The European Union recently adopted the #AI Act. It is the first far-reaching legal framework dedicated to AI. But what are its implications for the healthcare domain? A new journal article by some of our #COMFORTproject team members sheds light on this issue. 💡

Our new npj Digital Medicine commentary analyzes the EU AI Act's impact on healthcare. We explain the risk-based approach, explore implications for radiology AI, and discuss regulatory challenges for medical AI. Full article here: rdcu.be/dQDBn Thanks to Felix Busch Keno Bressem

Is there a future for Meta's open source Llama 3 large language model (LLM) in radiology AI applications? Find out in this original research study by Lisa Adams, Daniel Truhn, Felix Busch, Keno Bressem et al. TU München Charité - Universitätsmedizin Berlin bit.ly/4cpeJwJ

#DeepLearning model highly accurate at classifying cardiac implants chest xrays doi.org/10.1148/ryai.2… Felix Busch Hugo Aerts Keno Bressem #ChestRad #AI #MachineLearning

With AI becoming increasingly crucial in healthcare, we wondered: how do patients feel about its use? To find out, we conducted a massive global survey, gathering insights from 13,806 patients across 74 hospitals in 43 countries as part of the #COMFORTproject.

The study is now available as a preprint at: medrxiv.org/cgi/content/sh… Many thanks to our global collaborators who made this study possible! Special shout out to Felix Busch for leading this initiative. #COMFORTproject #HorizonEU

🚨 New Paper Alert! 🚨 We've discovered a major vulnerability in medical large language models (LLMs): they're highly susceptible to targeted misinformation attacks. This could have serious implications for healthcare AI! Daniel Truhn Jakob Nikolas Kather Full paper: doi.org/10.1038/s41746…

How will large language models transform structured reporting in radiology and beyond? In our comprehensive review just published in European Radiology, we deeply dive into the past, present, and future of LLMs for radiology reporting. Read the article here: doi.org/10.1007/s00330…

Analysis of commercial and open source LLMs for labeling chest radiograph reports showed superior performance of ChatGPT-4 vs open source models in zero-shot labeling and comparable performance for few-shot prompting. Felix Dorfner Keno Bressem QTIM Lab bit.ly/40jr0jV

This recent Review published in #EuropeanRadiology explores the use of #LargeLanguageModels (LLMs) in #StructuredReporting. Felix Busch et al. look at limitations, regulatory obstacles, and more. (D. Pinto dos Santos, Daniel Truhn, Renato Cuocolo) 🔗 buff.ly/4hjuHMy

Very happy to share our article about AI agents in cancer research and oncology, with Yongju Lee Dyke Ferber & Aviv Regev, out in Nature Cancer now -> nature.com/articles/s4301… katherlab Nationales Centrum für Tumorerkrankungen Dresden NCT Heidelberg

Large language models can translate radiology reports into clear and readable non-English texts, although medical accuracy needs improvement and quality varied based on model and language pair. bit.ly/4iUgQgD

AI regulation in healthcare around the world: what is the status quo? medrxiv.org/cgi/content/sh… #medRxiv

📢 Excited to share our article “Cybersecurity Threats and Mitigation Strategies for Large Language Models in Health Care” in Radiology: Artificial Intelligence 🔗 doi.org/10.1148/ryai.2… Judy Gichoya @AliTejaniMD Bardia Khosravi, MD Shahriar Faghani MD ManaMoassefi Christian Bluethgen Keno Bressem Lisa Adams Felix Busch

Patients preferred explainable AI systems and physician-led decision-making in this cross-sectional survey study. ja.ma/3ZoDdT6

We're proud to welcome the journal's 2025-2027 Trainee Editorial Board! Learn more about these talented individuals: pubs.rsna.org/page/ai/teb