Neil Sarkar

Brown University’s Division of Biology and Medicine is seeking a teaching track faculty member to teach courses in statistics and AI for its graduate programs as well as contribute to a new Master’s in Health Informatics program. Application Deadline: January 15, 2026. apply.interfolio.com/176254

YouTube video by Neil's Cookery Pork & Veggies with a Dash of Desi Spice [S1V4]

Check out the latest recipe in Neil’s Cookery: a pork-based dog food with a dash of Indian spice!
Nutritious, cost-effective, and easy to make with everyday ingredients. Augi & Chaz approved!!
youtu.be/idNyHQb2sBg?...

HIEs evolving to HDUs... As necessary for our nation as the federal highway system: 10.0.4.69/jamia/ocaf032 #Informatics

We are recruiting for a Lecturer to teach AI and Statistics for Health courses at Brown University-- please share! apply.interfolio.com/162962

Neil's Cookery Join us at Neil’s Cookery, where we create nutritious, homemade meals for dogs, cats, birds, fish, and people. Our step-by-step videos make it easy to prepare balanced, species-specific meals using re...

Launching Neil's Cookery: Healthy Food, Healthy Pet! (Subscribe and share!) www.youtube.com/@neilscookery

YouTube video by Julia Dispatch Tidier.jl with Karandeep Singh

Why is #JuliaLang a great home for a flavor of the tidyverse? What does Tidier.jl do? Will you get sent to Julia jail for using an ecosystem inspired by #rstats?

In this convo with @chrisrackauckas.bsky.social and Michael Tiemann, I don’t have answers, but I have thoughts!

youtu.be/oLnAiCqYjzw?...

Interventions to Reduce Electronic Health Record-Related Burnout: A Systematic Review Thieme E-Books & E-Journals

Electronic Health Records are increasingly seen as a source of clinician burnout. We reviewed interventions to reduce burnout, and the TLDR is that there is still much work to do!

$200/month? Yeah, no. If there were reason to drive us away from ChatGPT to LLAMA, this might be it!

Thank you to all 180 members of the ASTP, including @mickytripathi.bsky.social , who keep moving things forward to the benefit of all of us, especially our patients! #ASTP2024

What are animals saying? AI may help decode their languages — National Geographic What are animals saying? Researchers are finally building the tools to understand.

Dr. AI Doolittle? apple.news/AnyllA5BtSWW...

LLM-based agentic systems in medicine and healthcare - Nature Machine Intelligence Large language model-based agentic systems can process input information, plan and decide, recall and reflect, interact and collaborate, leverage various tools and act. This opens up a wealth of oppor...

The opportunities, challenges and outlook for LLM-based agents in medicine and healthcare—our paper published today

nature.com/articles/s42...

Transforming Cancer Navigation with Open Data & APIs | HeroX Support care Navigators with digital tools that integrate openly available datasets and APIs. Enhance patient care and support systems.

ASTP and CancerX want to give you money (and the title of “prize winner”!) to improve cancer care navigation. Check it out! www.herox.com/CancerNaviga... #ASTP2024

How close is AI to human-level intelligence? Large language models such as OpenAI’s o1 have electrified the debate over achieving artificial general intelligence, or AGI. But they are unlikely to reach this milestone on their own.

There is a difference between "intelligence" and leveraging AI in "intelligent ways"... The latter being human intelligence, and requires experience and insights that we have yet to see in any of the LLMs...

as a kid, i fixed my parent's computer. as an adult I fix my kids's computer. pretty sure we are the only gen that knows how computers work

I am super excited about this new leadership role in my research group, @d4cg.bsky.social. Help build novel methods for getting patient data directly from the EHR. Please apply! sam.am/PD2024
This will help our cancer survivorship work as well as other projects like our monogenic epilepsy commons.

How close is AI to human-level intelligence? Large language models such as OpenAI’s o1 have electrified the debate over achieving artificial general intelligence, or AGI. But they are unlikely to reach this milestone on their own.

Why the large language models of today cannot reach AGI, a new Nature feature www.nature.com/articles/d41...

