Siamese Survival Analysis with Competing Risks

TL;DR

This paper introduces SSPN, a deep learning model that estimates personalized risks in competing risks survival analysis by avoiding nonidentifiability issues and directly optimizing risk discrimination metrics.

Contribution

The paper presents SSPN, a novel deep learning architecture that bypasses the nonidentifiability problem in competing risks survival analysis and optimizes risk discrimination directly.

Findings

SSPN effectively estimates risk scores without needing cause-specific survival curves.

SSPN directly optimizes the C-discrimination index, improving risk prediction.

The model demonstrates superior performance in personalized risk estimation.

Abstract

Survival analysis in the presence of multiple possible adverse events, i.e., competing risks, is a pervasive problem in many industries (healthcare, finance, etc.). Since only one event is typically observed, the incidence of an event of interest is often obscured by other related competing events. This nonidentifiability, or inability to estimate true cause-specific survival curves from empirical data, further complicates competing risk survival analysis. We introduce Siamese Survival Prognosis Network (SSPN), a novel deep learning architecture for estimating personalized risk scores in the presence of competing risks. SSPN circumvents the nonidentifiability problem by avoiding the estimation of cause-specific survival curves and instead determines pairwise concordant time-dependent risks, where longer event times are assigned lower risks. Furthermore, SSPN is able to directly optimize an approximation to the C-discrimination index, rather than relying on well-known metrics which are unable to capture the unique requirements of survival analysis with competing risks.