Meiqin Zheng
Training and Education Strategies of Mental Health Nursing Personnel in the Era of Artificial Intelligence
Abstract: With the rapid development of artificial intelligence (AI) technology, its widespread use in various industries, especially in education, has triggered an in-depth exploration of the role of AI in specific fields. Mental health nursing education, as a technology-sensitive and rapidly responsive field, is particularly important for research on the use of AI technology in order to enhance educational effectiveness and efficiency. Based on an in-depth analysis of existing educational models, this study explores how AI technology can revolutionize mental health nursing education, and comprehensively analyses the actual potential of AI technology in enhancing the quality of mental health nursing education through questionnaires, experimental design and the construction and application of statistical models.
Keywords: Artificial Intelligence , Educational Technology Application , Mental Health Nursing Education , Statistical Model , Teaching Effect
1. Introduction
When discussing the impact of artificial intelligence (AI) on mental health education, multiple research perspectives are introduced. Hartman and Phillips [1] emphasize the importance of integrating mental health nursing into the nursing curriculum to provide a foundation for understanding mental health education. Happell et al. [2] studied the role of consumer participation in mental health education and proposed to combine AI technology to enhance the educational effect. San et al. [3] demonstrated the application potential of AI in nursing student education through the international multi-center standardized patient simulation study, while Carr et al. [4] discussed the effectiveness of multi-mode teaching in cultivating mental health concepts and supported the application of AI technology. Danesh et al. [5] studied the value of remote presence technology in mental health nursing education and provided insights for the application of AI in distance teaching.
Compared to current state-of-the-art research, this study adds in-depth understanding and practical applications to the field of mental health nursing education, particularly in terms of the effective integration of AI technology [6,7].
The research includes the following main aspects: Section 1 introduces the background, purpose, and importance of the study, setting the tone for the research by clearly identifying the value of the application of AI technology and research gaps in the field of education, particularly in mental health nursing education. Section 2 divided into two parts, explores the theoretical foundations of AI technology in education, including the principles and methods of educational applications of AI technology. Focusing on the theory and practice of mental health nursing education, it analyses how AI can help the cultivation of mental health nursing talents. Section 3 conducts questionnaire design and implementation to collect educators' and learners' views and feedback on the application of AI technology to mental health nursing education.
2. Theoretical Exploration and Application
2.1 Theoretical Discussion of AI Technology in Education
The main role of AI technology is to support the realization of educational goals [8], solve educational problems and optimize the educational process through technology, tools, programs or systems [9,10]. Cognitive theory explores how to improve the learning process through personalized learning paths and adaptive learning systems to meet the needs of different learners [11].
2.2 Theory and Practice of Mental Health Nursing Education
The theory and practice of mental health nursing education aims at in-depth analysis and understanding of educational concepts, teaching methods and practical challenges in this field [12].
At the theoretical level, mental health nursing education focuses on a comprehensive understanding of mental illness [13], covering biological, psychological and sociological factors, emphasizing the integration of traditional and recent research results [14], teaching learners ways to diagnose, evaluate and treat mental health problems, and ethical and legal issues of patient care [15].
3. Questionnaire Design and Implementation
3.1 Questionnaire Construction and Design Concept
The questionnaire was designed to assess the use of AI in mental health education, with a particular focus on its impact on educational outcomes, learning experiences, and educational strategies. The content and structure of the questionnaire are shown in Table 1.
Table 1.
| Questionnaire section | Problem sample | Response option |
|---|---|---|
| Basic information | Occupation | Educators/learners |
| Attitude and acceptance | Views on the application of AI in education | Very supportive to very unsupportive |
| Educational effect | The view that AI technology improves learning efficiency | Strongly agree to strongly disagree |
| Practical challenge | Challenges encountered when using AI technology | Multiple choice question |
3.2 Data Collection and Preprocessing
This study collected data on the use of AI in mental health education through online questionnaires, educational institution partnerships, and paper questionnaires. Sample selection ensures diversity and randomness, covering educators and learners from different regions, different educational institutions, and different backgrounds (Table 2).
