Generative Artificial Intelligence Nurse Staffing Study

NCT06978790 | Not Yet Recruiting

• 1 other identifier: 41775
• Study Type: interventional
• Target: 660
• Locations: 0 countries
• Sites: N/A

Brief Summary

This study is guided by Maslach's Burnout Theory and with Normalization Process Theory supporting the implementation of the GAINS intervention by facilitating its integration into routine system-level practice. In Year 1, the investigative team will collaborate with hospital-based nursing leadership and key stakeholders to identify staffing-specific factors essential for operationalizing the GAINS AI model/intervention. In Year 1, the investigators will also conduct a survey amongst nursing staff to measure baseline burnout. In Year 2, the AI-staffing intervention will be implemented with the medical-surgical nursing float pool team. In Year 3, the investigators will first repeat the nurse burnout survey and second, expand the intervention to include the nursing assistant float pool team. In Year 4, the investigators will conduct the final burnout survey with nurses, assess feasibility of GAINS (target vs. actual staffing- nurses and nursing assistants), and assess preliminary efficacy of GAINS to reduce costs related to staffing. the investigators will compare outcomes at three time points (pre, mid, and post-intervention). Interviews with nurses, nursing assistants, unit nurse managers, and leadership will further explicate the intervention's acceptability, feasibility, and impact on burnout.

Conditions

Burnout, Healthcare Workers

Outcome Measures

Primary Outcomes (2)

• Maslach's Burnout Inventory

  Using Maslach's Burnout Inventory, burnout is the primary outcome measure and will assess burnout (1) at baseline over a time frame of 2 weeks, (2) 12-months after the GAINS intervention is applied to the float pool nurses over a time frame of 2 weeks, and 12-months after the GAINS intervention is applied to the float pool nurses and nursing assistants over a time frame of 2 weeks.

  Up to 2.5 years

• Qualitative Interviews to Evaluate Feasibility, Normalization, and Acceptability of the GAINS Intervention

  We will interview 10-20 key stakeholders to collect and analyze qualitative data to evaluate the feasibility, normalization, and acceptability of the GAINS intervention. T3here are two phases of the GAINS intervention. 1. Phase I: GAINS study applied to nurses in Year 2 2. Phase 2: GAINS study applied to nurses and nursing assistants in Year These qualitative interviews will be held in Year 3 after Phase 1 over a 1-month time frame and Year 4 after Phase 2 completion of the study over a 1-month time frame. Interviews will be conducted to gather in-depth feedback on the intervention's feasibility, acceptability, and normalized into nursing practice.

  Up to 3 years

Secondary Outcomes (2)

• Optimization Staffing Rates [Target staffing rate - Actual staffing rate]

  Up to 2 years

• Total Cost: Travel Nurse and Nurse Overtime

  Up to 2 years

Study Arms (3)

Arm 1: Standard staffing practice for float pool nurse and nursing assistants.

EXPERIMENTAL

This arm represents the control or standard of staffing practice to assign float pool nurse and nursing assistants.

Other: Generative Artificial Intelligence Nurse Staffing (GAINS) Intervention

Arm 2: GAINS intervention applied to float pool nurses

EXPERIMENTAL

Generative Artificial Intelligence Nurse Staffing (GAINS) intervention applied to float pool nurses.

Other: Generative Artificial Intelligence Nurse Staffing (GAINS) Intervention

Arm 3: GAINS intervention applied to float pool nurses and nursing assistants

EXPERIMENTAL

Generative Artificial Intelligence Nurse Staffing (GAINS) intervention applied to float pool nurses and nursing assistants.

Other: Generative Artificial Intelligence Nurse Staffing (GAINS) Intervention

Interventions

Generative Artificial Intelligence Nurse Staffing (GAINS) Intervention OTHER

The Generative Artificial Intelligence intervention is an industrial engineering and nursing-informed innovation developed to optimize team-based staffing of registered nurses and nursing assistants. We anticipate that the GAINS intervention will enhance staffing efficiency, reduces reliance on travel nurses, minimizes overtime costs, and supports nurse well-being by proactively managing workload distribution and reducing burnout. At the core of GAINS is a generative AI model that predicts future unit-level staffing needs using historical staffing patterns, patient turnover (admissions and discharges), and patient acuity scores (based on ICU versus medical/surgical status, physician orders, charge nurse input, and other clinical factors) reflective of workload. Based on the prediction, the intervention dynamically recommends float pool assignments by evaluating staffing gaps across units and optimally deploying available nurses and nursing assistants to where they are most needed.

Arm 1: Standard staffing practice for float pool nurse and nursing assistants.; Arm 2: GAINS intervention applied to float pool nurses; Arm 3: GAINS intervention applied to float pool nurses and nursing assistants

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Registered nurses, nursing assistants, or key stakeholders
• Employed by The Queen's Medical Center
• Working at least 24 hours per week
• Position associated with medical-surgical units where float pool nurses work

You may not qualify if:

• Employees working less than 24 hours per week at The Queen's Medical Center
• Employees whose roles are not related to medical-surgical units

Sponsors & Collaborators

• University of Hawaii: lead

MeSH Terms

Conditions

Burnout, Psychological

Interventions

Methods

Condition Hierarchy (Ancestors)

Stress, Psychological; Behavioral Symptoms; Behavior

Intervention Hierarchy (Ancestors)

Investigative Techniques

Study Officials

• Katie A Azama, PhD

  University of Hawaii at Manoa

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Katie A Azama, PhD, APRN

CONTACT

8082563382; katieu@hawaii.edu

Holly Fontenot, PhD, APRN

CONTACT

hbfont@hawaii.edu

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: NON RANDOMIZED
• Masking: NONE
• Purpose: HEALTH SERVICES RESEARCH
• Intervention Model: SEQUENTIAL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Assistant Professor

Study Record Dates

• First Submitted: May 1, 2025
• First Posted: May 18, 2025
• Study Start: April 1, 2026
• Primary Completion (Estimated): March 31, 2029
• Study Completion (Estimated): March 31, 2029
• Last Updated: May 18, 2025

Record last verified: 2025-05

Data Sharing

• IPD Sharing: Will not share