Logo

Stanford Center for Biomedical Informatics Research Colloquia - Shared screen with speaker view
Justin Miller
14:09
Excuse me, I was accidently moved into the attende list, could I go back to the panel bored please?
Justin Miller
14:23
board*
jonathan chen
21:19
Feel free to enter Q&A in to Q&A box
jonathan chen
47:21
Great thread of questions rolling in. We'll get to them in the next discussion break
jonathan chen
48:21
Questions pending: Ensuring distribution between training vs. validation sets is the same good enough?
jonathan chen
48:39
Is external validity essential if going to apply models locally?
jonathan chen
48:49
Why report sample size if 1M training data?
jonathan chen
49:07
Amin Adibi: Sometimes clinical journal reviewers ask for non-ideal methods
jonathan chen
50:20
You can post question to Q&A box
tina hernandez boussard
55:03
Moving forward, How do these models account for the drastic changes that we have seen as we learn more about COVID - going from a ~45% mortality rate in the onset of the pandemic to lower than 2% now; data collected from early pandemic can not accurately predict outcomes in 2021 given the changes in treatment etc. Is this ever taken into consideration?
Daniel Rubin
01:02:48
How do you update these models, doesn’t that require hospitals to share real-time data? Will they do that?
Amin Adibi
01:05:23
Does it even make sense to attempt develop prediction models for COVID? Aren’t prediction models more useful in case of well-understood diseases where we are trying to incrementally improve care? Does it even make sense to attempt prediction models for COVID-19, when we are not very well aware of disease mechanisms, and hardly know how to use predictions to guide treatment?
jonathan chen
01:10:27
Do yo uwant me to open your mic, or just post your message/question?