An Interpretable Machine Learning Approach to Predict Sensory Processing Sensitivity Trait in Nursing Students.

Area of Science:

• Psychology
• Nursing Education
• Machine Learning

Background:

• Sensory Processing Sensitivity (SPS), characterized by heightened sensitivity to stimuli, defines Highly Sensitive People (HSP).
• The SPS trait is common in nursing students and staff, yet early detection methods are limited.
• Accurate identification of HSP is crucial for effective nursing care and support.

Purpose of the Study:

• To develop an interpretable machine learning model for predicting the SPS trait in nursing students.
• To enable early identification of Highly Sensitive People (HSP) for individualized nursing assessments.
• To explore the relationship between SPS and other psychological factors in nursing students.

Main Methods:

• A cohort of 672 nursing students underwent evaluations for HSP diagnosis, emotional intelligence, communication skills, and conflict styles.
• An interpretable machine learning model was trained using the collected data to predict SPS trait presence.
• Statistical analyses were employed to identify characteristics associated with HSP.

Main Results:

• The prevalence of HSP among nursing students was found to be 33%, with higher rates in women and those with prior health training.
• HSP individuals demonstrated significantly higher emotional repair, empathy, and global communication skills.
• Key predictors for SPS trait detection included sex and specific dimensions of emotional intelligence.

Conclusions:

• An individualized prediction model for SPS trait in nursing students has been developed.
• This model can facilitate early identification of HSP, informing targeted nursing interventions.
• Understanding and supporting HSP traits in nursing can mitigate negative impacts and leverage positive attributes.