, some of his secrets in giving legendary talks, and his mission to use massive data to improve health. Episode link:

Tweet card media

An Iron Fist in a Velvet Glove: A Conversation with Dr. Atul Butte |...

In this episode, pioneering informatician Dr. Atul Butte guides listeners through his storied career, from his early days as a pediatric endocrinologist and informatician in Boston to his trailblaz...

ai-podcast.nejm.org

0

10

30

@arjunmanrai

Arjun (Raj) Manrai

3 months

Boston is lucky to keep @JamesADiao for at least three more years. Beyond proud of James for matching into medicine residency at @BrighamMedRes

@JamesADiao

James Diao

3 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

Tweet media one

Tweet media two

Tweet media three

Tweet media four

10

5

124

0

3

30

@arjunmanrai

Arjun (Raj) Manrai

8 months

Excited to 'debate' Prof. Stultz tmrw about the role of LLMs and AI in medical diagnosis at the annual @ImproveDX #SIDM2023 meeting in Cleveland. What role will LLMs and AI play in improving diagnostic accuracy? How will LLMs shape medical education incl. the excellent training I

Tweet media one

3

5

31

@arjunmanrai

Arjun (Raj) Manrai

3 years

Grassroots activism has prompted a long-overdue reconsideration of race across medicine. We can achieve both performance and equity with race-free equations. Here are our thoughts on eGFR in the latest @NEJM :

Tweet media one

Tweet media two

Tweet media three

Tweet media four

0

11

30

@arjunmanrai

Arjun (Raj) Manrai

5 years

A few years ago, we (cc @sacjai @zakkohane ) published a small study on medicine's uncomfortable relationship with math (). I wonder if our results would have improved if stats lectures in med school looked a little more like this:

1

10

30

@arjunmanrai

Arjun (Raj) Manrai

5 years

(Thread) 2019 problem: you have a big dataset and everything is significant after Bonferroni. What's spurious; what's real? How do you prioritize? Happy to share my take w/ John Ioannidis & @chiragjp out now in the American Journal of Epidemiology: 1/n 👇

Tweet media one

1

14

29

@arjunmanrai

Arjun (Raj) Manrai

5 years

Beautiful visualization of Roger Federer's longevity:

Tweet media one

Tweet media two

0

9

30

@arjunmanrai

Arjun (Raj) Manrai

6 years

Same trial, two very different conclusions. This study in @JAMA_current exposes a fundamental tension in interpreting RCTs: should we summarize them as Bayesians using priors informed by previous studies/meta-analyses or should we keep them isolated?

Tweet media one

Tweet media two

Tweet media three

3

13

30

@arjunmanrai

Arjun (Raj) Manrai

2 months

Just wrapped up a great conversation with the inimitable @DaphneKoller ...episode on @NEJM_AI Grand Rounds soon!

Tweet media one

1

2

28

@arjunmanrai

Arjun (Raj) Manrai

6 years

Advice to early grad students: choose a PhD mentor who cares enough to learn what "GOAT" stands for because of your LeBron obsession.

@zakkohane

Isaac Kohane

6 years

Eager for @arjunmanrai scholarly opinion on GOAT @KingJames move to @Lakers

0

0

5

4

2

28

@arjunmanrai

Arjun (Raj) Manrai

5 years

In sum, this paper is generating what I hope will be a useful discussion around reporting and bias. The less comfortable question it leads to is how much time/resources are spent on methods innovation that would be better spent on less glamorous data tasks. 12/12

3

5

29

@arjunmanrai

Arjun (Raj) Manrai

5 years

This never gets old.

Tweet media one

0

9

28

@arjunmanrai

Arjun (Raj) Manrai

5 years

That feeling when the inimitable @chiragjp shows your paper at ICML 2019

Tweet media one

2

3

28

@arjunmanrai

Arjun (Raj) Manrai

7 years

Geoff Hinton's advice for #DeepLearning #AI : "Read the literature but don't read too much of it." Trust intuition.

1

11

26

@arjunmanrai

Arjun (Raj) Manrai

5 years

Incredibly proud of my student Luke Melas-Kyriazi for being selected as a Rhodes Scholar. Keep an eye out for his machine learning+medicine work at ⁦ @UniofOxford ⁩!

