NEJM AI @NEJM_AI Twitter profile

Pinned Tweet

NEJM AI

2 days

In the latest episode of the AI Grand Rounds podcast, Dr. @drnigam shares his journey from training as a doctor in India to becoming a leading figure in biomedical informatics in the United States. Listen to the full episode:

0

7

32

Last Seen Profiles

@beehOnly

@KT_seeds

@ToshiroGrendel

@thwkeendd

@hijabjilbab1

@zeitms

@nylan_brown

@GaryMuircroft

@AtillaMenderes

@antideutsch_org

@AshleyWatter35

@Eniolaphilip7

@maxi_corazon

@sapnasappuu

@madiwxtkins

@JesseCosta11

@LajuIren

@AlickovicA1

@CamilleGrenu

@nasticmanresa

@Ta3meed

@jb86440

@sofiafonsoferre

@Ankolgunaktifim

@Lul_kyyyyy

@CLyman0

@bylandee

@1SozlukYazari_

@FarmSanctuary

@TofuKleb

@StPaulsWayTrust

@MediaSionnach

@magna_virtute

@sritoper

@Myth_

@bobstone12348

NEJM AI

@NEJM_AI

1 year

Episode 2 of NEJM AI Grand Rounds is here! @AndrewLBeam and @arjunmanrai are joined with @pranavrajpurkar , an assistant professor @HarvardDBMI who leads a lab focused on developing AI capable of highly complex medical decision making. Listen now:

Dr. Pranav Rajpurkar on AI and Radiology

nejm.org

7

122

1K

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:

Introducing NEJM AI

nejm.org

12

113

336

NEJM AI

@NEJM_AI

5 months

🚀 The new NEJM AI has launched! 💻 Experience the new website and explore the first issue:

NEJM AI

nejm.org

5

69

158

NEJM AI

@NEJM_AI

1 year

Will #ArtificialIntelligence replace doctors? Dr. Ashley says no: “I think that AI will allow doctors to focus on the reasons they went into medicine, which are the human ones.” Hear more from @euanashley in the NEJM AI Grand Rounds podcast:

Dr. Euan Ashley on AI, Genomics, and Cardiology

nejm.org

2

39

130

NEJM AI

@NEJM_AI

2 months

Med-PaLM Multimodal, a proof-of-concept for a generalist biomedical AI system, is a large multimodal generative model that flexibly encodes and interprets biomedical data. Read the full article by @taotu831 , PhD, et al.:

1

34

128

NEJM AI

@NEJM_AI

6 months

GPT-4 correctly diagnosed 57% of complex medical case challenges, outperforming >99% of simulated human readers generated from online answers. Read "Use of GPT-4 to Diagnose Complex Clinical Cases" by Drs. Alexander Eriksen, Sören Möller & @JesperRyg :

Use of GPT-4 to Diagnose Complex Clinical Cases

nejmgroup-production.org

3

46

122

NEJM AI

@NEJM_AI

2 months

AI models perform better when trained on underlying measurements rather than the associated diagnoses, because dichotomizing data loses information that is useful in training AI models. Read the Case Study by @amey_vrudhula , BS, et al.:

5

37

102

NEJM AI

@NEJM_AI

27 days

A nationwide study found that an AI language model outperformed physicians in medical board residency exams across multiple specialties. Learn more in "GPT versus Resident Physicians — A Benchmark Based on Official Board Scores" by @uriel_katz_ , et al.

