🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

I'm pleased to be participating in the 2020 NCI ITCR annual meeting #NCIITCR

Deeply saddened by this news. He was an amazing scientist, visionary, leader, and moreover, caring and passionate person. He will be deeply missed, and the seeds he has planted here and throughout the world will thrive.

This discussion was getting long, so I thought I'd lay out my thoughts on a common argument: should models produce probabilities or decisions? Ie 32% chance of cancer vs "do a biopsy". I favour the latter, because IMO it is both more useful and... more honest. IMO: 1/13

Absolutely agree models should output probabilities/confidence. If the model is not confident in its output, that affects trust..

Role of imaging in #AI clinical prediction is hot area: Deep Learning Using Chest Radiographs to Identify High-Risk Smokers for Lung Cancer Screening Computed Tomography acpjournals.org/doi/10.7326/M2…

Great blog about perspectives on what it will take for reimbursement of medical #AI, and the answer is "substantial clinical improvement" in care...

Time to reality check the promises of machine learning-powered precision medicine - The Lancet Digital Health thelancet.com/journals/landi…

Appreciate making this week's list by @drpenguin51 doctorpenguin.com on our paper on #AI approaches for predicting disease progression just out, great work by Imon Banerjee nature.com/articles/s4159…

Congrats to Aya!

These are the kinds of studies we need to see for all #AI algorithms before deployment in clinical care healthitanalytics.com/news/artificia…

Important study comparing medical #AI recommendations with actual medical decisions, we need more of these kinds of studies... academic.oup.com/jamia/advance-…

Important position paper just out on recommendations for the effective management and monitoring of adaptive #clinicaldecisionsupport academic.oup.com/jamia/advance-…

IBM may sell off Watson. Development and translation of #AI in medicine is not a trivial business pursuit. Maybe #radiology #imaging is a better bet? wsj.com/articles/ibms-…

The enthusiasm for #AI in addressing COVID-19 (and others) needs to be tempered by potential for #AIbias, very important research topic smithsonianmag.com/science-nature…

Following such guidelines when publishing #AI studies will address many issues and limitations (e.g., reproducibility) of current works nature.com/articles/s4159…

Important lesson for AI developers, getting value from healthcare #AI requires a nuanced, thoughtful and long-term solution, as well as clinical partnership healthcareitnews.com/blog/not-seein…

Delighted to announce that Juan Manuel Zambrano Chaves, a PhD student in the Rubin QIAI lab, won Best Technology Paper for his #AI work on opportunistic screening at the 2021 Society of Abdominal Radiology meeting! sar.virtualbyvario.com/awards/

I am delighted to announce that Isabel Gallegos, a Stanford undergraduate student in the Daniel Rubin QILab has been named a 2021 #GoldwaterScholar for her #AI proposal, “Use biomedical data science to build machine learning models to improve healthcare decision-making” 👏 Goldwater Scholar Community

We can value image data for #AI! See our Nature Scientific Data paper "Data valuation for medical imaging using Shapley value and application to a large-scale chest X-ray dataset" just out rdcu.be/ciN6F

Congratulations to Josh Sanyal, a high school student in our lab who won 3rd Place in Math and Computer Science Poster competition at the 2021 Northern California Junior Science & Humanities Symposium! docs.google.com/document/d/1Jw…