1

1

26

@arjunmanrai

Arjun (Raj) Manrai

5 years

⁦⁦ @Bos_CHIP ⁩ post journal club fun at ⁦ @trilliumbrewing ⁩ just outside our new space! cc ⁦⁦ @mandl ⁩ ⁦ @TMills ⁩ ⁦ @AartiAtWork ⁩ ⁦ @DianboLiu ⁩

Tweet media one

1

3

25

@arjunmanrai

Arjun (Raj) Manrai

1 year

Diving deep into LLMs, @AndrewLBeam and I interviewed @alan_karthi and @vivnat about Google's Med-PaLM model on the latest @NEJM_AI Grand Rounds. They reflect on the need for careful evaluation, the breakthroughs that led us here, and where we are headed.

Tweet card media

Google’s Exploration of Large Language Models in Medicine | NEJM AI...

Large language models (LLMs) like ChatGPT have proven highly capable of a broad array of natural language tasks including summarizing text, generating prose, and answering questions. This episode’s...

ai-podcast.nejm.org

1

9

26

@arjunmanrai

Arjun (Raj) Manrai

1 year

Excited to share our new @NEJM_AI Grand Rounds episode, an enlightening conversation with @pranavrajpurkar of @HarvardDBMI who takes us behind the scenes of a few seminal medical AI papers over the past decade and also gives us a preview of what's next:

Tweet card media

NEJM AI Grand Rounds | NEJM Group

NEJM AI Grand Rounds, hosted by Arjun (Raj) Manrai, Ph.D. and Andrew Beam, Ph.D., features informal conversations with a variety of unique experts exploring the deep issues at the intersection of...

ai-podcast.nejm.org

0

6

26

@arjunmanrai

Arjun (Raj) Manrai

6 years

At #NIPS2017 and interested in medicine? Witness how medicine is becoming an information processing discipline at the ML4H workshop on Friday with @AndrewLBeam @zakkohane @drfeifei @atulbutte et al.

1

13

25

@arjunmanrai

Arjun (Raj) Manrai

4 years

Estimating the Prevalence of COVID-19 in the United States: Three Complementary Approaches. From the brilliant @MauSantillana of @Bos_CHIP and @harvardmed : Full paper:

Tweet media one

Tweet media two

1

10

25

@arjunmanrai

Arjun (Raj) Manrai

3 years

We are rediscovering much of the conversation about machine learning in medicine from the 1970s and 1980s. HINT: tons of good research project ideas available by mapping that literature onto today's methods & data. Read & re-read Pete Szolovits and others!

@GHideas

Aman Bhandari

3 years

1987 NEJM. Shouldn’t we be asking the same question 34 yrs later about whether #AI has revolutionized medicine?

Tweet media one

3

9

38

0

7

24

@arjunmanrai

Arjun (Raj) Manrai

7 months

Really looking forward to joining @EricTopol & Dr. James to discuss AI's role in medical diagnosis and treatment and sharing some of work happening at @HarvardDBMI and @NEJM_AI

@Medscape

Medscape

7 months

AI is here. Is your practice ready? Join us for a live panel featuring insights from @EricTopol , @arjunmanrai , and Dr. Ted A. James as they delve into AI's role in diagnosis, treatment, precision medicine, and related areas. Register: #MedTwitter

Tweet media one

2

15

27

0

5

24

@arjunmanrai

Arjun (Raj) Manrai

2 years

Much confusion remains about appropriate clinical uses of genetic testing with thorny questions around 'normal' variation. Engage with leaders at the @HarvardDBMI @harvardmed precision medicine conference this fall. Speaker lineup & registration:

Tweet media one

0

3

24

@arjunmanrai

Arjun (Raj) Manrai

3 years

"Data about the timing of when laboratory tests were ordered were more accurate than the test results in predicting survival in 118 of 174 tests (68%)."

Tweet card media

Biases in electronic health record data due to processes within the healthcare system: retrospect...

Objective To evaluate on a large scale, across 272 common types of laboratory tests, the impact of healthcare processes on the predictive value of electronic health record (EHR) data. Design Retros...

0

4

23

@arjunmanrai

Arjun (Raj) Manrai

3 years

The fundamental question for medical machine learning papers: Yes the AUCs are 0.98, but what are we modeling?

@zakkohane

Isaac Kohane

3 years

Are AI programs really predicting patient's future from physiology? Or are they often taking cues frm clinician behavior? William Yuan @beaulieujones @AndrewLBeam @bratogram @GriffinMWeber provide evidence towards latter case @Nature_NPJ Digital Medicine

Tweet media one

Tweet media two

3

47

127

0

6

24

@arjunmanrai

Arjun (Raj) Manrai

2 months

We had a really fun conversation with @erichorvitz for @NEJM_AI Grand Rounds. It was a wide-ranging discussion on AI in medicine, from Eric’s early pioneering efforts to the latest advancements in prompting LLMs. We even snuck in some decision theory. Listen here:

@NEJM_AI

NEJM AI

2 months

📢 New episode of AI Grand Rounds! Dr. @erichorvitz describes his career evolution from an interest in neurobiology to significant contributions in AI, particularly in understanding complex systems and applying AI in medicine. Listen to the full episode:

Tweet media one

1

6

16

2

2

23

@arjunmanrai

Arjun (Raj) Manrai

5 years

Interested in machine learning and medicine? Check out this @JAMA_current collection of articles:

Tweet media one

1

7

22

@arjunmanrai

Arjun (Raj) Manrai

1 year

It takes real grit to transform a medical AI idea into clinical impact. Hear @MichaelAbramoff 's path-breaking story developing the first autonomous (no doc req'd) medical device to receive FDA authorization on the latest @NEJM_AI Grand Rounds:

Tweet card media

No Doctor Needed? Dr. Michael Abramoff on the Potential of Autonomous...

Dr. Michael Abramoff is a renowned ophthalmologist and medical AI pioneer. In this episode, we explore his groundbreaking work that led to the first FDA-authorized device that does not require a...

ai-podcast.nejm.org

0

8

23

@arjunmanrai

Arjun (Raj) Manrai

2 months

We know LLMs can ace multiple-choice exams. Taking us deeper, an important new study led by @stephcabral_ and @AdamRodmanMD conducts a nuanced evaluation of the clinical reasoning abilities of GPT-4 wrt physicians. Guess who wins? Need more of these!

Tweet card media

Clinical Reasoning of a Generative AI Model Compared With Physicians

This cross-sectional study assesses the ability of a large language model to process medical data and display clinical reasoning compared with the ability of attending physicians and residents.

jamanetwork.com

1

11

22

@arjunmanrai

Arjun (Raj) Manrai

5 years

The Manrai Lab at @Bos_CHIP / @harvardmed is recruiting a funded postdoc in stat gen and/or comp genomics. 2+ years, very competitive salary, and intellectual freedom. Relevant lab papers: If interested:

Tweet card media

Genetic Misdiagnoses and the Potential for Health Disparities | NEJM

For more than a decade, risk stratification for hypertrophic cardiomyopathy has been enhanced by targeted genetic testing. Using sequencing results, clinicians routinely assess the risk of hypertro...

0

13

22

@arjunmanrai

Arjun (Raj) Manrai

1 year

Check out the author list h/t ⁦ @AndrewLBeam ⁩ Performance of ChatGPT on USMLE: Potential for AI-Assisted Medical Education Using Large Language Models | medRxiv

Tweet card media

Performance of ChatGPT on USMLE: Potential for AI-Assisted Medical Education Using Large Language...

We evaluated the performance of a large language model called ChatGPT on the United States Medical Licensing Exam (USMLE), which consists of three exams: Step 1, Step 2CK, and Step 3. ChatGPT...

www.medrxiv.org

1

5

23

@arjunmanrai

Arjun (Raj) Manrai

1 year

Thrilled to announce @NEJM_AI Grand Rounds, a new podcast I'm co-hosting with @AndrewLBeam . We'll feature informal conversations with experts exploring deep issues at the intersection of artificial intelligence, machine learning, and medicine.

Tweet card media

NEJM AI Grand Rounds | NEJM Group

NEJM AI Grand Rounds, hosted by Arjun (Raj) Manrai, Ph.D. and Andrew Beam, Ph.D., features informal conversations with a variety of unique experts exploring the deep issues at the intersection of...

ai-podcast.nejm.org

@NEJM_AI

NEJM AI

1 year

Launching later this month, NEJM AI Grand Rounds is a new podcast exploring how #ArtificialIntelligence will change clinical practice and healthcare. Listen to the podcast trailer and subscribe: #AIinMedicine

0

13

34

1

8

22

@arjunmanrai

Arjun (Raj) Manrai

2 months

Excited to speak about artificial intelligence and pulmonary medicine next week ... will include some of our lab's work at @HarvardDBMI and also highlight papers we've published over the past few months at @NEJM_AI

@MassThoracic

Massachusetts Thoracic Society (MTS)

3 months

Registration is OPEN for the 77th Mass Thoracic Society conference! Taking place on April 4. Register here:

0

3

2

0

1

22

@arjunmanrai

Arjun (Raj) Manrai

6 years

THREAD - #AI is awesome, but will new algorithms reach patients? Shortliffe & Sepulveda in @JAMA_current remind us about the decades-long "challenges of credibility and adoption" that have long faced clinical decision support systems 1/n

Tweet media one

1

10

22

@arjunmanrai

Arjun (Raj) Manrai

2 months

This was a lot of fun this morning. Especially enjoyed the best cases presented by the fellows and discussed by faculty after my talk (and trialing GPT-4 as discussant!)