6

40

95

NEJM AI

@NEJM_AI

5 months

📢 New episode of AI Grand Rounds!  Dr. @zakkohane , professor @harvardmed and editor-in-chief of @NEJM_AI , shares his journey into AI and medicine, the importance of mentorship, and insights into the journal and its objectives.  🔊 Listen now:

AI Grand Rounds | Episode 13

nejm.org

3

23

69

NEJM AI

@NEJM_AI

5 months

“AI is not a fad. It will revolutionize the way medicine is practiced and change the doctor-patient relationship." –Editor-in-Chief @zakkohane Read how @NEJM_AI will apply the same rigorous standards as @NEJM to determine which AI tools are ready for use in medicine:

News Release

eurekalert.org

3

33

72

NEJM AI

@NEJM_AI

1 year

In the latest episode of AI Grand Rounds, Dr. Peter Lee ( @peteratmsr ) reveals @Microsoft ’s interest in health care and the origins of the OpenAI and Microsoft partnership, and he speculates on how large language models like ChatGPT will transform medicine. Listen now:

Dr. Peter Lee on the Future of Language Models in Medicine

nejm.org

1

34

71

NEJM AI

@NEJM_AI

1 year

AI has tremendous potential to advance clinical practice and patient care. @NEJM recently kicked off a new article series examining the application of AI technology in clinical medicine and across the health care continuum. Explore the series:

AI in Medicine | A Review Series from NEJM

nejm.org

1

32

70

NEJM AI

@NEJM_AI

9 months

Dr. @oziadias argues that the best work in cross-disciplinary fields such as medical machine learning often arises when a single person acquires a deep understanding of both disciplines as opposed to two experts in separate fields being brought together.

6

25

66

NEJM AI

@NEJM_AI

5 months

In this first editorial in NEJM AI, Editor-in-Chief @zakkohane reflects on AI’s historical milestones and current capabilities, particularly large language models, and the imperative for their rigorous clinical evaluation. Read it here:

Editorial: Injecting Artificial Intelligence into Medicine

nejm.org

2

29

58

NEJM AI

@NEJM_AI

5 months

Volume 1, Number 1 is here! Read the inaugural issue of NEJM AI, a new journal on medical artificial intelligence and machine learning from NEJM Group: 📚 🔖 Bookmark for later. Share with colleagues.

4

21

61

NEJM AI

@NEJM_AI

1 year

NEJM AI Grand Rounds, a new podcast from NEJM Group exploring #ArtificialIntelligence and its application to medicine, is coming later this month. Listen to a preview and subscribe: #AIinMedicine

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

2

18

60

NEJM AI

@NEJM_AI

11 months

🗣️ New AI Grand Rounds! Dr. @MarzyehGhassemi 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 learning to understand and improve health. Listen now:

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

nejm.org

6

20

58

NEJM AI

@NEJM_AI

1 year

A model named PubMedGPT 2.7B was trained on millions of scientific articles. On a dataset of exam prep questions for USMLE Step 1, the model answered 50% correctly. Read more about this autoregressive language model:

PubMedGPT 2.7B

stanford.edu

2

20

56

NEJM AI

@NEJM_AI

1 year

This paper asks “Do We Still Need Clinical Language Models?” in the era of ChatGPT? Their analysis finds the answer, at least for now, is yes:

Do We Still Need Clinical Language Models?

Although recent advances in scaling large language models (LLMs) have resulted in improvements on many NLP tasks, it remains unclear whether these models trained primarily with general web text...

arxiv.org

4

14

56

NEJM AI

@NEJM_AI

9 months

📢 New episode of AI Grand Rounds out now! Informatician Dr. @atulbutte guides listeners through his storied career, from his early days as a pediatric endocrinologist and informatician in Boston to his trailblazing work on the West Coast. 🎧 Listen now:

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

nejm.org

0

22

56

NEJM AI

@NEJM_AI

2 months

Editorial by Jeffrey M. Drazen, MD, and @charlottehaug , MD, PhD: Trials of AI Interventions Must Be Preregistered

2

24

54

NEJM AI

@NEJM_AI

4 months

In a talk @BrownMedicine , Editor-in-Chief @zakkohane , urged doctors-in-training to understand and make use of artificial intelligence. “It's an existential opportunity and threat to medicine to not take [AI] seriously.” See what else he said:

Bioinformatics expert to med students: Ignore the AI revolution at the peril of patients, providers

In a presentation at Brown’s Warren Alpert Medical School, Dr. Isaac Kohane, who has worked on medical AI since the 1990s, urged doctors-in-training to understand and make use of artificial intelli...

www.brown.edu

4

17

54

NEJM AI

@NEJM_AI

1 year

GPT-4, without any specialized prompt crafting, outperforms earlier models and exceeds the passing score on the USMLE by 20+ points. The model is also significantly better calibrated and can predict the likelihood that its answers are correct.

