9. Temporal Health Data Flashcards

1
Q

what are some considerations when working with EHR data

A
  • contains many vars e.g. patient reaction to treatment, demographics, prescribed medication, radiographs
  • different data types = images, text, numbers
  • time intervals are different, different levels of detail
  • sparse data i.e. different patients get different tests, some may never require a particular test
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

what model can help to solve temporal data gaps

A

time series forecasting

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

what is cross validation

A
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

what is backtesting with refit

A
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

what is backtesting without refit

A
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

what is a use case for recurrent neural networks

A
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

what is the recurrent neural network algorithm

A
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q
A
How well did you know this?
1
Not at all
2
3
4
5
Perfectly