Sign in

Theodore Pak

@tedpak.bsky.social
489 followers 348 following 54 posts

Assistant Professor @ucirvine.bsky.social. Former fellow @mgh-id.bsky.social, MGH Medicine resident, Sinai MD-PhD, mghwhitebook.app creator. Posts my own. Lab website: tpaklab.org

PostsRepliesMedia
Reposted by Theodore Pak
Thanh Neville, MD, MSHS @thanh-neville.bsky.social · 05/08/2026
I am so triggered by RJK Jr's comment about ICU's being empty during #COVID. I re-read what I wrote after one of the surges. How do others forget. The trauma was--and is--real.
huffpost.com
I'm An ICU Doctor. I’m Haunted By What I’ve Seen During The Recent COVID-19 Surge.
“I can’t stop thinking about the 40-something man who told me, ‘I can’t die like this. I just got engaged and have a 6-month-old baby.’ I encouraged him to be positive, but that didn’t stop him from d...
611802624
Theodore Pak @tedpak.bsky.social · 02/08/2026
It is a deranged lie to say “there were ICUs… empty all over the country… at the height” of COVID. I was a medicine resident at Mass General in 2020. The hospital tripled its adult ICU capacity. Cancer units, peds ICUs, perioperative units all became COVID ICUs. They were full of dying patients.
1177
Theodore Pak @tedpak.bsky.social · 23/07/2026
Ever write "consider" or "can" in your consult note recs? Retrospective study of 250 ID consults in Australia found primary team adherence to these "ambiguous" recommendations was 59.5%, while it was 87.2% for recommendations without such qualifiers academic.oup.com/cid/advance-...
academic.oup.com
Reconsidering ambiguous language in infectious disease consult recommendations
In this retrospective study of 1087 Infectious Diseases consultation recommendations at a multi-site health network in Australia, ambiguous language occurr
020
Reposted by Theodore Pak
Max Kozlov @maxkozlov.bsky.social · 27/06/2026
NIH grants have been under political scrutiny since early 2025. But what does the screening process actually look like? What is being flagged? I spent a month digging into leaked docs and emails. We've published the 235-word list that are being flagged by an internal AI tool. And so much more. 🧵
nature.com
Inside the new political screening that’s stalling NIH grants
Mandatory reviews by top health officials and checks for 235 disfavoured terms have left hundreds of vetted grant applications in administrative limbo.
9541384
Reposted by Theodore Pak
Steven Tong @steventong.bsky.social · 22/06/2026
The SNAP Trial Exemplifies What EBM Should Look Like: www.sensible-med.com/p/the-snap-t... #IDSky
sensible-med.com
The SNAP Trial Exemplifies What EBM Should Look Like
It's always worth showing properly designed and conducted trials--though it's bad for pageviews. Nonetheless, SNAP authors show the way to answering questions in biomedicine
082
Reposted by Theodore Pak
Simon Hammann @simonhammann.bsky.social · 20/04/2026
Don't be shy to take on a little two-week side project. These five months will be the most precious three years of your academic journey.
191957537
Reposted by Theodore Pak
Kristian G. Andersen @kgandersen.bsky.social · 15/04/2026
U.S. infectious disease research is on the brink. Without immediate action from Congress, much of it will cease to exist within a year. For example👇 1️⃣ No collaborative RFAs posted for >1 year (normal: many / year). 2️⃣ No foreign collaborators allowed on grants. 🧪🪦 www.idsociety.org/globalassets...
Dear Member of Congress:
The Infectious Diseases Society of America (IDSA) and HIV Medicine Association (HIVMA) are deeply grateful for the longstanding bipartisan support from Congress for the National Institutes of Health (NIH). We want to inform you of current and likely impacts of delays and changes in funding policies and procedures for NIH grants.
Our concerns relate to the following areas within NIH:
• Massive reduction in notice of funding opportunities
• Delays in funding processes and inadequate capacity to administer grants
• Increase in forward funding of multiyear awards in year one
• Delays and potential lapses in funding for large clinical trial networks and clinical trial units
Lack of transparency around permitted international collaborative partners for research projects
• Disproportionate impact of grant terminations on vulnerable populations, especially women and people of color
7238163
Reposted by Theodore Pak
Sanjat Kanjilal @sanjatkanjilal.bsky.social · 01/04/2026
1/12 🎉 Our paper on colonization pressure (CP) and nosocomial pathogen acquisition is out in Nature Communications! Lots of surprising findings. www.nature.com/articles/s41...
nature.com
Using electronic health records to assess the relationship between colonization pressure and nosocomial pathogen acquisition - Nature Communications
Hospitalised patients are at risk of acquiring infections, and the risk increases when there is a higher prevalence among ward co-occupants, known as colonisation pressure. Here, the authors built an ...
141
Reposted by Theodore Pak
Theodore Pak @tedpak.bsky.social · 14/03/2026
🚨 My lab is hiring! @ucirvine.bsky.social Seeking full-time data scientists & machine learning engineers. We apply LLMs and AI tools to clinical data, rapidly scaling up epidemiological analyses and models of sepsis, hospital-acquired infections, and more. tpaklab.org #MedSky #IDsky 🧪 1/x
tpaklab.org
Theodore Pak's Lab
Using A.I. to accelerate research on infectious diseases. We work at the intersection of epidemiology, clinical informatics, microbial genomics, and computer science. Our lab is based in the Division ...
154
Theodore Pak @tedpak.bsky.social · 14/03/2026
🚨 My lab is hiring! @ucirvine.bsky.social Seeking full-time data scientists & machine learning engineers. We apply LLMs and AI tools to clinical data, rapidly scaling up epidemiological analyses and models of sepsis, hospital-acquired infections, and more. tpaklab.org #MedSky #IDsky 🧪 1/x
tpaklab.org
Theodore Pak's Lab
Using A.I. to accelerate research on infectious diseases. We work at the intersection of epidemiology, clinical informatics, microbial genomics, and computer science. Our lab is based in the Division ...
154
Reposted by Theodore Pak
IDSA @idsainfo.bsky.social · 13/03/2026
ID fellow Alejandro De La Hoz Gomez, MD, of Mass General Brigham shares three things people don’t realize about a career in infectious diseases. #WhyILoveID
094
Reposted by Theodore Pak
Jonathan Ryder, MD @jonathanrydermd.bsky.social · 07/03/2026
I'll try to TL;DR the debate lol (although its not a short TL;DR). ATS CAP guidelines say give antibiotics for CAP with +virus in severe CAP, non-severe hospitalized CAP, and outpatient CAP with comorbidities, but don't give antibiotics for non-comorbid outpatient CAP
132
Reposted by Theodore Pak
Bennett Waxse @bwaxse.bsky.social · 30/01/2026
I've been using #ClaudeCode for #research #informatics—cohort building, debugging pipelines, genomics in #AllofUs. Before any of that was useful, I had to set things up right. The setup isn't complicated, but it matters. Here's how I do it: 1/
111
Reposted by Theodore Pak
Roby Bhattacharyya @roby-b.bsky.social · 22/02/2026
The last part abt how measles disrupts immunity vs other infections is, imo, underappreciated (& mechanism was recently clarified). It's part of why measles vaccination was seen to help beyond just reducing measles complications - not getting measles reduces severity of subsequent infections too.
science.org
Measles virus infection diminishes preexisting antibodies that offer protection from other pathogens
Measles virus infection can cause long-term damage to the immune system.
513685
Reposted by Theodore Pak
Matthew J Shepherd @matthewjshepherd.bsky.social · 20/02/2026
🚨 New pre-print! 🚨 In the largest study of its kind to-date, we investigate the ecological and evolutionary mechanisms driving within-patient evolution of antimicrobial resistance (AMR). Read here: www.biorxiv.org/content/10.6... , and follow along with this thread, discussing our findings (1/21)
biorxiv.org
26533
Theodore Pak @tedpak.bsky.social · 06/01/2026
Clinical trials affected by NIH grant terminations "Approximately 1 in 30 trials and more than 74 000 trial participants were affected ... Affected trials disproportionately studied infectious diseases, prevention, and behavioral interventions" #MedSky #IDSky jamanetwork.com/journals/jam...
jamanetwork.com
Clinical Trials Affected by Research Grant Terminations at the National Institutes of Health
This cross-sectional study summarizes the number of trials with terminated grants from the National Institutes of Health (NIH) and calculates the proportion of affected trials among those with previou...
0149
Reposted by Theodore Pak
Bennett Waxse @bwaxse.bsky.social · 27/12/2025
What I'm Reading: Curiosity, a 1B-parameter model built on Epic Cosmos. It's genuinely interesting: zero-shot outputs rivaled supervised baselines across 78 real-world tasks, and the scaling laws (α=0.52) mirror NLP. Cool to see how information scales across domains. arxiv.org/abs/2508.12104 1/
lnkd.in
LinkedIn
This link will take you to a page that’s not on LinkedIn
121
Reposted by Theodore Pak
Ian Kremer @wolverinebear.bsky.social · 10/12/2025
Rise of anti-science rhetoric has fundamentally changed the relationship between doctors and patients www.statnews.com/2025/12/10/a... by @krutikakuppalli.bsky.social via @statnews.com #HHS #FDA #CDC #publichealth #vaccines #science #MedSky
statnews.com
Rise of anti-science rhetoric has fundamentally changed the relationship between doctors and patients
“The rise of anti-science and anti-vaccine rhetoric has fundamentally changed the relationship between clinicians and patients.”
