Sign in

Bennett Waxse

@bwaxse.bsky.social
2.7K followers 2.6K following 127 posts

Med-Peds ID Fellow Doing EHR Informatics Research | Driven by data, music, bicycle | Thoughts & typo-planting skill my own

PostsRepliesMedia
Bennett Waxse @bwaxse.bsky.social · 30/01/2026
I wrote up my approach in a blog post: bennettwaxse.com/blog/bioinfo... If you're a researcher curious about Claude Code, here's where I start. If you have a different workflow, I'd love to hear about it.
bennettwaxse.com
Using Claude Code for EHR Informatics: Getting Started, Part I
How I set up Claude Code for research informatics work in All of Us—from CLAUDE.md files to .claudeignore—and why context matters more than clever prompts.
020
Bennett Waxse @bwaxse.bsky.social · 30/01/2026
Why bother? Because LLM context windows are big enough to hold an entire project—so use them. Don't hide how you derived a cohort when that derivation can inform what you're asking the model to do next. 3/
100
Bennett Waxse @bwaxse.bsky.social · 30/01/2026
- #CLAUDE.md files that orient Claude to your project's structure, conventions, and domain quirks - Reference materials (data dictionaries, trusted queries), so the model knows what's actually in your tables - .claudeignore to prevent reading secrets, redundant files, or data you shouldn't share 2/
100
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
Bennett Waxse @bwaxse.bsky.social · 05/01/2026
Clearly a big fan of VZV vaccination as an ID doc, but I need to dig into this deeper before it makes its way into patient counseling for me. Curious what others took away from the sex-specific differences, and wonder if other types of analysis (e.g., TTE) might be better suited for this... 5/5
010
Bennett Waxse @bwaxse.bsky.social · 05/01/2026
Are we looking at detection bias? Do shingles episodes trigger cognitive screenings in women more readily? Is there a systematic difference in healthcare contacts between sexes? And we still don't know the mechanism: is it non-specific immunomodulation over VZV reactivation reduction? 4/
100
Bennett Waxse @bwaxse.bsky.social · 05/01/2026
First, this applies only to the live-attenuated vaccine, not Shingrix, which is now standard. Second (what's really nagging at me), the dementia protection really only appeared in women, even though the vaccine prevented shingles and post-herpetic neuralgia equally in both sexes (Table S3). 3/
100
Bennett Waxse @bwaxse.bsky.social · 05/01/2026
The 20% relative reduction in dementia risk is striking, and the regression discontinuity design is cool--particularly in the presence of no discontinuity among education (S15-S17) or in placebo temporal tests across other years (S12-S14). But, I was still left with more questions than answers. 2/
100
Bennett Waxse @bwaxse.bsky.social · 05/01/2026
What I've been reading: a natural experiment to estimate the herpes #zoster vaccine's effect on dementia--did you know that the effect was predominantly observed in females? pmc.ncbi.nlm.nih.gov/articles/PMC... 1/
pmc.ncbi.nlm.nih.gov
A natural experiment on the effect of herpes zoster vaccination on dementia
Neurotropic herpesviruses may be implicated in the development of dementia1–5. Moreover, vaccines may have important off-target immunological effects6–9. Here we aim to determine the effect of live-attenuated herpes zoster vaccination on the ...
100
Bennett Waxse @bwaxse.bsky.social · 01/01/2026
My daughters remind me daily why I'm lucky to call science work--not the grants or papers, but the pure pleasure of careful observation leading to discovery. Happy New Year, y'all. 4/4
020
Bennett Waxse @bwaxse.bsky.social · 01/01/2026
Getting back to work, I found similar joy. Staring at wearable data 180 days before COVID infection, discovering that people who developed Long COVID were already different 6 months before they got sick. Watching genetic signals shift depending on how we define disease in the same biobank. 3/
100
Bennett Waxse @bwaxse.bsky.social · 01/01/2026
Parental leave let me slow down and observe. Our daughter tracking me across the room for the first time. Tummy time shifting from torture to exploration. Our 3yo stringing together complex sentences about her day or her feelings. Capacities build invisibly, showing up in surprising ways. 2/
100
Bennett Waxse @bwaxse.bsky.social · 01/01/2026
There's something mesmerizing about watching an infant discover their smile. The way it floods the cheeks, squints the eyes, shakes down into the chest. They draw their gaze away--almost like it's too much--before turning back to do it all again. 1/
100
Reposted by Bennett Waxse
BK. Titanji @boghuma.bsky.social · 29/12/2025
The death of any child is tragic. We always think it will not be my child, they are healthy. Severe influenza can be unpredictable & deadly. Getting vaccinated considerably reduces dz severity and deaths. Please make sure you are vaccinated & your children are too. people.com/alabama-boy-...
people.com
Boy, 11, Dies After Severe Case of the Flu: ‘Jace Never Even Got to Open His Christmas Gifts’
Jace Watkins, 11, of Alabama died on Dec. 27 after being hospitalized due to complications from the flu.
