Recognition Of Depression Research Articles

Achieving EEG-based depression recognition using Decentralized-Centralized structure

Currently, electroencephalography (EEG)-based depression recognition using deep learning methods has become an important approach for early diagnosis and treatment. Due to the functional differences and activation differences among various brain regions, the channels in EEG data may potentially exhibit a certain degree of local correlation. Furthermore, several studies have indicated that there are significant differences in the synchronization for multiple brain regions between patients with depression and healthy controls. However, few researchers have designed depression recognition model architectures according to the spatial distribution characteristics of EEG data. In multiple existing EEG-based classification models, the channels of EEG data are directly merged. This approach hinders the model from effectively capturing the spatial information of EEG data and leads to a partial loss of synchronized information of several brain regions. In light of this, we propose a novel attention network named Decentralized-Centralized Structure Transformer (DCST), which can achieve effective depression recognition utilizing the spatial distribution characteristics of EEG data. The leave-one-subject-out cross-validation is employed to evaluate the classification performance for all models. The experimental results show that our proposed model achieves the highest classification accuracy, 89.8%.

Patterns of peripartum depression and anxiety during the pre-vaccine COVID-19 pandemic

BackgroundPregnant people are vulnerable to new or worsening mental health conditions. This study aims to describe prevalence and course of depression and anxiety symptoms in pregnancy during the pre-vaccine COVID-19 pandemic.MethodsThis is a prospective cohort study of pregnant individuals with known or suspected COVID-19. Participants completed Edinburgh Postnatal Depression Scale (EPDS) and Generalized-Anxiety Disorder-7 (GAD-7) questionnaires, screening tools for depression and anxiety, at 34weeks gestational age, 6-8weeks postpartum, and 6months postpartum. Prevalence of elevated depressive and anxiety symptoms at each visit was described. Univariable logistic regression analysis was used to determine the association between demographic and clinical factors and those with elevated depression or anxiety symptoms.Results317 participants were included. The prevalence of elevated antepartum depression symptoms was 14.6%, 10.3%, and 20.6% at 34weeks gestational age, 6-8weeks postpartum, and 6months postpartum, respectively. The rate of elevated anxiety symptoms was 15.1%, 10.0%, and 17.3% at 34weeks gestational age, 6-8weeks postpartum, and 6months postpartum, respectively. A prior history of depression and/or anxiety (p’s < 0.03), as well as higher EPDS and GAD-7 scores at enrollment (p’s < 0.04) associated with elevated depression and anxiety symptoms throughout pregnancy and the postpartum period. Quarantining during pregnancy was associated with elevated anxiety symptoms at 34weeks gestational age in univariate (P = 0.027) analyses. COVID-19 diagnosis and hospitalization were not associated with elevated depression or anxiety symptoms.ConclusionsElevated depression and anxiety symptoms were prevalent throughout pregnancy and the postpartum period, particularly in those with prior depression and/or anxiety and who quarantined. Strategies that target social isolation may mitigate potential adverse consequences for pregnant people, and continued vigilance in recognition of depression and anxiety in pregnancy should be considered.

Loss Relaxation Strategy for Noisy Facial Video-based Automatic Depression Recognition

Automatic depression analysis has been widely investigated on face videos that have been carefully collected and annotated in lab conditions. However, videos collected under real-world conditions may suffer from various types of noise due to challenging data acquisition conditions and lack of annotators. Although deep learning (DL) models frequently show excellent depression analysis performances on datasets collected in controlled lab conditions, such noise may degrade their generalization abilities for real-world depression analysis tasks. In this article, we uncovered that noisy facial data and annotations consistently change the distribution of training losses for facial depression DL models; i.e., noisy data–label pairs cause larger loss values compared to clean data–label pairs. Since different loss functions could be applied depending on the employed model and task, we propose a generic loss function relaxation strategy that can jointly reduce the negative impact of various noisy data and annotation problems occurring in both classification and regression loss functions for face video-based depression analysis, where the parameters of the proposed strategy can be automatically adapted during depression model training. The experimental results on 25 different artificially created noisy depression conditions (i.e., five noise types with five different noise levels) show that our loss relaxation strategy can clearly enhance both classification and regression loss functions, enabling the generation of superior face video-based depression analysis models under almost all noisy conditions. Our approach is robust to its main variable settings and can adaptively and automatically obtain its parameters during training.

