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

Misha Sadeghi; Robert Richer; Lydia Helene Rupp; Lena Schindler-Gmelch; Marie Keinert; Farnaz Rahimi; Malin Hager; Bernhard Egger

cs.CVSep 2, 2026

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

Authors: Misha Sadeghi, Robert Richer, Lydia Helene Rupp, Lena Schindler-Gmelch, Marie Keinert, Farnaz Rahimi, Malin Hager, Bernhard Egger, +2 more

Organizations: Dept. AIBE, FAU Erlangen-Nürnberg Munich Center for Machine Learning Germany · Dept. of Clinical Psychology and Psychotherapy, FAU Erlangen-Nürnberg Germany · Dept. of Computer Science, FAU Erlangen-Nürnberg Germany · Dept. AIBE, FAU Erlangen-Nürnberg Chair of AI-supported Therapy Decisions, LMU München Helmholtz Zentrum München Munich Center for Machine Learning Germany

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.

Figures & tables

Figure 1. Cross-corpus experimental pipeline pairing EmpkinS-EKSpression (EmpkinS) and E-DAIC. OpenFace ( Baltrušaitis et al., 2018 ) features feed a unified framework evaluated within-corpus and bidirectionally across corpora for severity regression and binary classification.

Characteristic	MDD $-$ ( $n=128$ )	MDD $+$ ( $n=128$ )	$p$
Demographics
Age, mean ± SD	36.7 ± 16.6	33.6 ± 13.4	0.622
18–25	49 (38.3%)	44 (34.4%)
26–35	27 (21.1%)	45 (35.2%)
$\geq$ 36	52 (40.6%)	39 (30.5%)
Sex (F / M / Diverse)	88 / 39 / 1	89 / 36 / 3	0.621

Table 1. Demographics and clinical characteristics of the EmpkinS-EKSpression (EmpkinS) dataset.

p

-values: Mann–Whitney

U

for continuous variables;

\chi^{2}

for categorical.

Characteristic	MDD $-$ ( $n=209$ )	MDD $+$ ( $n=66$ )	$p$
Demographics
Age, mean ± SD	41.1 ± 13.0	41.6 ± 11.8	0.697
18–25	29 (13.9%)	6 (9.1%)
26–35	55 (26.3%)	19 (28.8%)
$\geq$ 36	125 (59.8%)	41 (62.1%)
Sex (F / M / Unknown)	74 / 134 / 1	31 / 35 / 0	0.130

Table 2. Demographic and clinical characteristics of the E-DAIC dataset. Depression is defined as a PHQ-8

\geq 10

p

-values: Mann–Whitney

U

for continuous variables;

\chi^{2}

for categorical.

PHQ-8
	AFE		CR+AFE		CR		SHAM		All Conditions
Target / Phase	CCC	MAE	CCC	MAE	CCC	MAE	CCC	MAE	CCC	MAE
Preparatory	0.31 $\pm$ 0.22	5.34 $\pm$ 1.51	0.17 $\pm$ 0.11	5.03 $\pm$ 0.60	0.00 $\pm$ 0.20	5.83 $\pm$ 1.19	0.28 $\pm$ 0.17	4.85 $\pm$ 0.98	0.04 $\pm$ 0.15	5.11 $\pm$ 0.65
Mood Induction	$-$ 0.01 $\pm$ 0.08	7.34 $\pm$ 2.45	0.02 $\pm$ 0.15	5.54 $\pm$ 1.30	0.09 $\pm$ 0.24	5.18 $\pm$ 1.17	0.03 $\pm$ 0.12	6.05 $\pm$ 1.50	0.14 $\pm$ 0.05	5.10 $\pm$ 0.27
Negative Training	0.19 $\pm$ 0.18	5.14 $\pm$ 0.68	0.09 $\pm$ 0.26	4.86 $\pm$ 1.25	0.20 $\pm$ 0.20	5.11 $\pm$ 0.99	0.26 $\pm$ 0.16	5.03 $\pm$ 0.96	0.13 $\pm$ 0.10	5.26 $\pm$ 0.60
Positive Training	0.26 $\pm$ 0.33	5.19 $\pm$ 1.48	$-$ 0.04 $\pm$ 0.14	5.93 $\pm$ 0.96	0.18 $\pm$ 0.24	5.90 $\pm$ 1.29	0.24 $\pm$ 0.23	4.87 $\pm$ 1.05	0.09 $\pm$ 0.05	5.08 $\pm$ 0.49

Table 3. Within-corpus regression results. Cells report the mean

\pm

standard deviation across folds for the model achieving the highest mean CCC. Bold = best CCC within each condition across phases. Underline = best overall CCC per scale.

