Timezone: »

Temporal Label Smoothing for Early Event Prediction
Hugo Yèche · Alizée Pace · Gunnar Ratsch · Rita Kuznetsova

Wed Jul 26 02:00 PM -- 03:30 PM (PDT) @ Exhibit Hall 1 #121

Models that can predict the occurrence of events ahead of time with low false-alarm rates are critical to the acceptance of decision support systems in the medical community. This challenging task is typically treated as a simple binary classification, ignoring temporal dependencies between samples, whereas we propose to exploit this structure. We first introduce a common theoretical framework unifying dynamic survival analysis and early event prediction. Following an analysis of objectives from both fields, we propose Temporal Label Smoothing (TLS), a simpler, yet best-performing method that preserves prediction monotonicity over time. By focusing the objective on areas with a stronger predictive signal, TLS improves performance over all baselines on two large-scale benchmark tasks. Gains are particularly notable along clinically relevant measures, such as event recall at low false-alarm rates. TLS reduces the number of missed events by up to a factor of two over previously used approaches in early event prediction.

Author Information

Hugo Yèche (ETH Zürich)
Alizée Pace (ETH Zurich)
Gunnar Ratsch (ETH Zurich)
Rita Kuznetsova (Swiss Federal Institute of Technology)

More from the Same Authors