32866325
Bennett Waxse @bwaxse.bsky.social · 28/12/2025
3. What did this look like in other states? There was a more muted response for a prior outbreak, but that was during a time of social isolation (COVID-19). Would love to see local vs. national effects. Overall, super cool study. As an ID doc, I’d love to get my hands on realtime EHR data! 5/5
100
Bennett Waxse @bwaxse.bsky.social · 28/12/2025
2. The study included a breakdown by age, but how does this look across social determinants of health? The study is restricted to those with regular healthcare access, so what happens to families not as well-resourced? Curious what data Truveta have in this domain. 4/
100
Bennett Waxse @bwaxse.bsky.social · 28/12/2025
1. An early dose doesn't count toward the official 2-dose series. So of course it’s too early now, but do parents here also get the doses at 12-15 months and 4-6 years that actually confer immunity? 3/
100
Bennett Waxse @bwaxse.bsky.social · 28/12/2025
Early MMR vaccination (6-11 months of age) jumped from a 0.7% baseline to 20.1% during the outbreak. That's a massive behavioral shift. What caught my attention most though is what else they could look at: 2/
100
Bennett Waxse @bwaxse.bsky.social · 28/12/2025
What I’m reading: a super cool real-time RWE EHR study by Truveta that assessed vaccination behavior during the recent Texas measles outbreak. jamanetwork.com/journals/jam... 1/
jamanetwork.com
Early MMR Vaccine Adoption During the 2025 Texas Measles Outbreak
This cross-sectional study examines early vaccination rates for measles in Texas following updated 2025 guidance from the US Centers for Disease Control and Prevention.
110
Bennett Waxse @bwaxse.bsky.social · 27/12/2025
Very curious to see how this project evolves in peer review, and whether that will occur before we start to see this model in action. I heard at a talk that they’re already thinking about deployment. Would love to hear from those with expertise in this domain. 6/6
000
Bennett Waxse @bwaxse.bsky.social · 27/12/2025
These research decisions, including the omission of social drivers of health, all matter and should be evaluated in work that can be as profound as something integrated in the most common US EHR. Overall, it reads like the project prioritized demonstrating scale over clinical utility. 5/
100
Bennett Waxse @bwaxse.bsky.social · 27/12/2025
The 90/10 random split and absence of statistical tests for comparison with task-specific baselines are interesting choices. No prospective validation (coding changes, prevalence shifts, new treatments). The margins over supervised baselines are small without CIs or multiple testing correction. 4/
100
Bennett Waxse @bwaxse.bsky.social · 27/12/2025
Figure 23 also stood out. Performance is best in low-risk populations (younger, healthier patients) compared to higher-risk groups (elderly with higher rates of heart disease or COPD). That's backwards from clinical utility. Is it just good at predicting healthy outcomes in healthy people? 3/
100
Bennett Waxse @bwaxse.bsky.social · 27/12/2025
But here's what caught me: the model omits vitals, and not for computational reasons. When I think of differential severity for a given condition (e.g., COPD exacerbation, or sepsis), what better way to ascertain severity? Are lab quantiles and meds really enough? 2/
100
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
Bennett Waxse @bwaxse.bsky.social · 02/06/2025
12/ As an ID fellow doing EHR research, this represents my path toward independence - using informatics to understand host-pathogen interactions. Huge thanks to Josh Denny lab at NHGRI, #AllofUs Research Program, and www.niaid.nih.gov/about/infect... for making this possible! 🙏 #MedSky #IDSky
niaid.nih.gov
Infectious Diseases Clinical Fellowship Program
The NIAID Infectious Diseases Fellowship Program provides training for internal medicine and pediatric residents interested in academic careers.
020
Bennett Waxse @bwaxse.bsky.social · 02/06/2025
11/ For the #IDSky #EpiSky #AcademicSky community: What other episodic infectious diseases need computable phenotypes? UTIs? Pneumonia subtypes? C. diff? I'm building expertise in ID EHR methods - reach out for collaborations! Always happy to help with phenotyping approaches in and out of ID.
