A Quasi-experimental study to assess the effectiveness of plan teaching on Knowledge regarding Artificial Intelligence-based learning among nursing students in selected College of Wardha City: A Protocol

Introduction

As healthcare grows, nursing education must evolve to keep nurses updated on nursing care. Higher education has been integrated with Artificial Intelligence (A.I.) technology, which has the potential to develop education by implementing more personalized and efficient student learning.¹ The integration of A.I. into the education sector has had a long history since the 1970s, which resulted in the development of multimedia learning resources, interactive stimulation, online learning, and game development.² A.I. holds significant potential to create more complex stimulation that can help to develop critical thinking capacity in student nurses by preparing them for real-life situations, as A.I. technology simulation will become even more advanced by offering more realistic situations to students, allowing them to practice and help in decision making and critical thinking skills.³ The benefits of A.I. in nursing education, such as interactive learning experiences using chatbot systems, will raise concerns about academics and proper guidance and ethics. However, A.I. can significantly improve nursing students’ learning.⁴

A.I. is an impactable field for nursing and other healthcare industries. A.I.-based learning in nursing is a new field in nursing in which students will gain hands-on experience. A.I.-based learning has the potential to revolutionize nursing education by engaging learning experiences. There are several challenges in nursing education, including preparing students for rapidly changing healthcare; A.I.-based learning can address challenges in healthcare and improve student skills and knowledge. After an intervention, we will assess students’ post-tests to see significant improvement in knowledge of A.I.-based learning among B.Sc. nursing students.⁵ For example, by using Artificial intelligence, the patient outcome of the hospital will increase, and by using simulation teaching, the student knowledge and practice will increase.

This study will assess the knowledge regarding A.I.-based learning and its implication for nursing education, such as the need to provide more resources for A.I.-based learning in nursing to improve the quality of instruction, address student concerns about technology and update the knowledge on A.I. among students of primary BSc nursing students.

Protocol

Sample size calculation

The sample size calculation with reference studies.⁶ The following formula was used for the sample size calculation:

$$\mathrm{N}=\frac{{\left({\mathrm{Z}}_{\left(\mathrm{\alpha }/2\right)}+{\mathrm{Z}}_{\mathrm{\beta }}\right)}^2\left({\mathrm{P}}_1\left(1-{\mathrm{P}}_1\right)\right)+\left({\mathrm{P}}_2\left(1-{\mathrm{P}}_2\right)\right)}{{\left(\mathrm{P}2-\mathrm{P}1\right)}^2}$$

$${\mathrm{Z}}_{\mathrm{\alpha }/2}=\mathrm{at}95\%\left(\mathrm{CI}\right)=1.96$$

Represents the desired level of statistical significance at 5% Type I Error

${\mathrm{Z}}_{\mathrm{\beta }}=0.84$: Represents the desired power for 80%

$$\mathrm{N}=\text{Minimum samples required for each group}$$

Primary variable = knowledge of A.I.

The percentage for knowledge before teaching structured programs regarding A.I. = 34.07% (As per Reference study).⁶

Percentage for knowledge after teaching structured program = 54.07% (Expected).

Considering % a clinically significant margin of improvement, 20%

Minimum sample size required

$$\mathrm{N}={\left(1.96+0.84\right)}^2{\left(0.3407\right)}^{\ast }\left(1-0.3407\right)+{\left(0.5407\right)}^{\ast }\left(1-0.5407\right)/0.20=93\text{Students}.$$

A total of 93 students will be included in the study. The participants will be selected conveniently, and the method used will be a non-probability convenient sampling technique. Figure 1 shows a schematic presentation of the pre-experimental one group and post-experimental research design used for the present study.

Figure 1. Schematic presentation of pre-experimental one group and post-experimental research design used for the present study.

Discussion

Many studies have been performed on A.I., but more research is needed for nursing education.⁷ Harsh et al. provided a comprehensive overview of A.I., Machine Learning (ML) and Deep Learning (DL) in healthcare industries that describes the cost of care, the shortage of staff and the need for better data management. The author then discusses how A.I., ML and DL can address these challenges. The article also discusses the challenges that must be addressed to realize the potential of A.I., ML, and DL entirely in healthcare settings.⁶ Allam JP et al. proposed a deep learning algorithm for drowsiness detection using single-channel electroencephalogram (E.E.G.) signals. The algorithm is based on the conventional neural networks (CNN) that are trained on datasets of E.E.G. signals collected from awake or drowsy participants. The author evaluated the performance of the algorithms on a test set of E.E.G. signals and found that they achieved an accuracy of 90%⁹—a significant improvement over previous methods for drowsiness detection, which had 70% detection. The author also discusses the algorithms’ limitations and suggests possible future research directions. One limitation of the algorithm is that it is only designed to work with single channels in people wearing E.E.G. headsets with multiple channels.⁷ A cross-sectional study conducted in Syria by Sarya Swed et al. on knowledge, attitude and practice of A.I. among doctors. 1494 samples from doctors and medical students. The inclusion was voluntary. Of the total participants, 255 participants (16%) were doctors, and others, 1,252 (83%) were undergraduate medical students, about 1,055 (70%) knew A.I. and 357 (23%) participants knew about an application in the medical field.¹⁰

In Middle Eastern countries, the implication of A.I. for the diagnosis and treatment of patients is more significant for better outcomes.¹¹ There are many articles published on planned teaching related to different medical categories. Nursing education has several challenges, including preparing students for rapidly changing healthcare.^6,12,13 A.I.-based learning has the potential to address challenges and provide students with the skills and knowledge they need to succeed.¹⁰