An exploratory mixed-method study will be conducted to test acceptance and trust of an AI-powered falls risk predictor system by inpatient hospital nurses
This protocol covers the trial component of a 4-year PhD research study covering focus group discussions with nurses on AI risk systems, workshops to gather feedback on the AI system and feasibility testing in a simulated environment and clinical environment
Study Type
INTERVENTIONAL
Allocation
NON_RANDOMIZED
Purpose
HEALTH_SERVICES_RESEARCH
Masking
NONE
Enrollment
60
FAIR is an alert system built into the hospital's electronic medical record system. It is an adaptation of a machine learning model for fall risk calculation built in another hospital in Singapore. FAIR combines multiple patient-specific variables to identify if a patient is at increased risk of falling during their inpatient stay, marking them as a 'falls risk'. Based on the 'flag' raised, the nurse will be instructed to prioritise her falls risk assessment of the patient (If deemed 'high risk') or to do so subsequently as a lower priority once other pressing patient care issues are resolved (if deemed 'low risk'). That way, it ensures the requirements of each patient receiving a falls risk assessment as scored through mWHeFRA are still met, with FAIR allowing nurses to better prioritise their focus and attention on the patient that most needs the assessment at point of admission,
The mWHeFRA is the hospital's standard falls risk assessment tool. All nurses are expected to be proficient in its use to guide their risk assessment of patients
Incidence of FAIR's flag acceptance
Examination of how often the flags raised by FAIR are accepted by nurses, and whether they are accepted or ignored correctly.
Time frame: 1 Day of Study
Time taken to do falls risk assessment
The time taken by the nurses to perform their falls risk assessment will be recorded
Time frame: 1 Day of Study
Time spent looking at FAIR
The time each nurses takes looking at the FAIR falls risk assessment will be assessed
Time frame: 1 Day of Study
Baseline and Post-Simulation Nurse trust and acceptance of FAIR
Measured by the adapted Unified Theory of Acceptance and Use of Technologies and System Usability Survey, adjusted to better capture the key predictors of nurse acceptance
Time frame: Baseline
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.