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

TL;DR

The paper surveys preprocessing and imputation of missing values in multisensor health data for hypoglycemia prediction in Type 1 diabetes. It analyzes diverse datasets and exposes temporal dynamics of glucose-related features, highlighting data quality issues and missingness patterns. It synthesizes a paradigm that imputes different features with time-gap-aware strategies, and considers cross-domain ML/DL methods to handle longer gaps. The work emphasizes feature-wise analysis, data quality limitations, and the potential for transfer learning and multi-sensor data integration to improve early detection of glycemic events.

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.

Figures (6)

• Figure 1: Flowchart of selection process
• Figure 2: Clinical Datasets used in studies
• Figure 3: Types of Imputation Techniques Used
• Figure 4: Prediction Models used
• Figure 5: Evaluation Metrics Used