Julián Nicolás Acosta
@jn_acosta
Medical AI Researcher at Rajpurkar Lab @HarvardDBMI | Scientist at @a2zradiologyai | Neurologist | http://jnacosta.com | Opinions are my own. 🇦🇷🇺🇸
Are you a radiologist interested in shaping the future of AI in healthcare? At Rajpurkar Lab, we are looking for collaborators to join us in an exciting upcoming project. If interested, please reach out - DMs are open! @pranavrajpurkar
How AI might change medical care—Interviews w/DBMI's @zakkohane & @pranavrajpurkar begin 3:03. Bonus note: The mom who diagnosed her own son's tethered cord syndrome w/ChatGPT after 3 years & 17 doctors (3:33) co-keynotes our 10th annual Precision Medicine conference 10/1/24.
Artificial intelligence has been called medicine's biggest moment since antibiotics. It has the potential for diagnosing rare illnesses, developing new treatment options and exciting new drug discovery. @Brook examines how scientists are using AI for faster results that could…
The audacity of scientific journals to charge you to publish, charge you to read, and still hit you with annoying pop-up ads every time you open a paper.
Incredibly proud to share @a2zradiologyai's first research paper evaluating a2z-1. Our AI model detects 21 conditions in abdomen-pelvis CTs with an AUC of 0.931. This represents the most comprehensive external validation of a multi-disease detection AI in abdominal imaging to…
🚨 AI in Radiology Alert! 🚨 How much can AI help radiologists reduce reporting time while maintaining accuracy? @harvardmed & collaborators present a pilot study on AI-assisted radiology workflows using AI-generated draft reports! Authors: @jn_acosta, @siddograMD,…
@HopfieldJohn and @geoffreyhinton, along with collaborators, have created a beautiful and insightful bridge between physics and AI. They invented neural networks that were not only inspired by the brain, but also by central notions in physics such as energy, temperature, system…
BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”
It's launch day! 🚀 Announcing a2z Radiology AI and our first product, a2z-1. a2z-1 is an AI that analyzes abdominal-pelvis CT scans and reports to catch potential misses across 21 conditions. Our mission is to create a comprehensive AI safety net for radiology, ensuring no…
Years ago, as a neuroscience obsessed med student, I came across artificial neural networks. Later, when I first learned about deep learning, I was immediately convinced that it would work, which led me to take very unconventional career paths. Fortunately, deep learning worked.
The Intelligence Age: ia.samaltman.com
Excited to be moving beyond chest X-rays and diving into more complex studies—as a neurologist, working on head CT feels like coming home.
📢 Introducing HeadCT-ONE: Our new paper addresses a major gap in AI evaluation for radiology—capturing semantic equivalence. Using ontologies, we standardize medical terms, making AI-generated head CT reports more accurately comparable, even when phrasing differs.🧠✨
💫Excited to share our new study: “Uncovering Knowledge Gaps in Radiology Report Generation Models through Knowledge Graphs”. We’ve developed a system ReXKG to extract structured information from radiology reports, building a comprehensive knowledge graph for in-depth model…
⭐️ Announcing ReXRank, a competition for radiology report generation from Chest X-Rays. Featuring 16 existing competitive approaches, a large private test leaderboard of 10k cases indicative of more real-world performance, and a live arena where radiology experts can do a…
🚨 New Multimodal Generative Medical AI 🚨 Our team just announced MedVersa, a groundbreaking multimodal medical image interpretation model. 🩺🖥️ MedVersa is the first generalist medical AI capable of learning from both visual & linguistic supervision to tackle a wide range of…
Just published Our review article of all the medical #AI randomized controlled trials @LancetDigitalH thelancet.com/journals/landi… Ryan Han @jn_acosta @pranavrajpurkar
a reference implementation, no matter how hacky, often provides more clarity than any spec
Radiologists, are you ready to shape the future of your field with AI? 10 min application: shorturl.at/fgmSY Join the Medical AI Bootcamp, where you'll have the unique opportunity to embed yourself in an environment that allows you to think deeply about and write a…
Very insightful study. A must read if you’re in medical AI!
Who benefits from AI? Our new study with 140 radiologists in Nature Medicine challenges prevailing assumptions. We find years of experience, subspecialty and familiarity with AI tools fail to reliably predict the impact of AI assistance. nature.com/articles/s4159…
1/ 📰 Breaking: @Forbes covers @RadAI’s partnership with @Google, which builds upon our leadership in GenAI reporting and collaboration on the latest #GenAI models like #MedLM, including #GeminiAI based models in the future. forbes.com/sites/saibala/… Key highlights in 🧵
Not everyday a large language model scores 85.4% on the US medical licensing exam (USMLE) Implications erictopol.substack.com/p/multimodal-a…