120
Bennett Waxse @bwaxse.bsky.social · 02/06/2025
10/ What's next from our NHGRI lab: 🧬 GWAS to identify genetic risk factors for severe respiratory infections 📈 Clinical determinants of hospitalization across viruses 💊 Diagnostic stewardship for multiplex respiratory panels Phenotypes are just the beginning! #IDSky
100
Bennett Waxse @bwaxse.bsky.social · 02/06/2025
9/ Important caveats (transparency matters): Low sensitivity = can't estimate true prevalence #AllofUs demographics ≠ general US population Oversamples severe disease, misses mild infections Remember: Always validate your phenotypes But, methods likely applicable to any US EHR dataset
100
Bennett Waxse @bwaxse.bsky.social · 02/06/2025
8/ Want to use these phenotypes or create your own EHR methods? Let's collaborate! 🤝 ✨ Code available in #AllofUs Community Workspace 🧬 Perfect for GWAS, health disparities, clinical outcomes research 📊 Framework adaptable to other episodic infectious diseases DM me - my passion is EHR phenotyping
100
Bennett Waxse @bwaxse.bsky.social · 02/06/2025
7/ Unexpected finding: Our phenotype oversamples severe disease 🏥 Non-flu/non-COVID viruses showed high hospitalization rates vs. known epidemiology. Why? Limited outpatient testing No specific treatments = less testing motivation Diagnostic value mainly in hospital settings
levels of care by virus and by phenotype composition. more intense bars are higher level of care (e.g., hospitalization)
110
Bennett Waxse @bwaxse.bsky.social · 02/06/2025
6/ Our phenotypes matched CDC surveillance beautifully 🎯 ✅ Expected seasonal patterns ✅ Geographic distribution aligned with national data ✅ Virus type proportions matched NREVSS/GISRS Mean absolute error: <6% for all viruses vs CDC positivity rates
test percent positivity for All of Us (gray) and CDC (blue) cohorts by virus, over timevirus type proportions for those with available data
100
Bennett Waxse @bwaxse.bsky.social · 02/06/2025
5/ Plot twist: COVID disrupted everything 😷 Common coronavirus ICD codes spiked during the pandemic (clinicians coding concern for COVID) despite no positive tests. Excluding hCoV codes after Feb 2020 corrected counts and PPV. Lesson: Always validate phenotypes across time periods!
hCOV PPV and episode counts during the COVID pandemic.
100
Bennett Waxse @bwaxse.bsky.social · 02/06/2025
4/ Performance varied dramatically by virus: High ICD sensitivity: Influenza (67%), RSV (55%) Moderate: COVID-19, adenovirus, hMPV (33-45%) Low: Rhinovirus (9%), parainfluenza (8%) But, PPV was consistently high (90-97%) for non-flu/non-COVID viruses 📈
specificity, PPV, and sensitivity by virus and phenotype composition.
100
Bennett Waxse @bwaxse.bsky.social · 02/06/2025
3/ Our approach combines 3 data types within 90-day episodes: 🔹 Virus-specific ICD codes (e.g., J12.1 for RSV pneumonia) 🔹 Laboratory results (PCR, antigen, culture) 🔹 Antiviral prescriptions (flu/COVID only) This integration > any single component alone, with varying breakdowns by virus.
Schematic for computable phenotype and heatmap of detected cohorts.
120
Bennett Waxse @bwaxse.bsky.social · 02/06/2025
2/ Why does this matter? 🤔 Respiratory infections are the most common human diseases, but research typically focuses on influenza, RSV, and COVID-19. Meanwhile, rhinovirus, hMPV, PIV, and common coronaviruses cause comparable illness but remain understudied. #EHRphenotyping could unlock this. #IDSky
110
Bennett Waxse @bwaxse.bsky.social · 02/06/2025
🧵How do you study 8 respiratory viruses across 265K (now 369K) patients across the US? We built computable phenotypes using #AllofUs EHR data - out now in Scientific Reports! 📊 Spoiler: performance varies wildly by pathogen 🔗 nature.com/articles/s41598-025-02183-9 #IDSky #EpiSky
nature.com
Computable phenotypes to identify respiratory viral infections in the All of Us research program - Scientific Reports
Scientific Reports - Computable phenotypes to identify respiratory viral infections in the All of Us research program
161
Bennett Waxse @bwaxse.bsky.social · 06/04/2025
#VaccinesSaveLives
020
Bennett Waxse @bwaxse.bsky.social · 01/04/2025
Good people trying to do good work because they believe in the promise of science. This is a dark, difficulty day for the NIH. www.nature.com/articles/d41...
nature.com
‘One of the darkest days’: NIH purges agency leadership amid mass layoffs
In shock move, four institute directors at the US biomedical agency are removed from their posts.
