Sebastian Foersch
LightNews LightNews
banner
twittlabs.bsky.social
Sebastian Foersch
@twittlabs.bsky.social
100 followers 160 following 4 posts
Board-certified Pathologist, Former Member of the Board of Directors of the German Society of Pathology (no medical advice-opinions are my own) https://www.unimedizin-mainz.de/pathologie/das-institut/mitarbeiter/aerzte/foersch.html
Posts Replies Media Videos
Pinned
twittlabs.bsky.social
Sebastian Foersch @twittlabs.bsky.social · Nov 12
Welcome to our group 🔬🩺💻 Our focus is on #AI in #pathology and #cancer #research www.unimedizin-mainz.de/pathologie/f...
Institut für Allgemeine Pathologie | Pathologie » Forschung » AG Digitale Pathologie & Kü...
www.unimedizin-mainz.de
Reposted by Sebastian Foersch
rheinmainunis.bsky.social
🎇 Die Allianz der Rhein-Main-Universitäten (RMU) @goetheuni.bsky.social, @unimainz.bsky.social und @tuda.bsky.social wünscht einen guten Start in ein gesundes und glückliches neues Jahr - cheers to a healthy, happy and successful 2026 🎇

#RMU #RheinMainUniversitäten #Verbund #FrohesNeues
January 6, 2026 at 2:46 PM
Reposted by Sebastian Foersch
ai.nejm.org
In the latest episode of the AI Grand Rounds podcast, Dr. Zak Kohane, editor-in-chief of NEJM AI, explains why this year’s advances in #AI were personal, why it’s spreading fast, and why its most profound theme is values. Full episode: nejm.ai/ep37

#MedSky #MLSky
AI Grand Rounds Episode 37 What Values Are in AI? A Conversation with Dr. Zak Kohane A photo of Dr. Kohane
December 17, 2025 at 3:30 PM
Reposted by Sebastian Foersch
ai.nejm.org
Humans and machines make the same mistakes — just for different reasons. On NEJM AI Grand Rounds, Dr. Laura Zwaan discusses bias, cognition, and #AI. Full episode: nejm.ai/ep36

#MedSky #MLSky
December 11, 2025 at 1:31 PM
Reposted by Sebastian Foersch
fionakolbinger.bsky.social
Now out in @natcomputsci.nature.com: "Adaptive validation strategies for real-world clinical artificial intelligence"

It was a pleasure working on this piece with @jnkt.bsky.social, excited to finally see it published!

#medicalAI #clinicalAI #digitalhealth #translationalresearch
November 17, 2025 at 5:36 PM
Reposted by Sebastian Foersch
unimainz.bsky.social
#DFG verlängert Förderung für exzellente Forschung an der Universitätsmedizin Mainz: 3. Förderperiode für #Sonderforschungsbereich zur Entwicklung neuer Immuntherapien gegen #Krebs unter Federführung der #UnimedizinMainz 👉 https://sohub.io/qdbx
November 21, 2025 at 1:14 PM
Reposted by Sebastian Foersch
natcomputsci.nature.com
📢 @fionakolbinger.bsky.social and @jnkt.bsky.social characterize the discordance between metrics used to evaluate AI tools and their clinical impact, proposing a framework to reduce this disconnect. www.nature.com/articles/s43... @tudresden.bsky.social @ekfzdigital.bsky.social

🔓 rdcu.be/eQmQp
Adaptive validation strategies for real-world clinical artificial intelligence - Nature Computational Science
Technical metrics used to evaluate medical artificial intelligence tools often fail to predict their clinical impact. We characterize this discordance and propose a framework of study designs to guide...
www.nature.com
November 17, 2025 at 3:23 PM
Reposted by Sebastian Foersch
nature.com
AI models are 50% more sycophantic than humans

go.nature.com/4nr2HIL
AI chatbots are sycophants — researchers say it's harming science
Nature asked researchers who use artificial intelligence how its propensity for people-pleasing affects their work — and what they are doing to mitigate it.
go.nature.com
October 27, 2025 at 9:38 AM
Reposted by Sebastian Foersch
ai.nejm.org
A new study introduces a publicly available script concordance test benchmark that reveals important limitations in the clinical reasoning capabilities of leading LLMs, particularly in processing new information under uncertainty. nejm.ai/3KlD5yX

