Precision Nudging Drives Wellness Visit Attendance at Scale

Employing Machine Learning and Behavioral Science Solutions to Increase Women's Wellness Scheduling and Attendance: A Randomized Controlled Trial

The purpose of the present randomized controlled trial is to explore the effectiveness of a 12-month well woman digital health intervention leveraging Precision Nudging - the application of behavioral science and reinforcement learning to create individualized, tailored health messaging at scale that matches the right message to the right person at the right time - in promoting behavior change. Specifically, it is hypothesized that scaling behavioral science through reinforcement learning will be more effective at motivating participants to engage with well woman messages and to schedule and to attend a well woman visit compared to a standard of care message.

Study Overview

• Status: Completed
• Conditions: Health Behavior; Women's Health; Prevention; Annual Visit; Well Visit
• Intervention / Treatment: Other: Precision nudging; Other: Standard of care

• Study Type: Interventional
• Enrollment (Actual): 30068
• Phase: Not Applicable

Contacts and Locations

Study Locations

• United States
  • New York
    • New York, New York, United States, 14617
      • Rochester Regional Health

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 21 years to 65 years (Adult, Older Adult)
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

• Patient of health care system.
• Visit with OBGYN office in the last 36 months.
• OBGYN office provider is a Women's Wellness group approved provider.

Exclusion Criteria:

• Completed a women's wellness within the last 366 days.
• Upcoming women's wellness appointment.
• Had a childbirth episode (e.g., C-section vaginal delivery, or other event, including stillbirth) within the last 3 months or has a pregnancy due date in the future.
• Unsubscribed.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Other
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Triple

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Treatment; Behavioral science and reinforcement learning-driven hyper-personalized messages	Other: Precision nudging; Precision nudging (i.e., the application of behavioral science and reinforcement learning to create individualized, tailored health messaging at scale that matches the right message to the right person at the right time)
Active Comparator: Control; Standard of care message	Other: Standard of care; Standard of care communication (e.g., personalized letters and patient portal notices)

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Time Frame
Proportion of participants who attended a well woman visit	3 months
Proportion of participants who attended a well woman visit	6 months
Proportion of participants who attended a well woman visit	9 months
Proportion of participants who attended a well woman visit	12 months
Proportion of participants who scheduled a well woman visit	3 months
Proportion of participants who scheduled a well woman visit	6 months
Proportion of participants who scheduled a well woman visit	9 months
Proportion of participants who scheduled a well woman visit	12 months
Proportion of participants who scheduled a well woman visit and did not attend (and did not Cancel and/or Reschedule)	3 months
Proportion of participants who scheduled a well woman visit and did not attend (and did not Cancel and/or Reschedule)	6 months
Proportion of participants who scheduled a well woman visit and did not attend (and did not Cancel and/or Reschedule)	9 months
Proportion of participants who scheduled a well woman visit and did not attend (and did not Cancel and/or Reschedule)	12 months

Secondary Outcome Measures

Outcome Measure	Time Frame
Proportion of participants who opened and/or clicked Call-to-Action, or otherwise engaged with the communication(s)	3 months
Proportion of participants who opened and/or clicked Call-to-Action, or otherwise engaged with the communication(s)	6 months
Proportion of participants who opened and/or clicked Call-to-Action, or otherwise engaged with the communication(s)	9 months
Proportion of participants who opened and/or clicked Call-to-Action, or otherwise engaged with the communication(s)	12 months

Collaborators and Investigators

• Sponsor: Lirio
• Collaborators: Rochester Regional Health
• Investigators: Principal Investigator: Laurie Ernest, DNP, BSN, MS, WHNP-C, Rochester Regional Health

Study record dates

Study Major Dates

• Study Start (Actual): September 7, 2022
• Primary Completion (Actual): January 9, 2024
• Study Completion (Actual): January 9, 2024

Study Registration Dates

• First Submitted: August 17, 2022
• First Submitted That Met QC Criteria: August 17, 2022
• First Posted (Actual): August 19, 2022

Study Record Updates

• Last Update Posted (Estimated): January 17, 2024
• Last Update Submitted That Met QC Criteria: January 16, 2024
• Last Verified: January 1, 2024

More Information

Terms related to this study

• Keywords: Artificial Intelligence; Behavior Change; Digital Health Intervention; Reinforcement Learning
• Other Study ID Numbers: LRRHWWRCT; IRB 2129 (Other Identifier: Rochester Regional Health Institutional Review Board)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No