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 Concept Videos

Rational Dosage Regimen: Maintenance Dose and Loading Dose01:24

Rational Dosage Regimen: Maintenance Dose and Loading Dose

4.2K
A rational dosage regimen considers a drug's pharmacokinetics, including its absorption, distribution, metabolism, and elimination from the body. By understanding these factors, the appropriate dosage can be determined, and the dosing schedule can be designed to achieve and maintain the desired therapeutic effect while minimizing adverse effects.
In most cases, drugs are administered repetitively or infused continuously to maintain a steady-state concentration in the body. At a steady...
4.2K
Three-Compartment Open Model01:06

Three-Compartment Open Model

311
The three-compartment open model is a pharmacokinetic model used to describe the distribution and elimination of drugs following extravascular administration. It comprises a central compartment representing the plasma and two peripheral compartments. The highly perfused peripheral compartment represents organs and tissues with a rich blood supply, such as the liver, kidneys, and lungs. The scarcely perfused peripheral compartment represents tissues with lower blood supply, such as adipose...
311
Pharmacokinetic Models: Comparison and Selection Criterion01:26

Pharmacokinetic Models: Comparison and Selection Criterion

115
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.
115
Dosage Regimen: Fixed Dose01:01

Dosage Regimen: Fixed Dose

1.9K
Fixed-dose regimens are a common approach to administer drugs to achieve and maintain desired levels of the drug in the body. In this dosing strategy, a specific amount of medication is given at regular intervals, often multiple times a day, to ensure a consistent drug concentration in the bloodstream.
Fixed-dose regimens can be used for various routes of administration, including intravenous (IV) injections and oral medications. For IV administration, a predetermined amount of the drug is...
1.9K
Model Approaches for Pharmacokinetic Data: Distributed Parameter Models01:06

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models

101
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
101
Drug Dosage Regimen: Overview01:15

Drug Dosage Regimen: Overview

3.6K
A drug dosage regimen describes the specific instructions and schedule for administering a drug to a patient. It considers factors such as drug dosage, frequency, route of administration, and duration of treatment. Designing an appropriate dosage regimen for a patient aims to achieve a target drug concentration at the site of action.
Typically, the starting dose and dosing interval are guided by the manufacturer's recommendations based on clinical trials conducted during and after drug...
3.6K

You might also read

Related Articles

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

Sort by
Same author

Additive effects of fecal microbiota transplantation and infliximab on gut microbiome and metabolome in refractory inflammatory bowel disease patients.

mSystems·2026
Same author

Mechanistic insights into how wheat flour mill streams affect Chinese steamed bread quality: A perspective from starch multi-scale structure and physicochemical properties.

Carbohydrate polymers·2026
Same author

Diagnostic performance of contrast-enhanced ultrasound vs. conventional ultrasound for lymph node metastasis in patients with thyroid cancer: A meta-analysis.

Oncology letters·2025
Same author

Study on Demulsification via Vacuum Filtration with Superamphiphilic Diatomite/G-C<sub>3</sub>N<sub>4</sub>/Rice Husk Charcoal Composite Filter Layer.

Nanomaterials (Basel, Switzerland)·2025
Same author

Diagnosis and Analysis of Vasa Previa Types With Flow HD Glass Body.

Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine·2024
Same author

STGIC: A graph and image convolution-based method for spatial transcriptomic clustering.

PLoS computational biology·2024

Related Experiment Video

Updated: Jul 31, 2025

A Data-Driven Approach to Quantifying Immune States in Sepsis
07:42

A Data-Driven Approach to Quantifying Immune States in Sepsis

Published on: February 7, 2025

278

A dosing strategy model of deep deterministic policy gradient algorithm for sepsis patients.

Tianlai Lin1, Xinjue Zhang2, Jianbing Gong3

  • 1Department of Critical Care Medicine, Quanzhou First Hospital Affiliated to Fujian Medical University, Quanzhou, Fujian, China.

BMC Medical Informatics and Decision Making
|May 4, 2023
PubMed
Summary

This study developed an AI system using the deep deterministic policy gradient (DDPG) algorithm to optimize sepsis treatment. The AI’s recommendations significantly reduced patient mortality by aligning clinician decisions with optimal dosing strategies.

Keywords:
ClinicianModelReinforcement learningSepsis

More Related Videos

A Controlled Mouse Model for Neonatal Polymicrobial Sepsis
14:54

A Controlled Mouse Model for Neonatal Polymicrobial Sepsis

Published on: January 27, 2019

11.1K
A Reproducible Intensive Care Unit-Oriented Endotoxin Model in Rats
05:56

A Reproducible Intensive Care Unit-Oriented Endotoxin Model in Rats

Published on: February 20, 2021

2.1K

Related Experiment Videos

Last Updated: Jul 31, 2025

A Data-Driven Approach to Quantifying Immune States in Sepsis
07:42

A Data-Driven Approach to Quantifying Immune States in Sepsis

Published on: February 7, 2025

278
A Controlled Mouse Model for Neonatal Polymicrobial Sepsis
14:54

A Controlled Mouse Model for Neonatal Polymicrobial Sepsis

Published on: January 27, 2019

11.1K
A Reproducible Intensive Care Unit-Oriented Endotoxin Model in Rats
05:56

A Reproducible Intensive Care Unit-Oriented Endotoxin Model in Rats

Published on: February 20, 2021

2.1K

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Medicine
  • Critical Care Medicine

Background:

  • Computerized decision support systems (CDSS) aid disease treatment and resource management.
  • Artificial intelligence (AI) is increasingly used in medical decision-making for optimal dosing and improved survival rates, particularly in sepsis.
  • Previous AI systems for sepsis treatment were developed by MIT and ICL.

Purpose of the Study:

  • To develop an AI-based medical decision-making system using the deep deterministic policy gradient (DDPG) algorithm.
  • To create a system that mimics professional clinician decisions for sepsis treatment.
  • To effectively reduce the mortality rate of sepsis patients.

Main Methods:

  • Utilized the Multiparameter Intelligent Monitoring in Intensive Care III (MIMIC-III) dataset, containing 38,600 adult sepsis patient hospitalizations.
  • Applied the DDPG algorithm, a reinforcement learning approach, to construct the AI medical decision-making system.
  • Analyzed model results in a two-dimensional space to determine optimal sepsis patient dosing combinations.

Main Results:

  • AI-recommended dosing led to the lowest patient mortality rate (11.59%), a 4.2% reduction compared to the baseline (15.7%).
  • Deviations from AI recommendations increased patient mortality.
  • The DDPG-based AI system's dosing recommendations were closer to those of human clinicians than the Deep-Q Learning Network (DQN) algorithm, increasing clinician adherence by 142.3% and reducing mortality by 2.58%.

Conclusions:

  • The DDPG-based AI system generates treatment plans aligned with clinicians, reducing sepsis patient mortality.
  • This AI system can assist clinicians in managing complex ICU patient conditions.
  • The AI system shows potential for providing optimal drug dosing recommendations.