Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Long Short-Term Memory Network for Accelerometer-Based Hypertension Classification.

Melissa Ouellet¹, Katarzyna Wac², Clauirton Siebra³

¹Digital Health Cluster, Hasso Plattner Institute, Potsdam, Germany.

Studies in Health Technology and Informatics

|May 17, 2025

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

Two decades of growth and trends in the FDA authorization of digital medical devices.

NPJ digital medicine·2026

Same author

Passive digital health technologies for Alzheimer's disease screening and diagnosis: a systematic review.

NPJ digital medicine·2026

Same author

Factors Influencing the Use of Mobile Apps and Wearables: Pre- and Post-Surgery Quality of Life Assessment Study.

JMIR formative research·2026

Same author

Multi-stakeholder use of patient experience data (PED): current state and future opportunities for the application of PED to inform decision-making.

Journal of patient-reported outcomes·2026

Same author

Quality of life in oncology drug approvals: evidence from Swiss decisions in relation to global regulatory trends.

Quality of life research : an international journal of quality of life aspects of treatment, care and rehabilitation·2026

Same author

Digital biomarkers for brain health: passive and continuous assessment from wearable sensors.

NPJ digital medicine·2026

Same journal

The Essential Components and Critical Conditions for Success in a Learning Health System in Oncology.

Studies in health technology and informatics·2026

Same journal

Use of Artificial Intelligence in Screening for Adolescent Idiopathic Scoliosis: A Scoping Review.

Studies in health technology and informatics·2026

Same journal

Movement Related Biomechanics in Adolescent Idiopathic Scoliosis: A Review of Reviews.

Studies in health technology and informatics·2026

Same journal

The Impact of Surgical Correction of Adolescent Idiopathic Scoliosis Using Posterior Spinal Fusion on Selected Radiological Parameters and Respiratory Function.

Studies in health technology and informatics·2026

Same journal

Acute Effect of Physio-logic® Exercises on Muscle Tone and Stiffness in Adolescent Idiopathic Scoliosis Patients: A Preliminary Study.

Studies in health technology and informatics·2026

Same journal

Effects of Integrated Music and Occupational Therapy on Motor and Autonomic Function in Children with Neurogenic Scoliosis.

Studies in health technology and informatics·2026

See all related articles

A Long Short-Term Memory (LSTM) model achieved 96.37% accuracy in classifying hypertension using accelerometer data on physical activity and sleep. This deep learning approach shows promise for wearable health monitoring systems.

Area of Science:

Biomedical Engineering
Health Informatics
Machine Learning

Background:

Hypertension classification traditionally relies on clinical measurements.
Wearable sensors offer continuous physiological data for health monitoring.
Analyzing complex sequential data from accelerometers is challenging for traditional methods.

Purpose of the Study:

To evaluate the efficacy of a Long Short-Term Memory (LSTM) architecture for hypertension classification.
To compare LSTM performance against other sequence models and traditional machine learning algorithms.
To assess the potential of LSTM for early hypertension detection using accelerometer data.

Main Methods:

Utilized the NHANES 2011-2012 dataset containing accelerometer data on physical activity and sleep.

Keywords:

Behavioral analytics Deep learning Hypertension Long Short-Term Memory Mobile health

Related Experiment Videos

Developed and applied a Long Short-Term Memory (LSTM) neural network model.

Compared LSTM performance with Recurrent Neural Networks (RNN), Transformers (TF), 1D Convolutional Networks (Conv1D), and traditional machine learning models.

Main Results:

The LSTM model achieved a superior classification accuracy of 96.37% for hypertension.
LSTM significantly outperformed RNN (75.67%), TF (77.10%), Conv1D (89.34%), and traditional ML models (60.92%-64.75%).
Sequential pattern recognition in physical activity and sleep data by LSTM proved effective.

Conclusions:

LSTM architecture demonstrates high potential for accurate hypertension classification from accelerometer data.
LSTM models can be integrated into wearable health monitoring systems for early hypertension detection or management.
Deep learning sequence models offer advantages over traditional methods for analyzing complex physiological time-series data.