Deep conditional transformation models for survival analysis
This is an incremental improvement for clinical trials and survival analysis, enabling parametric and semiparametric modeling with non-linear hazards for various data types.
The authors tackled the problem of survival analysis with non-tabular data by proposing deep conditional transformation models (DCTMs), which compete with state-of-the-art deep learning approaches on real and semi-synthetic data.
An every increasing number of clinical trials features a time-to-event outcome and records non-tabular patient data, such as magnetic resonance imaging or text data in the form of electronic health records. Recently, several neural-network based solutions have been proposed, some of which are binary classifiers. Parametric, distribution-free approaches which make full use of survival time and censoring status have not received much attention. We present deep conditional transformation models (DCTMs) for survival outcomes as a unifying approach to parametric and semiparametric survival analysis. DCTMs allow the specification of non-linear and non-proportional hazards for both tabular and non-tabular data and extend to all types of censoring and truncation. On real and semi-synthetic data, we show that DCTMs compete with state-of-the-art DL approaches to survival analysis.