@MassThoracic

Massachusetts Thoracic Society (MTS)

2 months

First talk! “Artificial Intelligence and Its Potential Impact on Pulmonary Medicine” by Deputy Editor of @NEJM_AI of @harvardmed and @BIDMChealth , @arjunmanrai !

Tweet media one

0

4

15

1

0

22

@arjunmanrai

Arjun (Raj) Manrai

1 year

Table 1 from the new GPT-4 paper. Each exam is individually impressive but how many people could pass all of these exams?

Tweet media one

1

5

22

@arjunmanrai

Arjun (Raj) Manrai

9 months

Just had a great conversation about radiology, artificial intelligence, and algorithmic bias with @judywawira for @NEJM_AI Grand Rounds. Episode coming soon

Tweet media one

1

5

21

@arjunmanrai

Arjun (Raj) Manrai

5 years

Oh man - millions of PowerPoints worldwide need to be updated (including my own).

@erlichya

Yaniv Erlich 💔

5 years

I did not look at this slide for a long time. But now I am concerned. We are about to complete four years of ZERO change in WGS costs, the longest stagnation in the past 20 years. #stagnation

Tweet media one

22

201

399

1

2

21

@arjunmanrai

Arjun (Raj) Manrai

5 years

The question I get most often from students new to data analysis is: What can I do to improve my practical skills? My answer: read and work through . And then do it again in a few months. And then again.

0

6

20

@arjunmanrai

Arjun (Raj) Manrai

11 months

Excited to share our conversation with the always engaging and insightful @MarzyehGhassemi on @NEJM_AI Grand Rounds Check it out here:

Tweet card media

Can AI Be Harmful? A Conversation with MIT’s Dr. Marzyeh Ghassemi |...

Dr. Marzyeh Ghassemi has been at the forefront of medical machine learning for several years. In this episode, she describes her group’s work and her perspectives on developing and applying machine...

ai-podcast.nejm.org

0

5

20

@arjunmanrai

Arjun (Raj) Manrai

4 years

Incredibly privileged to work alongside this group and proud of all they accomplished in 2019. Excited for the next year!

Tweet media one

0

2

19

@arjunmanrai

Arjun (Raj) Manrai

26 days

It was really great for me and @AndrewLBeam to chat with @AdamRodmanMD and/or his digital simulacrum about LLMs, diagnostic reasoning, and the history of medicine for @NEJM_AI Grand Rounds. Episode coming soon!

Tweet media one

0

3

19

@arjunmanrai

Arjun (Raj) Manrai

1 year

Illuminating and fun (and at times high entropy!) conversation with Michael Abramoff and @AndrewLBeam coming to @NEJM_AI Grand Rounds soon

Tweet media one

2

3

19

@arjunmanrai

Arjun (Raj) Manrai

10 months

New episode of @NEJM_AI Grand Rounds is out! A conversation with the amazing @oziadias on AI bias, safety, and generalizability. Ziad illustrated how AI is a double-edged sword that can both exacerbate and reduce health disparities. Link here:

Tweet card media

The Double-Edged Sword of AI, with Dr. Ziad Obermeyer | NEJM AI Grand...

In this thought-provoking episode, Dr. Ziad Obermeyer delves into the complex issues of bias, safety, and generalizability of medical AI. Dr. Obermeyer emphasizes the importance of machine learning...

ai-podcast.nejm.org

0

4

19

@arjunmanrai

Arjun (Raj) Manrai

5 years

The search for illness is becoming increasingly proactive in the digital and genomic age. What are the consequences? My new piece with @mandl in STAT @statnews : about our recent @JAMA_current piece on Biomarkup:

Tweet media one

Tweet media two

Tweet media three

Tweet media four

0

7

18

@arjunmanrai

Arjun (Raj) Manrai

1 year

⁦ @JamesADiao ⁩ giving a great talk on the opportunities and limitations of using synthetic images produced by generative AI to improve the performance of dermatological classifiers #SAIL2023

Tweet media one

Tweet media two

2

2

18

@arjunmanrai

Arjun (Raj) Manrai

5 years

How can we measure the exposome comprehensively and associate it with disease? Watch @chiragjp 's @TEDxSFbay talk live now:

Tweet card media

Exposome: decoding human health and diseases | Chirag Patel |...

The genome was said to code life, but that's not the entire story in health. In this insightful talk, Chirag Patel asks us to think beyond the Human #Genome ...

www.youtube.com

0

8

17