Evaluation metrics for temporal preservation in synthetic longitudinal patient data

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Perkonoja, Katariina, Movahedi, Parisa, Airola, Antti, Auranen, Kari, Virta, Joni
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917267167510528
author Perkonoja, Katariina
Movahedi, Parisa
Airola, Antti
Auranen, Kari
Virta, Joni
author_facet Perkonoja, Katariina
Movahedi, Parisa
Airola, Antti
Auranen, Kari
Virta, Joni
contents This study introduces a set of metrics for evaluating temporal preservation in synthetic longitudinal patient data, defined as artificially generated data that mimic real patients' repeated measurements over time. The proposed metrics assess how synthetic data reproduces key temporal characteristics, categorized into marginal, covariance, individual-level and measurement structures. We show that strong marginal-level resemblance may conceal distortions in covariance and disruptions in individual-level trajectories. Temporal preservation is influenced by factors such as original data quality, measurement frequency, and preprocessing strategies, including binning, variable encoding and precision. Variables with sparse or highly irregular measurement times provide limited information for learning temporal dependencies, resulting in reduced resemblance between the synthetic and original data. No single metric adequately captures temporal preservation; instead, a multidimensional evaluation across all characteristics provides a more comprehensive assessment of synthetic data quality. Overall, the proposed metrics clarify how and why temporal structures are preserved or degraded, enabling more reliable evaluation and improvement of generative models and supporting the creation of temporally realistic synthetic longitudinal patient data.
format Preprint
id arxiv_https___arxiv_org_abs_2602_10643
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Evaluation metrics for temporal preservation in synthetic longitudinal patient data
Perkonoja, Katariina
Movahedi, Parisa
Airola, Antti
Auranen, Kari
Virta, Joni
Machine Learning
This study introduces a set of metrics for evaluating temporal preservation in synthetic longitudinal patient data, defined as artificially generated data that mimic real patients' repeated measurements over time. The proposed metrics assess how synthetic data reproduces key temporal characteristics, categorized into marginal, covariance, individual-level and measurement structures. We show that strong marginal-level resemblance may conceal distortions in covariance and disruptions in individual-level trajectories. Temporal preservation is influenced by factors such as original data quality, measurement frequency, and preprocessing strategies, including binning, variable encoding and precision. Variables with sparse or highly irregular measurement times provide limited information for learning temporal dependencies, resulting in reduced resemblance between the synthetic and original data. No single metric adequately captures temporal preservation; instead, a multidimensional evaluation across all characteristics provides a more comprehensive assessment of synthetic data quality. Overall, the proposed metrics clarify how and why temporal structures are preserved or degraded, enabling more reliable evaluation and improvement of generative models and supporting the creation of temporally realistic synthetic longitudinal patient data.
title Evaluation metrics for temporal preservation in synthetic longitudinal patient data
topic Machine Learning
url https://arxiv.org/abs/2602.10643