Pinned Tweet
NEJM AI@NEJM_AI
Oct 21
On AI Grand Rounds, Dr. Michal Nedoszytko (@mnedoszytko) explains how AI can help physicians gather better information, improve the quality of conversations with patients, and prototype solutions to problems that clinicians experience every day. 🎧 nejm.ai/ep47
Promotional image for episode 47 of the NEJM AI Grand Rounds podcast featuring Dr. Michal Nedoszytko. The left side includes the title: "Abridge’s Dr. Michal Nedoszytko on Physicians Who Build Software." A photo of Dr. Nedoszytko is on the right.
3
8
22
6,179
NEJM AI@NEJM_AI
4h
Editorial by @AdamMarkovitz, MD, PhD, and @AlexChaitoff, MD, MPH: Comprehensive or Wasteful? Clinical AI and the Up-front Workup nejm.ai/4zyYg59

#ArtificialIntelligence #AIinMedicine
3
3
11
1,004
NEJM AI retweeted
NEJM Catalyst@nejmcatalyst
Oct 24
An ambient AI initiative at Jefferson Health involving 5234 provisioned clinicians and more than 283,000 ambulatory encounters has been associated with reduced time spent and effort expended in documenting patient encounters. Read the latest In Depth: nej.md/3W7jkB8
Image from NEJM Catalyst featuring a health care professional with a patient. A holographic display shows a dialogue about symptoms and questions like "What are your symptoms?" and "When did you first notice it?" The title reads "Ambient AI as a Tool for Returning Time to Care."
2
2
6
384
NEJM AI@NEJM_AI
Oct 24
Perspective by P. Jarrett et al.: No Mastery without the Machine — Medical Education in the Age of Clinical AI nejm.ai/4ybNSiw

#MedEd #AIinMedicine
A quote from a Perspective published in NEJM AI reads as follows: "The danger is not that trainees will use AI. The danger is that they may never learn what it feels like to reason before AI intervenes.” The Perspective is titled “No Mastery without the Machine — Medical Education in the Age of Clinical AI” and the authors are P. Jarrett et al. The background color is an orange-yellow gradient and includes the NEJM AI logo.
4
4
14
1,267
NEJM AI@NEJM_AI
Oct 23
A new study develops and externally validates an AI-enhanced digital auscultation system for detecting left ventricular dysfunction using prospective multicenter data. Learn more: nejm.ai/3W3zag4
The image is a flowchart titled "Figure 1. Study Pipeline." The chart shows how a training dataset (n=2359) was collected from a multicenter registry in Japan and evaluated using an independent dataset (n=964) derived from a separate registry conducted at six other hospitals in Japan.
4
10
33
5,978
NEJM AI@NEJM_AI
Oct 22
A new randomized controlled trial evaluated whether AI-generated, layperson-friendly summaries of medical findings provided before outpatient consultations improve physician–patient communication. Learn more: nejm.ai/3W3z9Zy
Illustration of an AI-generated, layperson-friendly summary of medical findings provided before outpatient consultations. On the left, a physician in a white coat and stethoscope speaks and gestures, set against a faded table of clinical trial statistics and medical terms. On the right, a patient in a hospital gown smiles and gestures back. A blue line connects a glowing pen icon with sparkles to a document icon labeled “Discharge Report Summary."
2
10
43
5,757
NEJM AI@NEJM_AI
Oct 20
A new study examines whether the clinical care recommended by contemporary LLMs carries a different cost than the care recommended by treating physicians, and whether that difference is influenced by how the models are prompted. Learn more: nejm.ai/4i18zYw
This image is a diagram titled "Study Design" for a clinical presentation MTS_0481. It outlines a comparative study across four scenarios: Physician, AI-Generalist, AI-Cost-Aware, and AI-Parsimonious. Each scenario includes details on diagnosis, diagnostic orders, and costs in US dollars. The scenarios focus on acute bronchiolitis. The diagram also features stages like case selection, note splitting, plan generation, order extraction, and Medicare pricing.
8
21
60
6,686
NEJM AI retweeted
Nobu Kagiyama｜弁膜症・心不全・医療AI
@KagiyamaNobu
Oct 20
お待たせしました！

