search

chl8856 / Dynamic-DeepHit

Dynamic-DeepHit: A Deep Learning Approach for Dynamic Survival Analysis With Competing Risks Based on Longitudinal Data
65 stars 38 forks source link

Censoring and uncensored - Same likelihood ? #3

Open Jeanselme opened 3 years ago

Jeanselme commented 3 years ago

Hello,

I was wondering if this is normal that the likelihood for censored and uncensored data is computed the same way, shouldn't tmp1 and tmp2 (lines 233 and 237) be different ? I think the current way is correct for uncensored data but I might have missed something ?

EthanSteinberg commented 1 year ago

@Jeanselme Just wondering, were you ever able to resolve this? I'm looking through this code base as well and I am very confused.

Jeanselme commented 1 year ago

@EthanSteinberg , I coded an alternative Pytorch implementation to tackle this issue (It might have its own issues though)