@liamgmccoy.bsky.social #AI #MedSky #MLSky
Figure 3. Per-Test Performance of Models and Humans of Varying Training Levels.
October 24, 2025 at 1:15 PM
twittlabs.bsky.social
I ❤️ science www.science.org/content/arti...
Chicago’s beloved ‘rat hole’ was actually made by a squirrel
Scientists reopen the case of “splatatouille”
www.science.org
October 15, 2025 at 11:03 AM
Reposted by Sebastian Foersch
w-i-d.de
Der #Hochschulwettbewerb 2026 startet! Wir suchen Ideen zur Medizin der Zukunft: von KI und Telemedizin bis hin zu gesellschaftlichen und künstlerischen Perspektiven.
Die besten 10 Projekte erhalten je 10.000 €!
Ihr könnt euch bis zum 30.11.2025 bewerben.
Alle Infos: www.hochschulwettbewerb.net/2026
"Der Hochschulwettbewerb im Wissenschaftsjahr 2026 - Medizin der Zukunft. Junge Forschende aller Fachrichtungen aufgepasst: 10 x 10.000 Euro zu gewinnen! Gesucht sind Projektideen, die Forschung lebendig erzählen, Begegnungsräume schaffen und neue Perspektiven öffnen. Wann wird eure Idee zur Brücke zwischen Wissenschaft und Gesellschaft? www.hochschulwettbewerb.net/2026" Logo Hochschulwettbewerb, "Darum geht's. Der Hochschulwettbewerb fördert kreative Projekte zum Thema Medizin der Zukunft an der Schnittstelle zwischen Forschung und Wissenschaftskommunikation. Wie wäre es mit der Science Fiction Simulation einer Praxis im Jahr 2025 oder einem Pop-Up-Labor zur Bestimmung des Blutzuckerspiegels? www.hochschulwettbewern.net/2026" )Logo Hochschulwettbewerb. "So könnt ihr mitmachen. Vom Studi bis Postdoc: Junge Forschende aller Fachrichtungen sind ausdrücklich eingeladen, sich zu bewerben. Die 10 besten Ideen erhalten jeweils 10.00 Euro zur Umsetzung und eine fachliche Begleitung durch das Jahr. Bewerbt euch online bis zum 30. November 2025 unter hochschulwettbewerb.net/2026" "Der Hochschulwettbewerb im Wissenschaftsjahr 2026-Medizin der Zukunft. Ein Projekt von: Logo Wissenschaft im Dialog, Logo Bundesministerium für Forschung, Technologie und Raumfahrt. In Kooperation mit: Logo Hochschulrektorenkonferenz, Logo Die Junge Akademie, Logo Bundesverband Hochschulkommunikation, Logo Gesellschaft Deutscher Naturforscher und Ärzte."
October 14, 2025 at 8:32 AM
Reposted by Sebastian Foersch
rwth.bsky.social
Die Uniklinik RWTH Aachen sucht dringend Blutspender*innen, um dem Engpass in der Versorgung zu begegnen. Ihr könnt innenstadtnah spenden in der Großkölnstraße 32 in Aachen. 👍Achtung: Eine Spende in der Uniklinik selbst ist nicht möglich.

➡️ www.ukaachen.de/kliniken-ins...
September 22, 2025 at 12:09 PM
Reposted by Sebastian Foersch
ai.nejm.org
MedAgentBench, a comprehensive benchmark designed to evaluate the agentic capabilities of large language models in realistic EHR environments, provides a critical foundation for advancing and integrating LLM agents into clinical workflows. Learn more: nejm.ai/45AUXwS

#AI #MedSky #MLSky
Figure 1. Schematic Diagram of MedAgentBench Framework.
August 21, 2025 at 1:30 PM
Reposted by Sebastian Foersch
businessinsider.com
Bluesky CEO Jay Graber emphasized the importance of critical thinking and developing a generalist skillset for the AI era.
Bluesky's CEO warns you shouldn't 'fully outsource your thinking' to AI
Bluesky CEO Jay Graber emphasized the importance of critical thinking and developing a generalist skillset for the AI era.
www.businessinsider.com
July 29, 2025 at 9:32 AM
Reposted by Sebastian Foersch
erc.europa.eu
📣 ERC Synergy Grant 2026 call for proposals is now open!

Application deadline 5 November 2025.

📝 Groups of 2-4 researchers
📝 Jointly addressing ambitious problems & with different skills

Application portal 👉 europa.eu/!XpwptY
General info 👉 europa.eu/!PR6gt8

#ERCSyG #FrontierResearch
July 10, 2025 at 2:47 PM
Reposted by Sebastian Foersch
janclusmann.bsky.social
Thank you for sharing! It was a pleasure working on this, together with @twittlabs.bsky.social , @jnkt.bsky.social and many others...
ai.nejm.org NEJM AI @ai.nejm.org · Jun 30
Case Study by J. Clusmann et al.: Incidental Prompt Injections on Vision–Language Models in Real-Life Histopathology nejm.ai/4mrSoEW

@janclusmann.bsky.social #AI #MedSky #DigitalHealth
Figure 1. Experimental Outline to Estimate the Impact and the Clinical Representation of Labeled Pathology Slides. Figure 2. Incorrect Labels on Whole-Slide Images Reduce the Accuracy of Vision–Language Models Regardless of Task. Figure 3. Misleading Watermarks Lead to a Loss in Accuracy of Tissue-of-Origin Prediction.
June 30, 2025 at 1:49 PM
Reposted by Sebastian Foersch
ai.nejm.org
Case Study by J. Clusmann et al.: Incidental Prompt Injections on Vision–Language Models in Real-Life Histopathology nejm.ai/4mrSoEW

