"All health care leaders bear the responsibility to support ways to help patients and staff take advantage of AI." That's the conclusion from To Do No Harm — and the Most Good — with AI in Health Care by carey goldberg @lauraadams, Laura D. Adams, MBAT1D, David Blumenthal, et al in

The first randomized trial of medical #AI to show it saves lives ECG-AI alert in 16,000 hospitalized patients 31% reduction of mortality (absolute 7 per 100 patients) in pre-specified high-risk group nature.com/articles/s4159… Nature Medicine

Dropped a new tutorial a few days ago that walks you through how to build a Streamlit UI for the PDF #RAG tutorial I published a few months ago. Stack/frameworks used: ✅ Streamlit - UI ✅ LangChain - RAG orchestration ✅ Unstructured - PDF parsing (LangChain integration)

1/ 🚨New paper alert! 🚨We've developed ReXErr, a method to inject clinically plausible errors into diagnostic radiology reports using large language models (LLMs). 🧠💻 This approach is a leap forward for improving error correction in AI-generated and human-written reports.

Congratulations to my friend and advisor Garry P. Nolan for his Lifetime Achievement Award in Biomedical Sciences from the Stanford School of Medicine! As a type 1 diabetic I am personally grateful for his contributions to the field. Same for cancer. And his willingness to approach

Inspiring. 5 years and 4B dollars to clean up the Great Pacific Garbage Patch.

U.S. cell phone providers were recently hacked. That means your calls and texts can be read by foreign governments. New guidance from CISA follows: 1. Use end-to-end encrypted texting apps like Signal 2. Enable Fast Identity Online (FIDO) phishing-resistant authentication 3.

We did it! We tested 300 Bay Area foods for plastic chemicals. We found some interesting surprises. Top 5 findings in our test results: 1. Our tests found plastic chemicals in 86% of all foods, with phthalates in 73% of the tested products and bisphenols in 22%. It's

When AI has an IQ of 200, and unlimited access to data, and is instantly accessible by anyone, anywhere, at anytime, it's going to fundamentally reshape what's possible for the human race, including the eradication of diseases. Exciting times we live in.

AlphaFold has reduced a billion years of PhD work into just the last two or three years. And they expect their new drugs to be available by the end of the year. The rate of scientific improvement we're experiencing is non-linear and will be difficult to comprehend.

Everyone: plastic is polluting the planet and causing health issues. Starbucks: here’s a long green piece of plastic for your hot coffee. X 90,000,000 cups served worldwide per day.

About a month after Donald Trump took office, almost all grant-review meetings remain suspended at the US National Institutes of Health, preventing the world’s largest public funder of biomedical research from spending much of its US$47 billion annual budget.

" I think maybe in the next 10, 15 years we can actually have a real crack at solving all disease." Nobel Prize Winner and DeepMind CEO Demis Hassabis on how AI can revolutionize drug discovery doing "science at digital speed."

Does RAG solve hallucination? Even w/ RAG, we found that >30% of LLMs' medical statements are not fully supported by (sometimes contradict) the cited refs Nature Communications nature.com/articles/s4146… We present #SourceCheckUp agent to verify faithfulness of LM to source info. Great job

It's not every day that you wake up to a Forbes article covering the great work of your team. We at Tahoe Therapeutics (Formerly Vevo) open sourced Tahoe-100M to start a movement in open data in biology. Thanks Amelia Palermo Briosi, PhD for taking note of that and the thoughtful piece. "By providing

A big day – we are making the largest dataset of chest X-rays available to the world. This is the first dataset to cross 100k patients. huggingface.co/datasets/rajpu…

One of the biggest problems we face today.

DeepMind just dropped a 106-page paper unveiling AlphaGenome. This single model could completely redefine how we discover disease-causing mutations and drug targets. This is massive. 🧵

Excited to pick up Proof by Adam Kucharski which talks about the pitfalls of p-values, the dangers of loose priors and the difficulty of communicating the efficacy of interventions. Clearly we need to get better at communicating complex and nuanced interpretations of data, or

Summary Table of the massive defunding of biomedical research in the United States nytimes.com/interactive/20…