In today’s fast-paced world, the rates of stress and depression present a surge. People use social media for expressing their thoughts and feelings through posts. Therefore, social media provide assistance for the early detection of mental health conditions. Existing methods mainly introduce feature extraction approaches and train shallow machine learning (ML) classifiers. For addressing the need of creating a large feature set and obtaining better performance, other research studies use deep neural networks or language models based on transformers. Despite the fact that transformer-based models achieve noticeable improvements, they cannot often capture rich factual knowledge. Although there have been proposed a number of studies aiming to enhance the pretrained transformer-based models with extra information or additional modalities, no prior work has exploited these modifications for detecting stress and depression through social media. In addition, although the reliability of a machine learning (ML) model’s confidence in its predictions is critical for high-risk applications, there is no prior work taken into consideration the model calibration. To resolve the above issues, we present the first study in the task of depression and stress detection in social media, which injects extra-linguistic information in transformer-based models, namely, bidirectional encoder representations from transformers (BERT) and MentalBERT. Specifically, the proposed approach employs a multimodal adaptation gate for creating the combined embeddings, which are given as input to a BERT (or MentalBERT) model. For taking into account the model calibration, we apply label smoothing. We test our proposed approaches in three publicly available datasets and demonstrate that the integration of linguistic features into transformer-based models presents a surge in performance. Also, the usage of label smoothing contributes to both the improvement of the model’s performance and the calibration of the model. We finally perform a linguistic analysis of the posts and show differences in language between stressful and nonstressful texts, as well as depressive and nondepressive posts.

Alzheimers disease (AD) is the main cause of dementia which is accompanied by loss of memory and may lead to severe consequences in peoples everyday life if not diagnosed on time. Very few works have exploited transformer-based networks and despite the high accuracy achieved, little work has been done in terms of model interpretability. In addition, although Mini-Mental State Exam (MMSE) scores are inextricably linked with the identification of dementia, research works face the task of dementia identification and the task of the prediction of MMSE scores as two separate tasks. In order to address these limitations, we employ several transformer-based models, with BERT achieving the highest accuracy accounting for 87.50%. Concurrently, we propose an interpretable method to detect AD patients based on siamese networks reaching accuracy up to 83.75%. Next, we introduce two multi-task learning models, where the main task refers to the identification of dementia (binary classification), while the auxiliary one corresponds to the identification of the severity of dementia (multiclass classification). Our model obtains accuracy equal to 86.25% on the detection of AD patients in the multi-task learning setting. Finally, we present some new methods to identify the linguistic patterns used by AD patients and non-AD ones, including text statistics, vocabulary uniqueness, word usage, correlations via a detailed linguistic analysis, and explainability techniques (LIME). Findings indicate significant differences in language between AD and non-AD patients.

Alzheimer's dementia (AD) entails negative psychological, social, and economic consequences not only for the patients but also for their families, relatives, and society in general. Despite the significance of this phenomenon and the importance for an early diagnosis, there are still limitations. Specifically, the main limitation is pertinent to the way the modalities of speech and transcripts are combined in a single neural network. Existing research works add/concatenate the image and text representations, employ majority voting approaches or average the predictions after training many textual and speech models separately. To address these limitations, in this article we present some new methods to detect AD patients and predict the Mini-Mental State Examination (MMSE) scores in an end-to-end trainable manner consisting of a combination of BERT, Vision Transformer, Co-Attention, Multimodal Shifting Gate, and a variant of the self-attention mechanism. Specifically, we convert audio to Log-Mel spectrograms, their delta, and delta-delta (acceleration values). First, we pass each transcript and image through a BERT model and Vision Transformer, respectively, adding a co-attention layer at the top, which generates image and word attention simultaneously. Secondly, we propose an architecture, which integrates multimodal information to a BERT model via a Multimodal Shifting Gate. Finally, we introduce an approach to capture both the inter- and intra-modal interactions by concatenating the textual and visual representations and utilizing a self-attention mechanism, which includes a gate model. Experiments conducted on the ADReSS Challenge dataset indicate that our introduced models demonstrate valuable advantages over existing research initiatives achieving competitive results in both the AD classification and MMSE regression task. Specifically, our best performing model attains an accuracy of 90.00% and a Root Mean Squared Error (RMSE) of 3.61 in the AD classification task and MMSE regression task, respectively, achieving a new state-of-the-art performance in the MMSE regression task.

Electronic health records (EHR) are patient-level information, e.g., laboratory tests and questionnaires, stored in electronic format. Compared to physical records, the EHR alternative allows patients to access their data easily and helps staff with management procedural tasks such as information sharing across different organizations. Moreover, this type of data is commonly used by researchers for predictive and classification purposes, employing statistical and machine learning methods. However, missingness is a phenomenon that is observed very frequently for such measurements. Even though this missingness is often significant, it is usually treated poorly with either case deletion or simple methods, resulting in suboptimal and/or inaccurate predictive results. This happens because the simple methods, e.g., k-nearest neighbors (kNN) and mean/mode imputation, fail in most cases to incorporate the complex relationships that define these medical datasets. To address these limitations, in this paper we test and improve state-of-the-art missing data imputation models and practices. We propose a new missing value imputation method based on denoising autoencoders (DAE) with kNN for the pre-imputation task. We optimize the training methodology by re-applying kNN to the missing data every $N$ epochs using a different value for the variable $k$ each time to yield more accurate results. We also revise a state-of-the-art missing data imputation approach based on a generative adversarial network (GAN). Using this as a baseline, we introduce improvements regarding both the architecture and the training procedure. These models are compared with the ones usually employed within clinical research studies for both the task of imputation and post-imputation prediction. Results show that our proposed deep learning approaches outperform the standard baselines, yielding better imputation and predictive results.