Learning Rich Geographical Representations: Predicting Colorectal Cancer Survival in the State of Iowa

TL;DR

This paper demonstrates that neural networks can effectively predict colorectal cancer survival curves in Iowa, with geographical features and spectral clustering-based representations significantly enhancing prediction accuracy.

Contribution

The study introduces a novel approach using spectral clustering-based geographical features to improve survival curve predictions for colorectal cancer patients.

Findings

Survival curves can be reasonably predicted with neural networks.

Geographical features improve predictive performance.

Spectral clustering-based features outperform binary representations.

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 2012. 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.