The Use of Text Mining to Identify Trends and Relationships between Social Determinants of Health and Congestive Heart Failure

Document Type

Conference Proceeding

Publication Date

1-1-2024

Abstract

In recent years, there has been a mounting recognition of the influence that Social Determinants of Health (SDOH) exert on health outcomes, especially for chronic illnesses. Chronic illnesses such as congestive heart failure (CHF) are the leading cause of hospitalization for older adults in the United States. Understanding the web of associations between SDOH, socioeconomic factors that affect health, and CHF might help reduce the high incidences of morbidity, mortality, and cost associated with this condition. This paper describes a method for uncovering developing trends, patterns, topics, and previously unknown correlations between the SDOH and CHF using the hierarchical clustering method and Latent Dirichlet allocation topic modeling procedure on the statistical software R. These text mining and natural language processing techniques will be used to extract, analyze, and synthesize textual data from a variety of recent sources, such as medical literature (journals and conference proceedings), and reports from public health institutes to expose the influence of non-traditional risk factors on the onset, progression, and successful management of CHF. The major strength of the proposed method is that it employs an unsupervised machine learning technique to identify all themes and latent relationships from thousands of medical publications on SDOH and CHF, which would otherwise be time-consuming and labor-intensive, or even humanly impossible to uncover using the standard traditional method of literature review.

Publication Source (Journal or Book title)

Proceedings of the IISE Annual Conference and Expo 2024

This document is currently not available here.

Plum Print visual indicator of research metrics
PlumX Metrics
  • Usage
    • Abstract Views: 1
see details

Share

COinS