Personalized Prognostic Models for Oncology: A Machine Learning Approach

TL;DR

This paper introduces a novel data transformation for SEER cancer data enabling machine learning models to predict full survival curves, achieving high accuracy and generalization in survival prediction tasks.

Contribution

The study presents a new data transformation method for censored survival data, allowing standard classifiers to predict full survival curves with high accuracy.

Findings

AUC values between .765 and .885 for survival predictions

High agreement between Random Forest and neural network models

Effective handling of censored data in survival analysis

Abstract

We have applied a little-known data transformation to subsets of the Surveillance, Epidemiology, and End Results (SEER) publically available data of the National Cancer Institute (NCI) to make it suitable input to standard machine learning classifiers. This transformation properly treats the right-censored data in the SEER data and the resulting Random Forest and Multi-Layer Perceptron models predict full survival curves. Treating the 6, 12, and 60 months points of the resulting survival curves as 3 binary classifiers, the 18 resulting classifiers have AUC values ranging from .765 to .885. Further evidence that the models have generalized well from the training data is provided by the extremely high levels of agreement between the random forest and neural network models predictions on the 6, 12, and 60 month binary classifiers.