In conducting the data processing component of the Mental Health Nursing Education Study, three key steps were taken to ensure the accuracy and reliability of the data: data cleansing, missing value processing, and data coding. First, the data cleaning step involved the removal of inconsistent or contradictory responses in the dataset.
Table 2.
| Data processing procedure | Description | Give an example |
|---|---|---|
| Data cleaning | Delete inconsistent answers | 2% of the answers were deleted because the answers were contradictory. |
| Missing value processing | Fill in or delete missing values | The missing values of 3% were filled in using the mean. |
| Data coding | Qualitative to quantitative | The “Very supported” code is 5, and the “very unsupported” code is 1. |
3.3 Statistical Analysis and Interpretation
The statistical analysis was conducted to reveal the effects and potential challenges of the application of AI in mental health care education.
(1) Descriptive statistical analysis: The horizontal bar graph provides information on two different aspects related to AI applications, focusing on mean values and their respective standard deviations (Fig. 1).
(2) Frequency analysis: The bar graph illustrates responses to two elements critical to the theme of mental health care training and education strategies in the AI era. The attitudes towards AI applications and the perceived impact of learning efficiency on perception are compared across four response categories: “Very much,” “Support/agree,” “Neutrality,” and “Do not” (Fig. 2).
4. Experimental Design and Implementation
4.1 Experimental Framework and Hypothesis Setting
This study designed an experiment to validate the effects of AI in mental health education, measuring the differences between AI technology and traditional teaching methods in terms of learning outcomes and learning engagement.
4.2 Experimental Procedures and Operating Procedures
Verify the effect of AI in mental health education, as shown in Table 3.
4.3 Processing and Analysis of Experimental Results
After the experiment is completed, the experimental results are processed and analyzed to verify the experimental hypothesis (Fig. 3).
In the context of training and education strategies for mental health care in the AI era, the bar and line graph reflects the efficacy of an experimental educational approach compared to a control group.
Table 3.
| Procedure | Description | Experimental group | Control group |
|---|---|---|---|
| Preparatory phase | Recruit volunteers and assign them randomly | 50 students | 50 students |
| Prepare teaching materials | AI teaching software and simulation tools | Traditional teaching materials | |
| Teaching implementation | Implement a 4-week teaching program | Ai-assisted instruction | Traditional teaching method |
| Effect evaluation | After the end of the exam and comprehension test | Test scores and comprehension tests | Test scores and comprehension tests |
| Engagement evaluation | Learners' engagement and motivation were assessed through questionnaires | Engagement questionnaire | Engagement questionnaire |
| Data collection and analysis | Collect and analyze data | Data analysis | Data analysis |
5. Model Construction and Application
5.1 Model Design and Construction Methods
Regression analysis models were used to estimate the impact of AI application on learning outcomes. The Formula (1) is shown:
(1)
[TeX:] $$Y=\beta_0+\beta_1 X_1+\beta_2 X_2+\beta_3 X_1 X_2+\beta_4 X_3+\beta_5 X_1^2+\beta_6 X_2^2+\beta_7 X_3^2+\beta_8 X_1 X_3+\beta_0 X_2 X_3+\epsilon$$[TeX:] $$X_1^2 \text { and } X_2^2$$ are squared terms for the degree of AI technology adoption and learner engagement, respectively, and are used to examine the nonlinear effects of these variables on learning outcomes.
[TeX:] $$X_3^2$$ is the squared term for other factors (e.g., level of learner prior knowledge), again used to assess nonlinear effects.
[TeX:] $$X_1 X_3 \text { and } X_2 X_3$$ are interaction terms to explore the interactions between the extent of AI technology adoption and the level of learner prior knowledge, and learner engagement and the level of learner prior knowledge.
Model description is shown in Table 4.
