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: May 10, 2026

Application of Unsupervised Multi-Omic Factor Analysis to Uncover Patterns of Variation and Molecular Processes Linked to Cardiovascular Disease
08:51

Application of Unsupervised Multi-Omic Factor Analysis to Uncover Patterns of Variation and Molecular Processes Linked to Cardiovascular Disease

Published on: September 20, 2024

Computational phenotype discovery using unsupervised feature learning over noisy, sparse, and irregular clinical

Thomas A Lasko1, Joshua C Denny, Mia A Levy

  • 1Department of Biomedical Informatics, Vanderbilt University School of Medicine, Nashville, Tennessee, USA. tom.lasko@vanderbilt.edu

Plos One
|July 5, 2013
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

Longitudinal analysis of CYFRA 21-1 levels in patients with pulmonary nodules: Differential trajectories between benign and malignant cases.

PloS one·2026
Same author

Systematic common and rare variant association testing in 392,030 whole genomes in <i>All of Us</i>.

medRxiv : the preprint server for health sciences·2026
Same author

Contrastive Patient-level Pretraining Enables Longitudinal and Multimodal Fusion for Lung Cancer Risk Prediction.

Proceedings of machine learning research·2026
Same author

Scalable Identification of Clinically Relevant Chronic Obstructive Pulmonary Disease Documents in Large-Scale Electronic Health Record Datasets With a Lightweight Natural Language Processing Model: Retrospective Cohort Study.

JMIR medical informatics·2026
Same author

Multi-scale data improves performance of machine learning model for long COVID identification.

Communications medicine·2026
Same author

Downward bias in the association between APOE and Alzheimer's disease using prevalent and by-proxy disease sampling in the All of Us research program.

BMC medical genomics·2026
Same journal

Analysis of strength degradation of coal and rock masses and stability of mined areas under long term immersion environment.

PloS one·2026
Same journal

Biogenic Silver-Selenium nanocomposite with anticancer activity and potent efficacy against vancomycin-resistant Staphylococcus aureus.

PloS one·2026
Same journal

Preparation and physicochemical characterization of a biodegradable chitosan/carboxymethyl cellulose hydrogel synthesized in NaOH/urea medium.

PloS one·2026
Same journal

Action-guilt, survivor-guilt, and depression in combat-related PTSD.

PloS one·2026
Same journal

Explainable machine learning for predicting activities of daily living at discharge in stroke patients: A retrospective study using SHAP interpretability.

PloS one·2026
Same journal

Deep learning based two-way feature depiction model for brain tumor detection.

PloS one·2026
See all related articles

This study introduces unsupervised feature learning for discovering patient subtypes from electronic health records. This method accurately identifies disease patterns, matching expert performance without prior labeling.

Area of Science:

  • Computational biology
  • Precision medicine
  • Machine learning in healthcare

Background:

  • Traditional supervised learning for clinical data analysis is limited by expert input and scalability.
  • Unsupervised feature learning offers a way to discover novel patterns without predefined labels.
  • Electronic Medical Records (EMR) data is often noisy and sparse, posing challenges for deep learning.

Purpose of the Study:

  • To apply unsupervised feature learning to discover phenotypes from challenging, real-world clinical data.
  • To develop a method that can handle noisy, sparse, and irregularly timed EMR data.
  • To demonstrate the potential of data-driven phenotypes for identifying disease subtypes.

Main Methods:

  • Coupling noisy clinical data to deep learning architectures using Gaussian process regression for longitudinal probability densities.

More Related Videos

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data
09:47

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

Related Experiment Videos

Last Updated: May 10, 2026

Application of Unsupervised Multi-Omic Factor Analysis to Uncover Patterns of Variation and Molecular Processes Linked to Cardiovascular Disease
08:51

Application of Unsupervised Multi-Omic Factor Analysis to Uncover Patterns of Variation and Molecular Processes Linked to Cardiovascular Disease

Published on: September 20, 2024

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data
09:47

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

  • Utilizing unsupervised feature learning to derive continuous phenotypic features from serum uric acid measurements.
  • Applying the learned features to distinguish between different disease signatures.

    • Main Results:

    • Generated continuous phenotypic features from longitudinal serum uric acid data in 4368 individuals.
    • Successfully distinguished between gout and acute leukemia signatures with 0.97 AUC, without task-specific optimization.
    • Unsupervised features demonstrated accuracy comparable to expert-engineered features.

    Conclusions:

    • Unsupervised feature learning can effectively discover computational phenotypes from large-scale, messy clinical data.
    • Data-driven phenotypes can reveal unknown disease variants and subtypes.
    • This approach holds promise for advancing precision medicine and genetic association studies.