Use of ChatGPT in Developing Health Materials on 'Immunization' for Nursing Students

Artificial intelligence is an innovative approach to simulation of human intelligence consisting of algorithms. Samoili defined artificial intelligence as "software (and possibly also hardware) systems designed by humans that, given a complex goal, act in the physical or digital dimension by perceiving their environment through data acquisition, interpreting the collected structured or unstructured data, reasoning on the knowledge, or processing the information, derived from this data and deciding the best action(s) to take to achieve the given goal. AI systems can either use symbolic rules or learn a numeric model, and they can also adapt their behavior by analyzing how the environment is affected by their previous actions". Artificial intelligence tries to imitate human cognitive abilities such as abstract reasoning, knowledge representation, learning, autonomous decision-making, communicating in natural languages, perceiving and interacting with the natural world. Today, artificial intelligence is widely used in many fields. Especially in the field of health, the use of artificial intelligence is becoming increasingly widespread in the field of nursing. In a century where technology is rapidly advancing in the world, artificial intelligence applications represent a largely new era in nursing practice.

This study aims to determine the effect of using ChatGPT, an artificial intelligence program, on the development of health materials on immunization by senior nursing students. Materials and Methods: This study was conducted as a randomized controlled trial. The universe of the study consists of N=156 senior nursing students. However, 16 students who did not participate in the study were excluded from the study. The students filled out the 'Introductory Data Form' and 'Consent' form. Then, a faculty member other than the researchers completed the assignment of the students to the groups using the simple randomization technique (randomizer.org website) and forwarded the results to one of the researchers (DN) using the sealed envelope method. The study was completed with 63 students in the intervention group and n=77 students in the control group. Within the scope of a course taken by the students, the subject of 'immunization' was explained to the class as a theoretical lesson through traditional narration. The students were given the task of designing educational materials on the subject explained. One of the researchers (DN) made an appointment with the group of students assigned to the intervention group, arranged a meeting and provided 1-hour consultancy on the use of ChatGPT. Students were asked to conduct a search on ChatGPT using 3 keywords: 'nursing, health material and immunization'. On the specified date and time, students in the intervention and control groups were gathered in the classroom and introduced the health materials, students designed in the classroom. The health materials were evaluated by the researcher (KE) in the classroom using data collection forms ('Evaluation Form of Visual Design Principles and Elements' and 'Global Quality Scale'). The research was conducted in 3 months. The data were evaluated using the SPSS 25.0 package program. In order to conduct the research, ethics committee permission, institutional permission, scale permission and written consents were obtained from the participants.

Inclusion criteria:

• Volunteering to participate in the study
• Being in the final year of the Turkish nursing department
• Participating in the Evidence-Based Nursing Practices course

Exclusion criteria: Having previously prepared health materials using an artificial intelligence program

Research variables While the independent variables of the study were the adolescent's introductory data, the dependent variable was the average scores participants received from the 'Evaluation Form of Visual Design Principles and Elements' scale and the 'Global Quality Scale'.

Data evaluation: SPSS 25.0 package program was used in statistical analyses. Percentage and frequency tests were applied in the evaluation of the data. The Kolmogorov-Smirnov Test was used to evaluate the data's compliance with normal distribution. Independent t Test was used for data that conformed to normal distribution. Data were evaluated with a 95% confidence interval and a p-value of 0.05 margin of error.