katherlab

Research group "Clinical Artificial Intelligence" @Medizin_TUD @tudresden_de, led by @jnkath

[Jakob Nikolas Kather @jnkath]

Twitter is really becoming unbearable. I fully support keeping science separate from politics, but this is going too far. Foreign oligarchs should not be influencing European politics. I’ll still be around here, but my main activity is now on 🦋👇

[Jakob Nikolas Kather @jnkath]

Very happy to share our article about AI agents in cancer research and oncology, with @LeeTaliq @Dykex6 & Aviv Regev, out in @NatureCancer now -> https://t.co/A3tZ6omeAf
@katherlab @NCT_UCC_DD @NCT_HD

[Jakob Nikolas Kather @jnkath]

Happy to share a new review article led by Laura @zigutyte from @Katherlab. We surveyed all contributions at Europe’s largest conference on hepatology, @EASLnews 2024. The liver research field is already integrating AI techniques for diagnostics, evaluating treatment effectiveness, assessing risks, and more. https://t.co/zd0lqTB6BT

[Jakob Nikolas Kather @jnkath]

Today, we hosted the first conference on LLMs in medicine at @katherlab / @tudresden_de, chaired by @IsabellaWies 🤩 We are not just riding the hype train🚆 - we are working hard to provide scientific & clinical evidence for benefits and limitations of LLMs in healthcare

[Jakob Nikolas Kather @jnkath]

We had a fun session on artificial intelligence at the @dgho_eV German/Swiss/Austrian conference of #hematology and #oncology in Basel 🇨🇭Both the main room and the overflow room were overflowing ... thanks to excellent speakers @leukaemielabor @C_V_Schneider & others

[katherlab @katherlab]

New paper from @katherlab led by @ElNahhasOSM et al. 😊👇

[Nature Protocols @NatureProtocols]

#NewNProt moves from whole-slide image to #biomarker prediction: end-to-end weakly-supervised #deeplearning in #computationalpathology https://t.co/6gpy1muACs

[katherlab @katherlab]

New research from @katherlab led by @IsabellaWies 🤩

[npj Digital Medicine @npjDigitalMed]

This study developed an open-source tool using a LLM to extract important medical information from clinical text, focusing on decompensated #LiverCirrhosis.

The tool identified liver cirrhosis from free text with 100% sensitivity and 96% specificity, and showed strong results for other symptoms inc. ascites & abdominal pain, demonstrating its potential for efficiently analyzing clinical data.

https://t.co/OdqjUj1jIS

[Jakob Nikolas Kather @jnkath]

New article from @katherlab in @NatureMedicine: large language models for interoperability in healthcare 👇

[Roxana Pintican @RPintican]

This week was about research. It is inspiring to see how people come together, clinicians with computational scientists, all with a common goal, to help cancer patients on their journey.
Together, we are better!

Thanks, @jnkath, for organizing a great AI in medicine week.

[katherlab @katherlab]

Exciting new research by @ElNahhasOSM from @katherlab ���

[Omar S.M. El Nahhas @ElNahhasOSM]

Excited to present my latest work accepted in #MICCAI2024 on joint multi-task learning in computational pathology!

We reach SOTA performance on predicting MSI and HRD status by learning auxiliary regression tasks related to the tumor microenvironment 🔬

https://t.co/YgBowkkU9k

[Jakob Nikolas Kather @jnkath]

New research from @katherlab, led by @JClusmann : "Prompt Injection Attacks on Large Language Models in Oncology" https://t.co/pw6jBb9uJg We show that vision-language models in oncology can be attacked easily, creating malicious output which could harm patients.
@tudresden_de @NCT_UCC_DD @NCT_HD @EKFZdigital @DKFZ

[katherlab @katherlab]

Just out from @katherlab 👇

[Radiology @radiology_rsna]

This review explores the transition of deep learning in radiology from laborious fully supervised methods to more scalable weakly supervised methods. @laim_uka @ekfzdigital @jnkath @katherlab @danieltruhn @LeoMisera @FranzesGustav https://t.co/MuCmWg0D1d

[katherlab @katherlab]

New research led by @ChiaraMLL 🤩

[Jakob Nikolas Kather @jnkath]

Happy to share a new computational pathology preprint from @katherlab & many other groups: "HIBRID - Histology and ct-DNA based Risk-stratification with Deep Learning". Deep Learning 💻+ ctDNA 🧬= very powerful prognostic model in colorectal cancer ☑️
https://t.co/NdgVbpmyBN
@NCT_UCC_DD @NCT_HD @EKFZdigital @tudresden_de @Medizin_TUD @uniklinik_hd @DKFZ @_mhoffmeister @twittlabs @myESMO

[Jakob Nikolas Kather @jnkath]

New preprint from @katherlab: large language models for end-to-end clincial trial matching. Our system parses study protocols and patient records, and matches them. We evaluate thoroughly against human experts and find >90% correspondence. Led by @Dykex6 🤩 https://t.co/vTnTVd19gq
@NCT_UCC_DD @NCT_HD @DKFZ @DataScienceDKFZ @uniklinik_hd @myESMO CC @tompowles1 @NEJM_AI @Agrawal_Mri @alexia_zz @PepPamies

[Jakob Nikolas Kather @jnkath]

Weekend read: We are discussing the future of AI in cancer research in @Cancer_Cell https://t.co/sJAg4mcyfO ... with @MoritzGerstung @james_y_zou @MarzyehGhassemi @diegochowell @jonasteuwen @AI4Pathology 🤩
@NCT_UCC_DD @nct_hd @DKFZ @uniklinik_hd @tudresden_de

[Jakob Nikolas Kather @jnkath]

New preprint from @katherlab, led by @IsabellaWies - large language models can solve one of the hardest problems in medical informatics - robustly anonymizing unstructured medical documents. This unlocks a large source of clinical data for downstream AI applications. Available open source.
@NCT_UCC_DD @DKFZ @NCT_HD @tudresden_de @prof_ebert @NEJM_AI @EricTopol @Medizin_TUD

[Jakob Nikolas Kather @jnkath]

So proud of @IsabellaWies from @tudresden_de and @unimedizinma who is presenting about the “skill of prompt engineering” at our AI session at @EASLedu #EASLcongress

[Jakob Nikolas Kather @jnkath]

What a fun session at @EASLedu @EASLnews #EASLcongress 2024 about "Research in the age of AI" in Milan 🇮🇹🇪🇺. Any biomedical researcher should be aware of current AI tools and develop a basic literacy. @tudresden_de @NCT_UCC_DD @NCT_HD @Medizin_TUD @uniklinik_hd

[Jakob Nikolas Kather @jnkath]

Out today in @Nature - a broad overview of AI in oncology, happy to have contributed to this along with many colleagues and friends @PrelajArsela @anantm & others

[katherlab @katherlab]

RT @jnkath: Finally out in @NEJM_AI 🤖 "GPT-4 for Information Retrieval and Comparison of Medical Oncology Guidelines". We've developed a RA…