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

Optimizing warfarin dosing using deep reinforcement learning.

Sadjad Anzabi Zadeh1, W Nick Street1, Barrett W Thomas1

  • 1Department of Business Analytics, Tippie College of Business, University of Iowa, Iowa City, IA 52242, USA.

Journal of Biomedical Informatics
|December 9, 2022
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

Personalized Antibiograms Using Multi-Task Machine Learning: Toward Mechanistic Understanding and Robust Calibration.

Clinical infectious diseases : an official publication of the Infectious Diseases Society of America·2026
Same author

Personalized Antibiogram: A Novel Multi-Task Machine Learning Framework for Simultaneous Prediction of Antimicrobial Resistance Profile with Enhanced Detection of Carbapenem Resistance in Enterobacteriaceae.

Clinical infectious diseases : an official publication of the Infectious Diseases Society of America·2026
Same author

Predicting Nephrotoxic Acute Kidney Injury in Hospitalized Adults: A Machine Learning Algorithm.

Kidney medicine·2024
Same author

Harnessing Natural Language Processing and High-Dimensional Clinical Notes to Detect Goals-of-Care and Surrogate-Designation Conversations.

Clinical nursing research·2024
Same author

Prediction of Cancer Symptom Trajectory Using Longitudinal Electronic Health Record Data and Long Short-Term Memory Neural Network.

JCO clinical cancer informatics·2024
Same author

Evaluating the performance of machine learning methods for risk estimation of delirium in patients hospitalized from the emergency department.

Acta psychiatrica Scandinavica·2023
Same journal

CoAff-DTI: Fine-grained drug-target interaction prediction using pre-trained language models and affinity-guided mechanisms.

Journal of biomedical informatics·2026
Same journal

Evaluation of temporal preservation in synthetic longitudinal patient data.

Journal of biomedical informatics·2026
Same journal

ARKE: An ontology-driven framework for automated mapping of local radiology procedure terms to the LOINC-RadLex playbook using large language model.

Journal of biomedical informatics·2026
Same journal

A validation-driven training controller for cross-lingual biomedical NER via reinforcement learning-based adaptive loss weighting.

Journal of biomedical informatics·2026
Same journal

ASP-HR: An Adaptive Spatial Perception and Hierarchical Reasoning mechanism for document-level biomedical relation extraction.

Journal of biomedical informatics·2026
Same journal

Beyond Accuracy: Safety-Centered guidelines for the evaluation of LLM-based therapy recommendation systems for chronic multimorbidity patients.

Journal of biomedical informatics·2026
See all related articles

A new deep reinforcement learning model improves warfarin dosing for patients. This AI approach simulates virtual patients to create personalized warfarin dosing, outperforming current clinical methods and enhancing patient safety.

Area of Science:

  • Pharmacology and Artificial Intelligence
  • Clinical Decision Support Systems

Background:

  • Warfarin is a critical anticoagulant with a narrow therapeutic range, necessitating precise dosing.
  • Current warfarin dosing protocols often fall short, particularly for sensitive patient populations, leading to potential adverse events.
  • Individualized dosing is essential to mitigate risks associated with warfarin under- or over-dosing.

Purpose of the Study:

  • To develop and evaluate a novel deep reinforcement learning (DRL) model for optimizing warfarin dosage.
  • To address the challenge of limited sample sizes in clinical warfarin dosing trials through simulation.
  • To compare the efficacy of the proposed DRL dosing model against established clinical protocols.

Main Methods:

  • A deep reinforcement learning algorithm was employed to create a warfarin dosing model.
Keywords:
AnticoagulationDeep reinforcement learningDrug dosingPersonalized medicineSequential decision making

Related Experiment Videos

  • Pharmacokinetic/Pharmacodynamic (PK/PD) models of warfarin were utilized to generate simulated dose-response data from virtual patients.
  • The DRL model's performance was evaluated on virtual patient cohorts using established PK/PD simulations.

    • Main Results:

    • The proposed DRL-based warfarin dosing model demonstrated superior performance compared to a set of clinically accepted dosing protocols.
    • Simulations indicated that the DRL model significantly improved dosing accuracy and patient outcomes in virtual trials.
    • Robustness testing on a secondary PK/PD model confirmed the DRL protocol's performance was comparable to baseline methods.

    Conclusions:

    • Deep reinforcement learning offers a promising approach for personalized warfarin dosing.
    • AI-driven simulation using PK/PD models can effectively overcome data limitations in drug dosing research.
    • The developed DRL model has the potential to enhance warfarin therapy safety and efficacy.