65331
Reposted by Theodore Pak
Joseph Marcus @josephmarcusid.medsky.social · 08/12/2025
A @idsainfo.bsky.social position statement in @cidjournal.bsky.social describing why the society backed out of ATS CAP guidelines. [In viral pneumonia] “briefly withholding antibiotics for patients with nonsevere illness to clarify the diagnosis is safe” #IDSky academic.oup.com/cid/advance-...
academic.oup.com
Infectious Diseases Society of America (IDSA) Position Statement: Why IDSA Did Not Endorse the Community-Acquired Pneumonia Guidelines 2025 Update
The Infectious Diseases Society of America (IDSA) did not endorse updated community-acquired pneumonia guidelines because they recommend antibiotics for pa
1124
Reposted by Theodore Pak
Sanjat Kanjilal @sanjatkanjilal.bsky.social · 05/12/2025
Today I am very proud to announce the release of the Antibiotic Resistance Microbiology Dataset - Mass General Brigham (ARMD-MGB; physionet.org/content/armd...) , as part of an NIH-funded collaboration led by Jonathan Chen at Stanford. (1/6)
physionet.org
Antibiotic Resistance Microbiology Dataset Mass General Brigham (ARMD-MGB) v1.0.0
ARMD-MGB contains detailed microbiology and clinical metadata for >225,000 patients and >970,000 cultures collected over 10 years
1308
Reposted by Theodore Pak
Simon P. Couch @simonpcouch.com · 13/11/2025
To be effective, data science agents need to be able to read plots reliably. @sara-altman.bsky.social and I wrote about some concerning findings on LLMs' ability to interpret plots when the content contradicts their expectations on the @posit.co blog. posit.co/blog/introdu...
posit.co
When plotting, LLMs see what they expect to see - Posit
Data science agents need to accurately read plots even when the content contradicts their expectations. Our testing shows today's LLMs still struggle here.
14718
Reposted by Theodore Pak
Sanjat Kanjilal @sanjatkanjilal.bsky.social · 05/11/2025
Gave my 1st talk in NL: how to make multicenter data analysis with patient data actually work. tl;dr: common data models (global interoperability) + LLMs (data harmonization, mapping, future-proofing) + federated learning (privacy) Let me know what you think! drive.google.com/file/d/1N3yk...
032
Reposted by Theodore Pak
JAMA Network Open @jamanetworkopen.com · 25/10/2025
An #LLM extracted signs and symptoms for patients with sepsis with similar accuracy to humans, and identified 7 syndromes differentially correlating with multidrug-resistant infection risk and mortality. ja.ma/47onWVE
Heatmaps show symptom co-occurrence and infection sources. Panel A charts 30 signs/symptoms (skin, cardiopulmonary, gastrointestinal, dizziness, constitutional), with red indicating high co-occurrence. Panel B links infection sources to symptoms via ICD-10-CM codes.
153
Reposted by Theodore Pak
Antibiotic Steward 🅱️C🆔🅿️🌟 @absteward.bsky.social · 24/10/2025
Maybe AI Knows Something That We Do Not! 🆕💫 Cohort study LLM accurately extracted presenting signs & symptoms from admission notes that clustered into syndromes differentially correlated with infection sources, MDR infections, and mortality #IDsky jamanetwork.com/journals/jam...
jamanetwork.com
Syndromic Analysis of Sepsis Cohorts Using Large Language Models
This cohort study compares the performance of a large language model against manual medical record review for extracting presenting signs and symptoms data from hospital admission notes and uses these...
251
Reposted by Theodore Pak
Alex Sundermann, DrPH @sundermannaj.bsky.social · 14/10/2025
My new piece in @medpagetoday.com We Can Stop Deadly Hospital Outbreaks - So Why Aren't We? Genomic surveillance can prevent outbreaks from spreading, save lives, and costs. So what’s holding it back from being implemented in hospitals? #IDSky www.medpagetoday.com/opinion/seco...
medpagetoday.com
Opinion | We Can Stop Deadly Hospital Outbreaks -- So Why Aren't We?
