Assessing Chronic Kidney Disease from Office Visit Records Using Hierarchical Meta-Classification of an Imbalanced Dataset

TL;DR

This study introduces a hierarchical meta-classification approach to detect and stratify Chronic Kidney Disease severity from imbalanced office visit data, achieving high accuracy and robustness even with reduced features and training data.

Contribution

The paper presents a novel hierarchical meta-classification method tailored for imbalanced datasets to effectively classify CKD severity levels from office visit records.

Findings

High sensitivity, precision, and F-measure (~93%) in CKD stratification.

Method remains effective with reduced feature sets and training data.

Stable and generalizable performance across different data conditions.

Abstract

Chronic Kidney Disease (CKD) is an increasingly prevalent condition affecting 13% of the US population. The disease is often a silent condition, making its diagnosis challenging. Identifying CKD stages from standard office visit records can help in early detection of the disease and lead to timely intervention. The dataset we use is highly imbalanced. We propose a hierarchical meta-classification method, aiming to stratify CKD by severity levels, employing simple quantitative non-text features gathered from office visit records, while addressing data imbalance. Our method effectively stratifies CKD severity levels obtaining high average sensitivity, precision and F-measure (~93%). We also conduct experiments in which the dimensionality of the data is significantly reduced to include only the most salient features. Our results show that the good performance of our system is retained even when using the reduced feature sets, as well as under much reduced training sets, indicating that our method is stable and generalizable.