Artificial intelligence for predicting depression anxiety and stress using psychometric data.

Area of Science:

• Computational psychiatry
• Digital mental health

Background:

• Mental health is vital but often neglected due to stigma and access barriers.
• Early detection of psychological conditions like depression, anxiety, and stress is crucial for timely intervention.

Purpose of the Study:

• To evaluate the efficacy of artificial intelligence (AI) in predicting common psychological conditions.
• To assess the performance of various machine learning models using psychometric and demographic data.

Main Methods:

• Analysis of the Depression Anxiety Stress Scales-42 (DASS-42) questionnaire responses from 39,775 participants.
• Preprocessing included handling missing data, standardization, and validity checks.
• Evaluation of five machine learning models (decision tree, random forest, k-NN, naive Bayes, SVM) using cross-validation.

Main Results:

• The Support Vector Machine (SVM) model demonstrated superior predictive accuracy.
• SVM achieved 99.3% accuracy for depression, 98.9% for anxiety, and 98.8% for stress.
• AI models showed high performance in identifying psychological conditions based on questionnaire data.

Conclusions:

• AI-based approaches show significant potential for early mental health screening.
• The study underscores the utility of machine learning in analyzing psychometric data for psychological condition prediction.
• Further clinical validation is essential to implement these AI tools in real-world healthcare settings.