Genomic surveillance can help contain local and nationwide threats
35215
Theodore Pak @tedpak.bsky.social · 12/06/2025
#IDsky #Medsky 🧪🦠
030
Reposted by Theodore Pak
Alex Sundermann, DrPH @sundermannaj.bsky.social · 27/04/2025
New preprint from our lab by Rangachar Srinivasa et al: We WGS 4 major respiratory viruses in 3 hospitals (RSV, influenza, rhinovirus, HMPV) & found silent transmission happening under the radar Genomics uncovered hidden spread, complex transmission chains #IDSky 📄: www.medrxiv.org/content/10.1...
3237
Reposted by Theodore Pak
Emily Moin @emilymoin.com · 14/04/2025
How many hospitalized patients need care in the ICU? How many of them survive? What interventions do they receive there? These are some of the questions I had two years ago while trying to write the "background" section for my masters thesis. But I couldn't find the answers... they did not exist.
3256
Reposted by Theodore Pak
Gabriele Pollara @gpollara.bsky.social · 15/03/2025
The amount of green on this level of evidence guiding antifungal treatment duration demonstrates nicely the research knowledge gap in this field! #IDSky #ClinMicro #AMR @drneilstone.bsky.social
1246
Reposted by Theodore Pak
Yaneer Bar-Yam @yaneerbaryam.bsky.social · 12/03/2025
ondering how this year’s measles outbreaks compare to previous years? This chart shows that 2025 (dark purple) is already about 4x higher than this time last year (light purple), which was itself a sharp increase over 2023. The trend is alarming. Prevention—including vaccination—is critical.
08227
Reposted by Theodore Pak
@IM_Crit_ @imcrit.bsky.social · 21/01/2025
ID - Return to Basics: This was the 1st reported case of an adult immunocompetent host who survived measles complicated by ARDS. A 36 yo female ED nurse, unvaccinated, who was exposed to a patient w active measles in October 1989. Ten days later, she developed measles
43415
Theodore Pak @tedpak.bsky.social · 08/02/2025
Your AI can't see gorillas – A comparison of LLMs' ability to perform exploratory data analysis chiraaggohel.com/posts/llms-e...
chiraaggohel.com
Your AI can’t see gorillas – Chiraag Gohel
A comparison of LLMs’ ability to perform exploratory data analysis
020
Theodore Pak @tedpak.bsky.social · 05/02/2025
Clever tricks with token sampling can guide a "reasoning" LLM like Deepseek's R1 (and the many new models it is already inspiring) into <think>'ing longer, and thereby producing more accurate output There is a lot more juice to squeeze from these kinds of models. timkellogg.me/blog/2025/02...
timkellogg.me
S1: The $6 R1 Competitor?
020
Reposted by Theodore Pak
Sanjat Kanjilal @sanjatkanjilal.bsky.social · 01/02/2025
New paper in JAMA Network Open! jamanetwork.com/journals/jam... The IDSA released their guidelines for treatment of uncomplicated UTI back in 2011. We looked at a large claims database formatted into the OMOP common data model to see whether the recommendations still hold tl;dr They do. (1/7)
jamanetwork.com
Use of Machine Learning to Assess the Management of Uncomplicated UTI
This cohort study examines the effectiveness and adverse event profile for first-line antibiotics, fluoroquinolones, and oral β-lactams for treating uncomplicated urinary tract infection (UTI) in cont...
111
Reposted by Theodore Pak
IDSA @idsainfo.bsky.social · 31/01/2025
The removal of #HIV- and #LGBTQ-related resources from the websites of CDC and other health agencies is deeply concerning. Access to this information is crucial for ID and HIV health care professionals. Our full statement: buff.ly/42AO8LI
14553304
Reposted by Theodore Pak
Hakeem Jefferson @hakeemjefferson.bsky.social · 31/01/2025
It is simply not enough for universities to say, “Our grants & research offices are looking into how research will be affected by the latest directive.” University leaders must actively and very publicly make the case for the kind of work many of us do. The silence on this front is deafening.
4123522409
Reposted by Theodore Pak
Abbie Richards @abbierichards.bsky.social · 31/01/2025
It appears that the CDC has removed its guidelines for contraception and STIs. www.cdc.gov/contraceptio...
68440
Reposted by Theodore Pak
Dr. Becca @docbecca.bsky.social · 31/01/2025
The entire website for the NIH Office of Research on Women's Health (ORWH) is very nearly stripped bare. This is so, so devastating. orwh.od.nih.gov/research/fun...
orwh.od.nih.gov
43973615
Reposted by Theodore Pak
Matthew Herper @matthewherper.bsky.social · 31/01/2025
It's one thing to take down pages talking about diversity in science. It's another thing entirely to take down research databases that are used for observational studies. That is exactly what it seems just happened at the CDC. www.statnews.com/2025/01/31/c... www.statnews.com/2025/01/31/c...
statnews.com
CDC removes data on sexual orientation, gender identity from website
Data from an expansive federal survey on youth behavioral habits, including their sexual orientation and gender identity, have been removed from the website of the CDC.
