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

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

2.0K

MISSING DATA IMPUTATION IN THE ELECTRONIC HEALTH RECORD USING DEEPLY LEARNED AUTOENCODERS.

Brett K Beaulieu-Jones1, Jason H Moore

  • 1Genomics and Computational Biology Graduate Group, Computational Genetics Lab, Institute for Biomedical Informatics, Perelman School of Medicine, University of Pennsylvania, 3700 Hamilton Walk, Philadelphia PA, 19104, USA, brettbe@med.upenn.edu.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
|November 30, 2016
PubMed
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

Session Introduction: AI and Machine Learning in Clinical Medicine Bridging or Separating Model Intelligence and Human Expertise.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2026
Same author

Quantifying surprise in clinical care: Detecting highly informative events in electronic health records with foundation models.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2026
Same author

Advancing healthcare AI governance through a comprehensive maturity model based on systematic review.

NPJ digital medicine·2026
Same author

Diagnostic Codes in AI Prediction Models and Label Leakage of Same-Admission Clinical Outcomes.

JAMA network open·2026
Same author

Predicting Postpartum Hemorrhage Using Clinical Features Extracted With Large Language Models.

O&G open·2025
Same author

Synthetic data distillation enables the extraction of clinical information at scale.

NPJ digital medicine·2025

Deep learning autoencoders effectively impute missing electronic health record data, outperforming traditional methods. This approach enhances the accuracy of predicting Amyotrophic Lateral Sclerosis (ALS) disease progression.

Area of Science:

  • Biomedical Informatics
  • Data Science in Healthcare
  • Neurology Research

Background:

  • Electronic health records (EHRs) are crucial for patient outcome data.
  • Missing data in EHRs poses a significant challenge, potentially introducing bias.
  • Effective imputation methods are needed to handle missing EHR data.

Purpose of the Study:

  • To compare multiple imputation strategies against a deep learning autoencoder for EHR data.
  • To evaluate imputation accuracy under different missingness mechanisms (MCAR, MNAR).
  • To assess the impact of imputation models on predicting Amyotrophic Lateral Sclerosis (ALS) disease progression.

Main Methods:

  • Utilized the Pooled Resource Open-Access ALS Clinical Trials Database (PRO-ACT).
  • Compared established multiple imputation techniques with a deep autoencoder model.

Related Experiment Videos

Last Updated: Mar 11, 2026

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

2.0K
  • Evaluated imputation accuracy using simulated missing data (MCAR and MNAR).
  • Assessed predictive performance for ALS disease progression.

    • Main Results:

    • Autoencoders demonstrated superior imputation accuracy compared to traditional methods.
    • The autoencoder model resulted in the most accurate predictor of ALS disease progression.
    • Time from onset was identified as the primary predictor of ALS progression, despite clinical heterogeneity.

    Conclusions:

    • Deep learning autoencoders offer a powerful solution for handling missing EHR data.
    • Accurate data imputation using autoencoders can significantly improve clinical outcome prediction models.
    • ALS disease progression shows a relatively homogenous pattern over time from onset.