Predicting Participation in Cancer Screening Programs with Machine Learning

TL;DR

This study develops machine learning models to predict individual participation in Korea's cancer screening programs, aiming to enhance screening rates through targeted interventions.

Contribution

It compares various machine learning algorithms and identifies gradient boosted decision trees as the most effective for predicting screening participation.

Findings

Gradient boosted decision trees achieved an AUC-ROC of 0.8706.

Models show promise for integration into Korea's healthcare system.

Encouraging results suggest potential to increase screening participation.

Abstract

In this paper, we present machine learning models based on random forest classifiers, support vector machines, gradient boosted decision trees, and artificial neural networks to predict participation in cancer screening programs in South Korea. The top performing model was based on gradient boosted decision trees and achieved an area under the receiver operating characteristic curve (AUC-ROC) of 0.8706 and average precision of 0.8776. The results of this study are encouraging and suggest that with further research, these models can be directly applied to Korea's healthcare system, thus increasing participation in Korea's National Cancer Screening Program.