Do Depressive Facial Patterns Transfer Across Cultures and Contexts? Evidence from a German RCT and E-DAIC

📅 2026-09-02
📈 Citations: 0
Influential: 0
📄 PDF
📝 Abstract
Automated assessment of depression from facial dynamics holds promise for scalable mental health monitoring, yet cross-corpus generalization of learned biomarkers remains an open challenge. We present a systematic bidirectional transfer study pairing the EmpkinS-EKSpression randomized controlled trial (RCT; N = 256, SCID-5-CV diagnoses) with the Extended Distress Analysis Interview Corpus (E-DAIC; N = 275, semi-structured clinical interviews), predicting depression severity and binary diagnostic status from facial action units, head pose, and gaze. Cross-corpus binary classification proves more robust than continuous PHQ-8 severity regression, with forward transfer achieving AUC = 0.70. Regression transfer is governed by functional context alignment: passive observation phases yield the most transferable models, while active emotion regulation phases elicit stronger within-corpus signals. These findings establish functional context alignment as the primary determinant of cross-corpus generalization, with passive elicitation contexts offering the best trade-off between within-corpus sensitivity and cross-corpus robustness.
Problem

Research questions and friction points this paper is trying to address.

depression
facial dynamics
cross-corpus generalization
automated assessment
mental health monitoring
Innovation

Methods, ideas, or system contributions that make the work stand out.

cross-corpus generalization
functional context alignment
depressive facial patterns
💼 Related Jobs
No related jobs found.
M
Misha Sadeghi
Dept. AIBE, FAU Erlangen-Nürnberg; Munich Center for Machine Learning
Robert Richer
Robert Richer
Dept. AIBE, FAU Erlangen-Nürnberg; Munich Center for Machine Learning
L
Lydia Helene Rupp
Dept. of Clinical Psychology and Psychotherapy, FAU Erlangen-Nürnberg
L
Lena Schindler-Gmelch
Dept. of Clinical Psychology and Psychotherapy, FAU Erlangen-Nürnberg
M
Marie Keinert
Dept. of Clinical Psychology and Psychotherapy, FAU Erlangen-Nürnberg
F
Farnaz Rahimi
Dept. AIBE, FAU Erlangen-Nürnberg
M
Malin Hager
Dept. of Clinical Psychology and Psychotherapy, FAU Erlangen-Nürnberg
Bernhard Egger
Bernhard Egger
Dept. of Computer Science, FAU Erlangen-Nürnberg
M
Matthias Berking
Dept. of Clinical Psychology and Psychotherapy, FAU Erlangen-Nürnberg
Bjoern M. Eskofier
Bjoern M. Eskofier
MaD Lab, FAU Erlangen-Nürnberg & TDH Group, Helmholtz Munich
Machine LearningArtificial IntelligenceWearable ComputingDigital HealthBiomedical Eng