Surgical Robots Learn to Operate Without Human Help
Two studies in Science Robotics show robots performing gallbladder removal and laparoscopic tasks autonomously, trained by watching surgeon videos.
Tag
Two studies in Science Robotics show robots performing gallbladder removal and laparoscopic tasks autonomously, trained by watching surgeon videos.
New AI foundation model trained on 585,000 hours of sleep data can forecast dementia, heart disease, cancer, and death with surprising accuracy.
An LLM trained on yeast genetics outperforms commercial tools at optimizing codon sequences for protein production. Five out of six test cases beat existing solutions.
Penn researchers are using AI to find antibiotic compounds in ancient genomes, from Neanderthals to giant sloths, and testing them against drug-resistant bacteria
First randomized controlled trial shows AI-supported screening improves detection and cuts aggressive interval cancers by 27%
SIGNET platform identifies hub genes driving brain cell rewiring, opening new paths for early diagnosis and treatment.
Insilico Medicine's rentosertib improved lung function in IPF patients, marking the first clinical validation of AI-driven drug discovery.
Only 5% of medical AI studies use real patient data. A new report documents the gap between lab performance and hospital reality.
Nature Biotechnology paper describes 'in silico team science' where AI agent collectives handle literature review, hypothesis generation, and data analysis
CleaveNet system designs peptide sensors that detect cancer-linked enzymes, potentially enabling at-home screening for dozens of cancer types
Half of the tested AI tools produced prediction models that matched or beat human researchers. A master's student and high schooler built working code in minutes.
UCSF study finds generative AI can build prediction models in minutes that took human teams months, though only half the tested systems worked.
Shanghai researchers built DeepRare, an AI system using 40+ tools that identifies rare diseases 64% vs 55% for experienced physicians on first attempt.
University of Missouri releases the world's largest quality-assessed protein structure database to help researchers know when to trust AI predictions.
Mass General Brigham's foundation model trained on ~49,000 brain MRIs outperforms specialized tools at predicting dementia, cancer survival, and mutations.
In a retrospective study of 6,401 cases, DeepRare's top diagnosis was correct 64.4% of the time, compared with 54.6% for specialists.
Valar Labs publishes JCO study showing its AI can identify optimal chemotherapy from routine pathology slides.
Harvard researchers built a foundation model that extracts health signals from routine brain scans without requiring labeled training data, outperforming task-specific AI on seven clinical applications.
Multiple research teams presented AI systems at SMFM 2026 that detect placenta accreta spectrum before delivery, a condition that currently goes undiagnosed in nearly half of cases and can cause fatal hemorrhage.
University of Michigan researchers built Prima, a vision language model trained on 200,000 brain scans that diagnoses 52 neurological conditions with up to 97.5% accuracy and triages emergencies in real time.
Google DeepMind spinoff claims its unified AI system can identify hidden binding sites and predict drug interactions faster than physics-based methods