A Study of Major Depressive Disorder Based on Resting-State Multilayer EEG Function Network

Depression is a complex mental disease with its pathological mechanism unclear. To depict the complete picture of the abnormal information interaction in a depressed brain, this study is the first to apply fully connected multilayer brain functional (FCMBF) network framework and proposed composite FCMBF (CFCMBF) network framework, combined with graph theory to analyze the within-frequency coupling (WFC) and cross-frequency coupling (CFC) of sensor-layer and source-layer electroencephalography (EEG) signals in relevant subjects. Results showed that in the sensor-layer FCMBF network, depressive patients showed significantly reduced functional connectivity, as well as abnormal global and local information processing abilities of the network, and these network properties were significantly correlated with depressive symptoms. In addition, from the perspective of depression recognition, we found that the sensor-layer CFCMBF network could achieve better classification accuracy, especially when using the overlapping degree of node under the right center region, its accuracy could reach <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$86.88\% \pm 9.25 \%$</tex-math> </inline-formula> . More importantly, the construction of the CFCMBF network has higher time efficiency and less information loss, since it not only measures the WFC and CFC between brain region representative signals (BRRSs) extracted from different brain regions, but also measures these two couplings between all nodes within each brain region. Although the FCMBF network contains more complete information by calculating WFC and CFC between all nodes distributed in each region, it will result in an enormous computational cost. In summary, this study proved the utility of multilayer brain network in revealing the abnormal brain interaction patterns of depression, and our proposed method might provide methodological support for efficient depression recognition research based on multilayer brain networks.

The Influence of Depression in the Evolution of Parkinson’s Disease: A Psychiatric Perspective

IntroductionParkinson’s disease (PD) is a neurodegenerative condition that is predominantly characterised by its motor symptoms. Nevertheless, it is important to note that non-motor symptoms, particularly depression often occur concurrently, exerting a substantial influence on the progression of the disease and the overall well-being of individuals affected by it.ObjectivesThe objective of this study is to examine the influence of depression on the advancement of Parkinson’s disease (PD) from a psychiatric perspective. This analysis will involve an assessment of the common neurobiological pathways involved and the potential implications for clinical treatment and care.MethodsA comprehensive assessment of the literature was conducted, focusing on clinical observations, neurochemical interactions, and neuroimaging investigations that provide insight into the concurrent presence of depression and Parkinson’s disease (PD). This study aimed to investigate the potential impact of depression on the severity of Parkinson’s disease symptoms, the course of the disease, and the responsiveness to treatment.ResultsDepression in Parkinson’s disease (PD) is not only a reactive occurrence, but rather it may be attributed to common pathophysiological mechanisms, such as changes in dopamine and serotonin pathways. The coexistence of depression among individuals with Parkinson’s disease (PD) has been linked to heightened severity of motor and cognitive symptoms, accelerated development of the disease, and diminished effectiveness of therapy interventions. Furthermore, the presence of depression in individuals with Parkinson’s disease intensifies the psychosocial difficulties experienced by both patients and their carers.ConclusionsThe recognition and management of depression in individuals with Parkinson’s disease (PD) is of utmost importance in order to enhance treatment approaches and enhance the overall well-being of patients. The establishment of interdisciplinary collaboration between neurologists and psychiatrists is necessary in order to guarantee a holistic approach to patient care.Disclosure of InterestNone Declared

An Obstetrics &amp; Gynecology Resident Education Program to Address Gaps in the Knowledge, Screening, and Treatment of Postpartum Mood and Anxiety Disorder (PMAD)

