Reinforcement Learning for Aging
(REINFORCE-EHR Trial)
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.12345Why 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
Exclusion Criteria
Timeline for a Trial Participant
Screening
Participants are screened for eligibility to participate in the trial
Treatment
Primary care providers are randomized to either a reinforcement learning intervention or usual care for deprescribing high-risk medications
Follow-up
Participants are monitored for safety and effectiveness after treatment
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?
2
Treatment groups
Experimental Treatment
Active Control
The intervention is a reinforcement learning program that personalizes EHR-based tools for PCPs to promote deprescribing high-risk medications over follow-up. The reinforcement learning intervention selects a tool for each provider based on an algorithm from an inventory of EHR tools and chooses tools that are predicted to motivate action for the individual provider. The effectiveness of each tool will be assessed on a selected interval based on whether a deprescribing action is taken by PCPs for eligible patients. The algorithm is trained to maximize these actions over time.
No EHR-based tools provided beyond those used in regular clinical practice.
Find a Clinic Near You
Who Is Running the Clinical Trial?
Brigham and Women's Hospital
Lead Sponsor
National Institute on Aging (NIA)
Collaborator
Atrius Health
Collaborator
Published Research Related to This Trial
Citations
Reinforcement Learning for Aging
The 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 Adults
This 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 Results
We believe in providing patients with all the options.
Your Data Stays Your Data
We only share your information with the clinical trials you're trying to access.
Verified Trials Only
All of our trials are run by licensed doctors, researchers, and healthcare companies.