4

23

54

NEJM AI

@NEJM_AI

3 months

Editorial by @arjunmanrai , @AndrewLBeam , and @zakkohane : What We Want to Publish at NEJM AI

0

13

53

NEJM AI

@NEJM_AI

4 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:

1

15

49

NEJM AI

@NEJM_AI

5 months

The inaugural issue of @NEJM_AI is here. Each issue explores the cutting-edge research and applications of artificial intelligence in clinical medicine. View the Table of Contents and start learning: 🔖 Bookmark and share with a colleague.

Vol. 1, No. 1 | NEJM AI

nejm.org

2

18

44

NEJM AI

@NEJM_AI

8 months

In this flagship paper, Dr. @atulbutte and colleagues demonstrate that deep learning models using entire electronic health records can accurately predict mortality, readmissions, and diagnoses without manual data harmonization.

Scalable and Accurate Deep Learning with Electronic Health Records

nature.com

3

17

48

NEJM AI

@NEJM_AI

6 months

Recently, a paper exploring the potentials of GPT-4 showed it was able to answer questions in the USMLE correctly. However, how well it performs on real-life clinical cases is less well understood. The authors of a new Perspective take a deeper look:

Use of GPT-4 to Diagnose Complex Clinical Cases

nejmgroup-production.org

2

18

44

NEJM AI

@NEJM_AI

8 months

📢 New episode of AI Grand Rounds! Business magnate and investor @mcuban describes his journey from humble beginnings to successful entrepreneur and NBA team owner. He also unpacks the potential of AI in addressing previously intractable problems in health care. Listen now:

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

nejm.org

1

20

45

NEJM AI

@NEJM_AI

1 year

Microsoft's Peter Lee predicts large language models such as ChatGPT will be used every day in clinical settings by patients, physicians, and nurses. He argues that public debate is urgently needed to ensure these tools are used well. Full episode:

1

26

45

NEJM AI

@NEJM_AI

3 months

AI models that accurately predict risk of sepsis onset could speed delivery of interventions. A @michigan_AI study by @Fhdfudgy , et al. examines an evaluation framework for AI models that accounts for the clinical recognition of the outcome. Full study:

1

26

43

NEJM AI

@NEJM_AI

1 year

How will clinicians get compensated for using AI? How can health care systems decide whether to deploy AI systems? How should AI companies plan for adoption of this technology by providers? This free virtual event addresses these questions. Sign up:

The Value Distribution of Clinical AI

nejm.org

1

18

41

NEJM AI

@NEJM_AI

8 days

Perspective: “Patient Portal — When Patients Take AI into Their Own Hands” by @goldbergcarey : #AIinMedicine

0

16

44

NEJM AI

@NEJM_AI

5 months

View the inaugural issue of NEJM AI, a new journal that explores cutting-edge applications of artificial intelligence and machine learning in clinical medicine: Share with a colleague and subscribe:

Vol. 1, No. 1 | January 2024

nejm.org

2

22

40

NEJM AI

@NEJM_AI

6 months

This Original Article examines the adoption and usage of medical AI devices in the U.S. by tracking CPT codes explicitly created for medical AI. Results indicate that medical AI device adoption is still nascent, with most usage driven by a few leading devices. Full study:

Clinical Adoption of Medical AI Devices through U.S. Insurance Claims

nejm.org

1

16

42

NEJM AI

@NEJM_AI

4 months

A new Case Study describes lessons learned and challenges encountered by the largest health care system in the state of Rhode Island in utilizing AI to successfully address a widespread problem in healthcare: the poor readability of medical consent forms. Read it here:

