A Depression-Risk Mental Pattern Identified by Hidden Markov Model in Undergraduates

Area of Science:

• Psychiatry
• Psychology
• Data Science

Background:

• Depression screening in youth often relies on direct symptom reporting, which can be hindered by stigma and embarrassment.
• Existing universal depression screening methods may not adequately capture the nuances of depression risk in all individuals.

Purpose of the Study:

• To identify an accessible screening approach for indirectly predicting depression risk in undergraduates.
• To utilize a Hidden Markov Model (HMM) for identifying depression risk stages.

Main Methods:

• A Hidden Markov Model (HMM) was employed to analyze depression risk stages.
• 1247 undergraduates completed inventories assessing depressive symptoms, emotion regulation, subjective well-being, and coping styles.
• Data were analyzed to differentiate between a 'risk pattern' (state 1) and a 'health pattern' (state 2).

Main Results:

• Distinct differences were observed between the risk and health patterns in emotion regulation, subjective well-being, and coping styles.
• The HMM approach successfully identified different stages of depression development.
• Subjective well-being, emotion regulation, and coping style were key indicators in differentiating risk levels.

Conclusions:

• Screening for prospective depression risk can be improved by incorporating subjective well-being, emotion regulation, and coping style within an HMM framework.
• This indirect screening method offers a more accessible alternative to direct symptom reporting.
• Findings have implications for developing evidence-based depression screening initiatives for young adults.