Reinforcement Learning for Warfarin Dosing

NCT03962400 | Withdrawn Phase 4

• 1 other identifier: KDP002
• Study Type: interventional
• Target: N/A
• Locations: 0 countries
• Sites: N/A

Brief Summary

This is a clinical study designed to test the hypothesis that a computer model for dosing warfarin is superior to current clinical practice. Subjects will be randomized to two groups based on how warfarin dose is determined and followed for 6 months. The primary outcome is the percent of the time that the INR is maintained in the effective range.

Conditions

Clotting Disorder

Keywords

warfarin

Outcome Measures

Primary Outcomes (1)

• Percent in Range

  Percent of INR measurements within the Target Range

  6 months

Secondary Outcomes (1)

• Adverse Events

  6 Months

Study Arms (2)

Control

ACTIVE COMPARATOR

Subjects will have warfarin dose determined in the usual fashion by a health care provider.

Procedure: Heath Care Provider

Treatment

EXPERIMENTAL

Subjects will have warfarin dose determined using a reinforcement learning computer model.

Procedure: Reinforcement Learning

Interventions

Reinforcement Learning PROCEDURE

New computer based procedure for determining dose using a decision support tool

Treatment

Heath Care Provider PROCEDURE

Warfarin dose will be determined by a qualified health care provider

Control

Eligibility Criteria

• Age: 18 Years - 99 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Receiving anticoagulation treatment with warfarin.

You may not qualify if:

• Pregnancy.
• History of hemorrhagic cerebrovascular incident.
• Acquired or inherited hemophilia.
• Thrombocytopenia (\<100,000 platelets per mm3) on 2 occasions separated by 2 days.
• Anemia with hemoglobin concentration \< 10 g/dL.
• Active cancer excluding non-melanoma skin cancers.
• Active liver disease as documented by prolonged baseline INR ≥ 1.6.
• Uncontrolled hypertension with 2 readings \>180/110.
• Recent (\< 2 weeks) neurosurgical procedure.
• Enrollment in hospice program for any diagnosis.

Sponsors & Collaborators

• University of Louisville: lead

MeSH Terms

Conditions

Hemostatic Disorders

Interventions

Reinforcement Machine Learning

Condition Hierarchy (Ancestors)

Vascular Diseases; Cardiovascular Diseases; Hemorrhagic Disorders; Hematologic Diseases; Hemic and Lymphatic Diseases

Intervention Hierarchy (Ancestors)

Machine Learning; Artificial Intelligence; Algorithms; Mathematical Concepts

Study Design

• Study Type: interventional
• Phase: phase 4
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: PARTICIPANT
• Masking Details: Subjects will not be informed of group designation
• Purpose: TREATMENT
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Associate Professor

Model Details: Randomized Controlled Trial of 2 groups. Subjects in the Control group will receive warfarin with dose adjustment guided by standard protocol. Subjects in the Treatment group will receive warfarin with dose adjustment guided by personalized protocol.

Study Record Dates

• First Submitted: May 21, 2019
• First Posted: May 24, 2019
• Study Start: January 1, 2022
• Primary Completion: December 31, 2024
• Study Completion: December 31, 2025
• Last Updated: March 4, 2022

Record last verified: 2022-02

Data Sharing

• IPD Sharing: Will not share