Logo image
Back
Learning rich geographical representations: Predicting colorectal cancer survival in the state of Iowa
Conference proceeding

Learning rich geographical representations: Predicting colorectal cancer survival in the state of Iowa

Michael T Lash, Yuqi Sun, Xun Zhou, Charles F Lynch and W. Nick Street
2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Vol.2017-, pp.778-785
11/2017
DOI: 10.1109/BIBM.2017.8217754
url
https://arxiv.org/pdf/1708.04714View
Open Access

Abstract

Neural networks are capable of learning rich, nonlinear feature representations shown to be beneficial in many predictive tasks. In this work, we use these models to explore the use of geographical features in predicting colorectal cancer survival curves for patients in the state of Iowa, spanning the years 1989 to 2013. Specifically, we compare model performance using a newly defined metric - area between the curves (ABC) - to assess (a) whether survival curves can be reasonably predicted for colorectal cancer patients in the state of Iowa, (b) whether geographical features improve predictive performance, and (c) whether a simple binary representation or richer, spectral clustering-based representation perform better. Our findings suggest that survival curves can be reasonably estimated on average, with predictive performance deviating at the five-year survival mark. We also find that geographical features improve predictive performance, and that the best performance is obtained using richer, spectral analysis-elicited features.
 Geography Smoothing methods Neural networks Predictive models Indexes Spectral analysis Cancer

Details

Metrics

10 Record Views
Logo image