Automatic Classification of Irregularly Sampled Time Series with Unequal Lengths: A Case Study on Estimated Glomerular Filtration Rate

TL;DR

This paper introduces an automated method for classifying irregularly sampled eGFR time series into stable or unstable, using Gaussian process regression and machine learning classifiers, achieving high accuracy close to human experts.

Contribution

The paper presents a novel two-tier system combining Gaussian process regression and machine learning for automatic eGFR trend classification with high accuracy.

Findings

Achieved an F-score of 0.90 with the automated system.

Performance comparable to human experts, who scored 0.96.

Effective handling of irregular sampling and varying series lengths.

Abstract

A patient's estimated glomerular filtration rate (eGFR) can provide important information about disease progression and kidney function. Traditionally, an eGFR time series is interpreted by a human expert labelling it as stable or unstable. While this approach works for individual patients, the time consuming nature of it precludes the quick evaluation of risk in large numbers of patients. However, automating this process poses significant challenges as eGFR measurements are usually recorded at irregular intervals and the series of measurements differs in length between patients. Here we present a two-tier system to automatically classify an eGFR trend. First, we model the time series using Gaussian process regression (GPR) to fill in `gaps' by resampling a fixed size vector of fifty time-dependent observations. Second, we classify the resampled eGFR time series using a K-NN/SVM classifier, and evaluate its performance via 5-fold cross validation. Using this approach we achieved an F-score of 0.90, compared to 0.96 for 5 human experts when scored amongst themselves.