- Learning effect (test score): 85
- Degree of AI technology adoption: 4
- Level of learner engagement: 4
- Level of learner prior knowledge: 3 (assuming a quantitative range of 1–5 as well)
- Model parameters (assumed values):
(2)
[TeX:] $$\beta_0=50, \beta_1=5, \beta_2=3, \beta_3=2, \beta_4=4, \beta_5=-0.5, \beta_6=-0.3, \beta_7=-0.4, \beta_8=1, \beta_9=1.5$$
The results of regression analysis are as follows: [TeX:] $$\widehat{\beta_0}=50, \widehat{\beta_1}=5, \widehat{\beta_2}=3 .$$
Then the model can be expressed as follows:
Table 4.
| Variable | Description | Data range |
|---|---|---|
| Learning effect (Y) | Examination result | 60–100 |
| AI application ([TeX:] $$X_1$$) | Degree of application of AI technology | 1–5 |
| Degree of participation ([TeX:] $$X_2$$) | Learner engagement | 1–5 |
5.2 Model Verification and Optimization
Cross-validation and residual analysis were adopted in this study, as shown in Table 5.
Table 5.
| Validation index | Value | Explain |
|---|---|---|
| Average cross-validation score | 0.75 | The average performance of the model on different data subsets is good. |
| Normality test of residual | Conform to | The residual distribution conforms to the normal distribution and satisfies the hypothesis of linear regression. |
| value | 0.70 | The model can explain 70% of the variability. |
The optimization results are shown in formula (7):
Added independent variable [TeX:] $$X_3$$: Complexity of course content
The statistical indicators of the optimized model are shown in Fig. 4.
5.3 Model Application and Effect Analysis
The model is used to predict the impact of different AI applications on learning outcomes. The model formula is shown in Formula (8):
Among them, Y is learning effect (test score), [TeX:] $$X_1$$ is application degree of AI technology, [TeX:] $$X_2$$ is learner engagement, and [TeX:] $$X_3$$ is complexity of course content.
The model effect analysis is shown in Fig. 5.
6. Strategy Discussion
Firstly, educational institutions need to identify the most suitable AI instructional tools by assessing their technological infrastructure and the technological proficiency of their teachers. After selecting the tool, special training sessions should be organized to ensure that teachers are proficient in using AI technology for instructional design and implementation. The results of this study showed that the introduction of AI technology into mental health nursing education significantly improved learning outcomes and engagement.
Biography
Meiqin Zheng
https://orcid.org/0009-0001-6189-9254
She received her Bachelor of Science degree in Applied Psychology (Clinical direction) from Fujian University of Traditional Chinese Medicine in 2010. In 2013, she graduated from Fujian University of Traditional Chinese Medicine with a master's degree. Her current research interests include mental health education, psychological counseling and psychotherapy.
References
- 1 A. M. Hartman and B. C. Phillips, "Integrating mental health nursing in the prelicensure nursing curriculum," Journal of Nursing Education, vol. 59, no. 7, pp. 405-408, 2020. https://doi.org/10.3928/0148483420200617-10doi:[[[10.3928/014848342017-10]]]
- 2 B. Happell, W. Bennetts, J. Tohotoa, D. Wynaden, and C. Platania-Phung, "Promoting recovery-oriented mental health nursing practice through consumer participation in mental health nursing education," Journal of Mental Health, vol. 28, no. 6, pp. 633-639, 2019. https://doi.org/10.1080/09638237.2017.1294734doi:[[[10.1080/09638237.2017.1294734]]]
- 3 E. O. San, G. Dikec, and E. E. Ata, "An International multicenter mental health standardized patient simulation on nursing students’ beliefs toward mental health conditions," Clinical Simulation in Nursing, vol. 76, pp. 47-56, 2023. https://doi.org/10.1016/j.ecns.2022.11.004doi:[[[10.1016/j.ecns.2022.11.004]]]