An Intersectional Approach to Cervical Cancer Screening Disparities by Race/Ethnicity and Immigrant Status | Journal of Women's Health Background: Disparities in cervical cancer (CC) screening exist within racial/ethnic minority and immigrant groups. However, few studies have explored the joint influence of race/ethnicity and immigrant status on screening, and the disparities that have been identified by existing studies remain incompletely explained. This study aims to identify the joint influence of race/ethnicity and immigrant status on CC screening and elucidate the barriers contributing to identified disparities. Methods: A cross-sectional analysis of 25,660 U.S. women from the 2005, 2010, and 2015 National Health Interview Surveys was done. The CC screening up-to-date status of cases was analyzed by race/ethnicity and immigrant status using logistic regression models. Conceptualized mediators were added to models to identify their contribution to identified disparities. Results: All immigrants had lower screening odds than U.S.-born non-Hispanic White women with foreign-born non-Hispanic Asians having the lowest odds (adjusted odds ratio [aOR]: 0.36, 95% confidence interval [CI]: 0.26–0.49) followed by foreign-born non-Hispanic White (aOR: 0.52, 95% CI: 0.36–0.76), Hispanic/Latinx (aOR: 0.58, 95% CI: 0.47–0.73), and non-Hispanic Black women (aOR: 0.62, 95% CI: 0.38–0.99). Adjusting for only socioeconomic status or access to care attenuated the aOR: for foreign-born Hispanic/Latinx and non-Hispanic Black women only. Adjusting simultaneously for language and acculturation attenuated the aOR: for all immigrants. Conclusions: Disparities in CC screening were only found in the immigrant populations of various racial/ethnic groups. Targeting insurance and health care access may address disparities in immigrant Hispanic/Latinx and non-Hispanic Black women. Focusing on culturally and linguistically competent care and education may be more crucial for immigrant non-Hispanic Asian and White women.

It is important to consider other drivers of disparities, beyond race/ethnicity-- e.g., immigrant status. This is especially essential in considering differing cultures around key prevention approaches, such as cancer screenings.

Internship - TLAB 25 Description TLab has summer internship opportunities in data science and health AI. As a summer research intern in the Tatonetti Lab at Cedars-Sinai you will conduct research to improve drug safety an...

TLab @ Cedars-Sinai is looking for summer interns in data science, drug safety science, and health AI!

🔬 Research drug safety, cancer care & more
📍 LA-based (Pacific Design Center)
🗓 Apply by Jan 27!
👉 Learn & grow with us!

More info here: docs.google.com/document/d/1...

#HealthAI #Internship

"How health IT and AI can improve patient safety gaps while mitigating unintended consequences." @jama.com #medsky #ArtificialIntelligence

Thanks! @hardeepsinghmd.bsky.social

Read more
jamanetwork.com/journals/jam...

Exploring the Impact of Artificial Intelligence in Teaching and Learning of Science: A Systematic Review of Empirical Research - Research in Science Education The use of Artificial Intelligence (AI) in education is transforming various dimensions of the education system, such as instructional practices, assessment strategies, and administrative processes. I...

AI will be an essential tool in the modern era of science, and we must equip future generations to demonstrate their proficiency. I allow and REQUIRE students in my courses to use AI to develop their responses. I then challenge them to identify what AI missed or got wrong...

PDF of "Recommendations to Ensure Safety of AI in Real-World Clinical Care."

Viewpoint: To safely integrate #AI into healthcare, healthcare organizations (HCOs) and clinicians must proactively mitigate risks through pre-implementation quality checks, ongoing monitoring, and patient/clinician engagement.

https://ja.ma/419xF0h

Opening lecture to an “Intro to R” course in Ecuador namedrops #JuliaLang and Tidier.jl. 🚀🧹

github.com/laboratoriol...

Submit an abstract to join us in Puerto Rico!

✨focus on real-world deployment of AI into the clinic with practical, in-depth discussions
✨intimate setting for detailed conversations & networking to start new collaborations
✨beachfront hotel 🌴

We are now recruiting our first cohort of Master's students in Health Informatics at Brown University in Providence, RI. You will have the opportunity to impact real world healthcare delivery. Consider joining us and share with those who may be interested! graduateprograms.brown.edu/graduate-pro...

What is AI code-generation? | IBM Using AI code generation software is straightforward, available for many programming languages and accessible to both developers and non-developers.

I have been tinkering with using generative AI to help me with my development work, and will say that I am VERY impressed! Hours saved. Now, the question will be, can I as a scientist do more with AI and rely less on staff programmers? www.ibm.com/think/topics...

Matching patients to clinical trials with large language models - Nature Communications Patient recruitment is challenging for clinical trials. Here, the authors introduce TrialGPT, an end-to-end framework for zero-shot patient-to-trial matching with large language models.

The potential for LLMs to enable next level research is astounding! This is what we dreamed of decades ago… www.nature.com/articles/s41...

To get a sense of how I think about HIEs, here is a perspective about HIEs as utilities that I penned last year... journal.chestnet.org/article/S001...

Barriers to obtaining and using interoperable information among non-federal acute care hospitals AbstractObjective. To understand barriers to obtaining and using interoperable information at US hospitals.Materials and Methods. Using 2023 nationally rep

The TLDR is that HIEs are essential to fill the data gap needed to enact clinical decision making! academic.oup.com/jamia/advanc...

Brown University Health is hiring an inaugural Director of Artificial Intelligence! Check out the listing here: www.linkedin.com/jobs/view/di... and consider a move to Little Rhody!

Delighted to be part of this community! I thought it important that my first post be a simple reflection— our success depends on resilience and the ability to see the view through the forest!