The pressures faced by college students frequently lead to heightened levels of stress. Wearable devices, which collect sensor data in a non-intrusive manner, present an opportunity for early detection of stress. Nonetheless, there is a lack of diversity in current research concerning psychological assessments, physiological metrics, and time series features. In this work, we utilize a Fitbit dataset and evaluate its use in predicting stress through machine learning. Our results demonstrate that physiological data such as calories burned and sleep hold promise for stress screening, with F1 scores reaching up to 0.81. These findings illustrate the potential of wearable technology for continuous stress monitoring and emphasize the need for selecting appropriate data aggregation levels and physiological modalities for effective screening.

Major depressive disorder (MDD) and post-traumatic stress disorder (PTSD) are mental disorders that reduce quality of life. As they are challenging to detect in a timely manner, recent studies explore the mental illness screening potential of language models on modalities such as transcripts. Such datasets suffer from a limited number of participants. To overcome these challenges, we take a two-pronged approach: (1) we leverage multi-task learning to model multiple illnesses concurrently namely MDD and PTSD screening, and (2) we plug in pre-trained language models as a backbone, namely, Bidirectional Encoder Representations from Transformers (BERT) variants – which are capable of learning the linguistic content of clinical interview transcripts. In particular, we experiment with three multi-task weighting strategies and five BERT variants, applying them to 15 transcript sets extracted from the Distress Analysis Interview Corpus. Our results indicate that leveraging multi-task learning, especially with meta-weighting, increases the screening performance compared to single-task learning. Our multi-task learning model strategies improved the F1 scores for all 15 datasets for both MDD and PTSD screening. Notably, multitask learning improved MDD screening ability by 20 percent with transcripts regarding ‘regret’ and achieved F1 of 0.89 and 0.82 respectively for MDD and PTSD screening with transcripts regarding ‘medical history’. Our findings may help researchers develop more effective mental illness screening models.

Depression is a prevalent mental health condition with severe impacts on physical and social health. It is costly and difficult to detect, requiring substantial time from trained mental professionals. To alleviate this burden, recent research explores the diagnostic capabilities of deep learning models trained on modalities extracted from videos of clinical interviews for depression screening. However, training deep learning models is challenging because in the mental health domain datasets contain a small number of patients. To address this challenge, we propose DeepScreen, a recurrent deep-learning architecture for depression screening whose performance is boosted by deploying a self-supervised auxiliary task for selective missing value imputation. DeepScreen leverages a multi-task architecture with a bidirectional recurrent deep learning model and a self-attention mechanism, jointly optimizing the supervised depression and the self-supervised auxiliary task. Our first study assesses the capability of the auxiliary task training of DeepScreen under different correlation levels and masking sub-sequence sizes of multi-variate time series. Found to be effective, our second study evaluates DeepScreen on 15 data sets composed of real-world temporal facial landmark features extracted from responses to different clinical interview questions. The results achieved across all 15 datasets demonstrate that the imputation task boosts the depression prediction metrics significantly. Specifically, DeepScreen improves the F1 score for one of the datasets by 57%. Further, our best-performing model achieves an F1 score of 0.85. This work provides valuable insights into improving deep learning driven mental screening applications by leveraging auxiliary tasks such as imputation for learning a better representation even from small datasets.

Major depressive disorder (MDD) and post-traumatic stress disorder (PTSD) are prevalent mental health conditions with severe physical and social impacts. They are expensive and detection is difficult, requiring substantial time from trained mental professionals. To alleviate this issue, recent studies explore the diagnostic potential of deep learning models trained on modalities extracted from clinical interview videos, conducted by a virtual agent. However, deep learning models are challenging to train because of the long sequences and small number of participants common in the mental health community. To combat these challenges, we leverage multi-task learning, using temporal facial features as input, to screen for MDD and PTSD. The multi-task architecture is based on a bidirectional GRU model with self-attention. We evaluate our multi-task model on temporal facial features extracted from responses to 15 clinical interview questions conducted by a virtual agent. The results suggest that multi-task learning increases the generalization performance compared to single-task learning. For MDD screening, multi-task learning improved the balanced accuracy over single-task learning for 11 of the 15 datasets. In fact, our multi-learning model increased the MDD screening ability by 25 percent to a balanced accuracy of 0.87 in some scenarios. This work provides valuable findings for the future of mental screening applications leveraging temporal facial features.