Jie Yang, PhD, FACMI

Assistant Professor @Harvard | AI in Healthcare | NLP | EHR | Views my own.

[Jie Yang, PhD, FACMI @JieHealthAI]

@kchonyc Multiple-choice medical exams oversimplify the complexity of medicine. Try our BRIDGE benchmark, which is based on 87 real-world clinical tasks and includes far more complex, realistic tasks. We have evaluated 95 LLMs with over 3.4 billion LLM inferences https://t.co/M5jxe0LRYT

[Jie Yang, PhD, FACMI @JieHealthAI]

Great resource! Love seeing more real-world health benchmarks beyond USMLE and PubMedQA! 🙌
Two weeks ago, we also just released BRIDGE, a multilingual, real-world EHR-based LLM benchmark covering 87 tasks in 9 languages.
📄 Paper: https://t.co/awZZiNuMGC
🚀 Leaderboard: https://t.co/9p23YW8KNq

[Jie Yang, PhD, FACMI @JieHealthAI]

@EnricoSantus Big congratulations, Enrico!

[Jie Yang, PhD, FACMI @JieHealthAI]

Sure. As I replied to Dan, we can only access the datasets but we don't have the right to redistribute them. Each dataset needs to be requested to the original publisher. We listed all the contact information in our paper. If you think there still exists interested topics that we can discuss, I am happy to the talk.

[Jie Yang, PhD, FACMI @JieHealthAI]

Our recent paper "Clinical Text Datasets for Medical Artificial Intelligence and Large Language Models — A Systematic Review" has been published in @NEJM_AI ! The lack of clinical text data is a long-term challenge/pain for #AIinMedicine and clinical LLM researchers. After reviewing 3962 papers and 239 tasks from clinical #NLP challenges, we found that less than half of these datasets are accessible, with significant regional, language, and disease imbalances. We have shared a list of over 90 accessible clinical text datasets, hoping it can serve as a dataset landscape for clinical NLP research. Free access link: https://t.co/UTnpj5uKAo

[Jie Yang, PhD, FACMI @JieHealthAI]

@dancaron @NEJM_AI Hi Dan, although we have accessed these datasets, we can't redistribute them. Users who are interested in the listed datasets need to request the dataset from the original dataset publishers (we listed the contact information in our paper).

[Jie Yang, PhD, FACMI @JieHealthAI]

@LiamGMcCoy @zakkohane @NEJM_AI Thanks! Yes, actually the difficulty of accessing data for published papers is the main reason for us to start this review.

[Jie Yang, PhD, FACMI @JieHealthAI]

@ZainKhalpey @NEJM_AI Thanks Zain!😀

[Jie Yang, PhD, FACMI @JieHealthAI]

@bnrome Cool! Where is it? Can't see it in Cambridge.

[Jie Yang, PhD, FACMI @JieHealthAI]

@hbouamor @rose_e_wang @abeirami @emnlpmeeting @juanmiguelpino Hi @hbouamor and @juanmiguelpino , we have the same issue (submission#1538) with score 345 but got rejected without a detailed reason. We sent an email to PCs on Oct 7 but got no response until now. Our follow-up emails also got no response. Can you pls give us an update? Tks

[Jie Yang, PhD, FACMI @JieHealthAI]

Code: https://t.co/4gMlLsUCTv

[Jie Yang, PhD, FACMI @JieHealthAI]

@NeneKa31793581 https://t.co/LNWcvTGrLK

[Research Square Covid-19 Preprints @RS_COVID19]

Tracking the impact of COVID-19 and lockdown policy on public mental health using social media #covid https://t.co/6cxHd0gV04

[Kimberly Blumenthal, MD, MSc @KimberlyBlumen1]

3/Recently we looked at ~3K allergic reactions in healthcare settings @MassGenBrigham: contrasts caused allergy the most & just 6 vaccine reactions in 10-years. @NeelamPhadkeMD @MGH_ClinEpi @lizhou08 @JieHealthAI @PaigeWickner
https://t.co/kcGTHb2Tam

[Li Zhou @lizhou08]

Check out our recent study on changes in outpatient mental health/substance use disorder visits during the initial Massachusetts COVID-19 surge and partial state re-opening. https://t.co/D4KjbEChOf

[David Duong, MD, MPH @DrDavidDuong]

A message from my team @BrighamWomens ICU consisting of #Doctors #Nurses #RespiratoryTherapist ... please #StayAtHome #COVIDー19 #frontlineworkers

[UW Virology @UWVirology]

~2300 tests were reported yesterday from @UWVirology @UWMedicine. Positive rate seems stable. Lab running smoothly the first half of today with lots of results going out. Realtime tracker at https://t.co/81ED3b8zk5

[UW Virology @UWVirology]

Over 1300 #SARSCoV2 #CoronavirusUSA #HCoV19 tests completed 3/11 by @UWVirology @UWMedicine, about 9% positive. Many tests were for patients in other parts of the US lacking access to testing. We have capacity for more. Order info here https://t.co/vbIsdTp2ny. #WhereAreTheTests

[Jie Yang, PhD, FACMI @JieHealthAI]

NCRF++ (dev branch) now supports the sentence (and doc) classification! You can build the classification model just using a simple configuration file without writing any code. LSTM/CNN/FF/Attention/Custom features are all supported! (will + BERTs)
https://t.co/Qfbo89oZ4P