Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 7, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

A Review of Deep Learning Methods for Irregularly Sampled Medical Time Series Data.

Chenxi Sun^1,2, Moxian Song^3,4, Derun Cai^3,4

¹Harvard Medical School, Boston, MA USA.

Health Data Science

|May 6, 2026

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Developing and Validating a Context-Sensitive Scale of Excellence-Driven Behavior in Public Universities: A Mixed-Methods Psychometric Study.

Behavioral sciences (Basel, Switzerland)·2026

Same author

Unit-specific fate and ecological drivers of antibiotic resistome in a full-scale swine wastewater treatment system.

Environmental pollution (Barking, Essex : 1987)·2026

Same author

Bidirectional regulatory effects of exercise on emotional eating in depression: an ERP-based narrative review.

Frontiers in nutrition·2026

Same author

High color rendering index white organic light-emitting diodes based on a polymer-small-molecule excited system.

Optics letters·2026

Same author

Impact of death education programs on nurses' and nursing students' mortality perceptions and end-of-life coping competencies: a decade-long systematic review and meta-analysis.

Frontiers in medicine·2026

Same author

Analgesic effect of premixed nitrous oxide in postoperative rehabilitation for ankle fractures: a randomized controlled trial.

Annals of medicine·2026

Same journal

Integrating Electronic Health Records and Large Language Models for Coarse-to-Fine Hybrid Disease Prediction.

Health data science·2026

Same journal

Electronic Health Record-Based Machine Learning Model for Predicting Disease Activity in Patients with Rheumatoid Arthritis.

Health data science·2026

Same journal

Exploring the Relationship between Dietary Intake and Clinical Outcomes in Peritoneal Dialysis Patients Stratified by Serum Albumin Levels: A 12-Year Follow-Up Using Fine-Grained Electronic Medical Records Data.

Health data science·2026

Same journal

Health in a Digital Age: From Determinants to Dynamic Systems.

Health data science·2026

Same journal

Digital and AI-Empowered Health Elements: An Integrated Pathway to Advancing Health.

Health data science·2026

Same journal

ECGomics: An Open Platform for AI-ECG Digital Biomarker Discovery.

Health data science·2026

See all related articles

Deep learning models struggle with irregularly sampled medical time series data, common in electronic health records. This study categorizes methods, analyzes their performance, and offers recommendations for future research in this challenging area.

Area of Science:

Biomedical Informatics
Machine Learning
Data Science

Background:

Medical time series data, a significant component of electronic health records, are frequently irregularly sampled.
Irregular sampling presents challenges due to uneven time intervals, missing data, and varying sampling rates, complicating deep learning model application.

Purpose of the Study:

To categorize and analyze existing deep learning methodologies for handling irregularly sampled medical time series.
To provide a comprehensive overview of the strengths and limitations of different approaches from an irregularity-aware and data-centric viewpoint.

Main Methods:

Categorization of deep learning methods into missing-data-based and raw-data-based approaches.
Theoretical analysis of the foundations and practical implications of each category.

Related Experiment Videos

Last Updated: May 7, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Experimental evaluation on benchmark and real-world medical datasets.

Main Results:

Comparison of the performance of missing-data-based and raw-data-based methods on diverse medical time series datasets.
Identification of the specific challenges and advantages associated with each modeling approach.
Empirical evidence highlighting the effectiveness and limitations of current deep learning techniques.

Conclusions:

Summary of findings regarding the efficacy of different deep learning strategies for irregularly sampled medical data.
Practical recommendations for selecting and applying appropriate methods.
Discussion of open research questions and future directions in modeling complex medical time series.