skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: AudiFace: Multimodal Deep Learning for Depression Screening
Depression is a very common mental health disorder with a devastating social and economic impact. It can be costly and difficult to detect, traditionally requiring a significant number of hours by a trained mental health professional. Recently, machine learning and deep learning models have been trained for depression screening using modalities extracted from videos of clinical interviews conducted by a virtual agent. This complex task is challenging for deep learning models because of the multiple modalities and limited number of participants in the dataset. To address these challenges we propose AudiFace, a multimodal deep learning model that inputs temporal facial features, audio, and transcripts to screen for depression. To incorporate all three modalities, AudiFace combines multiple pre-trained transfer learning models and bidirectional LSTM with self-Attention. When compared with the state-of-the-art models, AudiFace achieves the highest F1 scores for thirteen of the fifteen different datasets. AudiFace notably improves the depression screening capabilities of general wellbeing questions. Eye gaze proved to be the most valuable of the temporal facial features, both in the unimodal and multimodal models. Our results can be used to determine the best combination of modalities, temporal facial features, as well as clinical interview questions for future depression screening applications.  more » « less
Award ID(s):
2021871
PAR ID:
10432304
Author(s) / Creator(s):
Date Published:
Journal Name:
Proceedings of Machine Learning Research
Volume:
182
ISSN:
2640-3498
Page Range / eLocation ID:
609-630
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, HCI International 2020 – Late Breaking Papers: Virtual and Augmented Reality)
    Stephanidis, Constantine; Chen, Jessie Y.; Fragomeni, Gino (Ed.)
    Post-traumatic stress disorder (PTSD) is a mental health condition affecting people who experienced a traumatic event. In addition to the clinical diagnostic criteria for PTSD, behavioral changes in voice, language, facial expression and head movement may occur. In this paper, we demonstrate how a machine learning model trained on a general population with self-reported PTSD scores can be used to provide behavioral metrics that could enhance the accuracy of the clinical diagnosis with patients. Both datasets were collected from a clinical interview conducted by a virtual agent (SimSensei) [10]. The clinical data was recorded from PTSD patients, who were victims of sexual assault, undergoing a VR exposure therapy. A recurrent neural network was trained on verbal, visual and vocal features to recognize PTSD, according to self-reported PCL-C scores [4]. We then performed decision fusion to fuse three modalities to recognize PTSD in patients with a clinical diagnosis, achieving an F1-score of 0.85. Our analysis demonstrates that machine-based PTSD assessment with self-reported PTSD scores can generalize across different groups and be deployed to assist diagnosis of PTSD. 
    more » « less
  2. ; ; ; (, Biomedical Optics Express)
    Multimodal data fusion is one of the current primary neuroimaging research directions to overcome the fundamental limitations of individual modalities by exploiting complementary information from different modalities. Electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) are especially compelling modalities due to their potentially complementary features reflecting the electro-hemodynamic characteristics of neural responses. However, the current multimodal studies lack a comprehensive systematic approach to properly merge the complementary features from their multimodal data. Identifying a systematic approach to properly fuse EEG-fNIRS data and exploit their complementary potential is crucial in improving performance. This paper proposes a framework for classifying fused EEG-fNIRS data at the feature level, relying on a mutual information-based feature selection approach with respect to the complementarity between features. The goal is to optimize the complementarity, redundancy and relevance between multimodal features with respect to the class labels as belonging to a pathological condition or healthy control. Nine amyotrophic lateral sclerosis (ALS) patients and nine controls underwent multimodal data recording during a visuo-mental task. Multiple spectral and temporal features were extracted and fed to a feature selection algorithm followed by a classifier, which selected the optimized subset of features through a cross-validation process. The results demonstrated considerably improved hybrid classification performance compared to the individual modalities and compared to conventional classification without feature selection, suggesting a potential efficacy of our proposed framework for wider neuro-clinical applications. 