- 4 K. Carr, K. A. Rhodes, M. M. Klamm, and S. McElwain, "Engaging nursing students in mental health concepts through multiple teaching modalities," Journal of Nursing Education, vol. 62, no. 6, pp. 359-363, 2023.custom:[[[-]]]
- 5 V . Danesh, D. Rolin, S. V . Hudson, and S. White, "Telehealth in mental health nursing education health care simulation with remote presence technology," Journal of Psychosocial Nursing and Mental Health Services, vol. 57, no. 7, pp. 23-28, 2019. https://doi.org/10.3928/01484834-20230315-01doi:[[[10.3928/01484834-0315-01]]]
- 6 J. D. Bosse, K. D. Clark, and S. Arnold, "Implementing trauma-informed education practices in undergraduate mental health nursing education," Journal of Nursing Education, vol. 60, no. 12, pp. 707-711, 2021. https://doi.org/10.3928/01484834-20211103-02doi:[[[10.3928/01484834-2003-02]]]
- 7 B. A. Finley, K. D. Shea, S. P. Gallagher, R. Palitsky, and J. Gauvin, "A theoretical framework for conducting psychiatric mental health nursing virtual care & research," Issues in Mental Health Nursing, vol. 44, no. 10, pp. 1002-1008, 2023. https://doi.org/10.1080/01612840.2023.2258213doi:[[[10.1080/01612840.2023.2258213]]]
- 8 G. O. Silva, N. D. A. Aredes, and H. Galdino-Junior, "Academic performance, adaptation and mental health of nursing students: a cross-sectional study," Nurse Education in Practice, vol. 55, article nbo. 103145, 2021. https://doi.org/10.1016/j.nepr.2021.103145doi:[[[10.1016/j.nepr.2021.103145]]]
- 9 M. Annion, M. Ojasoo, U. Emits, and K. Puusepp, "Emotional coping of nursing students during mental health nursing simulation training," Proceedings of the Estonian Academy of Sciences, vol. 72, no. 3, pp. 212219, 2023. https://doi.org/10.3176/proc.2023.3.03custom:[[[-]]]
- 10 T. Wand, S. Glover, and. D. Paul, "What should be the future focus of mental health nursing? Exploring the perspectives of mental health nurses, consumers, and allied health staff," International Journal of Mental Health Nursing, vol. 31, no. 1, pp. 179-188, 2022. https://doi.org/10.1111/inm.12947doi:[[[10.1111/inm.12947]]]
- 11 M. J. Rice, J. Stalling, and A. Monasterio, "Psychiatric-mental health nursing: data-driven policy platform for a psychiatric mental health care workforce," Journal of the American Psychiatric Nurses Association, vol. 25, no. 1, pp. 27-37, 2019. https://doi.org/10.1177/1078390318808368doi:[[[10.1177/1078390318808368]]]
- 12 C. Bond, A. Hui, S. Timmons, and A. Charles, "Mental health nurses' constructions of compassion: a discourse analysis," International Journal of Mental Health Nursing, vol. 31, no. 5, pp. 1186-1197, 2022. https://doi.org/10.1111/inm.13026doi:[[[10.1111/inm.13026]]]
- 13 V . Goodwin, R. McMaster, S. Hyde, M. Appleby, and T. Fletcher, "Qualitative evaluation of a postgraduate course in mental health nursing," Nurse Education in Practice, vol. 36, pp. 40-46, 2019. https://doi.org/10.1 016/j.nepr.2019.02.015doi:[[[10.1016/j.nepr.2019.02.015]]]
- 14 K. Kirkbakk-Fjær and H. Skundberg-Kletthagen, "Nursing students’ in mental health nursing shown by the debriefing phase in low-fidelity simulation," Issues in Mental Health Nursing, vol. 39, no. 9, pp. 773-778, 2018. https://doi.org/10.1080/01612840.2018.1455774doi:[[[10.1080/01612840.2018.1455774]]]
- 15 M. V . Bui, E. McInnes, G. Ennis, and K. Foster, "Mental health nurses' experience of resilience during COVID‐19: a qualitative inquiry," International Journal of Mental Health Nursing, vol. 32, no. 6, pp. 17351744, 2023. https://doi.org/10.1111/inm.13213doi:[[[10.1111/inm.13213]]]