Using ChatGPT to Facilitate Truly Informed Medical Consent | NEJM AI

nejm.org

1

23

41

NEJM AI

@NEJM_AI

1 year

Authored by leading experts, “AI in Medicine” is a new Review Article series from @NEJM examining the role of AI technology in clinical medicine, along with the promise and pitfalls of its application across the health care continuum. Explore the articles:

AI in Medicine

nejm.org

0

17

42

NEJM AI

@NEJM_AI

7 months

. @EricTopol describes vast applications of multimodal AI in medicine, and underscores the expansive behaviors of large-scale models. 1/2

2

21

36

NEJM AI

@NEJM_AI

4 months

CASE STUDY: Using ChatGPT to Facilitate Truly Informed Medical Consent

5

11

40

NEJM AI

@NEJM_AI

23 days

In a new Perspective, Jonathan H. Chen, M.D., Ph.D. ( @jonc101x ), discusses how human–computer interactions with artificial intelligence may stimulate our most human activities needed in medicine. Read "Who’s Training Whom?" here:

1

17

41

NEJM AI

@NEJM_AI

1 month

A novel AI–based system provides accurate and generalizable broad-spectrum disorder detection in medical imaging. Read the Original Article by Yuwei He, PhD, et al.:

0

15

39

NEJM AI

@NEJM_AI

1 year

Meet the hosts: @AndrewLBeam , PhD, is an assistant professor of epidemiology at @HarvardChanSPH and the @CAUSALab . The Beam lab develops new deep learning & causal inference methods for medical decision making, and they have a special interest in neonatal and perinatal medicine.

1

6

40

NEJM AI

@NEJM_AI

9 months

Dr. @atulbutte explains how he built his lab and career while at Stanford using massive amounts of publicly available data, which he then used to create a new molecular taxonomy of human disease. Listen to the latest episode of AI Grand Rounds:

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

nejm.org

2

13

39

NEJM AI

@NEJM_AI

4 months

New Original Article: Augmenting LLMs with knowledge databases (e.g., browser, calculators) demonstrated improved factuality, safety, completeness, and physician preference when compared to other models. Read the full study by @cyrilzakka and others:

2

16

39

NEJM AI

@NEJM_AI

11 months

A new systematic review evaluates the impact of self-supervised learning in medical image classification. Findings show improved model performance, especially in radiology. Combining different SSL strategies appears promising.

Self-supervised learning for medical image classification: a systematic review and implementation...

npj Digital Medicine - Self-supervised learning for medical image classification: a systematic review and implementation guidelines

www.nature.com

0

12

39

NEJM AI

@NEJM_AI

1 year

What makes or breaks a medical AI application is often the quality of data and labels used in model training. Here, @lhpeng highlights the fundamental role of data quality and “ground truth” labels in determining the success of medical AI. Hear more:

2

7

33

NEJM AI

@NEJM_AI

6 months

The authors of a new Original Article found that the overall utilization of medical AI products is still limited and focused on a few leading procedures. However, utilization has generally increased exponentially for each medical AI procedure. Read more:

Clinical Adoption of Medical AI Devices through U.S. Insurance Claims

nejm.org

0

14

38

NEJM AI

@NEJM_AI

1 year

Announcing "The Value Distribution of Clinical AI," a free virtual event featuring expert viewpoints on the current state of AI in health care and how to align financial incentives for successful AI adoption. Learn more and register:

The Value Distribution of Clinical AI

nejm.org

1

20

37

NEJM AI

@NEJM_AI

4 months

Dr. @marinkazitnik is an Assistant Professor of Biomedical Informatics @harvardmed with additional appointments @harvard_data and @broadinstitute of Harvard and MIT. Dr. Zitnik works on infusing knowledge, structure, and geometry into machine learning models.

Editorial Board | NEJM AI

nejm.org

2

9

38

NEJM AI

@NEJM_AI

10 months

Medical thinking is evolving. With the rapid expansion of medical knowledge and complex patient data, the human mind's capacity is being tested. Computers could be key to managing this complexity and shaping the future of medicine.

Lost in Thought

nejm.org

0

12

36

NEJM AI

@NEJM_AI

1 year

🎙️ New episode! LLMs have proven capable of a broad array of natural language tasks including summarizing text, generating prose, and answering questions. Google's @alan_karthi and @vivnat describe their team’s efforts to adapt and evaluate LLMs for clinical applications.

Google’s Exploration of Large Language Models in Medicine

nejm.org

1

13

36

NEJM AI

@NEJM_AI

6 months

We’re one year into our journey on X and one year closer to the official launch of our new journal dedicated to identifying and evaluating applications for #AIinMedicine . Who else is excited!? #MyXAnniversary

5

6

35

NEJM AI

@NEJM_AI

10 days

Datasets, Benchmarks, and Protocols: “Large Language Models Are Poor Medical Coders — Benchmarking of Medical Code Querying” by @AliSoroushMD et al.: #ArtificialIntelligence

1

11

35

NEJM AI

@NEJM_AI

1 year

Microsoft’s Peter Lee describes the dangers of “irrational exuberance” in bringing technology to health care. He explains how he approaches problems at Microsoft grounded in understanding the health care day-to-day workflow. Hear more from @peteratmsr :

0

8

33

NEJM AI

@NEJM_AI

1 month

Session three of our next free live web event will feature @David_Ouyang , Sonja Fulmer, @heacockmd , and @kdpsinghlab as they discuss post-market surveillance and monitoring of ongoing AI performance. View the full agenda and sign up:

3

10

34

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

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

13

34

NEJM AI

@NEJM_AI

4 months

A new editorial by @arjunmanrai , @AndrewLBeam , and @zakkohane highlights recurring themes from the first year of the AI Grand Rounds podcast, focusing on examples that illustrate the types of content we are eager to publish at NEJM AI going forward.

1

18

33

NEJM AI

@NEJM_AI

7 months

In a recent paper by Huang et al., multimodal AI models generate chest x-ray reports to support emergency department workflows with quality/accuracy comparable to radiologists, and superior to teleradiologists. 1/2

3

7

33

NEJM AI

@NEJM_AI

1 month

In the latest episode of the AI Grand Rounds podcast, Dr. @DaphneKoller charts her professional trajectory, tracing her early fascination with computers to her influential role in AI and health care. 🎧 Listen to the full episode:

2

10

33

NEJM AI

@NEJM_AI

7 months

Dr. Nigam Shah ( @drnigam ) is Professor of Medicine @Stanford , and Chief Data Scientist for @StanfordHealth . His research group analyzes multiple types of health data to answer clinical questions, generate insights, and build predictive models for the learning health system.

NEJM AI | Featured Speakers

nejm.org

0

5

29

NEJM AI

@NEJM_AI

4 months

Researchers share their experience implementing an AI algorithm and explore the implications of “induced belief revision bias.” They also discuss how clinical end-users and AI researchers can recognize and safeguard themselves from being trained by the very models they create.

CASE STUDY: When the Model Trains You

nejm.org

1

12

32

NEJM AI

@NEJM_AI

11 days

AI-MARRVEL is an #ArtificialIntelligence system for genetic diagnosis that improves diagnostic accuracy, surpassing state-of-the-art benchmarked methods. Read the Original Article by Dongxue Mao, PhD, et al.:

1

8

32

NEJM AI

@NEJM_AI

7 months

📢 New episode of AI Grand Rounds!  Vanguard geneticist Dr. @geochurch recounts his storied career and provides insights into founding genomics companies and the role of AI in advancing biotechnology. Listen now:

Machines & Genes: The Future of AI in Biology with Dr. George Church

nejm.org

0

13

32

NEJM AI

@NEJM_AI

29 days

In the most comprehensive head-to-head comparison of modern AI-based LLMs for application in oncology, a significant heterogeneity in model accuracy was observed, with GPT-4 showing performance competitive with a human benchmark.

