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 Videos

A bayesian recurrent neural network for unsupervised pattern recognition in large incomplete data sets.

Roland Orre1, Andrew Bate, G Niklas Norén

  • 1Mathematical Statistics, Stockholm University, SE-106 91 Stockholm, and NeuroLogic Sweden AB, Solna, Sweden. orre@math.su.se

International Journal of Neural Systems
|July 14, 2005
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

Global Perspective on the Evolution and Future of Pharmacovigilance: Deliverables from the 24th Annual Meeting of the International Society of Pharmacovigilance Celebrating 25 Years of Excellence.

Drug safety·2026
Same author

Reply to "A Comment about AI Methods that May Help Advance Pharmacovigilance".

Clinical pharmacology and therapeutics·2026
Same author

International Medicinal Product Information Documents: A Quantitative Content Analysis of Instructions for Preventing, Mitigating, and Monitoring Adverse Drug Reactions.

Drug safety·2026
Same author

9<sup>th</sup> ISoP Intelligent Automation Boston Seminar: From Innovation to Impact. Building Trustworthy AI in Pharmacovigilance 4-5 December 2025 | Cambridge, USA & Virtual.

Drug safety·2026
Same author

Critical Appraisal of Artificial Intelligence for Rare-Event Recognition: Principles and Pharmacovigilance Case Studies.

Drug safety·2026
Same author

Ontology-based Semantic Similarity Measures for Clustering Medical Concepts in Drug Safety.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026
Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026
Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026
Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026
Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026
See all related articles

A novel recurrent neural network effectively performs unsupervised pattern recognition on incomplete adverse drug reaction data. This method shows comparable performance to AutoClass on simulated data and superior results on real-world datasets.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Pharmacovigilance

Background:

  • Adverse drug reaction databases are crucial for pharmacovigilance but often contain highly incomplete data.
  • Unsupervised pattern recognition is vital for identifying novel safety signals within these large datasets.
  • Existing methods may struggle with the scale and incompleteness of real-world observational data.

Purpose of the Study:

  • To describe a modified recurrent neural network designed for unsupervised pattern recognition in incomplete datasets.
  • To evaluate the performance of this neural network against a established method, AutoClass.
  • To demonstrate the utility of the neural network for analyzing the World Health Organization (WHO) adverse drug reaction database.

Main Methods:

  • Development of a recurrent neural network architecture capable of handling missing data.

Related Experiment Videos

  • Application of unsupervised pattern recognition techniques using the neural network.
  • Comparative analysis using simulated datasets and the WHO adverse drug reaction database.
  • Benchmarking against the AutoClass algorithm.

    • Main Results:

    • The recurrent neural network demonstrated effective unsupervised pattern recognition on incomplete adverse drug reaction data.
    • Performance on simulated data was comparable to the AutoClass method.
    • The neural network significantly outperformed AutoClass when applied to real-world WHO adverse drug reaction data.
    • The proposed neural network exhibited superior scaling properties for large datasets.

    Conclusions:

    • The modified recurrent neural network is a promising tool for unsupervised pattern recognition in large, incomplete observational databases.
    • This approach offers advantages over traditional methods like AutoClass, particularly with real-world pharmacovigilance data.
    • The method holds potential for improving the identification of adverse drug events and enhancing patient safety.