Risk Factor Identification In Osteoporosis Using Unsupervised Machine Learning Techniques

TL;DR

This paper introduces a novel clustering-based framework, CLIF, utilizing Wasserstein distance and feature selection methods to identify and validate risk factors for osteoporosis from electronic medical records.

Contribution

It presents a new iterative clustering framework, CLIF, that integrates feature selection and principal feature identification for osteoporosis risk factor analysis.

Findings

Confirmed some known risk factors for osteoporosis.

Questioned the reliability of certain previously identified risk factors.

Demonstrated effectiveness of Wasserstein distance in feature identification.

Abstract

In this study, the reliability of identified risk factors associated with osteoporosis is investigated using a new clustering-based method on electronic medical records. This study proposes utilizing a new CLustering Iterations Framework (CLIF) that includes an iterative clustering framework that can adapt any of the following three components: clustering, feature selection, and principal feature identification. The study proposes using Wasserstein distance to identify principal features, borrowing concepts from the optimal transport theory. The study also suggests using a combination of ANOVA and ablation tests to select influential features from a data set. Some risk factors presented in existing works are endorsed by our identified significant clusters, while the reliability of some other risk factors is weakened.