3

17

31

NEJM AI

@NEJM_AI

6 months

📢 New episode of AI Grand Rounds!  Dr. @judywawira , associate professor of @EmoryRadiology , details her journey from Kenya to the United States, from interventional radiology to artificial intelligence.  Listen now:

Examining Open Source Frameworks & AI in Medicine w/ Dr. Judy Gichoya

nejm.org

1

12

31

NEJM AI

@NEJM_AI

3 months

An ophthalmologist and a clinician scientist @unibirmingham , Deputy Editor @DrXiaoLiu co-leads the AI & Digital Health Research & Policy Group @uhbtrust . Her work focuses on responsible innovation in AI health technologies. Read her full bio:

0

7

31

NEJM AI

@NEJM_AI

4 months

Dr. @pranavrajpurkar is an Assistant Professor @harvardmed leading a research lab working on developing AI technologies for medical applications. Prof. Rajpurkar co-hosts The AI Health Podcast and co-edits the Doctor Penguin AI health newsletter. Full bio:

Editorial Board | NEJM AI

nejm.org

2

3

31

NEJM AI

@NEJM_AI

5 months

In this publication, Dr. @judywawira et al. reveal a novel, interactive dashboard that tracks global AI research in clinical settings, focusing on theme development and equitable representation.

A Dashboard to Track Themes, Maturity & Equity in Clinical AI Research

thelancet.com

2

7

30

NEJM AI

@NEJM_AI

9 months

New study in radiology adds a twist to the AI narrative. While AI assistance doesn't uniformly improve diagnostic quality, the addition of contextual information does. This underlines the need to rethink our strategies for human-AI collaboration in health care.

Combining Human Expertise with Artificial Intelligence

nber.org

2

9

30

NEJM AI

@NEJM_AI

1 year

Dr. Lily Peng’s work on AI for diabetic retinopathy was a significant advancement for medical AI and laid the groundwork for many subsequent studies. Listen to a conversation with @lhpeng on the latest episode of NEJM AI Grand Rounds:

AI for Ophthalmology and the Challenges of AI in the Real World

nejm.org

0

7

29

NEJM AI

@NEJM_AI

14 days

The performance of four histopathology slide search engines varied in reliability and accuracy across three patient cases. The authors of a Case Study recommend essential improvements to facilitate the clinical adoption of these engines. Read the study:

0

10

29

NEJM AI

@NEJM_AI

2 months

Dr. @David_Ouyang is a cardiologist and researcher in the Department of Cardiology and Division of AI in Medicine @CedarsSinai . His group works on applications of deep learning, computer vision, and the statistical analysis of large datasets. Learn more:

0

8

29

NEJM AI

@NEJM_AI

8 months

What are the most impactful applications of AI – and Large Language Models (LLMs) in particular – for clinical decision-making and administrative tasks in health care? The next NEJM AI free virtual event addresses this question and more. 🎟️ Sign up:

Free Virtual Event

nejm.org

1

18

29

NEJM AI

@NEJM_AI

1 year

Meet the hosts of NEJM AI Grand Rounds: @arjunmanrai , PhD, is an assistant professor of biomedical informatics @harvardmed . Raj directs a research lab of #machinelearning scientists, clinicians, and biomedical data scientists working to improve medical decision making.

