Reinforcement Learning for Warfarin Dosing

NCT03962400 — Phase 4, Withdrawn, University of Louisville

ClinicalTrials Daily · Areas · Conditions · Drugs · Sponsors ·

Randomized Trial of Reinforcement Learning for the Dosing of Warfarin

Registry	NCT03962400
Status	Withdrawn - The study did not receive anticipated funding and therefore never opened to enrollment. The study was never submitted to the IRB for approval since the funding failed.
Phase	Phase 4
Study type	Interventional; randomized, parallel, masking: single, treatment
Sponsor	University of Louisville (Other)
Conditions	Clotting Disorder
Interventions	Reinforcement Learning, Heath Care Provider (Procedure)
Dates	start 2022-01-01 (estimated), primary completion 2024-12-31 (estimated), completion 2025-12-31 (estimated), first posted 2019-05-24, last updated 2022-03-04

-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.

Expand all sections · Collapse all

+Detailed description

This will be a single-center, open-label, randomized prospective study. Primary outcome will be percent of time within a specific INR range. Subjects will be randomized to to control and treatment groups and stratified 1:1 based on sex. The control group will have warfarin doses adjusted by experts in the treatment of patients with warfarin. The treatment group will have warfarin doses determined using a clinical support tool based on reinforcement learning. Based on simulations of the experimental design with an expectation that the percent of INR values within the target range increase by 20%, 70 subjects per group are required for statistical significance. Based on an attrition rate of 15%, the investigators will enroll 80 subjects per group. Statistical analysis will compare the percent of patients within the target INR range between groups as the primary outcome with number of adverse events between groups as the safetly outcome.

+Arms and interventions

Arm	Type	Interventions	Description
Control	Active comparator	Procedure: Heath Care Provider	Subjects will have warfarin dose determined in the usual fashion by a health care provider.
Treatment	Experimental	Procedure: Reinforcement Learning	Subjects will have warfarin dose determined using a reinforcement learning computer model.

Reinforcement Learning (Procedure): New computer based procedure for determining dose using a decision support tool
Heath Care Provider (Procedure): Warfarin dose will be determined by a qualified health care provider

+Outcome measures

Primary outcomes

Percent in Range [6 months]: Percent of INR measurements within the Target Range

Secondary outcomes

Adverse Events [6 Months]: Composite of all adverse events attributed to warfarin

+Eligibility

Sex: All, ages: 18 Years to 99 Years

Inclusion Criteria:

* Receiving anticoagulation treatment with warfarin.

Exclusion Criteria:

* 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.