Table 1_Cultural validation of the RCADS and use of ensemble learning for symptom profilin

Zamir Hussain's study provides data from 237 Pakistani children and adolescents used to culturally validate the Revised Child Anxiety and Depression Scale (RCADS). The work includes Cronbach's alpha scores for RCADS subscales and results from four trained machine learning algorithms, with Random Forest models achieving accuracies from 0.85 to 0.98. The dataset was uploaded to figshare on March 18, 2026, under a CC-BY-4.0 license.

Use Cases

• Validate the cultural significance of the RCADS subscales based on Cronbach's alpha scores reported.
• Profile dominant symptoms of anxiety and depression using Gini importance metrics from trained models.
• Train ensemble learning models for clinical screening support, based on the reported performance of Random Forest algorithms.
• Investigate associations between demographic factors and psychopathology scales using chi-square test results.

Strengths

• Includes data from a specific community sample of 237 Pakistani children and adolescents.
• Reports Cronbach's alpha scores for all RCADS subscales, with most above 0.7.
• Machine learning models, particularly Random Forests, achieved reported accuracies between 0.85 and 0.98.

Limitations

• The dataset is very small at 27.8 KB; row count and column-level documentation are unknown.
• The subscales for Separation Anxiety Disorder (SAD) and Obsessive-Compulsive Disorder (OCD) had low Cronbach's alpha values, suggesting potential measurement issues.
• The models require external validation on unseen data before practical implementation, as noted in the conclusion.

Provenance

Source

Zamir Hussain via figshare

Collection Method

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

Freshness

Last updated 2026-03-18 07:35:49

Geography

Pakistan