2

6

29

NEJM AI

@NEJM_AI

10 months

Many have argued that AI models must be explainable to ensure safe clinical use. In this latest episode of AI Grand Rounds, Dr. @MarzyehGhassemi warns that explainability in practice is a “technically squishy” concept. 🔗 Listen to the full episode:

1

14

27

NEJM AI

@NEJM_AI

5 months

Dr. Ziad Obermeyer ( @oziadias ) is an Associate Professor and Blue Cross of California Distinguished Professor @UCBerkeley . He works at the intersection of machine learning and health. View Dr. Obermeyer's full bio:

Editorial Board | NEJM AI

nejm.org

1

4

27

NEJM AI

@NEJM_AI

4 months

This study by Wu et al. investigated the medical knowledge capability of large language models, specifically in the context of their internal medicine subspecialty multiple-choice test-taking ability. Read it here:

0

12

28

NEJM AI

@NEJM_AI

1 year

Generalist #MedicalAI models have great potential for transforming radiology. These models can produce complete radiologic reports containing interpretive & descriptive findings derived from various sources such as imaging, clinical context & previous imaging. Read more in @NEJM :

The Current and Future State of AI Interpretation of Medical Images

nejm.org

0

11

27

NEJM AI

@NEJM_AI

1 year

In this clip from episode six of the AI Grand Rounds podcast, Dr. @alan_karthi reflects on his interactions with the Med-PaLM model and deliberates on the potential impact of large language models on medical education. Listen to the full episode:

0

11

27

NEJM AI

@NEJM_AI

2 months

Two of the editors of @NEJM_AI , discuss why after January 1, 2025, trials that use an AI intervention as part of an approach to answering a clinical question will need to be registered in a database before results can be published. Read the editorial:

0

10

25

NEJM AI

@NEJM_AI

1 month

Dr. @kdpsinghlab is the Chief Health AI Officer for @UCSDHealth and Joan and Irwin Jacobs Chancellor’s Endowed Chair in Digital Health Innovation @UCSanDiego . View full speaker lineup:

0

7

26

NEJM AI

@NEJM_AI

24 days

Datasets, Benchmarks, and Protocols: GPT versus Resident Physicians — A Benchmark Based on Official Board Scores by Dr. @uriel_katz_ and team: #ArtificialIntelligence

0

8

27

NEJM AI

@NEJM_AI

9 months

New paper introduces Med-PaLM Multimodal, a generalist biomedical AI system that flexibly interprets a range of biomedical data. The future of medicine lies in the hands of such versatile AI models.

Towards Generalist Biomedical AI

arxiv.org

0

12

26

NEJM AI

@NEJM_AI

2 months

In a world where technological advances outpace the speed of policy and regulation, how do we ensure cutting-edge technologies are safe, and that regulatory requirements enable the potential benefits of AI? Register now for this free event from @NEJM_AI :

1

17

26

NEJM AI

@NEJM_AI

4 months

Dr. @zakkohane interrogates how AI will impact medical training, and he calls for biomedical leaders to engage deeply with AI and emerging biotechnologies to transform health care. 🎧 Listen to episode 13 of AI Grand Rounds:

Medicine as a Knowledge Processing Discipline with Dr. Zak Kohane

nejm.org

1

14

26

NEJM AI

@NEJM_AI

9 months

Med-PaLM Multimodal, a new AI system, shows potential clinical utility, with clinicians preferring its reports over those produced by radiologists in up to 40% of cases. A step forward in the integration of AI in health care.

Towards Generalist Biomedical AI

arxiv.org

2

6

24

NEJM AI

@NEJM_AI

4 months

Volume 1, No. 2 is now available! Here are the latest articles in NEJM AI: Editorial: What We Want to Publish at NEJM AI Original Article: Prospective Evaluation of Machine Learning for Public Health Screening 🔖 Save for later

3

17

25

NEJM AI

@NEJM_AI

7 months

Dr. Karandeep Singh ( @kdpsinghlab ) is an Assistant Prof. of Learning Health Sciences, Internal Medicine, Urology, & Information @UMich . He directs the ML4LHS Lab, which focuses on translational issues related to the implementation of machine learning models within health systems.