Background: Postpartum mood and anxiety disorders has been shown to cause significant problems for caregivers, their newborn and children. Despite this widespread issue, only 55% of healthcare providers assess for these symptoms/disorders. Objective: The objective of this study is to design a training class to increase OBGYN residents’ knowledge and confidence in diagnosing and treating postpartum mood and anxiety disorders. Methods: In 2023 we implemented a program designed to educate Obstetrics &amp; Gynecology resident physicians about the symptoms of postpartum mood and anxiety disorders as well as interventions for validated screening and treatment modalities. Results: A total of 26 residents participated in this training program at of the 49 who were recruited. This resulted in an improvement in foundational knowledge, notably the recognition of postpartum blues versus depression, as well as understanding how to screen for postpartum depression. Conclusions: The program increased resident confidence in recognizing and treating postpartum mood and anxiety disorders.

A machine learning based depression screening framework using temporal domain features of the electroencephalography signals.

Depression is a serious mental health disorder affecting millions of individuals worldwide. Timely and precise recognition of depression is vital for appropriate mediation and effective treatment. Electroencephalography (EEG) has surfaced as a promising tool for inspecting the neural correlates of depression and therefore, has the potential to contribute to the diagnosis of depression effectively. This study presents an EEG-based mental depressive disorder detection mechanism using a publicly available EEG dataset called Multi-modal Open Dataset for Mental-disorder Analysis (MODMA). This study uses EEG data acquired from 55 participants using 3 electrodes in the resting-state condition. Twelve temporal domain features are extracted from the EEG data by creating a non-overlapping window of 10 seconds, which is presented to a novel feature selection mechanism. The feature selection algorithm selects the optimum chunk of attributes with the highest discriminative power to classify the mental depressive disorders patients and healthy controls. The selected EEG attributes are classified using three different classification algorithms i.e., Best- First (BF) Tree, k-nearest neighbor (KNN), and AdaBoost. The highest classification accuracy of 96.36% is achieved using BF-Tree using a feature vector length of 12. The proposed mental depressive classification scheme outperforms the existing state-of-the-art depression classification schemes in terms of the number of electrodes used for EEG recording, feature vector length, and the achieved classification accuracy. The proposed framework could be used in psychiatric settings, providing valuable support to psychiatrists.

Surface depression recognition of spring plate based on feature construction and improved AdaBoost algorithm

Machine learning has introduced novel solutions for the surface quality inspection of spring plates. Hence, an improved method was proposed based on logistic regression and AdaBoost (LR-RBAdaBoost) for recognizing surface depressions in spring plates. In order to obtain the measured attributes for spring plates, feature construction methods were adopted. Then, logistic regression was used to analyze and rank the attributes of the spring plate and the filter method was used for the feature selection process. To improve the predicted performance of AdaBoost, RBAdaBoost was proposed in this paper, which is used in the issue of recognition of surface defects in spring steel plates. The effectiveness and sophistication of LR-RBAdaBoost are validated on a real spring steel plate sampling dataset. The results show that the accuracy of LR-RBAdaBoost is 0.968 and f1-score is 0.967, which can be better than the results of only using AdaBoost, random forest, and CatBoost. Furthermore, the results prove that the research has a certain reference value for the recognition of spring plate as well.

EEG-based depression recognition using feature selection method with fuzzy label

Depression diagnosis is easily affected by subjective consciousness.It is of great significance to study objective and accurate identification methods. Electroencephalogram (EEG) can reflect brain activity and working state. Therefore, this paper aims to explore features with significant differences based on brain functional connectivity to improve the accuracy of depression recognition. We propose a Functional Connection Feature Selection based on Fuzzy Label (FLFCFS), it calculates the correlation between electrode pairs through the phase lag index (PLI), constructing a functional connection matrix. The cluster center is initialized with the same number as the actual category, and the local distance from the sample to the cluster center is calculated to determine its membership degree, serving as the fuzzy label. And a sparse regression model is employed to select the most related features associated with the fuzzy label. Finally, the top ranked feature subset is selected and input into support vector machine (SVM) for depression recognition. The experimental results show that FLFCFS effectively improves the recognition accuracy, reaching 92.59%, and obtains the highest classification performance. Our method makes full use of the semantic information implied in category markers, it effectively guides feature selection to obtain discriminant feature subsets, enhancing the accuracy of depression recognition.

