# Faces of the Mind: Unveiling Mental Health States Through Facial Expressions in 11,427 Adolescents

arXiv: https://arxiv.org/abs/2405.20072 · HTML: https://mlsanity.com/paper/2405.20072/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 100 references that are in the map.
- First posted on arXiv 30 May 2024.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [Deep Learning for Depression Recognition with Audiovisual Cues: A Review](https://mlsanity.com/paper/2106.00610/) (2021)
- [Attention-Based Acoustic Feature Fusion Network for Depression Detection](https://mlsanity.com/paper/2308.12478/) (2023)
- [Exploring the relationship between response time sequence in scale answering process and severity of insomnia: a machine learning approach](https://mlsanity.com/paper/2310.08817/) (2023)

## Abstract (arXiv)

Mood disorders such as depression and anxiety often manifest through facial expressions, but existing machine learning algorithms designed to assess these disorders have been hindered by small datasets and limited real-world applicability. To address this gap, we analyzed facial videos of 11,427 participants - a dataset two orders of magnitude larger than those used in previous studies - including standardized facial expression videos and psychological assessments of depression, anxiety, and stress. However, scaling up the dataset introduces significant challenges due to increased symptom heterogeneity, making it difficult for models to learn accurate representations. To address this, we introduced the Symptom Discrepancy Index (SDI), a novel metric for quantifying dataset heterogeneity caused by variability in individual symptoms among samples with identical total scores. By removing the 10% most heterogeneous cases as identified by the SDI, we raised the F1 scores of all models from approximately 50% to 80%. Notably, comparable performance gains were observed within both the retained and excluded subsets. These findings demonstrate symptom heterogeneity, not model capacity, as the principal bottleneck in large scale automated assessment and provide a general solution that is readily applicable to other psychometric data sets.