This describes nearly all predictive modeling on EHR data
This is an important point for epidemiology too. Some of the questions we want to answer need complex methods, but many of our important questions could be answered much more easily if only we had the right, good quality data.https://twitter.com/hspter/status/1223315485128683522 …
-
-
-
Yup, for sure
Kraj razgovora
Novi razgovor -
-
-
Though often the right time to collect the ideal data would have been ten years ago, to allow for follow-up
-
(I've just been at a conference where people working with cohorts got told about exciting measurements that hadn't been invented at baseline)
- Još 1 odgovor
Novi razgovor -
-
-
I think this also highlights an important role epidemiologists within data science. Often Big Data assumes the increased precision afforded outweighs biases. But the increased precision can often do more harm!
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
This is absolutely the case. Also, we don't create sufficient systems around qualifying data. As a result we keep having to revert to the base data unnecessarily
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
It's a completely right!
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.