Duke AI Health

If you missed out on last week's 2024 Invented at Duke event, hosted by the Duke's Office for Translation & Commercialization, don't fret: you can get caught up with this excellent summary courtesy of OTC: https://lnkd.in/eX_bq8Hu

Please join us in congratulating Nicoleta Economou-Zavlanos, PhD, on her appointment as the inaugural Director of the Duke Health AI Evaluation & Governance Program! In this new role, Dr. Economou-Zavlanos will help drive the trustworthy, responsible, and equitable integration of AI in healthcare, as well as lead programs and initiatives relevant to AI governance and evaluation at Duke Health. She will also be responsible for a portfolio of projects dedicated to framework development and advancing research in AI evaluation and governance, ensuring that AI technologies are trustworthy and aligned with high standards of quality, ethics, and fairness.

In this week’s Duke AI Health Friday Roundup: are LLMs facing a cliff in performance?; role of digital health in combating antimicrobial resistance; AI’s effects on job markets already being felt; epigenetic changes and obesity; how stress warps memory, feeds anxiety; developing medical AI curricula via Delphi; tech bans and teen mental health; growing strains on scientific publishing; operator guidance can help bystanders in performing CPR; more: https://lnkd.in/gBcj48_6

?? ?? ICYMI: There's still time to register for Duke AI Health's Electronic Health Records Study Design Workshop taking place December 2-6, 2024! The Workshop is a virtual five-day class that provides foundational lectures and hands-on studios on the fundamentals of working with and designing EHR-based studies. In addition to lectures, participants will get hands-on experience in working with publicly available tools to facilitate EHR studies as well as feedback on effective study designs. Registration remains open until Thursday, November 21, 2024. Don't miss out! For more information, or to register for the course, visit https://lnkd.in/eYykMgkm

In this week’s Duke AI Health Friday Roundup: perils of predictive algorithms; soil fungus grooves to white noise; a new angle on Alzheimer disease; dishonest data rampant in online surveys; dispensing with tattooing for radiation therapy; using NLP to extract adverse events in postmarket scenarios; teaching convolutional neural nets to recognize shapes; first-in-human stem cell trials for repairing corneas; going beyond paywalls in ensuring accessibility; much more: https://lnkd.in/eHhCmfeN

?? ICYMI: Duke AI Health is hosting an Electronic Health Records Study Design Workshop (EHR-SDW) on Dec 2-6, 2024.?This 5-day virtual workshop combines lectures + hands-on studio sessions on working with and designing clinical studies using EHR data. The EHR-SDW will introduce learners to the components of EHR data and in considerations for designing effective studies. In addition to didactic lectures, participants will get hands-on experience in working with publicly available tools to facilitate EHR studies (e.g., RxNorm, CCS codes, geocoding), as well as feedback on effective study designs. Deadline for registration is Thursday, 11/21/2024. Learn more: https://lnkd.in/eYykMgkm

Make sure to check out the new white paper on health AI governance from Duke-Margolis Institute for Health Policy & Duke Health ahead of the upcoming webinar on November 18. You can find a link to the full report, along with registration information for the webinar, at this link: https://lnkd.in/eVjJnAUm

?? ?? ICYMI: Duke-Margolis Institute for Health Policy and Duke Health are co-hosting a webinar exploring AI governance in health systems on November 18, 2024 from 2:00-3:30 PM Eastern. During this public webinar, Duke-Margolis and Duke Health will dive deeper into the topic of their newly released white paper on how health systems are navigating the role of AI governance. The webinar will begin with an overview presentation of key takeaways from the white paper followed by a fireside chat where experts will discuss the benefits of governance, as well as lessons learned while building their own AI governance processes. After the fireside chat, there will be a panel discussion on methods and supports to facilitate the democratization of AI governance so more health organizations can safely and responsibly use these novel tools. To learn more and to read the recently published white paper, click on this link: https://lnkd.in/eVjJnAUm

In this week’s Duke AI Health Friday Roundup: the promise of AI agents in discovery science; new mechanism for MRSA resistance found; LLMs for matching patients with clinical trials; the science behind cats’ love of tuna; memorization vs reasoning in LLMs; deep phenotyping illuminates sex-based differences in aging; data sleuths dig into dodgy science; weighing different definitions for Alzheimer disease; much more: https://lnkd.in/eW97uzqY

The question about what neural networks really learn is becoming increasingly important. Check out our study on whether convolutional neural network learn shape when segmenting images (spoiler: they usually do not). Published in Pattern Recognition. Here is the link to the arXiv preprint: https://lnkd.in/dYS8QwYM