A Deployed Online Reinforcement Learning Algorithm In An Oral Health Clinical Trial

Anna L. Trella, Kelly W. Zhang, Hinal Jajal, Inbal Nahum-Shani, Vivek Shetty +2 more
9/3/2024
cs.AIcs.HC

No official code found. Best implementation: StatisticalReinforcementLearningLab/oralytics-post-deployment-analysis (1 star, GPL-3.0, last commit 2024-12-18).

Abstract

Dental disease is a prevalent chronic condition associated with substantial financial burden, personal suffering, and increased risk of systemic diseases. Despite widespread recommendations for twice-daily tooth brushing, adherence to recommended oral self-care behaviors remains sub-optimal due to factors such as forgetfulness and disengagement. To address this, we developed Oralytics, a mHealth intervention system designed to complement clinician-delivered preventative care for marginalized individuals at risk for dental disease. Oralytics incorporates an online reinforcement learning algorithm to determine optimal times to deliver intervention prompts that encourage oral self-care behaviors. We have deployed Oralytics in a registered clinical trial. The deployment required careful design to manage challenges specific to the clinical trials setting in the U.S. In this paper, we (1) highlight key design decisions of the RL algorithm that address these challenges and (2) conduct a re-sampling analysis to evaluate algorithm design decisions. A second phase (randomized control trial) of Oralytics is planned to start in spring 2025.

View on arXivView PDF

Code Implementations(1)

StatisticalReinforcementLearningLab/oralytics-post-deployment-analysisCommunity100%
GPL-3.0

Code for a re-sampling analysis of the RL algorithm deployed in the MRT (phase 1) of the Oralytics trial. The re-sampling analysis re-evaluates algorithm design decision made for phase 1.

11TeX, ShellJun 21, 20241 years agoGPL-3.0

Similar Papers

Monitoring Fidelity of Online Reinforcement Learning Algorithms in Clinical Trials

84% match2024

Toward a Reinforcement-Learning-Based System for Adjusting Medication to Minimize Speech Disfluency

79% match2023

MedGym:A Unified Continuous-Time Benchmark for Dynamic Medical Treatment Reinforcement Learning

79% match2026

SigmaScheduling: Uncertainty-Informed Scheduling of Decision Points for Intelligent Mobile Health Interventions

78% match2025

Diabetes Lifestyle Medicine Treatment Assistance Using Reinforcement Learning

77% match2025

Designing and evaluating an online reinforcement learning agent for physical exercise recommendations in N-of-1 trials

77% match1 repo42023

Cite this paper

@article{trella2024deployed,
  title  = {A Deployed Online Reinforcement Learning Algorithm In An Oral Health Clinical Trial},
  author = {Anna L. Trella and Kelly W. Zhang and Hinal Jajal and Inbal Nahum-Shani and Vivek Shetty and Finale Doshi-Velez and Susan A. Murphy},
  year   = {2024},
  eprint = {2409.02069},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2409.02069v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2409.02069.svg)](https://codeofpaper.com/paper/2409.02069)

Discussion