STAT’s Post

Check out this great article by Isabella Wiest and her colleagues, developing a new #LLM-based pipeline to extract critical insights from free-text data in medical research. https://lnkd.in/d5zKztb9

This news story in Nature Magazine highlights just one of the ways Signals is supporting the research community in evaluating research. As well as helping publishers to safeguard their journals’ integrity, we’re enabling researchers to identify and filter problematic articles out of systematic reviews — critical resources that guide medical decisions for doctors and patients. https://lnkd.in/d7j2tB-k

Did you know that almost 90% of clinical trials struggle to meet their enrollment goals? #AI could be the solution needed. We recently teamed up with the Institute for Precision Medicine at UPMC and the University of Pittsburgh to host an expert panel on the potential of #AI to revolutionize #clinicaltrials. You can now watch a recap and recording of this insightful discussion. ⤵️

Beading plot: a novel graphics for ranking interventions in network evidence https://lnkd.in/dYzP8E5p Network meta-analysis is developed to compare all available treatments; therefore it enriches evidence for clinical decision-making, offering insights into treatment effectiveness and safety when faced with mu...

Good to know the outcome on the Advanced Research Projects Agency for Health (ARPA-H) Biomedical Data Fabric Awards! Thanks for sharing this, Alastair Thomson. Well done. A few comments: 1) This is a big win for Boston, with 5 of 17 ARPA-H awards in my neighborhood. That’s not surprising, because much of the foundational technology was and continues to be developed here. 2) Colleagues working on systematic literature reviews, clinical guideline development, and learning health systems may want to keep an eye on this space. If I’m reading this correctly, some awardees will develop AI tools that query findings from peer-reviewed literature together with clinical data. I hope they’ll build on the methodological foundation established by the Agency for Healthcare Research and Quality for systematic literature reviews and guideline development.

Oh dear, but, unfortunately, not at all surprising. This excellent article by Doug Altman seems to be just as relevant today as when it was published in 1994. https://lnkd.in/es7HveFC In my experience things have got worse since then, not better. How can we change the current culture in academic publishing? In my opinion, it needs a root and branch change.

New blog: Interesting papers in 2024 Lots of interesting papers in 2024. I describe a few, and also list others I have mentioned in previous blogs. All are about evaluation, experimental rigour, real-world utility, and/or healthcare applications. https://lnkd.in/echE4QZx

Prevention and early intervention — that’s the power of #artificialintelligence in medicine. Groundbreaking technologies are advancing clinical efficiency and accuracy, providing medical professionals with valuable tools to improve health outcomes and patient experience. “AI will not replace doctors, but doctors who use A.I. will outperform doctors who don’t because it will dramatically increase their ability to care for patients,” said Dr. Lee Schwamm, Yale School of Medicine. WTNH-TV demonstrates how Connecticut healthcare institutions, like Hartford HealthCare and Yale New Haven Health, are leveraging AI to develop innovative treatments.

The concept of semantic knowledge which alludes to long term memory and knowledge achieved by studying a complex topic eg. medicine. A framework to organize the enormous heterogeneous medical data as a semantic health knowledge graph by integrating conceptual and theoretical graphs with health data. The GraphRAG can enhance the accuracy and they have the potential to transform patient care and clinical research. #knowledgegraph #generativeai #digitalhealth #graphrag

"When Medical A.I. is Lifesaving." "Counterbalanced by some disappointments" BY Eric Topol, MD "Progress in medical A.I. won’t occur in a straight line. One big step forward, 4 backwards. It’s exciting to see the reduction of mortality in a large, prospective, real-world randomized trial, while at the same time sobering to see 4 studies published that question whether we’re ready for LLMs in medical practice (and even coding). It’s still very early in the era of A.I. in medicine, especially with LLMs, but clearly the more trials like the one published today, the better" https://lnkd.in/dr8vdx2W