Scholarlink

<p>In Electronic Health Records (EHR), variables such as medications and diagnoses are recorded repeatedly over time, providing temporal information for clinical decision-making. Deep Learning (DL) has been applied to a variety of tasks using EHR time-series data, yet their characteristics pose major analytical challenges. This review examines studies that have applied DL to the analysis of multivariate time series (MTS) in EHRs, identifying prediction tasks, data types, and strategies used to address these challenges. <b>Methods:</b>Following PRISMA-ScR, we searched Scopus, Web of Science, PubMed, the ACM Digital Library, and IEEE Xplore, for studies published through December 2025. We included peer-reviewed English-language studies applying DL to MTS analysis of structured EHR data. <b>Results:</b>We included 182 articles analyzing key aspects of DL model development in MTS analysis of EHRs. The studies covered diverse tasks and data types across multiple databases, revealing common challenges addressed with shared strategies. MIMIC-III was the most commonly used database, particularly in studies focused on disease management and monitoring tasks involving laboratory results. Most studies addressed single-step classification tasks (e.g., mortality prediction), whereas relatively few addressed MTS forecasting. Attention mechanisms were the predominant interpretability approach, and post-hoc explainability methods were increasingly used. <b>Conclusions:</b>The task-oriented taxonomy indicates that predictive objectives influence the choice of data, model architecture, and explanation methods. Validation on public databases is essential for replicability, while external datasets are required to assess generalizability. Interpretability and explainability remain critical for clinical adoption, and clinician collaboration is essential to ensure clinical relevance.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep learning for multivariate time series analysis in electronic health records: a scoping review

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年8月4日

查看全文
  • C. A. Hernandez-Diaz,
  • Blanca Vazquez,
  • Gibran Fuentes-Pineda

摘要

In Electronic Health Records (EHR), variables such as medications and diagnoses are recorded repeatedly over time, providing temporal information for clinical decision-making. Deep Learning (DL) has been applied to a variety of tasks using EHR time-series data, yet their characteristics pose major analytical challenges. This review examines studies that have applied DL to the analysis of multivariate time series (MTS) in EHRs, identifying prediction tasks, data types, and strategies used to address these challenges. Methods:Following PRISMA-ScR, we searched Scopus, Web of Science, PubMed, the ACM Digital Library, and IEEE Xplore, for studies published through December 2025. We included peer-reviewed English-language studies applying DL to MTS analysis of structured EHR data. Results:We included 182 articles analyzing key aspects of DL model development in MTS analysis of EHRs. The studies covered diverse tasks and data types across multiple databases, revealing common challenges addressed with shared strategies. MIMIC-III was the most commonly used database, particularly in studies focused on disease management and monitoring tasks involving laboratory results. Most studies addressed single-step classification tasks (e.g., mortality prediction), whereas relatively few addressed MTS forecasting. Attention mechanisms were the predominant interpretability approach, and post-hoc explainability methods were increasingly used. Conclusions:The task-oriented taxonomy indicates that predictive objectives influence the choice of data, model architecture, and explanation methods. Validation on public databases is essential for replicability, while external datasets are required to assess generalizability. Interpretability and explainability remain critical for clinical adoption, and clinician collaboration is essential to ensure clinical relevance.