Benchmark RadarNeurai-VN Benchmark
Evaluates machine learning models on the Neurai-VN dataset for mental health classification. Four binary tasks (healthy control vs. depression, anxiety, clinical, and depression vs. anxiety) are defined using subject-wise cross-validation and standardized feature groups. Baseline models include linear, tree-based, and neural networks, with mean F1 scores reported.
- Released
- 2026-07-28
- Readiness
- Runnable
- Primary field
- Health & Life Sciences
Why it matters
Provides a standardized evaluation protocol for multimodal digital phenotyping in mental health, addressing inconsistencies in preprocessing and evaluation across datasets. Offers comparable baselines for future research.
Motivation
Digital phenotyping (DP) using smartphones and wearable devices has emerged as a promising approach for assessing mental health, particularly depression and anxiety.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.