Tim Woelfle

#LocalCitationNetwork now allows you to retrieve All References and All Citations from a given set of Input Articles with both @OpenAlex_org and @SemanticScholar! For example, these 11 input articles (via @vamrhein) have 406 references & 7143 citations: localcitationnetwork.github.io/?fromJSON=Amrh… 1/

🚀 Excited to share our latest Journal of Neurology publication on dreaMS app. Six gamified, adaptive cognitive tests (<10 min) improve sensitivity to change by addressing floor/ceiling & practice effects. Big thanks to our team & partners! Read more: link.springer.com/article/10.100…

@Michael_D_Moor @DeryaTR_ @SRSchmidgall Reminds me of @geoffreyhinton's warning to stop training radiologists from 2016.

As the original poster of @SRSchmidgall's figure I respectully disagree that this is a final warning for clinicians to become obsolete. I believe clinicians will be empowered by being augmented with up-to-date knowledge, guidelines and DDx ideas at their fingers' tip with increasingly better UIs. I agree though that certain abusive healthcare economies (with bad incentives) may find ways to provide cheaper & human-free care delivery that is not necessarily better for patients. It's up to us not to let this happen.

This is the final warning for those considering careers as physicians: AI is becoming so advanced that the demand for human doctors will significantly decrease, especially in roles involving standard diagnostics and routine treatments, which will be increasingly replaced by AI. This is underscored by the massive performance leap of OpenAI’s o-1 model, also known as the “Strawberry” model, which was released as a preview yesterday. The model performs exceptionally well on a specialized medical dataset (AgentClinic-MedQA), greatly outperforming GPT-4o. The rapid advancements in AI’s ability to process complex medical information, deliver accurate diagnoses, provide medical advice, and recommend treatments will only accelerate. Medical tasks like diagnosing illnesses, interpreting medical imaging, and formulating treatment plans will soon be handled by AI systems with greater speed and consistency than human practitioners. As the healthcare landscape evolves in the coming years, the number of doctors needed will drastically shrink, with more reliance on AI-assisted healthcare systems. While human empathy, critical thinking, and decision-making will still play an important role in certain areas of medicine, even these may eventually be supplanted by future iterations of models like o-1. Consequently, medicine is becoming a less appealing career path for the next generation of doctors—unless they specialize in intervention-focused areas (such as surgery, emergency medicine, and other interventional specialties), though these, too, may eventually be overtaken by robotic systems…maybe within a decade or so.

Human-AI collaboration may save time for a second human rater for reporting and bias assessments. We tested Claude-3-Opus, Claude-2, GPT-4, GPT-3.5, Mixtral-8x22B. Wonderful work led by @timwoelfle published in @JClinEpi jclinepi.com/article/S0895-…

Our work "Benchmarking Human-AI Collaboration for Common Evidence Appraisal Tools" is published in @JClinEpi! doi.org/10.1016/j.jcli… Evidence appraisal tools are very resource intensive but LLMs may assist human raters. Wonder how @OpenAI's o1 & @Meta's Llama 3.1 will perform?

@Michael_D_Moor @ETH @ETH_BSSE Congratulations and welcome to Basel!

Finally, it's official: I will join @ETH Zurich as an assistant professor!! My group will be part of the beautiful @ETH_BSSE department (see new building below right). Our group will focus on medical foundation models, multimodality, retrieval augmentation, dataset and benchmark curation and more! More updates to follow, stay tuned! I am beyond grateful to my wife and family as well as all my mentors who kept believing in me and supporting me all the way! This includes @kmborgwardt @jure @pranavrajpurkar @EricTopol @Pseudomanifold and more! Also super happy for the unforgetable time I spent at @Stanford (heavy hearted good-bye pic below left). I am keen to further strengthen the ETH / swiss - Stanford / Bay area exchange with exciting collaborations at the forefront of medical AI!

@nealhaddaway @TheLensOrg @SemanticScholar @OpenAlex_org @Scopus @webofscience By a lucky coincidence, such a comparison was actually published in a highly interesting paper by @michaelgusenb just 4 days after our exchange! However, I'm not sure whether it differentiated the "spurious citations" in Google Scholar you've mentioned. doi.org/10.1002/jrsm.1…

@timwoelfle @TheLensOrg @SemanticScholar @OpenAlex_org @Scopus @webofscience I’d like to see that!

#LocalCitationNetwork now allows you to retrieve All References and All Citations from a given set of Input Articles with both @OpenAlex_org and @SemanticScholar! For example, these 11 input articles (via @vamrhein) have 406 references & 7143 citations: localcitationnetwork.github.io/?fromJSON=Amrh… 1/

@aarontay @pure_suggest Looks very interesting, thanks Aaron! Haven’t seen it before.

There are other open source ones like Local Citation Network. Eg @pure_suggest is one I like github.com/fabian-beck/pu…

Shall we please stop worrying about rogue AI and instead worry about the Atlantic Overturning Circulation crossing a tipping point. It seems close and would make Europe basically unlivable. (Thanks to @jonkhler for the link) youtu.be/ZHNNW8c_FaA?si…

Why were so few RCTs done to find out optimal COVID control strategies (masks, isolation)? Why so few RCTs of educational strategies? We conduct uncontrolled experiments over & over, remain in the dark. Cultural change to accept RCTs outside conventional medicine urgently needed.

@nealhaddaway @TheLensOrg @SemanticScholar Furthermore, @aarontay just made me aware that there is even a difference in the data between @semantischolar's API compared to their website. twitter.com/aarontay/statu…

@timwoelfle @TheLensOrg @SemanticScholar Thanks Tim - given the size of the citation numbers I would suspect some over counting or the inclusion of spurious citations there. Similarly, Google Scholar supposedly ingests fake papers containing self citations, so I would treat those numbers with caution.

@nealhaddaway @TheLensOrg Thanks for your interest and for citationchaser Neal, great tool! #LocalCitationNetwork only searches one API at a time and the example network I've linked & the numbers I've shown are from @SemanticScholar (S2). I'm not aware of a comparative analysis of its graph accuracy.

@timwoelfle @TheLensOrg Interested in the discrepancy in citation numbers - The Lens absorbs Open Alex so the additional records are all from Semantic Scholar. Any idea on the accuracy?

Finally, check out this recent guidance on citation searching in the @bmj_latest: bmj.com/lookup/doi/10.… Direct citation searching is now fully implemented in #LocalCitationNetwork & we're working on indirect citation searching: doi.org/10.17605/OSF.I… Stay tuned! 7/7

#LocalCitationNetwork will always remain free & open source, meaning 100% transparency! There are many other great literature mapping tools like @Inciteful_xyz (also open source), but most are closed source: @RsrchRabbit, @LitmapsApp, @ConnectedPapers 6/ twitter.com/RaziaAliani/st…

Recommendations for researchers on when and how to conduct citation searching and how to report it bmj.com/content/385/bm…