Keynote:
Why epidemics are harder to forecast than the weather? (Jeff Shaman has a good graphic)
- uncertainty only exists in the future for weather
- uncertainty is in both the past *and* futre for epidemiology
Recent searches
Search options
#Amia
0 posts0 participants0 posts today
Keynote:
Common Approaches to Epidemic Forecasting:
- Mechanistic Approaches (you're painting a picture, telling a story)
-- compartmental models (e.g., S-I-R, S-E-I-R-S)
-- agent-based models (individual-level simulation)
- Non-Mechanistic (no story)
-- statistical/machine learning, e.g., SARIMA
- Semi-Mechanistic: data assimilation
- Wisdowm-of-the-Crowds: aggregated human judgement
Keynote:
French group in the 2000's was first to post flu forecasts in real time. (Commentary: wow, that seems so recent.)
Keynote:
Weather forecasting took about 160 years to get as "good" as we are at it now.
Keynote:
What kind of epidemics are forecastable?
- one of a kind events? No. Too rare to meaningfully evaluate.
- Across seasons? Eventually but not the focus of speakers work.
- Within season or short term? Yes.
Keynote:
Why don't we have local health/epidemic forecasts exactly like local weather reports?
Keynote Intro:
AI Themes in submission - implementation, evaluation, maturity, ethics
#AMIA2024 is coming up next week. Pre-symposium workshops start tomorrow. I'm going to try to be a little more vocal (posty?) during the conference this year. We'll see how I manage. Come find if you're attending #AMIA's Annual Symposium (Unfortunately, they're still on Twitter: @amiainformatics)
Register here to see me give a talk this Tuesday at noon Eastern (US) time: https://amia.org/webinar-library/behavioral-testing-and-evaluation-probe-language-models-algorithmic-bias
I'll be talking about using #BehavioralTesting to probe for #AlgorithmicBias in several of my clinical #NLP projects as part of #AMIA's Working Group Webinar Series
AMIA - American Medical Informatics AssociationBehavioral Testing and Evaluation to Probe Language Models for Algorithmic BiasWith growing legal and scientific evidence for the importance of reducing model bias, both model developers and deployers need tools to quantify the bias. Unfortunately, algorithmic bias can take as many forms as there are implementations. In this talk, Paul M. Heider covesr a range clinical NLP use cases like de-identification and predicting diagnoses, highlighting the utility of behavioral testing and comparative evaluation methods to identify the scope of a model’s bias.
Heute jährt sich in #Argentinien der Bombenanschlag auf das Gebäude der jüdischen Hilfsorganisation #Amia zum 30. Mal. Die Angehörige Laura Ginsberg sieht den Staat in der Verantwortung. https://www.nd-aktuell.de/artikel/1183798.argentinien-buenos-aires-keine-gerechtigkeit-fuer-die-terroropfer.html
nd-aktuell.deBuenos Aires: Keine Gerechtigkeit für die TerroropferAm Donnerstag jährt sich in Argentinien der Bombenanschlag auf das Gebäude der jüdischen Hilfsorganisation Amia zum 30. Mal. Die Angehörige Laura Ginsberg sieht den Staat in der Verantwortung.
What needs to be in a good progress note? There's a whole lot of controversy about that. Want to know what DOES NOT belong in a good progress note? Ahhh, that we can help you with! Join this #AMIA webinar with me and Aaron Grigg, MD. #NoteBloat https://amia.org/webinar-library/write-notes-you-want-read-not-ones-your-biller-used-require
We are organizing a #CHI2024 workshop on doing research in HCI, HCD, and health, with a focus on building and supporting teams with diverse expertise! Remote and in-person options for participation bit.ly/HCIHealthTeams! #HCI
#HCD #CSCW #MedInf #AMIA #ImplementationScience #PublicHealth #TeamScience
Excited to share the call for participation in a workshop on Conducting Research at the Intersection of HCI, HCD, and Health, with a focus on building and sustaining teams with different expertise. https://bit.ly/HCIHealthTeams
Options for participating virtually or co-located with CHI 2024.
sites.uci.eduConducting Research at the Intersection of HCI and Health
Looking to follow #Biomedical & #Health #Informatics & #DataScience folks? Check out this directory! Pls boost!
https://sites.google.com/view/informaticsdirectory
#BiomedicalInformatics #Bioinformatics #ClinicalInformatics #PublicHealthInformatics
#AcademicChatter #PhDLife #ConsumerHealthInformatics
#AMIAInformatics #AMIA #MedInfo #IMIA #CMIO #EHR #MedMastodon #CDS #MachineLearning #Telehealth #DigitalHealth #genomics #NursingInformatics #DataSharing #NLP
sites.google.comHome
Biomedical & Health Informatics Social Media Directory
Replied to Wayne Liang, MD MS FAMIA
@WayneLiangMD @lrasmus @healthinformatics @informatics
#MedInfodon makes more sense than #AMIA-odon. We'd still get some domain focus but also a lot more cross pollination than our current listserves and working groups make happen. That being said, I don't know. Is standing up a group instance the fedi equivalent of adopting a highway? You know, "We'll take care of the trash in this corner through supported moderation". I'm a fan of that.
Hey @lrasmus! Do you think anyone in the #AMIA #FOSS community with server admin background would be interested in spinning up an unofficial #AMIAInformatics #mastodon instance? A couple of folks have asked me about an AMIA one, and I doubt AMIA itself would do it.
I can see both pros and cons. Pro: we can find each other more easily and create tighter community. Cons: talking more to ourselves than to others?
Others' thoughts?
@healthinformatics @informatics #informatics #healthinformatics
Continued thread
My main professional organization is #AMIA with our #AMIAAnnualSymposium (see you at #AMIA2022) but I used to belong to #LSA (#LingSocAmerica).