Early Detection Of Depression Research Articles

Elderly depression in front-line health services:A descriptive and evaluative cross-sectional study

Introduction Depression is a common pathology in the elderly, often unrecognized and mostly affiliated to the consequences of aging,especially in front-line services. It induces somatic and functional impact and even a suicidal risk. When unrecognized or neglected, depression can reduce life expectancy and increases the use of healthcare and the institutionalization. Objectives -Determine the point-prevalence of depression in the elderly in a front-line heath service in Tunis. - Identify risk factors of depression in the elderly. Methods A descriptive and evaluative cross-sectional study on a sample of patients aged 65 or more, in a tunisian front-line service of general health care regardless of the medical reason. Sociodemographic and clinical forms along with the PHQ-9 scale (Patient health questionnaire-9) - validated in tunisian dialect- were used. Results Thirty patients have participated in our study (21 men and 9 women). The average age was 73.23 years. Chronic pathologies were found in 96.66% of cases. The found risk factors are: female sex in 70% of cases, loneliness and isolation in 10% of cases, widowhood in 50% of cases, grieving in 6.6% of cases and somatic comorbidity in 96 .66% of cases. The overall prevalence of depressive symptoms was 53.33%. This is correlated with advanced age and female sex (57.14% in women vs 33.33% in men). The depressive symptomatology found, was mild in 18.5% of cases, average in 62.5% of cases and moderately severe in 18.5% of cases. Conclusions Depression is a frequent pathology in the elderly with multiple risk factors. The aging of the Tunisian population on one hand and the change of the social model (family nucleus) on the other, encourage the early detection of depression in the elderly and the training of the health professionals in order to limit its prevalence. Disclosure of Interest None Declared

Early detection of depression using a conversational AI bot: A non-clinical trial.

Artificial intelligence (AI) has gained momentum in behavioural health interventions in recent years. However, a limited number of studies use or apply such methodologies in the early detection of depression. A large population needing psychological-intervention is left unidentified due to barriers such as cost, location, stigma and a global shortage of health workers. Therefore, it is essential to develop a mass screening integrative approach that can identify people with depression at its early stage to avoid a potential crisis. This study aims to understand the feasibility and efficacy of using AI-enabled chatbots in the early detection of depression. We use Dialogflow as a conversation interface to build a Depression Analysisn (DEPRA) chatbot. A structured and authoritative early detection depression interview guide, which contains 27 questions combining the structured interview guide for the Hamilton Depression Scale (SIGH-D) and the inventory of depressive symptomatology (IDS-C), underpins the design of the conversation flow. To attain better accuracy and a wide variety of responses, we train Dialogflow with the utterances collected from a focus group of 10 people. The occupation of the focus group members included academics and HDR candidates who are conscious, vigilant and have a clear understanding of the questions. In addition, DEPRA is integrated with a social media platform to provide practical access to all the participants. For the non-clinical trial, we recruited 50 participants aged between 18 and 80 from across Australia. To evaluate the practicability and performance of DEPRA, we also asked participants to submit a user satisfaction survey at the end of the conversation. A sample of 50 participants, with an average age of 34.7 years, completed this non-clinical trial. More than half of the participants (54%) are male and the major ethnicities are Asian (63%), Middle Eastern (25%), and others 12%. The first group comprises professional academic staff and HDR candidates, the second and third groups comprise relatives, friends, and volunteers who were recruited via social media promotions. DEPRA uses two scientific scoring systems, QIDS-SR and IDS-SR to verify the results of early depression detection. As the results indicate, both scoring systems return a similar outcome with slight variations for different depression levels. According to IDS-SR, 30% of participants were healthy, 14% mild, 22% moderate, 14% severe, and 20% very severe. QIDS-SR suggests 32% were healthy, 18% mild, 10% moderate, 18% severe, and 22% very severe. Furthermore, the overall satisfaction rate of using DEPRA was 79% indicating that the participants had a high rate of user satisfaction and engagement. DEPRA shows promises as a feasible option for developing a mass screening integrated approach for early detection of depression. Although the chatbot is not intended to replace the functionality of mental health professionals, it does show promise as a means of assisting with automation and concealed communication with verified scoring systems.

The relationship of depression and malnutrition with healthy eating index in elderly individuals

Depression, malnutrition, and the healthy eating index were assessed in this study of people aged 65 and up who sought treatment at an outpatient clinic for internal medicine. Participants were elderly people from Malatya, Türkiye, who had applied to the outpatient clinic for internal medicine. The three-day dietary recall method was used to obtain the records of food consumption among the elderly. The calculation of Healthy Eating Index-2015 (HEI-2015) scores from food consumption. Geriatric Depression Scale (GDS) was used to define probable depression, and Mini Nutrition Questionnaire-Short Form (MNA-SF) was used to determine nutritional status, using face-to-face interviews. The study were 185 individuals included. The mean age of individuals was 72.19±6.92 years. According to MNA-SF results, 32.3% of women and 27.4% of men were found to be malnourished. The mean body mass index (BMI) value of the individuals was 25.73±2.85 kg/cm2, and the BMI value of 56.22% of the individuals was within the normal range. The depression score mean was 8.86±4.73. Depression scores are higher in women, those with low monthly education and income, those who use multiple drugs, those with a low HEI-2015 score, and those who use them. There is a relationship between depression score and eating score. As the nutrition score and the HEI-2015 score decrease, the depression score increases. This study indicates that depressed older people consume less food. Early detection of depression and malnutrition is beneficial. Older adults should routinely use brief, easy-to-obtain diagnostic tools such as the MNA and GDS questionnaires to treat these related health issues quickly and effectively.

