Timeline for Longitudinal survival data analysis: predict survival by a repeated measure over time
Current License: CC BY-SA 3.0
11 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 7, 2017 at 12:37 | vote | accept | alittleboy | ||
| Mar 31, 2017 at 18:01 | answer | added | David C. Norris | timeline score: 4 | |
| S Mar 31, 2017 at 14:50 | history | bounty ended | CommunityBot | ||
| S Mar 31, 2017 at 14:50 | history | notice removed | CommunityBot | ||
| Mar 29, 2017 at 21:38 | history | tweeted | twitter.com/StackStats/status/847201295131955200 | ||
| Mar 29, 2017 at 12:10 | comment | added | alittleboy |
@DavidC.Norris Thanks for your feedback. The disease types actually consist of different tumor types, such as lung cancer, breast cancer, ovarian cancer, etc. The real-world problem is to see if any trend (increasing/decreasing) lab parameter value taken at different time points can help predict the survival time, taking into account the heterogeneity of different tumor types (type).
|
|
| Mar 28, 2017 at 19:20 | comment | added | David C. Norris | I am heartened to see you starting your exploration with simulated data, and have an idea about how to answer your question usefully. But one thing I'll need to understand better is the meaning of these 'disease types'. Are these unrelated diseases, or do they represent grades/levels of severity of a given disease? Also, although I appreciate your aiming for abstraction, it would also help me to know more about the real-world problem in the background. | |
| Mar 23, 2017 at 13:20 | comment | added | bdeonovic | IN recent years there have been lots of papers that jointly analyzed longitudinal and survival data using a Bayesian framework. | |
| S Mar 23, 2017 at 13:13 | history | bounty started | alittleboy | ||
| S Mar 23, 2017 at 13:13 | history | notice added | alittleboy | Draw attention | |
| Mar 21, 2017 at 13:11 | history | asked | alittleboy | CC BY-SA 3.0 |