Multi-Labeled Classification of Demographic Attributes of Patients: a case study of diabetics patients

TL;DR

This paper explores multi-label classification of diabetic patients' demographics to improve privacy-preserving data analysis, using ensemble methods to identify demographic groups associated with diabetes.

Contribution

It introduces a multi-label approach to analyze patient demographics related to diabetes, addressing a gap in multi-labeled demographic analysis.

Findings

Ensembles of multi-label algorithms effectively identify demographic groups linked to diabetes.

The approach advances privacy-preserving data mining by classifying patient demographics.

The study highlights the potential for multi-label analysis in healthcare data.

Abstract

Automated learning of patients demographics can be seen as multi-label problem where a patient model is based on different race and gender groups. The resulting model can be further integrated into Privacy-Preserving Data Mining, where it can be used to assess risk of identification of different patient groups. Our project considers relations between diabetes and demographics of patients as a multi-labelled problem. Most research in this area has been done as binary classification, where the target class is finding if a person has diabetes or not. But very few, and maybe no work has been done in multi-labeled analysis of the demographics of patients who are likely to be diagnosed with diabetes. To identify such groups, we applied ensembles of several multi-label learning algorithms.