Cardiologist and scientist @MGHHearthealth @harvardmed fascinated by statistics, genomics @broadinstitute, and exploring the world on two wheels.
Boston, MA
- Tweets 149
- Following 425
- Followers 1,109
- Likes 582
Pinned Tweet
One of my first consults as a cardiology fellow: a 34-year-old, textbook MI. A day earlier, no risk model would have flagged him for prevention. That paradox has driven my work ever since — our models miss how disease actually evolves, dynamically, on top of a genetic background. @Nature nature.com/articles/s41586-0…
14
71
239
67,521
Sarah Urbut retweeted
Accurately predicting an individual's health arc is a dream that has not been previously possible. Now we're headed there, thanks to a new @nature paper by @tigerstatdoc and team. Our conversation and annotations in the new Ground Truths
16
64
420
43,369
Nature research paper: A Bayesian framework for longitudinal EHR and genetic discovery
go.nature.com/4vDLFv4
2
18
114
27,825
Congratulations @tigerstatdoc & team!
#bwfcams
One of my first consults as a cardiology fellow: a 34-year-old, textbook MI. A day earlier, no risk model would have flagged him for prevention. That paradox has driven my work ever since — our models miss how disease actually evolves, dynamically, on top of a genetic background. @Nature nature.com/articles/s41586-0…
1
1
3
1,871
Sarah Urbut retweeted
Very exciting new method for inferring latent disease trajectories, led by the tireless Dr. Urbut with Natarajan and Parmigiani labs. If you're considering a postdoc in this area talk to Sarah!
One of my first consults as a cardiology fellow: a 34-year-old, textbook MI. A day earlier, no risk model would have flagged him for prevention. That paradox has driven my work ever since — our models miss how disease actually evolves, dynamically, on top of a genetic background. @Nature nature.com/articles/s41586-0…
2
10
67
9,654
Sarah Urbut retweeted
Very excited for this work led by @tigerstatdoc along with @SashaGusevPosts @g_parmigiani now in @Nature!
Wonderful collaboration across @MGBResearchNews @DanaFarber @broadinstitute @harvardmed @HarvardBiostats
One of my first consults as a cardiology fellow: a 34-year-old, textbook MI. A day earlier, no risk model would have flagged him for prevention. That paradox has driven my work ever since — our models miss how disease actually evolves, dynamically, on top of a genetic background. @Nature nature.com/articles/s41586-0…
3
13
87
21,810
Sarah Urbut retweeted
Check out @tigerstatdoc's thread if this topic interests you and we'll break it down on Friday
One of my first consults as a cardiology fellow: a 34-year-old, textbook MI. A day earlier, no risk model would have flagged him for prevention. That paradox has driven my work ever since — our models miss how disease actually evolves, dynamically, on top of a genetic background. @Nature nature.com/articles/s41586-0…
1
9
35
16,263
Sarah Urbut retweeted
Predicting a person's health and disease arc many years in advance from their electronic health records and polygenic risk scores, along with the biological mechanism for the diseases
just published @Nature
Will be discussing the paper with the brilliant lead author @tigerstatdoc this Friday in Ground Truths 10:30 AM PST
nature.com/articles/s41586-0…
5
117
565
77,547
One of my first consults as a cardiology fellow: a 34-year-old, textbook MI. A day earlier, no risk model would have flagged him for prevention. That paradox has driven my work ever since — our models miss how disease actually evolves, dynamically, on top of a genetic background. @Nature nature.com/articles/s41586-0…
14
71
239
67,521
Two things evolve smoothly in time: the signatures themselves (φ), and each person's loading on them (λ) — anchored in germline genetics, so the model builds from and reveals new biology, rather than black box artifacts. Then Bayesian updating does the work: every new diagnosis refines the estimate, turning past into present into a prediction of the future. Every parameter is interpretable and described in our generative framework, scaled to work with biobank level data.
1
10
1,187
In summary, we have a model that discovers and predicts: 151 genome-wide significant loci, biological subtypes inside single diagnoses, and 348-disease that outperforms existing clinical tools. Years in the making, SO thankful for an incredible team!!! Paper, code, interactive results: surbut.github.io/aladynoulli… @pnatarajanmd @SashaGusevPosts @g_parmigiani @MGHHeartHealth @harvardmed @broadinstitute @BWFUND
1
4
25
1,160
The recording of "Bayes in Action: Inspiration, observation, perspiration" by @tigerstatdoc is now available: piped.video/Ne5cffjhOY8. This talk is part of @broadinstitute's MPG Primer series. For more info, check out broad.io/MPGPrimer.
4
11
1,716
Sarah Urbut retweeted
Kick off the PQG Working Group Seminar Series with Dr. Urbut's fascinating research! Join us next Tuesday (Mar 24)!
1
3
10
1,929
Sarah Urbut retweeted
Many thanks @drjohnm. Fully agree with you. For that reason, I’m excited by this work led by @tigerstatdoc & with @SashaGusevPosts G. Parmigiani modeling numerous health trajectories simultaneously in interpretable fashion to better predict & prioritize medrxiv.org/content/10.1101/…
3
10
1,666