ELMV: an Ensemble-Learning Approach for Analyzing Electrical Health Records with Significant Missing Values

TL;DR

The paper introduces ELMV, an ensemble-learning framework designed to analyze electronic health records with high missing data, reducing bias and improving accuracy over traditional imputation methods.

Contribution

ELMV is a novel ensemble-learning approach that constructs multiple low-missing-rate data subsets and uses a support set to enhance analysis of incomplete EHR data.

Findings

ELMV outperforms traditional imputation methods in real-world healthcare data.

ELMV achieves higher accuracy in outcome prediction across various missing data rates.

ELMV effectively identifies critical features despite substantial missing values.

Abstract

Many real-world Electronic Health Record (EHR) data contains a large proportion of missing values. Leaving substantial portion of missing information unaddressed usually causes significant bias, which leads to invalid conclusion to be drawn. On the other hand, training a machine learning model with a much smaller nearly-complete subset can drastically impact the reliability and accuracy of model inference. Data imputation algorithms that attempt to replace missing data with meaningful values inevitably increase the variability of effect estimates with increased missingness, making it unreliable for hypothesis validation. We propose a novel Ensemble-Learning for Missing Value (ELMV) framework, which introduces an effective approach to construct multiple subsets of the original EHR data with a much lower missing rate, as well as mobilizing a dedicated support set for the ensemble learning in the purpose of reducing the bias caused by substantial missing values. ELMV has been evaluated on a real-world healthcare data for critical feature identification as well as a batch of simulation data with different missing rates for outcome prediction. On both experiments, ELMV clearly outperforms conventional missing value imputation methods and ensemble learning models.