Timezone: »
The application of deep learning in survival analysis (SA) allows utilizing unstructured and high-dimensional data types uncommon in traditional survival methods. This allows to advance methods in fields such as digital health, predictive maintenance, and churn analysis, but often yields less interpretable and intuitively understandable models due to the black-box character of deep learning-based approaches.We close this gap by proposing 1) a multi-task variational autoencoder (VAE) with survival objective, yielding survival-oriented embeddings, and 2) a novel method HazardWalk that allows to model hazard factors in the original data space. HazardWalk transforms the latent distribution of our autoencoder into areas of maximized/minimized hazard and then uses the decoder to project changes to the original domain. Our procedure is evaluated on a simulated dataset as well as on a dataset of CT imaging data of patients with liver metastases.
Author Information
Tobias Weber (LMU Munich)
Michael Ingrisch (Ludwig-Maximilians-Universität München)
Bernd Bischl (LMU Munich)
David Rügamer (LMU Munich)
Related Events (a corresponding poster, oral, or spotlight)
-
2021 : Towards modelling hazard factors in unstructured data spaces using gradient-based latent interpolation »
Dates n/a. Room
More from the Same Authors
-
2021 : OpenML Benchmarking Suites »
Bernd Bischl · Giuseppe Casalicchio · Matthias Feurer · Pieter Gijsbers · Frank Hutter · Michel Lang · Rafael Gomes Mantovani · Jan van Rijn · Joaquin Vanschoren -
2021 : Survival-oriented embeddings for improving accessibility to complex data structures »
Tobias Weber · Bernd Bischl · David Ruegamer -
2021 : Identifying the atmospheric drivers of drought and heat using a smoothed deep learning approach »
David Rügamer -
2022 : What cleaves? Is proteasomal cleavage prediction reaching a ceiling? »
Ingo Ziegler · Bolei Ma · Ercong Nie · Bernd Bischl · David Rügamer · Benjamin Schubert · Emilio Dorigatti -
2022 : Uncertainty-aware predictive modeling for fair data-driven decisions »
Patrick Kaiser · Christoph Kern · David Rügamer -
2021 Poster: Explaining Hyperparameter Optimization via Partial Dependence Plots »
Julia Moosbauer · Julia Herbinger · Giuseppe Casalicchio · Marius Lindauer · Bernd Bischl