Emoface: AI-assisted diagnostic model for differentiating major depressive disorder and bipolar disorder via facial biomarkers

Affective disorders, including Major Depressive Disorder (MDD) and Bipolar Disorder (BD), exhibit significant mood abnormalities, making rapid diagnosis essential for social stability and healthcare efficiency. Traditional diagnostic solutions, including medical history collection and psychological assessments, often struggle to differentiate their similar clinical presentations, leading to time-consuming, laborious, and a high rate of misdiagnosis. Here, we propose Emoface, an AI-assisted diagnostic model that reads the emotional activities of faces in affective disorders. By analyzing videos from 353 participants exposed to various emotional stimuli, Emoface identified unique facial digital biomarkers distinguishing BD from MDD. Based on this, Emoface contributed to develop the first digital facial mapping for clinical and teaching use. In clinical practice with 347 patients, Emoface achieved precise diagnosis based on various facial visual signals, with accuracy rates of 95.29% for BD and 87.05% for MDD, offering a reliable face-based AI solution in a new era of affective disorders.

Authors

Institutions

Publication Details

Journal
npj Mental Health Research
Published
2025-10-18
DOI
https://doi.org/10.1038/s44184-025-00164-4
Primary Topic
Mental Health Research Topics
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Emoface: AI-assisted diagnostic model for differentiating major depressive disorder and bipolar disorder via facial biomarkers

Huimin Huang, Hailong Lyu, Shaohua Hu, Jingkai Chen et al.
npj Mental Health Research
Mental Health Research Topics
article

Emoface: AI-assisted diagnostic model for differentiating major depressive disorder and bipolar disorder via facial biomarkers

Huimin Huang, Hailong Lyu, Shaohua Hu, Jingkai Chen, Yutong Zhang, Xin Xu, Wang Zhong, Yifeng Xu, Tianyu Ma, Jiahui Yu
article en

Abstract

Affective disorders, including Major Depressive Disorder (MDD) and Bipolar Disorder (BD), exhibit significant mood abnormalities, making rapid diagnosis essential for social stability and healthcare efficiency. Traditional diagnostic solutions, including medical history collection and psychological assessments, often struggle to differentiate their similar clinical presentations, leading to time-consuming, laborious, and a high rate of misdiagnosis. Here, we propose Emoface, an AI-assisted diagnostic model that reads the emotional activities of faces in affective disorders. By analyzing videos from 353 participants exposed to various emotional stimuli, Emoface identified unique facial digital biomarkers distinguishing BD from MDD. Based on this, Emoface contributed to develop the first digital facial mapping for clinical and teaching use. In clinical practice with 347 patients, Emoface achieved precise diagnosis based on various facial visual signals, with accuracy rates of 95.29% for BD and 87.05% for MDD, offering a reliable face-based AI solution in a new era of affective disorders.

npj Mental Health ResearchVol. 4(1)
Allen Institute for Brain Science (US), Wenzhou Medical University (CN), Interface (United States) (US), Westlake University (CN), Center for Excellence in Brain Science and Intelligence Technology (CN), Children's Hospital of Zhejiang University (CN), Zhejiang Lab (CN), Second Affiliated Hospital of Zhejiang University (CN), First Affiliated Hospital Zhejiang University (CN), Zhejiang University (CN)
National Natural Science Foundation of China, Hangzhou Science and Technology Bureau, National Key Research and Development Program of China, Natural Science Foundation of Zhejiang Province
Openalex Percentile: Top 69%
Mental Health Research Topics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.