Graph-guided network for irregularly sampled multivariate time series

X Zhang, M Zeman, T Tsiligkaridis, M Zitnik - arxiv preprint arxiv …, 2021 - arxiv.org
In many domains, including healthcare, biology, and climate science, time series are
irregularly sampled with varying time intervals between successive readouts and different …

[HTML][HTML] Interpretable clinical time-series modeling with intelligent feature selection for early prediction of antimicrobial multidrug resistance

S Martínez-Agüero, C Soguero-Ruiz… - Future Generation …, 2022 - Elsevier
Electronic health records provide rich, heterogeneous data about the evolution of the
patients' health status. However, such data need to be processed carefully, with the aim of …

VS-GRU: A variable sensitive gated recurrent neural network for multivariate time series with massive missing values

Q Li, Y Xu - Applied Sciences, 2019 - mdpi.com
Multivariate time series are often accompanied with missing values, especially in clinical
time series, which usually contain more than 80% of missing data, and the missing rates …

Moving Beyond Medical Statistics: A Systematic Review on Missing Data Handling in Electronic Health Records

W Ren, Z Liu, Y Wu, Z Zhang, S Hong, H Liu… - Health Data …, 2024 - spj.science.org
Background: Missing data in electronic health records (EHRs) presents significant
challenges in medical studies. Many methods have been proposed, but uncertainty exists …

Modeling regime shifts in multiple time series

EG Tajeuna, M Bouguessa, S Wang - ACM Transactions on Knowledge …, 2023 - dl.acm.org
We investigate the problem of discovering and modeling regime shifts in an ecosystem
comprising multiple time series known as co-evolving time series. Regime shifts refer to the …

[HTML][HTML] On missingness features in machine learning models for critical care: observational study

J Singh, M Sato, T Ohkuma - JMIR Medical Informatics, 2021 - medinform.jmir.org
Background: Missing data in electronic health records is inevitable and considered to be
nonrandom. Several studies have found that features indicating missing patterns …

Approaching adverse event detection utilizing transformers on clinical time-series

H Fredriksen, PJ Burman, A Woldaregay… - arxiv preprint arxiv …, 2023 - arxiv.org
Patients being admitted to a hospital will most often be associated with a certain clinical
development during their stay. However, there is always a risk of patients being subject to …

Categorization of phenotype trajectories utilizing transformers on clinical time-series

H Fredriksen, PJ Burman, AZ Woldaregay… - Proceedings of the …, 2024 - dl.acm.org
Patients being admitted to a hospital will most often be associated with a certain clinical
development during their stay. However, there is always a risk of patients being subject to …

As easy as APC: overcoming missing data and class imbalance in time series with self-supervised learning

F Wever, TA Keller, L Symul, V Garcia - arxiv preprint arxiv:2106.15577, 2021 - arxiv.org
High levels of missing data and strong class imbalance are ubiquitous challenges that are
often presented simultaneously in real-world time series data. Existing methods approach …

Deep Learning and Graph Analytics for Explainable Modeling of Clinical Time-Varying Data Associated with Infectious Diseases

S Martínez Agüero - 2024 - burjcdigital.urjc.es
Esta tesis doctoral realiza una investigación de las herramientas de ciencia de datos para
abordar dos problemas incipientes en entornos clínicos modernos: la Multiresistencia …