    more » « less
  3. ; ; ; ; ; ; (, Proceedings of the Eighth Workshop on Computational Linguistics and Clinical Psychology)
    Conversational Agents (CAs) powered with deep language models (DLMs) have shown tremendous promise in the domain of mental health. Prominently, the CAs have been used to provide informational or therapeutic services (e.g., cognitive behavioral therapy) to patients. However, the utility of CAs to assist in mental health triaging has not been explored in the existing work as it requires a controlled generation of follow-up questions (FQs), which are often initiated and guided by the mental health professionals (MHPs) in clinical settings. In the context of ‘depression’, our experiments show that DLMs coupled with process knowledge in a mental health questionnaire generate 12.54% and 9.37% better FQs based on similarity and longest common subsequence matches to questions in the PHQ-9 dataset respectively, when compared with DLMs without process knowledge support.Despite coupling with process knowledge, we find that DLMs are still prone to hallucination, i.e., generating redundant, irrelevant, and unsafe FQs. We demonstrate the challenge of using existing datasets to train a DLM for generating FQs that adhere to clinical process knowledge. To address this limitation, we prepared an extended PHQ-9 based dataset, PRIMATE, in collaboration with MHPs. PRIMATE contains annotations regarding whether a particular question in the PHQ-9 dataset has already been answered in the user’s initial description of the mental health condition. We used PRIMATE to train a DLM in a supervised setting to identify which of the PHQ-9 questions can be answered directly from the user’s post and which ones would require more information from the user. Using performance analysis based on MCC scores, we show that PRIMATE is appropriate for identifying questions in PHQ-9 that could guide generative DLMs towards controlled FQ generation (with minimal hallucination) suitable for aiding triaging. The dataset created as a part of this research can be obtained from https://github.com/primate-mh/Primate2022 
    more » « less
  4. ; ; ; ; ; (, 10th International Conference on Affective Computing and Intelligent Interaction)
    Agents must monitor their partners' affective states continuously in order to understand and engage in social interactions. However, methods for evaluating affect recognition do not account for changes in classification performance that may occur during occlusions or transitions between affective states. This paper addresses temporal patterns in affect classification performance in the context of an infant-robot interaction, where infants’ affective states contribute to their ability to participate in a therapeutic leg movement activity. To support robustness to facial occlusions in video recordings, we trained infant affect recognition classifiers using both facial and body features. Next, we conducted an in-depth analysis of our best-performing models to evaluate how performance changed over time as the models encountered missing data and changing infant affect. During time windows when features were extracted with high confidence, a unimodal model trained on facial features achieved the same optimal performance as multimodal models trained on both facial and body features. However, multimodal models outperformed unimodal models when evaluated on the entire dataset. Additionally, model performance was weakest when predicting an affective state transition and improved after multiple predictions of the same affective state. These findings emphasize the benefits of incorporating body features in continuous affect recognition for infants. Our work highlights the importance of evaluating variability in model performance both over time and in the presence of missing data when applying affect recognition to social interactions. 
    more » « less
  5. ; ; ; ; (, IEEE Access)
    Mental illness has grown to become a prevalent and global health concern that affects individuals across various demographics. Timely detection and accurate diagnosis of mental disorders are crucial for effective treatment and support as late diagnosis could result in suicidal, harmful behaviors and ultimately death. To this end, the present study introduces a novel pipeline for the analysis of facial expressions, leveraging both the AffectNet and 2013 Facial Emotion Recognition (FER) datasets. Consequently, this research goes beyond traditional diagnostic methods by contributing a system capable of generating a comprehensive mental disorder dataset and concurrently predicting mental disorders based on facial emotional cues. Particularly, we introduce a hybrid architecture for mental disorder detection leveraging the state-of-the-art object detection algorithm, YOLOv8 to detect and classify visual cues associated with specific mental disorders. To achieve accurate predictions, an integrated learning architecture based on the fusion of Convolution Neural Networks (CNNs) and Visual Transformer (ViT) models is developed to form an ensemble classifier that predicts the presence of mental illness (e.g., depression, anxiety, and other mental disorder). The overall accuracy is improved to about 81% using the proposed ensemble technique. To ensure transparency and interpretability, we integrate techniques such as Gradient-weighted Class Activation Mapping (Grad-CAM) and saliency maps to highlight the regions in the input image that significantly contribute to the model’s predictions thus providing healthcare professionals with a clear understanding of the features influencing the system’s decisions thereby enhancing trust and more informed diagnostic process. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email