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

Sadeghi M, Richer R, Rupp L, Schindler-Gmelch L, Keinert M, Rahimi F, Hager M, Egger B, Berking M, Eskofier BM (2026)

Publication Language: English

Publication Type: Conference contribution, Original article

Publication year: 2026

Conference Proceedings Title: ACM KDD 2026 Workshop on AI for Cognitive and Mental Health Support (AI4Mental)

Event location: Jeju KR

URI: https://chrystalii.github.io/AI4mental/assets/papers/ID10_KDD_2026_AI4Mental_camera-ready.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.

Authors with CRIS profile

Misha Sadeghi Sonderforschungsbereich 1483/1 - Empathokinästhetische Sensorik - Sensortechniken und Datenanalyseverfahren zur empathokinästhetischen Modellbildung und Zustandsbestimmung (SFB EmpkinS) Robert Richer Sonderforschungsbereich 1483/1 - Empathokinästhetische Sensorik - Sensortechniken und Datenanalyseverfahren zur empathokinästhetischen Modellbildung und Zustandsbestimmung (SFB EmpkinS) Lydia Rupp Lehrstuhl für Klinische Psychologie und Psychotherapie (KliPs) Lena Marie Gmelch Lehrstuhl für Klinische Psychologie und Psychotherapie (KliPs) Eva Marie Keinert Lehrstuhl für Klinische Psychologie und Psychotherapie (KliPs) Farnaz Rahimi Professur für Biomedical Network Science Malin Hager Lehrstuhl für Klinische Psychologie und Psychotherapie (KliPs) Bernhard Egger Juniorprofessur für Cognitive Computer Vision (Stiftungsprofessur) Matthias Berking Lehrstuhl für Klinische Psychologie und Psychotherapie (KliPs)

Related research project(s)

Empathokinästhetische Sensorik für Biofeedback bei depressiven Patienten (SFB 1483 EmpkinS D02) Empatho-Kinaesthetic Sensor Technology (SFB 1483 EmpkinS) July 1, 2021 - June 30, 2025

Involved external institutions

Ludwig-Maximilians-Universität (LMU) DE Germany (DE)

How to cite

APA:

Sadeghi, M., Richer, R., Rupp, L., Schindler-Gmelch, L., Keinert, M., Rahimi, F.,... Eskofier, B.M. (2026). Do Depressive Facial Patterns Transfer Across Cultures and Contexts? Evidence from a German RCT and E-DAIC. In ACM KDD 2026 Workshop on AI for Cognitive and Mental Health Support (AI4Mental). Jeju, KR.

MLA:

Sadeghi, Misha, et al. "Do Depressive Facial Patterns Transfer Across Cultures and Contexts? Evidence from a German RCT and E-DAIC." Proceedings of the ACM KDD AI4Mental '26 - Workshop on AI for Cognitive and Mental Health Support, Jeju 2026.

BibTeX: Download