[HTML][HTML] Deep imputation of missing values in time series health data: A review with benchmarking

M Kazijevs, MD Samad - Journal of biomedical informatics, 2023 - Elsevier
The imputation of missing values in multivariate time series (MTS) data is a critical step in
ensuring data quality and producing reliable data-driven predictive models. Apart from many …

TEST: Text prototype aligned embedding to activate LLM's ability for time series

C Sun, H Li, Y Li, S Hong - arXiv preprint arXiv:2308.08241, 2023 - arxiv.org
This work summarizes two ways to accomplish Time-Series (TS) tasks in today's Large
Language Model (LLM) context: LLM-for-TS (model-centric) designs and trains a …

Unsupervised representation learning for time series: A review

Q Meng, H Qian, Y Liu, Y Xu, Z Shen, L Cui - arXiv preprint arXiv …, 2023 - arxiv.org
Unsupervised representation learning approaches aim to learn discriminative feature
representations from unlabeled data, without the requirement of annotating every sample …

Predicting COVID-19 disease progression and patient outcomes based on temporal deep learning

C Sun, S Hong, M Song, H Li, Z Wang - BMC Medical Informatics and …, 2021 - Springer
Background The coronavirus disease 2019 (COVID-19) pandemic has caused health
concerns worldwide since December 2019. From the beginning of infection, patients will …

Hypergraph contrastive learning for electronic health records

D Cai, C Sun, M Song, B Zhang, S Hong, H Li - Proceedings of the 2022 SIAM …, 2022 - SIAM
Abstract Electronic Health Records (EHR) is the repository of patients' involved medical
codes in the hospital, including diagnosis codes, medication codes, procedure codes, lab …

A review of Generative Adversarial Networks for Electronic Health Records: applications, evaluation measures and data sources

G Ghosheh, J Li, T Zhu - arXiv preprint arXiv:2203.07018, 2022 - arxiv.org
Electronic Health Records (EHRs) are a valuable asset to facilitate clinical research and
point of care applications; however, many challenges such as data privacy concerns impede …

A survey of generative adversarial networks for synthesizing structured electronic health records

GO Ghosheh, J Li, T Zhu - ACM Computing Surveys, 2024 - dl.acm.org
Electronic Health Records (EHRs) are a valuable asset to facilitate clinical research and
point of care applications; however, many challenges such as data privacy concerns impede …

Time pattern reconstruction for classification of irregularly sampled time series

C Sun, H Li, M Song, D Cai, B Zhang, S Hong - Pattern Recognition, 2024 - Elsevier
Abstract Irregularly Sampled Time Series (ISTS) include partially observed feature vectors
caused by the lack of temporal alignment across dimensions and the presence of variable …

A ranking-based cross-entropy loss for early classification of time series

C Sun, H Li, M Song, S Hong - IEEE Transactions on Neural …, 2023 - ieeexplore.ieee.org
Early classification tasks aim to classify time series before observing full data. It is critical in
time-sensitive applications such as early sepsis diagnosis in the intensive care unit (ICU) …

Stop&Hop: Early Classification of Irregular Time Series

T Hartvigsen, W Gerych, J Thadajarassiri… - Proceedings of the 31st …, 2022 - dl.acm.org
Early classification algorithms help users react faster to their machine learning model's
predictions. Early warning systems in hospitals, for example, let clinicians improve their …