57940
Reposted by Theodore Pak
Courtney Boen @courtneyboen.bsky.social · 31/01/2025
🚨If you use public data products from the CDC or other US federal agencies 🚨 Download them NOW [This is how I’m spending my Friday]
46943
Reposted by Theodore Pak
BK. Titanji @boghuma.bsky.social · 30/01/2025
I'm just here to say for the 2nd week in a row, the CDC has not released its morbidly and mortality weekly report on schedule. Everyone who provides healthcare to patients in the US is less informed and less up to date as a direct result. This impacts negatively at the population level.
9515179
Reposted by Theodore Pak
Paul Sax @paulsaxmd.bsky.social · 25/01/2025
The communications pause for federal health agencies meant that the CDC couldn't publish the MMWR this week -- the first time in the publication's 60+ year history this has happened. Unhappy about this! Getting good data published on infectious threats is critical, especially as H5N1 looms. #IDSky
blogs.jwatch.org
Let's Hope the MMWR Resumes Publication Sooner Rather Than Later
To us specialists in Infectious Diseases, there are certain verities we hold near and dear to our hearts: Antibiotics are miracle drugs, but the bugs will become resistant if we don’t use them respons...
212245
Theodore Pak @tedpak.bsky.social · 19/12/2024
Board certified! Glad that I'm now officially qualified to wear sunglasses while ranting about doxycycline, the definition of "FUO," and Streptococcus taxonomy controversies 😎
5140
Reposted by Theodore Pak
Yaneer Bar-Yam @yaneerbaryam.bsky.social · 02/12/2024
New: Universal masking&testing reduce hospital infections, so does staff masking Stopping universal masking&testing led to 25% increase in respiratory viral infections Restarting staff masking led to 33% decrease 8 out of 100 (random sample) died in the hospital jamanetwork.com/journals/jam...
jamanetwork.com
Testing and Masking Policies and Hospital-Onset Respiratory Viral Infections
This cohort study examines the ratio between hospital- and community-onset respiratory viral infections at different levels of testing and masking from 2020 to 2024.
441383528
Reposted by Theodore Pak
🇨🇦Joe Vipond🇨🇦 @jvipondmd.bsky.social · 29/11/2024
short thread on this important paper I reviewed today: www.acpjournals.org/doi/10.7326/... Morbidity and Mortality of Hospital-Onset SARS-CoV-2 Infections Due to Omicron Versus Prior Variants 1/
35617
Theodore Pak @tedpak.bsky.social · 29/11/2024
So, this bloot about my paper blew up. Most common reaction: Duh! You need proof that masking in hospitals works? The reality: Yes, many healthcare epidemiologists, including CDC advisors, have advocated for weaker guidance on masking and testing. Read on... 1/🧵 #IDSky #MedSky
1219678
Theodore Pak @tedpak.bsky.social · 28/11/2024
This Thanksgiving, let's thank hospitals that use masking during winter respiratory virus season. Out in JAMA Network Open: Hospital-onset flu, COVID, and RSV rates when 10 Mass Gen Brigham sites stopped universal testing & masking, then restarted staff masking in Jan 2024. 0/🧵 #IDSky #MedSky
711633
Theodore Pak @tedpak.bsky.social · 28/11/2024
Two amusing cases of asking GPT-4o and Llama3.2 to interpret medical images GPT-4o gives serious consideration to inserting iron tablets into the ears, and reads an X-ray backwards (right vs left) Original source: composio.dev/blog/meta-ll...
030
Reposted by Theodore Pak
Paul Sax @paulsaxmd.bsky.social · 27/11/2024
Thanksgiving already! Time for an annual round-up of some ID things to be grateful for. (Plus a bonus few non-ID items.) Enjoy! #IDSky
blogs.jwatch.org
Some ID Things to Be Grateful for This Holiday Season — 2024 Edition
The calendar says it’s nearly the fourth Thursday of November, so here in the United States, the Thanksgiving holiday is upon us. It’s a day when we gather with family and friends to express thanks, t...
36918
Theodore Pak @tedpak.bsky.social · 26/11/2024
Solving the "onion problem": where do you point the knife when slicing a half-onion to make the most uniform pieces from all the layers? Answer: 55.7% of the radius below the center of the onion Assuming a spherical onion, and with a whole lot of math: medium.com/@drspoulsen/...
120