A research on depression recognition based on voice pre-training model

For the increasing number of patients with depression, this paper proposes an artificial intelligence method to effectively identify depression through voice signals, with the aim of improving the efficiency of diagnosis and treatment. Firstly, a pre-training model called wav2vec 2.0 is fine-tuned to encode and contextualize the speech, thereby obtaining high-quality voice features. This model is applied to the publicly available dataset - the distress analysis interview corpus-wizard of OZ (DAIC-WOZ). The results demonstrate a precision rate of 93.96%, a recall rate of 94.87%, and an F1 score of 94.41% for the binary classification task of depression recognition, resulting in an overall classification accuracy of 96.48%. For the four-class classification task evaluating the severity of depression, the precision rates are all above 92.59%, the recall rates are all above 92.89%, the F1 scores are all above 93.12%, and the overall classification accuracy is 94.80%. The research findings indicate that the proposed method effectively enhances classification accuracy in scenarios with limited data, exhibiting strong performance in depression identification and severity evaluation. In the future, this method has the potential to serve as a valuable supportive tool for depression diagnosis.

Automatic recognition of depression based on audio and video: A review.

Depression is a common mental health disorder. With current depression detection methods, specialized physicians often engage in conversations and physiological examinations based on standardized scales as auxiliary measures for depression assessment. Non-biological markers-typically classified as verbal or non-verbal and deemed crucial evaluation criteria for depression-have not been effectively utilized. Specialized physicians usually require extensive training and experience to capture changes in these features. Advancements in deep learning technology have provided technical support for capturing non-biological markers. Several researchers have proposed automatic depression estimation (ADE) systems based on sounds and videos to assist physicians in capturing these features and conducting depression screening. This article summarizes commonly used public datasets and recent research on audio- and video-based ADE based on three perspectives: Datasets, deficiencies in existing research, and future development directions.

A survey of mental health literacy in parents and guardians of teenagers.

Parents and guardians (hereafter caregivers) of teenagers need high levels of mental health literacy (MHL) to manage mental health problems arising in teenagers in their care. Previous studies assessing MHL levels in caregivers of teenagers have reported mixed results, making it difficult to clearly estimate caregiver MHL levels. This study aimed to investigate MHL levels in Japanese caregivers of regular teenagers. Responses from caregivers (n = 1,397) of students entering junior and senior high schools to a self-administered online questionnaire were analyzed. The questionnaire assessed (a) knowledge about mental health/illnesses and (b) attitudes towards mental health problems in teens in their care (e.g., recognition of depression as a medical illness and intention to engage in helping behaviors). The average proportion of correct answers to the knowledge questions (n = 7) was 55.4%; about one tenth (9.2%) of caregivers correctly answered only one or none of the questions. Few caregivers correctly answered about the life-time prevalence of any mental illnesses (46.1%) and appropriate sleep duration for teenagers' health (16.5%). The proportions of caregivers who had the intention to listen to the teen in their care, consult another person, and seek professional medical help if the teen suffered from depression were 99.5%, 91.5% and 72.7%, respectively. Many teenagers' caregivers appeared to be willing to help the teens in their care if they were suffering from mental health problems. However, there was much room for improvement in knowledge on mental health/illnesses and intention to seek help from medical professionals. Efforts toward better education should be made.

Spatial–Temporal Feature Network for Speech-Based Depression Recognition

Depression is a serious mental disorder that has received increased attention from society. Due to the advantage of easy acquisition of speech, researchers have tried to propose various automatic depression recognition algorithms based on speech. Feature selection and algorithm design are the main difficulties in speech-based depression recognition. In our work, we propose the spatial-temporal feature network (STFN) for depression recognition, which can capture the long-term temporal dependence of audio sequences. First, to obtain a better feature representation for depression analysis, we develop a self-supervised learning framework, called Vector Quantized Wav2vec Transformer Net (VQWTNet) to map speech features and phonemes with transfer learning. Second, the stacked gated residual blocks in SFNet are used in the model to integrate causal and dilated convolutions to capture multiscale contextual information by continuously expanding the receptive field. In addition, instead of LSTM, our method employs the hierarchical contrastive predictive coding (HCPC) loss in HCPCNet to capture the long-term temporal dependencies of speech, reducing the number of parameters while making the network easier to train. Finally, experimental results on DAIC-WOZ (AVEC 2017) and E-DAIC (AVEC 2019) show that the proposed model significantly improves the accuracy of depression recognition. On both datasets, the performance of our method far exceeds the baseline and achieves competitive results compared to state-of-the-art methods.

