Alyssa Pradhan
@alyssapradhan.bsky.social
2.5K followers 600 following 43 posts
Australian Infectious Diseases trainee | DPhil in Clinical Medicine @ndm.ox.ac.uk‬ Interested in equitable healthcare AI and tahini-based dips
Posts Media Videos Starter Packs
Reposted by Alyssa Pradhan
jama.com
JAMA @jama.com · Jun 16
Viewpoint: The sudden removal of all Advisory Committee on Immunization Practices (ACIP) members and changes to #COVID19 vaccine policy have critically weakened the US vaccine program.

#MedSky

https://ja.ma/43MpHvd
Advisory Committee on Immunization Practices at a Crossroads
Reposted by Alyssa Pradhan
kdpsingh.bsky.social
"All the data in the world will not make a difference, unless there are people ready to use it."

— Atul Butte, MD, PHD, FACMI
2024 Morris F. Collen Award Winner
alyssapradhan.bsky.social
I like these papers where the risk from subtle patterns we pick up on clinically can be somewhat quantified:

pubmed.ncbi.nlm.nih.gov/40345937/

#MedicalAI #MedSky #MLSky #DigitalHealth #AIinHealthcare
pubmed.ncbi.nlm.nih.gov
Reposted by Alyssa Pradhan
medicalattention.bsky.social
Can #LLMs introspect? Can they do maths? We're back (again) busting myths about #LLMs and #AIinmedicine! Listen now: podcasts.apple.com/au/podcast/m...
#MedicalAI #MedSky #FOAMed #digitalhealth
Reposted by Alyssa Pradhan
propublica.org
NEW: Pregnancy became far more dangerous in Texas after the state banned abortion, according to ProPublica’s first-of-its-kind analysis, which found the sepsis rate for women hospitalized as they miscarried in the 2nd trimester shot up by more than 50%.

https://propub.li/43487Tj
Texas Banned Abortion. Then Sepsis Rates Soared.
ProPublica’s first-of-its-kind analysis is the most detailed look yet into a rise in life-threatening complications for women experiencing pregnancy loss under Texas’ abortion ban.
propub.li
alyssapradhan.bsky.social
Would love to collaborate on one if we can't find one!
alyssapradhan.bsky.social
Interesting discussion with Hoffman, ft. some concerning sidestepping about regulation, conflating any guardrails with stifling innovation. Also interesting to see the anxiety around #DeepSeek immediately leading to justification / apology for tech billionaires..
#MLSky #digitalhealth #AI
alyssapradhan.bsky.social
This is gorgeous 😍
alyssapradhan.bsky.social
I really like the detail in this paper! Exploring the bias in #LLM responses through counterfactuals, SHAP, embeddings (oh my) and looking at intersections of gender x ethnicity 😍
TLDR: #Algorithmicbias runs deep
#MedSky #MLSky #digitalhealth #healthequity
arxiv.org/abs/2410.16574
How Can We Diagnose and Treat Bias in Large Language Models for Clinical Decision-Making?
Recent advancements in Large Language Models (LLMs) have positioned them as powerful tools for clinical decision-making, with rapidly expanding applications in healthcare. However, concerns about bias...
arxiv.org
alyssapradhan.bsky.social
Ever wondered what it’s like being stuck talking to me at a party? Look no further.
#MedSky #MLSky #algorithmicbias #healthcareAI
medicalattention.bsky.social
This month's episode is on #AlgorithmicBias. Listen here for a tour through this complex topic.
#MedSky #MLSky #healthcareAI #MedEd #healthequity
podcasts.apple.com/au/podcast/e...
Ep.8 Algorithmic Bias
Podcast Episode · Medical Attention · 17/01/2025 · 54m
podcasts.apple.com
alyssapradhan.bsky.social
"Replacement of just 0.001% of training tokens with medical misinformation results in harmful models more likely to propagate medical errors.... Corrupted models match the performance of their corruption-free counterparts on open-source benchmarks routinely used to evaluate medical LLMs."
natureportfolio.nature.com
A paper in Nature Medicine reports that large language models can be manipulated to generate misinformation by poisoning a small percentage of data on which they are trained and presents a harm mitigation strategy that can offer a method to address this vulnerability. #Medsky 🧪
Medical large language models are vulnerable to data-poisoning attacks - Nature Medicine
Large language models can be manipulated to generate misinformation by poisoning of a very small percentage of the data on which they are trained, but a harm mitigation strategy using biomedical knowledge graphs can offer a method for addressing this vulnerability.
go.nature.com
Reposted by Alyssa Pradhan
alyssapradhan.bsky.social
I'd love to be included if possible! Thanks ☺️
alyssapradhan.bsky.social
Specifically, at what point do you *not* run the model that works really well for the majority population, but performs very poorly in the minority...
alyssapradhan.bsky.social
The focus on close tracking of, and transparency about performance across subgroups is on point though
alyssapradhan.bsky.social
I agree with the call for more and better data and think there are cases where using protected attributes can improve diagnosis. But am not sure that the diagnostic nature of pathology / radiology mean that significant variation in performance across subpopulations is acceptable.
Reposted by Alyssa Pradhan
tripodstatement.bsky.social
Great to see "TRIPOD+AI and DECIDE-AI are the highest quality guidelines with respect to rigor of development and the involvement of the stakeholders" 😄 in

academic.oup.com/jamiaopen/ar...

Get TRIPOD+AI from www.bmj.com/content/385/...

#MLSky #StatsSky #MedSky
Reposted by Alyssa Pradhan
stephenpfohl.bsky.social
Check out our new paper "Tackling Algorithmic Bias and Promoting Transparency in Health Datasets: The STANDING Together Consensus Recommendations" jointly published in NEJM AI and The Lancet Digital Health, led by @jaldmn.bsky.social @xiaoliu.bsky.social
alyssapradhan.bsky.social
Move over Spotify wrapped, it's time for 49 minutes of us chatting about the trends in #healthcareAI for 2024!
#MLSky #MedSky #MedEd #Podcast
medicalattention.bsky.social
Our latest episode is live! Join as as we discuss the #AMIA Year in Review with @pushkala2307.bsky.social, Humayera Islam & Prof James Cimino.
#MedSky #MLSky #HealthcareAI #MedicalInformatics

podcasts.apple.com/au/podcast/m...
Ep. 7 Informatics Year in Review
Podcast Episode · Medical Attention · 17/12/2024 · 49m
podcasts.apple.com