Cross-corpus
	Preparatory phase						Best within-corpus phase per condition
	Prep./AFE		Prep./SHAM		Prep./All		Pos./AFE		Neg./CR+AFE		Neg./CR		Neg./SHAM
	CCC	MAE	CCC	MAE	CCC	MAE	CCC	MAE	CCC	MAE	CCC	MAE	CCC	MAE
EmpkinS ${}^{\dagger}_{\rm all}$ $\to$ E-DAIC	0.03	6.13	0.00	5.83	0.00	7.18	$-$ 0.03	6.86	0.13	5.62	0.15	5.77	0.10	5.49
EmpkinS $\to$ E-DAIC	0.01	6.98	0.08	5.40	0.03	9.59	0.04	8.76	0.03	8.75	0.21	8.87	0.03	6.27
E-DAIC $\to$ EmpkinS	0.14	6.83	0.26	5.50	0.10	4.77	0.10	7.25	0.25	5.40	0.04	5.31	0.14	5.06

Table 4. Cross-corpus PHQ-8 regression. Bold: best CCC within each experiment row. Underline: best CCC within each transfer direction.

Setting 1 – EmpkinS † : SCID labels vs. E-DAIC: PHQ-8 $\,\geq 10$ labels
	Preparatory phase						Best within-corpus phase per condition
	Prep./AFE		Prep./SHAM		Prep./All		Pos./AFE		Neg./CR+AFE		Neg./CR		Neg./SHAM
	AUC	F1 M	AUC	F1 M	AUC	F1 M	AUC	F1 M	AUC	F1 M	AUC	F1 M	AUC	F1 M
EmpkinS all $\to$ E-DAIC	0.62	0.30	0.60	0.50	0.70	0.59	0.55	0.28	0.67	0.42	0.57	0.31	0.66	0.41
EmpkinS $\to$ E-DAIC	0.59	0.50	0.55	0.41	0.57	0.23	0.58	0.58	0.57	0.48	0.65	0.46	0.59	0.41
E-DAIC $\to$ EmpkinS	0.88	0.33	0.79	0.58	0.57	0.52	1.00	0.33	0.67	0.50	0.69	0.44	0.74	0.58

Table 5. Cross-corpus binary depression classification. AUC and macro-averaged F1 per configuration and label setting. Bold: best AUC within each experiment row. Underline: best AUC within each transfer direction.

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Model	Search grid
Ridge	alpha $\in\{0.01,\,0.1,\,1,\,10,\,100\}$
Lasso	alpha $\in\{0.01,\,0.1,\,1,\,10\}$ ; max_iter=5000
ElasticNet	alpha $\in\{0.01,\,0.1,\,1\}$ , l1_ratio $\in\{0.2,\,0.5,\,0.8\}$ ; max_iter=5000
SVR (RBF)	C $\in\{0.1,\,1,\,10,\,100\}$ , gamma $\in\{\texttt{scale},\,\texttt{auto}\}$ , epsilon $\in\{0.1,\,0.5,\,1.0\}$
$k$ -NN	n_neighbors $\in\{3,\,5,\,7,\,9\}$
Random Forest	n_estimators $\in\{100,\,200\}$ , max_features $\in\{\sqrt{\cdot},\,0.3\}$ , min_samples_leaf $\in\{1,\,3\}$

Appendix

Table 6. Regression hyperparameter search grids. All tree ensembles use random_state=42 ; MLP uses max_iter=500 .

Model	Search grid
Logistic Regression	C $\in\{0.01,\,0.1,\,1,\,10\}$
SVC (RBF)	C $\in\{0.1,\,1,\,10\}$ , gamma $\in\{\texttt{scale},\,\texttt{auto}\}$
Random Forest	n_estimators $\in\{100,\,200\}$ , max_features $\in\{\sqrt{\cdot},\,0.3\}$ , min_samples_leaf $\in\{1,\,3\}$
Extra Trees	n_estimators $\in\{100,\,200\}$ , max_features $\in\{\sqrt{\cdot},\,0.3\}$
Gradient Boosting	n_estimators $\in\{100,\,200\}$ , learning_rate $\in\{0.05,\,0.1\}$ , max_depth $\in\{3,\,5\}$
XGBoost	n_estimators $\in\{100,\,200\}$ , learning_rate $\in\{0.05,\,0.1\}$ , max_depth $\in\{3,\,5\}$

Appendix

Table 7. Classification hyperparameter search grids. All tree ensembles use random_state=42 ; MLP uses max_iter=500 ; Logistic Regression uses solver=lbfgs , max_iter=2000 .

Figure 2. SHAP beeswarm plot for the best forward-transfer classifier: EmpkinS-EKSpression (EmpkinS) $\to$ E-DAIC (Prep./All, Setting 1, AUC = 0.70). Features ranked by mean $|$ SHAP $|$ ; computed on the source training partition to reflect learned feature importance.

Figure 3. SHAP beeswarm plot for the best reverse-transfer classifier: E-DAIC $\to$ EmpkinS-EKSpression (EmpkinS) (Pos./AFE, Setting 1, AUC = 1.00). Features ranked by mean $|$ SHAP $|$ ; computed on the source training partition to reflect learned feature importance.

Explore similar work

A Multi-Probe Audit of Clinical-Interview Depression Detection Benchmarks
May 13, 2026Takehiro Ishikawa, Jon DukeDepression Detection Mental Health
College of Computing, Georgia Institute of Technology, Atlanta, GA, USA · Georgia Tech Research Institute, Georgia Institute of Technology, Atlanta, GA, USA
Cross-Scale Transfer Learning for Depression Severity Prediction: From PHQ-8 to HAMD-17 Across Languages and Clinical Paradigms
Sep 23, 2026Wenjie Feng, Sahba Zojaji, Satoshi NakamuraClinical Outcome Prediction Depression Severity Estimation
School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China · School of Humanities and Social Science, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China · Shenzhen Loop Area Institute, Shenzhen, China
Entropy-Dominated Temporal Vocal Dynamics as Digital Biomarkers for Depression Detection
Apr 29, 2026Himadri S SamantaDepression Detection Mental Health
Independent Researcher, Austin, Texas, USA

May 13, 2026J/K move · Enter open · S save

A Multi-Probe Audit of Clinical-Interview Depression Detection Benchmarks

Takehiro Ishikawa, Jon Duke

College of Computing, Georgia Institute of Technology, Atlanta, GA, USA · Georgia Tech Research Institute, Georgia Institute of Technology, Atlanta, GA, USA

Depression Detection Mental Health Domain Generalization Benchmark Validity Multimodal Model Evaluation

Open paper AskPDF arXiv

This paper audits benchmark evaluation in clinical-interview depression detection through four complementary probes across DAIC/E-DAIC, CMDC, ANDROIDS, MODMA, and PDCH. First, we re-evaluate E-DAIC under strict subject-disjoint leave-one-subject-out cross-validation. A lightweight hybrid text-plus-LLM-score model reaches macro-F1 = 0.723 - the highest reported under this protocol, to our knowledge - providing a conservative out-of-fold reference point that does not depend on the privileged official holdout. Second, we test whether the E-DAIC official split supports fine-grained leaderboard rankings by sweeping 96 model configurations across modality bundles, pooling strategies, and learners. Development-side cross-validation and official-test rankings align only moderately: the best cross-validation configuration ranks twentieth on the official test, the official-test winner ranks forty-first by cross-validation, top-3 overlap is zero, and the apparent winner is rank-1 in only 32.3% of subject bootstraps. Third, we externally validate strong public CMDC and ANDROIDS baselines that achieve near-ceiling in-domain performance. Zero-shot transfer to external corpora is substantially weaker. Finally, we stress-test E-DAIC text and audio models using paired symptom-dense versus symptom-light interview slices defined by an SRDS-based annotator. Text scores rise sharply on symptom-dense slices, whereas audio scores remain nearly flat; the text-minus-audio gap is positive across all five seeds.

Abstract

Explore similar work

A Multi-Probe Audit of Clinical-Interview Depression Detection Benchmarks

Cross-Scale Transfer Learning for Depression Severity Prediction: From PHQ-8 to HAMD-17 Across Languages and Clinical Paradigms

Entropy-Dominated Temporal Vocal Dynamics as Digital Biomarkers for Depression Detection