Artificial Intelligence (AI), Deep Learning, Mechine Learning, Nursing
Conditions
Keywords
Nursing, Artificial Intelligence (AI), Medical Science and Technology
Brief summary
To address workforce shortages and increasing workloads in nursing, technological solutions and AI-powered robots for ward navigation have been introduced. However, limitations remain in their application to clinical care. This study aims to develop and test a programming framework for an AI-assisted nursing care robot ("E-Nursing Assistant") to reduce nurses' workload and improve the efficiency and quality of care.
Detailed description
In response to the challenges of workforce shortages and heavy workloads in the nursing field, clinical nursing practices are gradually integrating technological assistance, including the use of mobile phones to scan QR codes for viewing instructional videos and the introduction of robots with Artificial Intelligence (AI) technology for ward navigation. However, there are still several limitations to these technological applications in the nursing care process. Therefore, this study aims to develop and test the programming framework for an AI-assisted nursing care robot ("E-Nursing Assistant"). The goal is to reduce the workload of nursing staff and significantly improve the efficiency and quality of nursing work. The "E-Nursing Assistant" will be implemented in the ward to measure the nursing staff's workload, the time and frequency spent on specific nursing tasks, and to conduct interviews to gather their feedback.
Interventions
OTHERIntervention Group
The functions performed by the robot include guiding patients through unit-specific locations for environmental orientation and equipment usage instructions, playing educational videos related to care, reminding patients of important examination precautions, providing health education on specimen collection, and delivering responses through an expert-developed medical Q\&A system.
Sponsors
National Taiwan University Hospital
Study design
Allocation
NA
Intervention model
SINGLE_GROUP
Primary purpose
OTHER
Masking
NONE
Intervention model description
Since the robot will interact with patients or caregivers during its operation in the ward, in addition to the nursing staff completing the informed consent form, patients or caregivers will also be required to fill out a consent form.
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
Yes
Inclusion criteria
1. Nurse Inclusion Criteria: * Aged 18 years or older. * Currently employed as a ward nurse.
Exclusion criteria
* Nurses who do not actively participate in ward care, such as nursing unit supervisors. 2. Patients/Caregivers Inclusion Criteria: * Aged 18 years or older. * Willing to accept the "E-Nursing Assistant" intervention for care tasks that do not involve patient safety.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Workload-related stress in nursing staff | It will be measured pre-intervention and immediately after the intervention. | The investigators utilized the Nurse Stress Checklist Chinese version translated by Taiwanese scholars in 1996. The scale consists of four factors: "Personal Response," "Work Concerns," "Job Competence," and "Inability to Complete Personal Tasks." It contains a total of 43 items, each rated on a 9-point Likert scale (0 = not at all, 1 = not close, 8 = very close), with higher scores indicating greater levels of work-related stress. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| System Usability | It will be measured immediately after the intervention. | The investigators used the System Usability Scale (SUS) developed by scholar Brooke. The scale consists of 10 items, scored on a 5-point Likert scale (1 = strongly disagree, 5 = strongly agree). Odd-numbered items are positively worded, and the raw score for each item is subtracted by 1 to obtain the item score. Even-numbered items are reverse scored, with the item score calculated as 5 minus the raw score. The scores for all items are summed, and the total is then multiplied by 2.5 to obtain the overall SUS score, which ranges from 0 to 100. Higher scores indicate greater satisfaction with the system. |
| Number of patients served and time spent on various nursing tasks | It will be measured pre-intervention and during the intervention | A self-designed table will be used to list common and repetitive nursing tasks in the ward in detail. These tasks include: ward orientation (e.g., nursing station), instructions for using ward equipment (e.g., patient beds, call bells), patient fall prevention education, reminders for various examinations (e.g., urination), health education for specimen collection (e.g., blood, urine), discharge instructions, and answering common questions from patients after viewing nursing care instructional videos. Each task will include spaces to record the number of patients served and time spent. Initially, an audio recorder will be used to measure the time, after which the researchers will calculate the start and end times, as well as any interruptions during the process, and fill in the table accordingly. |
Countries
Taiwan
Contacts
CONTACTYun-Hsiang Lee Associate Professor, PhD
Outcome results
None listed