Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Mar 11, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

3.6K

$\mathtt {Deepr}$: A Convolutional Net for Medical Records.

Phuoc Nguyen, Truyen Tran, Nilmini Wickramasinghe

    IEEE Journal of Biomedical and Health Informatics
    |December 4, 2016
    PubMed
    Summary

    Deepr, a novel deep learning system, automatically extracts features from electronic medical records to predict patient risk. This approach improves accuracy in identifying clinical patterns for better healthcare outcomes.

    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

    Molecular design rules for wettability minimisation on grafted cellulose surfaces through human-machine teaming optimisation.

    Journal of colloid and interface science·2026
    Same author

    Predictors of depression outcomes among university students following brief smartphone-based interventions.

    Npj mental health research·2026
    Same author

    A theory-driven user-centered design framework for wellness applications targeting young adults: The MiCARE methodology.

    Digital health·2026
    Same author

    Development and Formative Usability Evaluation of a Theory-Driven Progressive Web Application for Young Adult Wellness Engagement (MiCARE): Protocol for a Mixed Methods Study.

    JMIR research protocols·2026
    Same author

    Digital Health Solutions for Type 2 Diabetes and Prediabetes: Systematic Review of Engagement Barriers, Facilitators, and Outcomes.

    JMIR diabetes·2026
    Same author

    Draw-Care, a Co-Designed Multilingual Digital Intervention for Family Carers of People Living With Dementia From Ethnically Diverse Communities: User-Testing Study.

    JMIR formative research·2026

    Area of Science:

    • Medical Informatics
    • Artificial Intelligence in Healthcare
    • Clinical Data Analysis

    Background:

    • Feature engineering is a significant challenge in developing predictive models from electronic medical records.
    • Identifying predictive clinical patterns within irregular patient data remains a critical unmet need.

    Purpose of the Study:

    • To introduce Deepr, an end-to-end deep learning system designed for automated feature extraction and risk prediction from medical records.
    • To address the limitations of traditional methods in detecting regular clinical motifs from episodic electronic health data.

    Main Methods:

    • Deepr processes medical records into sequences of discrete elements with time gaps and transfer information.
    • A convolutional neural network within Deepr identifies and integrates local clinical motifs for risk stratification.

    Related Experiment Videos

    Last Updated: Mar 11, 2026

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

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

    Published on: November 30, 2022

    3.6K
  • The system allows for transparent inspection and visualization of its internal operations.

    • Main Results:

    • Deepr demonstrated superior accuracy in predicting unplanned hospital readmissions compared to conventional techniques.
    • The system successfully identified clinically meaningful motifs from electronic medical record data.
    • Deepr provided insights into the underlying structure of disease and intervention patterns.

    Conclusions:

    • Deepr offers an effective deep learning solution for feature engineering in electronic medical records.
    • The system enhances the accuracy and interpretability of predictive models for patient risk.
    • Deepr has the potential to advance the application of AI in personalized medicine and clinical decision support.