The survival filter: Joint survival analysis with a latent time series

Rajesh Ranganath, Adler Perotte, Noémie Elhadad, David M. Blei

Research output: Contribution to conferencePaper

Abstract

Survival analysis is a core task in applied statistics, which models time-to-failure or time-to-event data. In the clinical domain, for example, meaningful events are defined as the onset of different diseases for a given patient. Survival analysis is limited, however, for analyzing modern electronic health records. Patients often have a wide range of diseases, and there are complex interactions among the relative risks of different events. To this end, we develop the survival filter model, a time-series model for joint survival analysis that models multiple patients and multiple diseases. We develop a scalable variational inference algorithm and apply our method to a large data set of longitudinal patient records. The survival filter gives good predictive performance when compared to two baselines and identifies clinically meaningful patterns of disease interaction.

Original languageEnglish (US)
Pages742-751
Number of pages10
StatePublished - 2015
Event31st Conference on Uncertainty in Artificial Intelligence, UAI 2015 - Amsterdam, Netherlands
Duration: Jul 12 2015Jul 16 2015

Other

Other31st Conference on Uncertainty in Artificial Intelligence, UAI 2015
CountryNetherlands
CityAmsterdam
Period7/12/157/16/15

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint Dive into the research topics of 'The survival filter: Joint survival analysis with a latent time series'. Together they form a unique fingerprint.

  • Cite this

    Ranganath, R., Perotte, A., Elhadad, N., & Blei, D. M. (2015). The survival filter: Joint survival analysis with a latent time series. 742-751. Paper presented at 31st Conference on Uncertainty in Artificial Intelligence, UAI 2015, Amsterdam, Netherlands.