Researcher in clinical #nlproc at Children's Hospital Computational Health Informatics Program (CHIP) and Associate Professor at Harvard Medical School.
Boston, MA
Joined March 2007
- Tweets2.3K
- Following191
- Followers565
- Likes1.6K
Tim Miller retweeted
Reminder to join us September 17th, at 12 EST for the next #RegSci forum! Dr. Tim Miller @TMills will be presenting on "Opportunities for Large Language Models in Regulatory Science"! #LLM #NLP #clinicalNLP
Register here: rb.gy/dxi1ma
Next #RegSci Forum, on September 17th, will feature guest speaker Tim Miller @TMills on “Opportunities for Large Language Models in Regulatory Science”.
Register here: rb.gy/psky6m
Tim Miller retweeted
1/9 Excited to introduce the LCD Benchmark! A new benchmark dataset for 30-day out-of-hospital mortality prediction (predicting the future!) using long clinical documents. Designed for testing the capabilities of LMs on lengthy documents! medrxiv.org/content/10.1101/… #ClinicalNLP
Tim Miller retweeted
#LLMs might help burnout by drafting responding to patient portal messages in #EHRs. But is this a low-risk efficiency aid, or do #LLMs impact clinical judgement in more meaningful ways?
We investigated this in our new study out in @LancetDigitalH: thelancet.com/journals/landi… 1/
Tim Miller retweeted
NEW Comment from @dbittermanmd and colleagues: The effect of using a large language model to respond to patient messages. #LLMs
Read it here: buff.ly/3JzLT0t
Tim Miller retweeted
Proud of @shan23chen presenting our work on synthetic clinical text generation to 🚀 accelerate clinical #NLP at #AMIA #IS24!
Tim Miller retweeted
It’s official on JAMIA! 🎈
After chatgpt being 1 years old and working with in context learning more. I think my points still stands firmly where LLM+prompting is fabulous, however the time investment and current performance gap is far from zero for domain specific tasks 😢
#ChatGPT has taken #NLProc by storm 🤖. We investigated time, data, and performance trade-offs of ChatGPT family of models in 2 health NLP tasks beyond QA: health advice classification and causal reasoning. ⚕️ [1/6] arxiv.org/abs/2304.02496 @ShaaanChen @BrighamRadOnc @Bos_CHIP
Tim Miller retweeted
💡🎉Learn more about the role of medical KGs in AI-augmented diagnostic systems via a graph prompting framework for LLM in our study.
👩⚕️👨⚕️ Featuring the first comprehensive human evaluation of LLMs for diagnostic safety. 1/🧵
#HealthAI #NLP #RAG
medrxiv.org/content/10.1101/…
Tim Miller retweeted
GPT-4 gives medical advice that saves doctors' time but can be harmful newscientist.com/article/240…
Tim Miller retweeted
LLMs could help manage the EHR and reduce burnout, but need careful safety checks - want some evidence? #NLP #LLM #AI
✅Introducing OncQA, an open dataset with clinician responses & evaluations
@dbittermanmd @BrighamRadOnc @Bos_CHIP
📑 huggingface.co/papers/2310.1…
⚕️[1/6]
Tim Miller retweeted
So very grateful for this award from my home community. Let’s celebrate this and many more good things in New Orleans at the @ColumbiaDBMI party! #AMIA2023
So thrilled that @AMIAinformatics has selected DBMI Chair @noemieelhadad as the 2023 Donald A.B. Lindberg Award for Innovation in Informatics recipient! We certainly agree with the selection!
Tim Miller retweeted
Deeply honored and grateful to receive the NIH/NLM K99/R00 award for my work in multi-modal #NLP & evaluation for diagnosis prediction... my very first grant submission🩷 🥇. Big thanks to my mentors @Majeans2011 @UW_ICU_DataSci , advisors @TMills @dmitriydligach @BPattersonMD
Congratulations to our Research Associate Dr. Gao
@Serena_pancakes
for gaining an NIH NLM Pathway to Independence Award [K99LM014308: "Developing & Evaluating Multi-Modal Clinical Diagnostic Reasoning Models for Automated Diagnosis Generation"]! @uw_medicine @Majeans2011 @NLM_NIH
Tim Miller retweeted
Apply now! NLM is seeking exceptional candidates for the position of Deputy Director, Operations and Innovation (DDOI)!
For more information and how to apply, please visit: hr.nih.gov/jobs/search/execu…
Closes 9.21.2023.
ALT Deputy Director. Operations and innovations. NIH. National Library of Medicine. Image: Two individuals in business wear looking pleasantly at the camera.
Tim Miller retweeted
It's not just people that would benefit from a safer 15th Ave NW.
"Bean loves exploring every square inch of Ballard, but we almost never go across 15th. More crossings and calmer car traffic will sew the neighborhood together for us!" - Tim M.
#repave15th #reconnectballard
ALT Bean (a cute, shaggy-haired black and white dog) sits on the sidewalk near 15th Ave NW.
Tim Miller retweeted
Adversarial Policies Beat Superhuman Go AIs
Their policies do not win by playing Go well. Instead, they trick AI into making serious blunders! These tricks transfer to other superhuman Go AIs and can be used by humans to consistently beat superhuman AIs.
arxiv.org/abs/2211.00241
Tim Miller retweeted
New JAMIA call for papers for the Special Focus Issue on ChatGPT and Large Language Models (LLMs) in Biomedicine and Health. Excited to be working with Zhiyong Lu, @nychunhua, Trevor Cohen, @MarzyehGhassemi, and @JAMIAEditor_Sue academic.oup.com/jamia/pages…
Tim Miller retweeted
Way to go @Serena_pancakes @Majeans2011 @TMills @dmitriydligach on standing up Task 1A for the 22nd BioNLP Workshop at #ACL2023. Paper below; part of workshop on #bionlp at #ACL2023 @NIDAnews #Informatics @datascience_uw @uw_medicine @uw_medicine arxiv.org/abs/2306.05270
Tim Miller retweeted
Excited to see @brihat91351 represent @uw_medicine at the 5th Clinical NLP Workshop at #ACL2023 on his paper below; part of workshop on #clinicalnlp @NIDAnews #Informatics @datascience_uw @uw_medicine @Majeans2011 @Serena_pancakes @TMills @dmitriydligach
arxiv.org/abs/2306.04551v2
Tim Miller retweeted
Read about the first NLP system to automatically generate real-world evidence on RT events from clinical narrative in the #RedJournal. @dbittermanmd @guergana_s @Bos_CHIP @BrighamResearch @DanaFarber bit.ly/bitterman1
