Girish Nadkarni
girishnadkarni.bsky.social
Girish Nadkarni
@girishnadkarni.bsky.social
Immigrant. Professor. Data Scientist.

Father.Son.Friend.

Opinions Own. RT≠endorse
Go Eagles Go.

#eagles
February 10, 2025 at 2:22 AM
Reposted by Girish Nadkarni
The economic chaos that will occur across the United States on Monday is something I hope is being well covered by journalists. Hospitals and Universities employ large sectors of communities.
Research universities are often the largest employers in their region. They are often the primary health care providers to communities. This funding shift will not only reduce US research leadership, it will put working people out of work and reduce healthcare access.
Excellent 🧵 on this evening's NIH announcement of a dramatic reduction in indirect rates for research institutions, which amounts to a generational restructuring of the US research and development ecosystem. These cuts are effective immediately, not just for new grants but for existing ones.
February 8, 2025 at 2:27 AM
Reposted by Girish Nadkarni
Can carefully developed electronic alerts help with management of #AKI? Yes, but developing an effective alert is both an art and science. Read about our experience in #ACI www.thieme-connect.com/products/ejo...
@girishnadkarni.bsky.social #informatics
Thieme E-Books & E-Journals -
www.thieme-connect.com
January 1, 2025 at 7:41 PM
Happy New Year! 2025 = 45² — we’re celebrating a perfect square year. Cheers to fresh starts, big dreams, happiness and contentment!
January 1, 2025 at 1:48 PM
Ok I dont like Superman and Lois anymore
December 11, 2024 at 2:14 AM
I have tried starbucks instant coffee and its a revelation.
December 10, 2024 at 8:48 PM
Reposted by Girish Nadkarni
Had so much fun discussing how #AI is shaping medicine and sharing the work from our lab at #apexpathshala @akforg.bsky.social @girishnadkarni.bsky.social
December 8, 2024 at 6:03 AM
How have I not watched Superman and Lois till now
December 1, 2024 at 2:51 AM
Reposted by Girish Nadkarni
Are #LLMs as good as human coders in extracting ICD codes? Of 6 LLMs we tested, GPT-4 achieved highest agreement with human coder but still only at 15.2%. Read our full study in #ACI at - pubmed.ncbi.nlm.nih.gov/39608761/ @girishnadkarni.bsky.social
Extracting International Classification of Diseases Codes from Clinical Documentation using Large Language Models - PubMed
Current LLMs have poor performance in extraction of ICD-10-CM codes from inpatient notes when compared against the human coder.
pubmed.ncbi.nlm.nih.gov
November 30, 2024 at 6:00 PM
Reposted by Girish Nadkarni
Excited to share our review article, which provides a step-by-step comprehensive overview of reinforcement learning tailored specifically for clinicians, presented in a clear and non-technical manner - www.nature.com/articles/s41... @girishnadkarni.bsky.social #AI #RL
A Primer on Reinforcement Learning in Medicine for Clinicians
npj Digital Medicine - A Primer on Reinforcement Learning in Medicine for Clinicians
www.nature.com
November 27, 2024 at 2:47 AM
The SAIL 2025 CALL FOR ABSTRACTS is open! Join us on May 6-9 in Río Grande, Puerto Rico! In-person attendance is limited to those with accepted work. NEJM_AI will award cash scholarships to the top abstracts. Travel support is available. Submit by January 17: sail.health/event/sail-2.... #SAIL25
Participate – SAIL: Symposium on Artificial Intelligence for Learning Health Systems
sail.health
November 25, 2024 at 9:48 PM
Sky is blue(kinda)
@bsky.app
November 21, 2024 at 2:04 PM
Reposted by Girish Nadkarni
We’ve all been under a lot of stress lately.

But did you know that stress affects blood coagulation?

If you didn’t before prepare to now with another #hemesky #skeetorial

1/
a man says you look pretty stressed in a showtime ad
Alt: a man says you look pretty stressed in a showtime ad
media.tenor.com
November 20, 2024 at 8:48 PM
Sky is blue @bsky.app
November 19, 2024 at 2:57 PM
Good morning
November 19, 2024 at 12:28 PM
November 19, 2024 at 3:11 AM
🚨 RESEARCH ALERT🚨
We explored how to make Large Language Models (LLMs) cost-effective and accurate for health systems. Why this matters:
Hospitals struggle to analyze mountains of EHR data. With the right AI, we can unlock better care for millions—and save $$. 🤖💉
Let's break it down. 🧵👇
November 18, 2024 at 7:46 PM
I love @bsky.app
November 16, 2024 at 10:36 PM
#goodmorning Skypeople? Skyers? Skyes? What are we calling ourselves. @bsky.app
November 14, 2024 at 2:15 PM
@scoca1.bsky.social is ON @bsky.app . Give him a follow
November 12, 2024 at 6:42 PM
My first science post on @bsky.app

🚨Research alert! Deep learning is now being used to detect neurologic changes in critically ill infants directly from video data. This novel approach could revolutionize NICU monitoring and improve outcomes for our tiniest patients. #AI #HealthcareInnovation
November 12, 2024 at 6:21 PM
Reposted by Girish Nadkarni
Great article that should be getting more traction

If you haven’t deactivated yet, it’s time to Dump Twitter

newrepublic.com/article/1881...
Dump Twitter
If you stick with Elon Musk, you’re complicit.
newrepublic.com
November 11, 2024 at 5:34 AM
Reposted by Girish Nadkarni
To recap, the Republican Party has opposed:

-Paid sick leave
-Paid family & medical leave
-Universal childcare
-Universal pre-K
-Tax increases on corporations & the rich
-The expanded Child Tax Credit
-Student debt relief

Doesn't sound like the party of the working class to me.
November 12, 2024 at 1:30 AM
This reminds me of the early days of twitter.

Do we have a medtwitter equivalent here?

#medsky?

@hswapnil.bsky.social @kidneyboy.bsky.social @roxanadaneshjou.bsky.social @christosargyrop.bsky.social whoever else is here
November 12, 2024 at 3:01 AM
Reposted by Girish Nadkarni
Please repost 🧪

Does anyone have a good document of "core competencies" for undergraduate researchers?

I like this Elife perspective for core competencies of PhD trained scientists. elifesciences.org/articles/34801
Point of View: Competency-based assessment for the training of PhD students and early-career scientists
A method to assess the training of scientists, based on a set of 10 core competencies, is proposed.
elifesciences.org
November 11, 2024 at 8:16 PM