RCADS: Cultural Validation and Symptom Profiling for Pakistani Youth

A Pakistani community sample of 237 children and adolescents was used to validate the Revised Child Anxiety and Depression Scale (RCADS). The study, authored by Zamir Hussain and last updated in March 2026, developed machine learning models for symptom profiling, with Random Forest models achieving accuracies from 0.85 to 0.98.

Use Cases

• Validating the cultural significance of psychometric screening tools based on a Pakistani youth sample.
• Profiling dominant symptoms of anxiety and depression disorders using Gini importance from ensemble models.
• Training and comparing machine learning algorithms for clinical screening support systems.
• Investigating the statistical associations between RCADS items and specific disorders like Separation Anxiety.

Strengths

• Includes validation results for 47 individual RCADS items in a specific cultural context.
• Reports Cronbach's alpha values for subscales, with most above the 0.7 threshold.
• Machine learning models achieved reported accuracies between 0.85 and 0.98.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The subscales for Separation Anxiety Disorder and Obsessive-Compulsive Disorder had low Cronbach's alpha values, suggesting potential measurement issues.

Provenance

Source

figshare, author Zamir Hussain.

Collection Method

Community sample survey using the Revised Child Anxiety and Depression Scale (RCADS).

Freshness

Last updated 2026-03-18 07:35:48; freshness should be verified.

Geography

Pakistan