Evaluating Clustering and Imputation Approaches for Multivariate Longitudinal Clinical Data Using a Real-World eCDF-Copula Resampling Framework
- 1Vanderbilt University Medical Center
Abstract
The rapid growth of technologies such as wearable devices and high-throughput sequencing has generated unprecedented volumes of longitudinal data, often with multiple correlated features. This trend highlights the need for robust clustering methods tailored to multi-feature longitudinal datasets. Although previous reviews have benchmarked clustering methods in this context, most evaluations relied heavily on simulated and overly simplified datasets, which substantially limit their interpretability and applicability to real-world data. Missing data is also ubiquitous in longitudinal data, yet understudied in the context of clustering. To address these gaps, we systematically evaluate clustering methods across three distinct types of real-world longitudinal datasets: (1) a high-dimensional, low-timepoint metagenomic study, (2) a low-dimensional, high-timepoint multi-site repeated-measure study, and (3) a high-dimensional, high-timepoint repeated-measure study. We further investigate how missing data and different imputation strategies influence clustering performance. In addition, we introduce a novel resampling framework based on the empirical cumulative distribution function (eCDF) and a copula. This framework enables us to simulate multi-feature longitudinal data that preserves the correlation structure of real datasets, while also allowing for controlled variations such as sample size. Our simulation framework naturally accommodates missing data, thereby providing a flexible tool for benchmarking and comparing clustering methods in more realistic longitudinal settings.
Related
- Alert-List Concordance for Evaluating Imputation Strategies in ICU Sepsis Prediction
- Evaluating imputation methods for determining North American honey bee (Apis mellifera) ancestry from low-pass whole-genome sequencing data
- Evaluating modeling approaches for estimating net ecosystem exchange in Canadian peatlands
- Defining and predicting outcomes of a work-injuries rehabilitation program through multivariate baseline phenotypes and longitudinal modeling
- QuImputer: an LD-informed QUBO/Ising formulation of genotype imputation with quantum-hardware execution
BibTeX
@misc{cai2026evaluating,
title = {{Evaluating Clustering and Imputation Approaches for Multivariate Longitudinal Clinical Data Using a Real-World eCDF-Copula Resampling Framework}},
author = {H. Cai and K. Xu and S. Osmundson and O. Ajilore and C. Andreescu and W. D. Taylor and J. Liu and X. Zhang},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.24.753982},
url = {https://www.biorxiv.org/content/10.64898/2026.09.24.753982v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Evaluating Clustering and Imputation Approaches for Multivariate Longitudinal Clinical Data Using a Real-World eCDF-Copula Resampling Framework
AU - H. Cai
AU - K. Xu
AU - S. Osmundson
AU - O. Ajilore
AU - C. Andreescu
AU - W. D. Taylor
AU - J. Liu
AU - X. Zhang
PY - 2026
DA - 2026/09/24
PB - bioRxiv
DO - 10.64898/2026.09.24.753982
UR - https://www.biorxiv.org/content/10.64898/2026.09.24.753982v1
AB - The rapid growth of technologies such as wearable devices and high-throughput sequencing has generated unprecedented volumes of longitudinal data, often with multiple correlated features. This trend highlights the need for robust clustering methods tailored to multi-feature longitudinal datasets. Although previous reviews have benchmarked clustering methods in this context, most evaluations relied heavily on simulated and overly simplified datasets, which substantially limit their interpretability and applicability to real-world data. Missing data is also ubiquitous in longitudinal data, yet understudied in the context of clustering. To address these gaps, we systematically evaluate clustering methods across three distinct types of real-world longitudinal datasets: (1) a high-dimensional, low-timepoint metagenomic study, (2) a low-dimensional, high-timepoint multi-site repeated-measure study, and (3) a high-dimensional, high-timepoint repeated-measure study. We further investigate how missing data and different imputation strategies influence clustering performance. In addition, we introduce a novel resampling framework based on the empirical cumulative distribution function (eCDF) and a copula. This framework enables us to simulate multi-feature longitudinal data that preserves the correlation structure of real datasets, while also allowing for controlled variations such as sample size. Our simulation framework naturally accommodates missing data, thereby providing a flexible tool for benchmarking and comparing clustering methods in more realistic longitudinal settings.
ER -