CSBN: a hybrid approach for survival time prediction with missing data
File(s)
Published version
Author(s)
Rabinowicz, Simon
Butz, Raphaela
Hommerson, Arjen
Williams, Matthew
Type
Conference Paper
Abstract
CSBN: A Hybrid Approach For Survival TimePrediction With Missing DataSimon Rabinowicz1, Raphaela Butz2,3, Arjen Hommersom3,4, and Matt Williams5,61Faculty Of Medicine, Imperial College London, UK2Institute for Computer Science, TH K ̈oln, Germany3Department of Computer Science, Open University of the Netherlands4Department of Software Science, Radboud University, The Netherlands5Department of Radiotherapy, Charing Cross Hospital, London, UK6Computational Oncology Laboratory, Imperial College London, UKAbstract.Survival prediction models most commonly use Cox Proportional Hazards (CPH) models, and are frequently used in medical statistics and clinical practice. However, such models underperform when the predictor variables are missing. By building Bayesian networks we automatically construct a model with the most important risk factors and relationships between risk factors and Bayesian networks are able to infer the likely values of missing data. We therefore propose a hybrid solution, consisting of a CPH model and a BN, where the predictive variables in the CPH model are the child nodes of a BN, which we call CSBN. We learn the CPH and BN models separately, using standard techniques, with the only constraint being that the variables that are predictors in the CPH model are child nodes in the BN. This allows us to fuse the two models, using the predictors of the CPH models as the join points. We test our approach by examining the performance of the CPH model, against the hybrid CSBN model, using both complete data cases and in cases with missing data. We calculate the performance of the survival prediction for both CPH and CSBN using the C-index and a normalised error function as metrics. For the CPH model, predictive error was significantly larger for missing data (±3120.8 days) compared to complete data (±1171.5 days;p= 3.6e−07). This was also true for the CSBN±1387.3 days for missing data compared with±1171.5 days with complete data (p= 0.01568). However, with missing data, the predictive error was significantly larger for the CPH model (±3120.8 days) than theCSBN (±1171.5 days;p= 0.03274). In conclusion the CSBN methodology provides a more effective method of predicting survival when using incomplete data.
Date Issued
2018-09-10
Date Acceptance
2018-03-03
Citation
AALTD 18: 3nd ECML/PKDD Workshop on Advanced Analytics and Learning on Temporal Data, 2018
Journal / Book Title
AALTD 18: 3nd ECML/PKDD Workshop on Advanced Analytics and Learning on Temporal Data
Copyright Statement
© 2018 The Author(s).
Sponsor
Imperial College Healthcare NHS Trust- BRC Funding
Cancer Research UK
Grant Number
RDB01 79560
27434
Source
AALTD: 3nd ECML/PKDD Workshop on Advanced Analytics and Learning on Temporal Data
Publication Status
Published
Start Date
2018-09-10
Finish Date
2020-09-14
Coverage Spatial
Dublin, Ireland
Date Publish Online
2018-09-14