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

Related Concept Videos

Pharmacokinetic Models: Comparison and Selection Criterion

Pharmacokinetic Models: Comparison and Selection Criterion

Physiological and compartmental models are valuable tools used in studying biological systems. These models rely on differential equations to maintain mass balance within the system, ensuring an accurate representation of the dynamic processes at play.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Respiratory and oxygen saturation data for improved modelling and detection of obstructive sleep apnoea.

Data in brief·2026

Same author

'Impossible' Insulin to C-Peptide Ratios are Common in Insulin-Free Pre-term NICU Infants: Antibodies Act as a Storage Medium.

Journal of diabetes science and technology·2026

Same author

Demand-Side Management for a Decentralised and Equitable Energy Transition in Aotearoa New Zealand.

Journal of the Royal Society of New Zealand·2026

Same author

Quantifying the recollection of discomfort and emotional suffering during a stay in intensive care: development and validation of the EXPRIM questionnaire : EXPRIM: quantification of discomfort experienced during an ICU stay.

Journal of patient-reported outcomes·2026

Same author

Tight Glycemic Control Can Be Achieved in Adult ICU Patients Safely: Results From a 5-Year Single-Center Observational Study Using the STAR Glycemic Control Framework.

Journal of diabetes science and technology·2026

Same author

Incorporating patient history into the insulin sensitivity prediction in intensive care by feedforward neural network models.

International journal of medical informatics·2026

Search research articles

Related Experiment Video

Updated: Jul 26, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Classification-based deep neural network vs mixture density network models for insulin sensitivity prediction

Balázs Benyó¹, Béla Paláncz¹, Ákos Szlávecz¹

¹Department of Control Engineering and Information Technology, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Budapest, Hungary.

Computer Methods and Programs in Biomedicine

|June 21, 2023

Summary

This summary is machine-generated.

New neural network models accurately predict insulin sensitivity for model-based glycemic control (GC) in intensive care units (ICUs). These advanced methods match or exceed current predictions, improving patient state monitoring.

Keywords:

Artificial intelligence Deep neural network Glycaemic control Intensive care Machine learning Mixture density network STAR insulin sensitivity

More Related Videos

An In Ovo Model for Testing Insulin-mimetic Compounds

An In Ovo Model for Testing Insulin-mimetic Compounds

Published on: April 23, 2018

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

Related Experiment Videos

Last Updated: Jul 26, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

An In Ovo Model for Testing Insulin-mimetic Compounds

An In Ovo Model for Testing Insulin-mimetic Compounds

Published on: April 23, 2018

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

Area of Science:

Biomedical Engineering
Artificial Intelligence in Medicine
Clinical Informatics

Background:

Intensive care units (ICUs) commonly manage stress-induced hyperglycemia using model-based glycemic control (GC) protocols.
The STAR (Stochastic-TARgeted) protocol, a widely used model-based GC, relies on patient-specific insulin sensitivity for accurate glucose management.
Predicting patient insulin sensitivity is crucial for optimizing GC effectiveness and patient outcomes.

Purpose of the Study:

To develop and evaluate novel neural network-based methods for predicting patient insulin sensitivity.
To compare the predictive accuracy of these new methods against existing model-based predictions used in clinical practice.
To assess the potential of these AI-driven approaches for enhancing patient state prediction in GC.

Main Methods:

Two deep neural network architectures were developed: a classification deep neural network and a Mixture Density Network.
These models were trained using treatment data from three distinct patient cohorts.
The prediction accuracy of the neural network models was benchmarked against the current model-based predictions guiding clinical care.

Main Results:

The developed neural network models demonstrated prediction accuracy that was equivalent to or surpassed the reference model-based predictions.
Both the classification deep neural network and the Mixture Density Network proved effective in estimating patient insulin sensitivity.
The findings suggest a strong potential for these AI methods in improving patient state prediction for GC.

Conclusions:

The study introduces promising neural network-based methods for predicting insulin sensitivity in the context of model-based glycemic control.
These AI approaches offer a potentially superior alternative to current methods for patient state prediction in ICUs.
Further validation through in-silico simulations and clinical trials is recommended to confirm the clinical utility and safety of these novel techniques.