FWDA: a Fast Wishart Discriminant Analysis with its Application to Electronic Health Records Data Classification

TL;DR

FWDA introduces a fast ensemble-based classifier using Wishart distribution to improve EHR data classification, addressing covariance estimation issues and linear inseparability, with proven robustness and superior performance.

Contribution

The paper proposes FWDA, a novel ensemble classifier that leverages Wishart distribution sampling and Bayesian voting to enhance EHR data classification.

Findings

FWDA outperforms existing algorithms on large-scale EHR datasets.

Theoretical analysis confirms fast convergence and robustness of FWDA.

FWDA effectively handles high-dimensional data and nonlinear separability.

Abstract

Linear Discriminant Analysis (LDA) on Electronic Health Records (EHR) data is widely-used for early detection of diseases. Classical LDA for EHR data classification, however, suffers from two handicaps: the ill-posed estimation of LDA parameters (e.g., covariance matrix), and the "linear inseparability" of EHR data. To handle these two issues, in this paper, we propose a novel classifier FWDA -- Fast Wishart Discriminant Analysis, that makes predictions in an ensemble way. Specifically, FWDA first surrogates the distribution of inverse covariance matrices using a Wishart distribution estimated from the training data, then "weighted-averages" the classification results of multiple LDA classifiers parameterized by the sampled inverse covariance matrices via a Bayesian Voting scheme. The weights for voting are optimally updated to adapt each new input data, so as to enable the nonlinear classification. Theoretical analysis indicates that FWDA possesses a fast convergence rate and a robust performance on high dimensional data. Extensive experiments on large-scale EHR dataset show that our approach outperforms state-of-the-art algorithms by a large margin.