@janclusmann.bsky.social #AI #MedSky #DigitalHealth
Figure 1. Experimental Outline to Estimate the Impact and the Clinical Representation of Labeled Pathology Slides. Figure 2. Incorrect Labels on Whole-Slide Images Reduce the Accuracy of Vision–Language Models Regardless of Task. Figure 3. Misleading Watermarks Lead to a Loss in Accuracy of Tissue-of-Origin Prediction.
June 30, 2025 at 1:31 PM
Reposted by Sebastian Foersch
ai.nejm.org
Handwritten labels and watermarks on histopathological images can unintentionally act as prompt injections, misleading vision–language models and resulting in inaccurate outputs that highlight a critical vulnerability in medical #AI systems. Learn more: nejm.ai/4mrSoEW

#MedSky #DigitalHealth
Figure 3. Misleading Watermarks Lead to a Loss in Accuracy of Tissue-of-Origin Prediction.
June 19, 2025 at 1:40 PM
Reposted by Sebastian Foersch
erictopol.bsky.social
A big day for medical A.I. publications!
—Oncology agent for decision making
nature.com/articles/s43...
—Forecasting infectious diseases
nature.com/articles/s43...
—Dermatology
nature.com/articles/s41...
—Predicting stroke
www.nature.com/articles/s41...
Development and validation of an autonomous artificial intelligence agent for clinical decision-making in oncology - Nature Cancer
Ferber et al. present an autonomous artificial intelligence agent system for deployment of specialized medical oncology computational tools, validating their system across various clinical scenarios r...
nature.com
June 6, 2025 at 1:35 PM
Reposted by Sebastian Foersch
jnkt.bsky.social
very happy to share our new paper on LLM-based tumor board agents. Submitted August 2024, published in @natcancer.nature.com today ☺️ Led by Dyke Ferber www.nature.com/articles/s43...
Development and validation of an autonomous artificial intelligence agent for clinical decision-making in oncology - Nature Cancer
Ferber et al. present an autonomous artificial intelligence agent system for deployment of specialized medical oncology computational tools, validating their system across various clinical scenarios r...
www.nature.com
June 6, 2025 at 9:09 AM
Reposted by Sebastian Foersch
deniswirtz.bsky.social
Dream Police alert: InterpolAI for enhanced 3D imaging (CODA, MRI, EM, confocal).

Read about and InterpolAI here: www.nature.com/articles/s41...
InterpolAI: deep learning-based optical flow interpolation and restoration of biomedical images for improved 3D tissue mapping
Nature Methods - InterpolAI leverages optimal flow-based artificial intelligence to produce synthetic images between pairs of images for diverse three-dimensional image types. InterpolAI is more...
www.nature.com
May 28, 2025 at 11:42 AM
Reposted by Sebastian Foersch
janclusmann.bsky.social
Finally out, in NEJM AI!
Everyday labels and watermarks can override medical knowledge of vision language models, just by their presence.

Was a lot of fun to work on this with @twittlabs.bsky.social , @jnkt.bsky.social and many others
May 26, 2025 at 5:30 AM
twittlabs.bsky.social
Excited to share our new publication in @ai.nejm.org „Incidental Prompt Injections on Vision-Language Models in Real-Life Histopathology“. Important work together with our amazing colleagues @janclusmann.bsky.social @jnkt.bsky.social @markuseckstein3.bsky.social et al. ai.nejm.org/stoken/defau...
Incidental Prompt Injections on Vision–Language Models in Real-Life Histopathology
Vision–language models (VLMs) can analyze multimodal medical data. However, a significant weakness of VLMs is their susceptibility to prompt injection attacks. Here, the model receives conflicting ...
ai.nejm.org
May 22, 2025 at 7:31 PM
Reposted by Sebastian Foersch
erictopol.bsky.social
A pie graph worth keeping in mind as the NIH budget plummets jamanetwork.com/journals/jam... for 356 new FDA drugs approved
graph of NIH basisfor new drugs
March 23, 2025 at 4:17 PM
Reposted by Sebastian Foersch
euacc.bsky.social
We are pushing for an acceleration… and it might end up coming.

It has been way too long until Europe started to slowly get moving.

Still need to do a lot
jnkt.bsky.social Jakob Nikolas Kather @jnkt.bsky.social · Feb 18
Really disappointed how slowly Europe (especially Germany) is moving these days
Obviously, to compete with US/China on any relevant topic (AI / economy / defense), we need more European integration, joing funding, joint efforts - and much much faster
more resources: eu-acc.com @euacc.bsky.social
February 18, 2025 at 8:15 PM
Reposted by Sebastian Foersch
jnkt.bsky.social
very happy to share our latest preprint, led by Michaela Unger: www.biorxiv.org/content/10.1... We are using Deep Learning to improve the detection of biomarkers in cancer genomic data 👇 This is an emerging field, much more to come.
January 9, 2025 at 11:25 AM