AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Time-to-Event Prediction with Neural Networks and Cox Regression

Håvard Kvamme, Ørnulf Borgan, Ida Scheel

JMLR 2019 · Learning theory and algorithms › Prediction and decision losses · approach: Losses for decision-making · 311 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use non-proportional Cox-Time instead of Cox-MLP (CC)Cox neural network · KKBox churnintegrated Brier score: 0.119 -> 0.107Improved
use non-proportional Cox-Time instead of Cox-MLP (CC)Cox neural network · KKBox churntime-dependent concordance: 0.844 -> 0.861Improved
use Cox-Time instead of classical linear CoxCox model · SUPPORTtime-dependent concordance: 0.598 -> 0.629Improved
use Cox-Time instead of classical linear CoxCox model · METABRICtime-dependent concordance: 0.628 -> 0.662Improved
use Cox-Time instead of DeepHitsurvival network · FLCHAINintegrated Brier score: 0.120 -> 0.102Improved
tune DeepHit by concordance (small alpha, more ranking loss)DeepHit · KKBox churnintegrated Brier score: 0.147 vs 0.107Hurt
tune RSF with Ctd instead of mortality concordance (ablation)RSF · KKBox churntime-dependent concordance: 0.855 -> 0.870Improved
tune RSF with Ctd instead of mortality concordance (ablation)RSF · SUPPORTtime-dependent concordance: 0.628 -> 0.634Improved
case-control sampling loss (Cox-MLP CC) instead of batch partial likelihood (DeepSurv) (ablation)proportional Cox MLP · SUPPORTtime-dependent concordance: 0.611 -> 0.613No clear effect
sample more controls (1,2,4,8) in Cox-SGD loss (ablation)Cox-SGD · simulationmean partial log-likelihood convergenceNo clear effect
sample more controls in Cox-SGD on small datasets (ablation)Cox-SGD · simulation (n=100)mean log-likelihood vs classical CoxImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy