Neural network-based data analysis for medical-surgical nursing learning.

Area of Science:

• Nursing Education
• Educational Technology
• Data Science in Healthcare

Background:

• Assessing student knowledge in medical-surgical nursing is crucial for effective learning.
• Traditional assessment methods may not fully capture individual knowledge gaps.
• Integrating technology can enhance the assessment and feedback process.

Purpose of the Study:

• To apply neural network-based data analysis for knowledge clustering in medical-surgical nursing students.
• To identify distinct patterns of knowledge acquisition among second-year nursing students.
• To explore the potential for customized feedback based on identified knowledge clusters.

Main Methods:

• Collected data from 208 second-year nursing students' end-of-term Multiple Choice Question (MCQ) tests.
• Utilized neural network analysis to cluster student performance data.
• Employed the snap-drift algorithm to create 23 distinct pattern groups.

Main Results:

• Successfully clustered 208 nursing students into 23 distinct knowledge pattern groups.
• Demonstrated the feasibility of using neural networks for analyzing student performance data.
• Identified specific knowledge clusters that can inform targeted educational interventions.

Conclusions:

• Neural network analysis provides a robust method for understanding student knowledge in medical-surgical nursing.
• The identified knowledge clusters can be used to provide customized feedback.
• Integrating this approach with an online MCQ system can support personalized student training and improve learning outcomes.