Trust, discrimination and preference for shared decision-making in adolescents diagnosed with depression: Implications from Chinese mental health professionals

BackgroundWhile evidence suggests that the attitudes of healthcare providers toward medical decision-making in adolescents diagnosed with depression merit exploration, research on their preferences for Shared Decision-Making (SDM) and the factors affecting these preferences remains limited. ObjectiveTo investigate Chinese mental health professionals’ (MHPs) preferences for SDM in adolescents with depression and identify the relationships between their preference for SDM and trust and discrimination. MethodsA cross-sectional design was used in this study. Clinical Decision-making Style-Staff (CDMS-S) was applied to evaluate their preferences for SDM. Physician Trust in the Patient Scale (PTPS) was utilised to assess their trust in consumers. Social Distance Scale to Mental Illness (SDSMI) was utilised to measure their discrimination against people with mental illness. ResultsA total of 581 MHPs were identified in China. MHPs rated their preference for participation in decision making (PD) as shared (1.89 ± 0.472), information (IN) as moderate (2.62 ± 0.682), and family involvement (FI) as high (3.13 ± 0.840). The preferences for three decision topics ranked from the highest to the lowest score were working-related decision (2.35 ± 0.681), general preferences in decision (1.82 ± 0.581) and medication-related decision (1.74 ± 0.826). The mean score of PTPS and SDSMI were 34.71 (SD=9.709) and 15.17 (SD=4.299), respectively. Logistic regression indicated that the preference for PD was associated with discrimination; the preference for IN was associated with trust, discrimination and SDM-related training experience; and the preference for FI was associated with both trust and discrimination. ConclusionsWhile MHPs generally exhibit a favourable attitude toward SDM, this positivity is not universally observed across all contexts. There remains room for improvement in the willingness to co-develop medication regimens and share health information. Rational recognition of depression, and building trusting and friendly therapeutic relationships are key to promoting MHPs’ preferences for SDM. Practical valueMHPs' preferences for SDM have a significant impact on SDM implementation, which will be promoted by implementing SDM-related training.

FNIRS-Driven Depression Recognition Based on Cross-Modal Data Augmentation.

Early diagnosis and intervention of depression promote complete recovery, with its traditional clinical assessments depending on the diagnostic scales, clinical experience of doctors and patient cooperation. Recent researches indicate that functional near-infrared spectroscopy (fNIRS) based on deep learning provides a promising approach to depression diagnosis. However, collecting large fNIRS datasets within a standard experimental paradigm remains challenging, limiting the applications of deep networks that require more data. To address these challenges, in this paper, we propose an fNIRS-driven depression recognition architecture based on cross-modal data augmentation (fCMDA), which converts fNIRS data into pseudo-sequence activation images. The approach incorporates a time-domain augmentation mechanism, including time warping and time masking, to generate diverse data. Additionally, we design a stimulation task-driven data pseudo-sequence method to map fNIRS data into pseudo-sequence activation images, facilitating the extraction of spatial-temporal, contextual and dynamic characteristics. Ultimately, we construct a depression recognition model based on deep classification networks using the imbalance loss function. Extensive experiments are performed on the two-class depression diagnosis and five-class depression severity recognition, which reveal impressive results with accuracy of 0.905 and 0.889, respectively. The fCMDA architecture provides a novel solution for effective depression recognition with limited data.

Trial Selection Tensor Canonical Correlation Analysis (TSTCCA) for Depression Recognition with Facial Expression and Pupil Diameter.

