Multilevel Stochastic Optimization for Imputation in Massive Medical Data Records

TL;DR

This paper introduces a multi-level stochastic optimization method for imputing missing data in massive medical datasets, demonstrating superior accuracy, speed, and robustness over existing techniques, including deep learning approaches.

Contribution

The paper presents a novel multi-level stochastic optimization framework for data imputation, offering exact formulations and improved performance for large-scale medical datasets.

Findings

Up to 75% reduction in imputation error.

Outperforms current methods in accuracy and robustness.

Applicable to massive datasets with high numerical stability.

Abstract

It has long been a recognized problem that many datasets contain significant levels of missing numerical data. A potentially critical predicate for application of machine learning methods to datasets involves addressing this problem. However, this is a challenging task. In this paper, we apply a recently developed multi-level stochastic optimization approach to the problem of imputation in massive medical records. The approach is based on computational applied mathematics techniques and is highly accurate. In particular, for the Best Linear Unbiased Predictor (BLUP) this multi-level formulation is exact, and is significantly faster and more numerically stable. This permits practical application of Kriging methods to data imputation problems for massive datasets. We test this approach on data from the National Inpatient Sample (NIS) data records, Healthcare Cost and Utilization Project (HCUP), Agency for Healthcare Research and Quality. Numerical results show that the multi-level method significantly outperforms current approaches and is numerically robust. It has superior accuracy as compared with methods recommended in the recent report from HCUP. Benchmark tests show up to 75% reductions in error. Furthermore, the results are also superior to recent state of the art methods such as discriminative deep learning.