PHQ-9 Student Depression Dataset

The PHQ-9 Enhanced Student Depression Dataset contains comprehensive responses from 682 students to the PHQ-9 questionnaire, a well-established clinical tool for diagnosing depression. This enhanced 5th edition represents a significant advancement from previous versions, incorporating additional psychosocial factors that influence mental health outcomes among young adults aged 17-26 years.

Important Note: This survey was conducted from the start under the supervision of qualified mental health professionals and clinical researchers, ensuring ethical data collection practices and participant welfare throughout the study.

PHQ-9 Assessment Framework
The PHQ-9 questionnaire includes 9 standardized questions assessing depression symptoms over the past two weeks, covering mood, energy levels, sleep, appetite, concentration, and suicidal ideation. Responses are scored on a 4-point scale from 0 (Not at all) to 3 (Nearly every day), with total scores ranging from 0 to 27.

Depression severity is classified into five categories:

Minimal (0-4): 206 participants (30.2%)
Mild (5-9): 155 participants (22.7%)
Moderate (10-14): 128 participants (18.8%)
Moderately Severe (15-19): 125 participants (18.3%)
Severe (20-27): 68 participants (10.0%)

New in 5th Edition
Key Improvements from Previous Editions
Increased sample size from 400 to 682 participants (70% increase)
Zero missing values across all 16 variables
Professional supervision throughout data collection
Enhanced ethical framework with IRB approval

New Psychosocial Variables
Three critical stress factors were added based on validated correlations with depression severity:
Sleep Quality: Good (34.9%), Average (31.5%), Bad (21.0%), Worst (12.6%)
Study Pressure: Good (26.7%), Average (31.1%), Bad (26.5%), Worst (15.7%)
Financial Pressure: Good (26.7%), Average (32.6%), Bad (25.5%), Worst (15.2%)

Demographics
Age Range: 17-26 years (mean: 21.4)
Gender: 418 males (61.3%), 264 females (38.7%)

Applications
Clinical Research: Depression prediction models, multi-factor analysis, risk stratification
Machine Learning: Multi-class classification, feature engineering, predictive analytics
Education: Clinical training, research methodology, statistical analysis

Ethical Considerations
All data collected under professional mental health supervision
IRB approval obtained with informed consent protocols
Crisis intervention procedures established
All PII removed, maintaining strict anonymity

Participant support resources provided throughout study

This enhanced dataset provides a robust foundation for automated depression detection research while maintaining the highest standards of ethical data collection and clinical relevance for student populations.