020
Reposted by Bennett Waxse
Altmetric @altmetric.com · 27/03/2025
THREAD The numbers are in. @bsky.app research sharing volumes vs X Formerly Twitter In March 2024, on most days, Bluesky hosts more posts linked to research published in 2025 than X. By quite a lot. Release the Kraken... #AcademicSky #HigherEd #Altmetrics 1/11
Butterflies on a blue sky
181211462
Reposted by Bennett Waxse
Mark Peifer (He, him) @peiferlabunc.bsky.social · 26/03/2025
14 pages of terminated NIH grants--everyone should read through the list. The sweep is VERY broad, including "The Impact of the Herpes Zoster Vaccine on Herpes Zoster Ophthalmicus" & "Mitochondrial-based Determinants of Sex Differences in Acute Kidney Injury"🧪 1/n taggs.hhs.gov/Content/Data...
taggs.hhs.gov
22681344
Bennett Waxse @bwaxse.bsky.social · 16/03/2025
“It is a strength of the scientific enterprise that we have diverse ideas, identities, and approaches to communication...just as leaders deserve some leeway to decide when to speak out most effectively, they should support their constituencies by not trying to squelch or steer more strident voices.”
science.org
Come together, right now
The chaos, conflicting information, firings, and hurtful rhetoric of the Trump administration’s approach to science over the past month are causing anxiety, grief, and concern for the scientific commu...
031
Reposted by Bennett Waxse
Prof Christina Pagel @chrischirp.bsky.social · 12/03/2025
🧵Censor, purge, defund - how Trump is following the authoritarian playbook on science & universities. This isn't chaos - it's deliberate & well-established methods. I've mapped 40 actions into 3 categories covering attacks on science, attacks on universities and international collaboration. 1/16
29934508
Reposted by Bennett Waxse
southpaw @nycsouthpaw.bsky.social · 12/03/2025
A lot of people who got the measles as children died or suffered lifelong disabilities as a result. The measles vaccine was a godsend to worldwide public health, and it’s an absolute scandal that this lethally ignorant dolt has any power over public health.
Logarithmic chart showing the case and death rates for measles in the USA per 100,000 population. The chart maps dramatic near total declines in both over the last century.
37184342424
Bennett Waxse @bwaxse.bsky.social · 12/03/2025
What an important conversation. Thanks for putting it out there!
010
Reposted by Bennett Waxse
Timothy Caulfield @caulfieldtim.bsky.social · 10/03/2025
Are we surprised? No. Horrifying? Yep. Dark Age 2.0. NIH to terminate or limit grants related to vaccine hesitancy and uptake wapo.st/3Dw7WG0
wapo.st
NIH to terminate or limit grants related to vaccine hesitancy and uptake
The order covers more than 40 awards to researchers around the country seeking to understand why vaccine acceptance has declined.
622962
Bennett Waxse @bwaxse.bsky.social · 10/03/2025
The data shouts for itself. (Yes, data is plural, but it didn’t sound as good to me.)
010
Bennett Waxse @bwaxse.bsky.social · 10/03/2025
Disrupted “treatment and diagnosis during the Covid pandemic resulted in doctors seeing “more complicated” forms of TB, Ditiu said, including some with holes in their lungs. It was a pattern she expected to see repeated, particularly among the poor and vulnerable.” Chillingly bad US policy on this
010
Bennett Waxse @bwaxse.bsky.social · 10/03/2025
2 deaths from measles w/ most “cases across [TX, NM] in people < 18 and people who are unvaccinated or have an unknown vaccination status.” This IS unusual #vaccinate #VaccinesSavesLives #IDSky #EpiSky apnews.com/article/measles-texas-new-mexico-deaths-mmr-vaccine-a1295c78fade561479da65d72d8a5774
apnews.com
West Texas reports nearly 200 measles cases. New Mexico is up to 30
Health officials say West Texas now has almost 200 measles cases and New Mexico's case number has tripled to 30. The case counts were updated on Friday.
000
Bennett Waxse @bwaxse.bsky.social · 09/03/2025
DC! So lovely seeing all of the activity across the world for #standupforscience2025.
020