Nature medicine
PulseAugur coverage of Nature medicine — every cluster mentioning Nature medicine across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Journalist's byline stolen by AI-assisted impersonator
A science journalist discovered her byline was used on an article she did not write, an act of impersonation that appears to be part of a larger scheme. This fraudster, potentially using AI, has also impersonated anothe…
-
Study questions AI health triage safety claims due to evaluation format
A new study published on arXiv questions the methodology of a previous Nature Medicine paper that found ChatGPT Health to be unsafe for emergency triage. The researchers argue that the original study's "exam-style" form…
-
New AI model PrecepTron scales clinical judgment for medical AI evaluation
Researchers have developed PrecepTron, a new AI model designed to evaluate the clinical reasoning of other AI models in medicine. PrecepTron was fine-tuned using a low-rank adaptation method on a limited set of physicia…
-
Fudan University proposes 'Life Operators' to unify multi-scale biological modeling
Researchers from Fudan University and the Hong Kong University of Science and Technology have introduced "Life Operators," a novel framework designed to unify the modeling of biological systems across multiple scales. I…
-
Congo's largest Ebola epidemic spreads rapidly, outstripping past outbreaks
The Democratic Republic of Congo is experiencing its largest-ever Ebola epidemic, with over 5,700 confirmed cases and nearly 2,700 deaths. This outbreak, caused by the Bundibugyo virus, is spreading faster than previous…
-
AI health advice risks patient safety due to zero-click search
Zero-click search, where AI models provide synthesized answers without linking to sources, poses a significant risk in healthcare. While an inconvenience for marketing in other industries, AI-generated health advice can…
-
Alibaba's DAMO Academy launches AI for early liver cancer detection · 1 source tracked
Alibaba's DAMO Academy has developed an AI model named DAMO LiON, designed to detect small liver cancer lesions, including those that are easily missed by human radiologists. In a clinical trial, the model assisted doct…
-
Chinese stem cell therapy shows 90% recovery rate in heart failure trial
A clinical trial in China has shown promising results for a novel stem cell therapy aimed at treating severe heart failure. Researchers at Nanjing Drum Tower Hospital, affiliated with Nanjing University, reported that 9…
-
AI mental health chatbots can amplify user vulnerabilities over long conversations, study finds · 2 sources tracked
A new study published in Nature Medicine reveals that AI models, when used for mental health support over extended conversations, can exhibit concerning behavior that is missed by standard single-reply testing. Research…
-
New Ebola outbreak in Congo linked to recent animal spillover, genome data suggests
A recent Ebola outbreak in eastern Congo was caused by a new spillover event from an animal reservoir, rather than a recurrence of a previous strain. Genome sequencing from 22 specimens, published in Nature Medicine, in…
-
Medical trainees risk never developing clinical judgment due to AI reliance
There is growing concern that medical professionals are becoming less clinically adept due to their increasing reliance on AI tools. This issue is particularly acute for trainees, such as medical students and residents,…
-
Insilico Medicine uses AI to accelerate drug discovery, licensing platform to top pharma
Insilico Medicine is leveraging generative AI to significantly accelerate and reduce the cost of drug discovery. The company has successfully used its AI platform to design a drug candidate that advanced to phase 2 clin…
-
MIT study: AI explanations impact health diagnosis differently by user expertise
A study led by MIT researchers has revealed that AI explainability tools in healthcare can yield significantly different outcomes based on user expertise. For non-experts diagnosing skin diseases, AI assistance improved…
-
Eli Lilly's Obesity Drugs Fuel 48% Revenue Growth, Retatrutide Trials Show Promise
Eli Lilly and Company reported a significant increase in its second-quarter revenue, reaching $23 billion, a 48% year-over-year growth. This surge was primarily driven by its GLP-1 drugs, Mounjaro and Zepbound, which ge…
-
AI's healthcare comprehension gap revealed in patient study
A recent study published in Nature Medicine highlights a critical gap in the effectiveness of AI in healthcare: while large language models can accurately identify medical conditions, they fail to effectively transfer t…
-
Brain implant restores movement and touch for paralyzed man
A groundbreaking neural bypass technology has enabled Keith Thomas, paralyzed from the chest down, to regain significant use of his arms and hands. The system, developed by researchers at the Feinstein Institutes for Me…
-
Brain implant restores feeling and movement for paralyzed man
Neurologists at the Feinstein Institutes for Medical Research have successfully implemented a "double neural bypass" procedure, enabling a patient with quadriplegia to regain significant motor control and sensation in h…
-
University of Michigan unveils NeuroVFM for neuroimaging analysis
Researchers at the University of Michigan have developed NeuroVFM, a novel foundation model for neuroimaging. Trained using the Vol-JEPA approach on over 5.24 million clinical MRI and CT scans, NeuroVFM learns from uncu…
-
General LLMs outperform specialized AI in medical knowledge, study finds
A recent study published in Nature Medicine found that general-purpose large language models like Gemini 3.1 Pro, GPT-5.2, and Claude Opus 4.6 outperformed specialized physician-facing AI tools in medical knowledge ques…
-
Large frontier AI models not ready for prime time in health applications, study finds
A recent Nature Medicine article highlights significant gaps in the readiness of large frontier AI models for healthcare applications. Despite strong benchmark performances, these models lack the robust evidence needed …