Jason Alan Fries
@jasonafries
Followers
1K
Following
2K
Media
50
Statuses
929
Researcher at Stanford University. Working on healthcare AI, multimodal foundation models, and data-centric AI.
California, USA
Joined June 2010
๐ We're thrilled to announce the general release of three de-identified, longitudinal EHR datasets from Stanford Medicineโnow freely available for non-commercial research-use worldwide! ๐ . Read our HAI blog post for more details: ๐๐ฎ๐๐ฎ๐๐ฒ๐.
hai.stanford.edu
Current evaluations of AI models in healthcare rely on limited datasets like MIMIC, lacking complete patient trajectories. New benchmark datasets offer an alternative.
3
26
104
๐ Headed to MLHC 2025 this weekend?. Swing by Poster #154 (Session C) on Saturday, Aug 16 to check out FactEHR โ our new benchmark for evaluating factuality in clinical notes!.
๐ข How factual are LLMs in healthcare?.Weโre excited to release FactEHR โ a new benchmark to evaluate factuality in clinical notes. As generative AI enters the clinic, we need rigorous, source-grounded tools to measure what these models get right โ and what they donโt. ๐ฅ ๐ค.
0
1
8
Amazing work by @SnorkelAI โscaling domain expertise for evaluation and data curation is key to unlocking AIโs potential in high-stakes fields like healthcare. So excited for whatโs next! ๐.
Agentic AI will transform every enterpriseโbut only if agents are trusted experts. The key: Evaluation & tuning on specialized, expert data. Iโm excited to announce two new products to support thisโ@SnorkelAI Evaluate & Expert Data-as-a-Serviceโalong w/ our $100M Series D!. ---
0
0
6
RT @AlyssaUnell: Excited to present this work at ICLR's SynthData Workshop on Sunday April 27! Come through from 11:30-12:30 @ Peridot 202โฆ.
0
9
0
RT @MayeeChen: !!! I'm at #ICLR2025 to present ๐งAioli๐ง a unified framework for data mixing on Thursday afternoon! .๐ .
0
55
0
RT @fredsala: Today at #ICLR2025---come chat with @Changho_Shin_ about our work on what types of data drive weak-to-strong generalization!โฆ.
0
11
0
RT @srush_nlp: Reminder: COLM abstract deadline! Should be an amazing conference this year in Montreal.
0
4
0
RT @AlyssaUnell: 1/๐งตIntroducing TIMER: Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Records. When we evaluate LLMโฆ.
0
21
0
RT @StanfordDeptMed: Can AI in healthcare truly be responsible without full patient histories? New longitudinal EHR datasets provide a bettโฆ.
hai.stanford.edu
Current evaluations of AI models in healthcare rely on limited datasets like MIMIC, lacking complete patient trajectories. New benchmark datasets offer an alternative.
0
2
0
RT @percyliang: 1/๐งตHow do we know if AI is actually ready for healthcare? We built a benchmark, MedHELM, that tests LMs on real clinical taโฆ.
0
70
0
RT @thekaransinghal: OpenAI's Health AI team is now hiring backend/fullstack SWEs towards our mission of universalizing access to health inโฆ.
0
96
0
RT @fredsala: Some new work from our group that I'm very excited about! What makes weak-to-strong generalization possible? We think it's alโฆ.
0
7
0
Excited to share that our paper "Time-to-Event Pretraining for 3D Medical Imaging" has been accepted to ICLR 2025! ๐ . Electronic health records (EHRs) contain a wealth of longitudinal data on disease progression. In this work, we use methods from survival analysis to transform.
๐ Excited to share that our latest research, ๐๐ช๐ฎ๐ฆ-๐ต๐ฐ-๐๐ท๐ฆ๐ฏ๐ต ๐๐ณ๐ฆ๐ต๐ณ๐ข๐ช๐ฏ๐ช๐ฏ๐จ ๐ง๐ฐ๐ณ 3๐ ๐๐ฆ๐ฅ๐ช๐ค๐ข๐ญ ๐๐ฎ๐ข๐จ๐ช๐ฏ๐จ, has been accepted at ๐๐๐๐ฅ 2025! ๐. ๐ ๐๐บ๐ฝ๐ฟ๐ผ๐๐ถ๐ป๐ด ๐ ๐ฒ๐ฑ๐ถ๐ฐ๐ฎ๐น ๐๐บ๐ฎ๐ด๐ฒ ๐ฃ๐ฟ๐ฒ๐๐ฟ๐ฎ๐ถ๐ป๐ถ๐ป๐ด ๐๐ถ๐๐ต ๐ง๐ถ๐บ๐ฒ-๐๐ผ-๐๐๐ฒ๐ป๐.
1
1
23
RT @percyliang: While we celebrate @deepseek_ai 's release of open-weight models that we can all play with at home, just a friendly remindeโฆ.
0
453
0
RT @mattlungrenMD: Excited to share our open-source code for cancer survival prediction using radiology (MRI) and pathology (H&E) images -โฆ.
0
15
0
RT @MattBMcDermott: Super excited to join @ColumbiaDBMI this coming July! If you're looking for postdoctoral or PhD opportunities in Healthโฆ.
0
10
0