70 Participants Needed

Reinforcement Learning for Aging

(REINFORCE-EHR Trial)

JL
Overseen ByJulie Lauffenburger, PharmD, PhD
Age: 18+
Sex: Any
Trial Phase: Academic
Sponsor: Brigham and Women's Hospital
No Placebo GroupAll trial participants will receive the active study treatment (no placebo)

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial aims to test a smart computer program designed to help doctors stop or reduce risky medications for older adults. The program uses reinforcement learning, a type of artificial intelligence, to select the best tools for doctors based on their past actions. Researchers will compare the program against regular care without these tools to determine which is more effective. Patients aged 65 or older who have frequently been prescribed high-risk medications in the last six months are a good fit for this trial. As an unphased trial, this study offers an opportunity to contribute to innovative research that could enhance medication safety for older adults.

Will I have to stop taking my current medications?

The trial does not specify if participants must stop taking their current medications. However, it focuses on helping doctors reduce or stop high-risk medications for older adults, so your doctor might discuss changes to your medication.

What prior data suggests that this reinforcement learning approach is safe for primary care providers?

Research has shown that using reinforcement learning in healthcare is generally safe for people. This method involves computer programs that assist doctors in making better decisions, such as when to stop or reduce high-risk medications for older adults. It has not shown any direct harm to patients because it focuses on enhancing doctors' actions rather than altering medications directly.

Studies have found that these tools can identify high-risk patients early and assist doctors in making safer medication choices. While researchers continue to study the use of reinforcement learning in medicine, no evidence suggests it causes negative effects on patients. Instead, it aims to improve how doctors prescribe or stop medications, leading to safer outcomes for patients.12345

Why are researchers excited about this trial?

Researchers are excited about the use of reinforcement learning in healthcare because it offers a personalized approach to medication management for aging patients. Unlike traditional methods that rely on fixed protocols, this reinforcement learning program adapts to each primary care provider by selecting electronic health record (EHR) tools tailored to encourage deprescribing of risky medications. The program's unique algorithm learns and improves its recommendations over time, aiming to optimize patient outcomes by promoting safer prescribing habits. This dynamic and personalized strategy could lead to more effective and safer medication use in older adults.

What evidence suggests that this reinforcement learning intervention is effective for deprescribing high-risk medications?

Research has shown that reinforcement learning can aid in deprescribing, which involves reducing or stopping medications that might be unhelpful or harmful. A review of studies found that deprescribing reduces unnecessary medications for older adults. In this trial, one group of participants will receive a reinforcement learning intervention that personalizes electronic health records (EHR) tools for primary care providers (PCPs) to promote deprescribing high-risk medications. This method uses adaptive computer programs to encourage doctors to make better medication choices for their patients over time. Another group will receive usual care, without additional EHR-based tools beyond those used in regular clinical practice. Studies have also shown that educational tools in healthcare improve medication management, enhancing patient safety.678910

Are You a Good Fit for This Trial?

This trial is for primary care providers (PCPs) at Atrius Health in Massachusetts. It's focused on helping them to safely reduce or stop prescribing high-risk medications for older adults. The PCPs will be part of a study that uses a new method within their electronic health records.

Inclusion Criteria

Intervention targets primary care providers (including physicians and PCP-designated nurse practitioners and physician assistants) at Atrius Health
I am 65 or older and have been prescribed 90 or more high-risk pills in the last 6 months.

Exclusion Criteria

Prior randomization to intervention arm in the prior NUDGE-EHR trial
Not a primary care provider at Atrius Health

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Treatment

Primary care providers are randomized to either a reinforcement learning intervention or usual care for deprescribing high-risk medications

30 weeks

Follow-up

Participants are monitored for safety and effectiveness after treatment

4 weeks

What Are the Treatments Tested in This Trial?

Interventions

  • Reinforcement Learning
Trial Overview The study tests a reinforcement learning-based tool integrated into EHR systems against usual care without the tool. Sixty PCPs will be randomly assigned to either use the new tool or continue with standard practices, and they'll participate for about 30 weeks.
How Is the Trial Designed?
2Treatment groups
Experimental Treatment
Active Control
Group I: Reinforcement learning interventionExperimental Treatment1 Intervention
Group II: Usual careActive Control1 Intervention

Find a Clinic Near You

Who Is Running the Clinical Trial?

Brigham and Women's Hospital

Lead Sponsor

Trials
1,694
Recruited
14,790,000+

National Institute on Aging (NIA)

Collaborator

Trials
1,841
Recruited
28,150,000+

Atrius Health

Collaborator

Trials
3
Recruited
1,500+

Published Research Related to This Trial

Current drug safety systems often fail to identify certain adverse drug reactions (ADRs) that may mimic age-related chronic diseases, especially in older populations.
To better detect these 'silent' ADRs that can develop from long-term drug use, a new systematic search strategy is needed alongside existing clinical trials and reporting systems.
The out-of-focus bias in drug surveillance.Gnädinger, M., Mellinghoff, HU.[2021]
Aging significantly increases the risk of liver-related adverse drug reactions (L-ADR), with a 33% increase in relative risk for every 10-year increase in age, based on an analysis of 64,702 reports from the China National ADR Monitoring System.
The study identified that certain drug categories, particularly antiarrhythmic, antilipemic, and antihypertensive medications, have a high correlation with L-ADR in older adults, highlighting the need for careful risk management when prescribing these drugs to this age group.
Age-Associated Risk of Liver-Related Adverse Drug Reactions.Han, YZ., Guo, YM., Xiong, P., et al.[2022]

Citations

Reinforcement Learning for AgingThe primary outcome will be discontinuation or ordering a dose taper for the high-risk medications for eligible patients by included primary care providers, ...
Effectiveness of educational interventions in general practice ...This review will explore educational interventions as key components of effective strategies to improve medication appropriateness and promote ...
Deprescribing in Community-Dwelling Older AdultsThis systematic review and meta-analysis found moderate certainty evidence that deprescribing interventions were associated with reducing medications in ...
Identifying Deprescribing Opportunities With Large Language ...The results of this study underscore the promise of LLMs in enhancing deprescribing workflows by providing rapid filtering of PIMs, which could ...
A New Model of Pharmacist-based Polypharmacy ...The machine learning approaches applicable to deprescribing are natural language processing (NLP) to retrieve medication-related data in clinical notes, ...
Reinforcement Learning and Its Clinical Applications ...Background/Objectives: Reinforcement learning (RL), a subset of machine learning, has emerged as a promising tool for supporting precision medicine and dynamic ...
Optimizing long term disease prevention with ...These tools have been extensively used to assist in identifying patients at elevated risk for early prevention. However, there has been limited ...
Comparing Fourteen Behavioral Science Electronic Health ...The primary outcome was deprescribing (composite of PCP-directed discontinuation or tapering) over follow-up, measured using EHR data. We used ...
Machine learning to predict adverse drug events based on ...This systematic review aimed to provide a comprehensive overview of the application of machine learning (ML) in predicting multiple adverse drug events (ADEs)
Medicine Optimisation and Deprescribing Intervention ...Medicine optimisation and deprescribing interventions generally reduced the number and increased the appropriateness of medications.
Unbiased ResultsWe believe in providing patients with all the options.
Your Data Stays Your DataWe only share your information with the clinical trials you're trying to access.
Verified Trials OnlyAll of our trials are run by licensed doctors, researchers, and healthcare companies.
Terms of Service·Privacy Policy·Cookies·Security