NEJM AI | Featured Speakers

nejm.org

0

7

25

NEJM AI

@NEJM_AI

10 months

📢 New episode of AI Grand Rounds! In this thought-provoking episode, Dr. Ziad Obermeyer ( @oziadias ) delves into the complex issues of bias, safety, and generalizability of medical AI. Listen to the full episode now:

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

nejm.org

0

10

25

NEJM AI

@NEJM_AI

2 months

In a single-institution, randomized controlled study, electronic health record–based machine learning accurately identified patients at high risk for acute care during radiotherapy and targeted them for supplemental clinical evaluations. Full results:

1

6

23

NEJM AI

@NEJM_AI

18 days

Tokenization algorithms may be to blame when generative large language models inconsistently match medical billing codes to their preferred code descriptions. Learn more in a new Datasets, Benchmarks, and Protocols article by @AliSoroushMD et al.:

0

12

24

NEJM AI

@NEJM_AI

3 months

Dr. @David_Ouyang is a Deputy Editor and an Assistant Professor, Department of Cardiology, Division of AI in Medicine, @CedarsSinai . David's focus is on cardiovascular imaging and AI applications in cardiology. Read his full bio:

0

4

24

NEJM AI

@NEJM_AI

3 months

A computer vision model developed to recognize fine-grained surgical activity in laparoscopic cholecystectomy videos reveals associations among surgical behaviors, adverse outcomes, and surgical skills. Read the Original Article by @AkliluJosiah2 , et al.:

Artificial Intelligence Identifies Factors Associated with Blood Loss and Surgical Experience in...

ai.nejm.org

0

6

22

NEJM AI

@NEJM_AI

1 year

Dr. @alan_karthi discusses ways to evaluate large language models in medicine that go beyond answering multiple-choice exam questions, including having expert physicians and laypeople rate the usefulness of model outputs. 🔗Listen to the full episode:

1

10

24

NEJM AI

@NEJM_AI

3 months

Dr. @james_y_zou walks through the data generation strategy for his lab’s recent @Nature paper, “Building a Visual-Language Model for Pathology Image Analysis using Medical Twitter,” and discusses key learnings. Listen to the full episode now:

0

8

24

NEJM AI

@NEJM_AI

8 months

NEJM AI Deputy Editor @AndrewLBeam , PhD, is an assistant professor of epidemiology at @HarvardChanSPH and the @CAUSALab . Andrew is a long time AI optimist and is deeply committed to realizing an AI-enabled health care system that works for everyone. Learn more and register:

NEJM AI | Event Speakers

nejm.org

1

7

22

NEJM AI

@NEJM_AI

1 year

The first episode of NEJM AI Grand Rounds is live! Listen as our first guest, @StanfordMed Associate Dean @euanashley , shares how his team is using #ArtificialIntelligence to prevent, predict, and beat disease:

Dr. Euan Ashley on AI, Genomics, and Cardiology | NEJM AI Grand Rounds

Dr. Euan Ashley is a pioneer. In 2010, he led the team that conducted the first clinical interpretation of a human genome, and he holds the record for the world’s fastest genomic diagnosis. He even...

ai-podcast.nejm.org

0

8

23

NEJM AI

@NEJM_AI

5 months

This pre-print by Dr. @judywawira and colleagues shows how synthetic data in medical imaging enhances model accuracy and generalizability, especially for rare pathologies, suggesting its potential in training robust deep learning models.

Synthetically Enhanced

arxiv.org

1

8

23

NEJM AI

@NEJM_AI

6 months

Dr. @geochurch and team authored a deep learning model to predict molecules with antibacterial activity and identify new antibiotics, training on growth inhibition data to discover a compound named halicin with broad-spectrum bactericidal activity. 1/2

1

2

22

NEJM AI

@NEJM_AI

6 months

In a groundbreaking study, Dr. @judywawira et al. demonstrate a deep learning model’s ability to detect type 2 diabetes from chest radiographs and EHR data, with a promising ROC AUC of 0.84.

Opportunistic Detection of T2D Using DL from Frontal Chest Radiographs

nature.com

0

9

23