A Proposed Paradigm for Imputing Missing Multi-Sensor Data in the Healthcare Domain

TL;DR

This paper proposes a new paradigm for imputing missing multi-sensor healthcare data by tailoring imputation strategies to feature types and missing durations, enhancing the accuracy of continuous health monitoring.

Contribution

It introduces a systematic, feature-specific imputation framework that considers temporal dynamics, improving upon existing methods for handling missing data in healthcare sensor datasets.

Findings

Analysis of current imputation techniques highlights their limitations.

Evaluation of machine learning and deep learning methods for long-gap imputation.

Proposed paradigm emphasizes feature-specific and temporal-aware imputation strategies.

Abstract

Chronic diseases such as diabetes pose significant management challenges, particularly due to the risk of complications like hypoglycemia, which require timely detection and intervention. Continuous health monitoring through wearable sensors offers a promising solution for early prediction of glycemic events. However, effective use of multisensor data is hindered by issues such as signal noise and frequent missing values. This study examines the limitations of existing datasets and emphasizes the temporal characteristics of key features relevant to hypoglycemia prediction. A comprehensive analysis of imputation techniques is conducted, focusing on those employed in state-of-the-art studies. Furthermore, imputation methods derived from machine learning and deep learning applications in other healthcare contexts are evaluated for their potential to address longer gaps in time-series data. Based on this analysis, a systematic paradigm is proposed, wherein imputation strategies are tailored to the nature of specific features and the duration of missing intervals. The review concludes by emphasizing the importance of investigating the temporal dynamics of individual features and the implementation of multiple, feature-specific imputation techniques to effectively address heterogeneous temporal patterns inherent in the data.