Generative Artificial Intelligence Nurse Staffing Study
ConditionBurnout, Healthcare Workers
Trial statusNot yet recruiting
Trial phaseNot applicable
Trial typeInterventional
Biological sexAll
Age18+
SponsorUniversity of Hawaii
About this trial
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.
Eligibility criteria
This trial accepts healthy volunteersQualifiers
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
Disqualifiers
Employees working less than 24 hours per week at The Queen's Medical Center
Employees whose roles are not related to medical-surgical units
Trial design
Design model
Sequential
Treatments tested in this trial
Generative Artificial Intelligence Nurse Staffing (GAINS) Intervention
Other interventionThe 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.
Treatment groups
660 Participants
are divided into 3 treatment groupsGroup A: Arm 1: Standard staffing practice for float pool nurse and nursing assistants.Experimental treatment 1 intervention
Group B: Arm 2: GAINS intervention applied to float pool nursesExperimental treatment 1 intervention
Group C: Arm 3: GAINS intervention applied to float pool nurses and nursing assistantsExperimental treatment 1 intervention
Trial outcomes
Primary outcomes
1
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.
Time frame
Up to 2.5 years2
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.
Time frame
Up to 3 yearsSecondary outcomes
1
Optimization Staffing Rates [Target staffing rate - Actual staffing rate]
Optimization staffing rates (target staffing rate - actual staffing rate) will be tracked at baseline over a 2-weeks, after Phase 1 over 2-weeks, and at the end of the study over 2-weeks.
Time frame
Up to 2 years2
Total Cost: Travel Nurse and Nurse Overtime
There 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 3. The total cost of travel nurses and nurse overtime will be tracked at baseline over 2-weeks, after Phase 1 is complete over a 2-week time frame, and at the end of Phase 2 over a time frame of 2-weeks.
Time frame
Up to 2 yearsLocations
Sponsors and contacts
Click on the lead sponsor to view all of their trials.
Source ClinicalTrials.gov
This trial is not recruiting at the moment. You can still explore other options: