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

Predicting Optimal Hypertension Treatment Pathways Using Recurrent Neural Networks.

Xiangyang Ye1, Qing T Zeng2, Julio C Facelli1

  • 1Department of Biomedical Informatics, The University of Utah, 421 Wakara Way, Suite 140, Salt Lake City, UT, 84108, USA.

International Journal of Medical Informatics
|April 28, 2020
PubMed
Summary

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

Structural homology of HHV-6B epitopes as candidates for molecular mimicry triggers of the onset type one diabetes mellitus.

Oxford open immunology·2026
Same author

Integrative multi-omics identifies CYP1B1 as a candidate molecular link between toxicant exposure and ferroptosis-related epithelial stress in COPD.

Inflammation research : official journal of the European Histamine Research Society ... [et al.]·2026
Same author

Bioorthogonal chemistry-driven multi-enzyme strategy for efficient terpenoid biosynthesis.

Bioresource technology·2026
Same author

Understanding uncertainty in large language model predictions of early death in critically ill patients: a conformal prediction approach.

JAMIA open·2026
Same author

Prescribing Trajectories in Type 2 Diabetes in the United States, 2019-2024.

Diabetes, obesity & metabolism·2026
Same author

Reliable Uncertainty Under Class Imbalance and Distribution Shift: Class-Conditional Conformal Prediction of Multiple Sclerosis.

medRxiv : the preprint server for health sciences·2026

Deep learning models accurately predict optimal hypertension treatment pathways for individual patients. These models can enhance clinical decision support systems for personalized hypertension management.

Area of Science:

  • Cardiology
  • Medical Informatics
  • Artificial Intelligence

Background:

  • Physicians in ambulatory care settings rely on clinical guidelines and decision support systems for hypertension treatment.
  • Current clinical evidence is insufficient for definitive optimal hypertension treatment strategies.

Purpose of the Study:

  • To test the feasibility of deep learning predictive models for identifying optimal hypertension treatment pathways.
  • To personalize hypertension treatment based on individual patient data from electronic health records.

Main Methods:

  • Utilized a dataset of 245,499 patients with essential hypertension treated between 2001-2010.
  • Employed recurrent neural networks (RNN), including long short-term memory (LSTM) and bi-directional LSTM, for risk-adapted predictive modeling.
Keywords:
clinical decision supportdeep learninghypertension treatment pathwayslong short-term memoryrecurrent neural networks

Related Experiment Videos

  • Models predicted the probability of achieving blood pressure (BP) control targets with different anti-hypertensive regimens.

    • Main Results:

    • LSTM models demonstrated high accuracy in predicting individual BP control probabilities.
    • Achieved F1-scores of 0.928 for systolic BP, 0.960 for diastolic BP, and 0.913 for both (<140/90 mmHg).

    Conclusions:

    • Predictive models show potential for optimizing hypertension treatment selection.
    • LSTM models can serve as decision-support tools, complementing guidelines and CDS systems for personalized, risk-adapted hypertension management, particularly for challenging cases.