Facial expressions have been widely used for depression recognition because it is intuitive and convenient to access. Pupil diameter contains rich emotional information that is already reflected in facial video streams. However, the spatiotemporal correlation between pupillary changes and facial behavior changes induced by emotional stimuli has not been explored in existing studies. This paper presents a novel multimodal fusion algorithm - Trial Selection Tensor Canonical Correlation Analysis (TSTCCA) to optimize the feature space and build a more robust depression recognition model, which innovatively combines the spatiotemporal relevance and complementarity between facial expression and pupil diameter features. TSTCCA explores the interaction between trials and obtains an effective fusion representation of two modalities from a trial subset related to depression. The experimental results show that TSTCCA achieves the highest accuracy of 78.81% with the subset of 25 trials.

Integrating Deep Facial Priors into Landmarks for Privacy Preserving Multimodal Depression Recognition

Integrating Deep Facial Priors into Landmarks for Privacy Preserving Multimodal Depression Recognition

An On-Board Executable Multi-Feature Transfer-Enhanced Fusion Model for Three-Lead EEG Sensor-Assisted Depression Diagnosis.

The development of affective computing and medical electronic technologies has led to the emergence of Artificial Intelligence (AI)-based methods for the early detection of depression. However, previous studies have often overlooked the necessity for the AI-assisted diagnosis system to be wearable and accessible in practical scenarios for depression recognition. In this work, we present an on-board executable multi-feature transfer-enhanced fusion model for our custom-designed wearable three-lead Electroencephalogram (EEG) sensor, based on EEG data collected from 73 depressed patients and 108 healthy controls. Experimental results show that the proposed model exhibits low-computational complexity (65.0K parameters), promising Floating-Point Operations(FLOPs) performance (26.6M), real-time processing (1.5s/execution), and low power consumption (320.8mW). Furthermore, it requires only 202.0MB of Random Access Memory(RAM) and 279.6KB of Read-Only Memory(ROM) when deployed on the EEG sensor. Despite its low computational and spatial complexity, the model achieves a notable classification accuracy of 95.2%, specificity of 96.9%, and sensitivity of 94.0% under independent test conditions. These results underscore the potential of deploying the model on the wearable three-lead EEG sensor for assisting in the diagnosis of depression.

DEP-Former: Multimodal Depression Recognition Based on Facial Expressions and Audio Features via Emotional Changes

DEP-Former: Multimodal Depression Recognition Based on Facial Expressions and Audio Features via Emotional Changes

Baby blues, premenstrual syndrome and postpartum affective disorders: intersection of risk factors and reciprocal influences.

The aetiology and consequences of 'baby blues' (lower mood following childbirth) are yet to be sufficiently investigated with respect to an individual's clinical history. The primary aim of the study was to assess the symptoms of baby blues and the relevant risk factors, their associations with clinical history and premenstrual syndrome (PMS), and their possible contribution to the early recognition of postpartum depression (PPD). Beginning shortly after childbirth, 369 mothers were followed up for 12 weeks. Information related to their clinical history, PMS, depression, stress and mother-child attachment was collected. At 12 weeks, mothers were classified as non-depressed, or with either PPD or adjustment disorder. A correlation was found between the severity of baby blues and PMS (r = 0.397, P < 0.001), with both conditions increasing the possibility of adjustment disorder and PPD (baby blues: OR = 6.72, 95% CI 3.69-12.25; PMS: OR = 3.29, 95% CI 2.01-5.39). Baby blues and PMS independently predicted whether a mother would develop adjustment disorder or PPD after childbirth (χ2(64) = 198.16, P < 0.001). Among the non-depressed participants, baby blues were found to be associated with primiparity (P = 0.012), family psychiatric history (P = 0.001), PMS (P < 0.001) and childhood trauma (P = 0.017). Baby blues are linked to a number of risk factors and a history of PMS, with both conditions adding to the risk of PPD. The neuroendocrine effects on mood need be understood in the context of individual risk factors. The assessment of both baby blues and PMS symptoms within the first postpartum days may contribute to an early identification of PPD.