"いいジャーナルにアクセプト！"って何処？と思ってた方いるかもですが！
NEJM AI @NEJM_AI に、新しい論文が出ました！！

聴診データをAI 解析することで、EF低下を見分けるという論文です！大学院生の佐藤先生が筆頭。ぜひ読んでください！

ai.nejm.org/doi/full/10.10…
14
16
189
18,519
NEJM AI@NEJM_AI
Oct 19
On @NEJM_AI Grand Rounds, @DrXiaoLiu is excited by the possibility of combining medical knowledge to uncover new biomarkers, disease phenotypes, and treatment-response patterns that challenge today’s categories. Listen to the full episode: nejm.ai/ep46
1
2
3
946
NEJM AI@NEJM_AI
Oct 17
A new editorial discusses the need to assess the use of AI technology to understand how it impacts what matters to the patient and to society. Full editorial: nejm.ai/4zyYg59
The image features a quote from an NEJM AI editorial by Adam A. Markovitz , M.D., Ph.D., and Alexander M. Chaitoff, M.D., M.P.H.: " It is easy to imagine AI lowering spending . . . . It is just as easy to imagine AI increasing spending.” A colorful silhouette of a face with horizontal lines is on the left. The NEJM AI logo is at the bottom right.
3
2
10
1,142
NEJM AI@NEJM_AI
Oct 16
A new Perspective suggests that medical education must adapt as AI shifts clinical expertise from unaided cognitive performance toward the ability to evaluate, supervise, and appropriately defer to increasingly capable AI systems. Learn more: nejm.ai/4ybNSiw
This figure shows a hypothetical clinical interface in which AI generates diagnostic and management recommendations while the physician evaluates their appropriateness, incorporates patient priorities, and judges when to defer or intervene. Displayed findings and confidence estimates are illustrative.
6
12
39
3,701
NEJM AI@NEJM_AI
Oct 13
On @NEJM_AI Grand Rounds, @DrXiaoLiu imagines clinicians becoming “companions of experience” — helping patients through deterioration, uncertainty, treatment failure, recovery, and life-changing diagnoses. Hear more from Dr. Liu: nejm.ai/ep46
3
2
6
1,209
NEJM AI@NEJM_AI
Oct 9
Original Article by B. Lahrmann et al.: Closing the Automation Gap in HPV-Based Cervical Cancer Screening: Independent External Validation of an AI Model for Dual-Stain Triage nejm.ai/4xRsEXe

#ArtificialIntelligence #AIinMedicine
A flowchart consisting of three panels showing the iterative development, validation, and locked evaluation of an ensemble-based AI system. Panel A shows population-based outcome studies that provided whole-slide images of p16/Ki-67 DS cytology prepared with SurePath or ThinPrep. Panel B shows image tiles spanning unstable LH ranges being extracted in batches and processed using Cytoreader-Core for automated labeling. Panel C shows relabeled tiles being used to construct a deep ensemble with predefined parameters.
6
2
7
1,560
NEJM AI retweeted
NEJM Catalyst@nejmcatalyst
Oct 9
Today’s health care leaders face fundamental disruptions in their ecosystems and a convergence of challenges across countries requiring new leadership approaches that have not yet been explored in depth. Read the full Commentary: nej.md/3U5A8Ye
The image contains text on a gradient purple and blue background with a quotation: "The rapidly evolving technology landscape requires leaders to thoughtfully integrate digital health tools and artificial intelligence within their organizations, which can be challenging in established organizations with entrenched policies and workflows." Below the quote reads the article headline "New Leadership Approaches for Health System Transformation in a Time of Rapid Change" by R. Bonesteel, et al. The image is from NEJM Catalyst | Innovations in Care Delivery.
0
7
8
4,461
NEJM AI@NEJM_AI
Oct 8
Editorial by Dr. @RoxanaDaneshjou: Where Are the Prepared Minds? The Impact of AI on Scientific Thinking nejm.ai/3TKfJbp

#ArtificialIntelligence #AIinMedicine
The image is page 1 of the editorial "Where Are the Prepared Minds? The Impact of AI on Scientific Thinking" published in NEJM AI. A dark blue banner at the bottom encourages readers to access the full editorial at ai.nejm.org.
7
7
34
2,471
NEJM AI@NEJM_AI
Oct 7
On @NEJM_AI Grand Rounds, @DrXiaoLiu discusses how she moved from academic AI and clinical ophthalmology into product development because she wanted firsthand experience of the other side of the evidence pipeline. Full episode: nejm.ai/ep46
2
2
7
966
NEJM AI@NEJM_AI
Oct 5
Case Study by V.J. Nolan et al.: Language Models for Value-Informed Proxy Decision Support nejm.ai/3UfoOc9

#AIinMedicine #EndOfLifeCare
A bar chart showing the average large language model–patient agreement (blue bars) compared with average human proxy–patient agreement (horizontal brown and black dotted lines) across 10 repetition trials (±95% confidence intervals). A bar chart showing the mean adjudicator score (±95% bootstrapped confidence intervals) assessing the accuracy of large language model value profile generation (score out of 10) for each patient in the electronic health record cohort across the three reading levels: fifth grade, eighth or ninth grade, and college graduate level.
A bar chart showing the adjudication of large language model treatment recommendations at the three reading levels (fifth grade, eighth/ninth grade, or college graduate level) averaged across adjudicators and the 35 electronic health record cohort patients.
3
1
6
1,121
NEJM AI retweeted
NEJM Catalyst@nejmcatalyst
Oct 2
To more efficiently synthesize lengthy patient charts comprising demographics, medical and behavioral history, health-related social needs, care team interaction history, and care plan info, Pair Team developed and deployed an AI Patient Summary tool. 👉 nej.md/4yQ4aOZ
1
3
3
560
NEJM AI retweeted
Isaac Kohane
@zakkohane
Oct 5
AI (?SI) in medicine conversations by knowledgeable AIM (?SIM) scientists on the @NEJM_AI Grand rounds. Kudos @arjunmanrai @AndrewLBeam for the top AI in Healthcare ranking podcast.feedspot.com/ai_health_podc…
I envy us.
1
7
16
1,471
NEJM AI@NEJM_AI
Oct 2
A new study explores the use of AI to automate p16/Ki-67 dual-stain cytology evaluation, a key step in triaging HPV-positive patients during cervical cancer screening. Learn more: nejm.ai/4xRsEXe
A collection of digital tissue samples is being analyzed by a stylized robotic device. The headline reads: "Closing the Automation Gap in HPV-Based Cervical Cancer Screening: Independent External Validation of an AI Model for Dual-Stain Triage," dated September 24, 2026.
2
2
6
1,220
Load more