Association between depression and suicidal ideation among people living with HIV

Background: Psychological illnesses among PLHIV may cause poor engagement to their HIV care and it may lead to poor treatment outcomes. Therefore, early detection of depression and suicidal behaviour is important for timely intervention to improve mental health and HIV/AIDS-related treatment outcomes. So, the AIM of the study was to assess the prevalence of depression and its relation with suicidal ideation among PLHIV.Methods: This was a cross-sectional and facility-based study, 205 PLHIV were recruited by using systematic random sampling from ART plus centre, Lucknow. Depression and suicidal ideation were assessed using the nine-item patient health questionnaire (PHQ-9) tool. Data were analysed using Chi-square test and multivariate logistic regression in SPSS version-23.Results: The results revealed that the prevalence of depression among study participants was 36.6%, in which about more than half (56.0%) were females and about 54.4% females had suicidal ideation. In the multivariate logistic analysis, gender; AOR=3.07, 95% CI (1.53-6.14), category; AOR=3.66, 95% CI (1.60-8.34), type of family; AOR=0.26, 95% CI (0.12-0.58), socio-economic status; AOR=7.93, 95% CI (2.32-27.06) and PLHIV on co-trimoxazole prophylactic treatment; AOR=0.47, 95% CI (0.23-0.99) were significantly associated with depressionConclusions: The results signify the psychological morbidities of illness among PLHIV, so without good mental health care, people with HIV may fail their treatment, which also affects their health.

Quality of Life and Its Associated Factors among Patients with Psoriasis in a Semi-Urban Northeast Malaysia.

Psoriasis is a chronic relapsing dermatological disorder that significantly affects the patients’ psychosocial well-being and quality of life (QOL). This study aimed to determine the proportion of severely impaired QOL, the factors associated with severely impaired QOL, and its correlation with depression among semi-urban populations on the Northeast Coast of the Peninsular Malaysia. A cross-sectional study was conducted among 257 patients with psoriasis at the Dermatology Clinic of Hospital Sultanah Bahiyah via a self-administered questionnaire that included sociodemographic profiles, the validated Malay version of the Dermatology Life Quality Index (DLQI), and the Malay version of the Beck depression scale. The data were analysed using logistic and linear regression models. About 20.5% of the patients had severely impaired QOL quality of life, while 79.5% of the patients had non-impaired QOL. Multiple logistic regression analysis showed that the psoriatic severity [Adjusted OR = 1.91, 95% CI: 1.76, 9.93; p < 0.001] and exposed area [Adjusted OR 2.93, 95% CI: 0.38, 2.29; p = 0.050] had a significant association with severely impaired QOL. Among the patients, 18.7% had a positive result in the screening for depression, which revealed a significant association between QOL and depression scores [r = 0.47, 95% CI: 0.35, 0.56, p < 0.001]. Psoriasis can impair QOL and have a relation with mental health. Regular screening for depression among patients with psoriasis is a beneficial strategy for the early detection of depression, especially in semi-urban areas.

Depression among Older Adults in Indonesia: Prevalence, Role of Chronic Conditions and Other Associated Factors.

Depression is one of the most common illnesses worldwide, with a prevalence of 5.7% among older adults aged over 60. Depression is a severe health condition that can significantly affect the quality of life. The objective of this study is to investigate the determinant factors of depression among older adults in Indonesia. Data of 4236 adults of 60 years old and over were taken from the fifth wave of the Indonesian Family Life Survey (IFLS-5). Sociodemographic and multiple health-related variables collected through interviews and measurements were analyzed. Multivariate logistic regression was used to evaluate depression and its associated factors. The prevalence of depression assessed using ten questions from the Center for Epidemiologic Studies Depression Scale (CES-D 10) was 16.3%. Significant associated factors for depression were moderate and low subjective economic status, living in Java or other regions outside Sumatra and Java, no life satisfaction, self-perceived as having poor health, having dependency (IADL scores), and experienced falls and insomnia. Among chronic conditions, stroke, arthritis, and hearing impairment were also more common in depressed older adults. Predictors of depression identified in this study may be used to help prevent and improve depression in Indonesian older adults, especially those who live on Java. Improvement in healthcare, especially in the prevention and rehabilitation of stroke, arthritis, possible frailty (falls and dependency), hearing impairment, and insomnia, concurrent with early detection of depression in these chronic conditions, may help create a better quality of life among Indonesian older adults.

Identification of normal and depression EEG signals in variational mode decomposition domain.

Early detection of depression is critical in assisting patients in receiving the best therapy possible to avoid negative repercussions. Depression detection using electroencephalogram (EEG) signals is a simple, low-cost, convenient, and accurate approach. This paper proposes a six-stage novel method for detecting depression using EEG signals. First, EEG signals are recorded from 44 subjects, with 22 subjects being normal and 22 subjects being depressed. Second, a simple notch filter with EEG signals differencing approach is employed for effective preprocessing. Third, the variational mode decomposition (VMD) approach is implemented for nonlinear and non-stationary EEG signals analysis, resulting in many modes. Fourth, mutual information-based novel modes selection criterion is proposed to select the most informative modes. In the fifth step, a combination of linear and nonlinear features are extracted from selected modes and at last, classification is performed with neural networks. In this study, a novel single feature is also proposed, which is made using Log energy, norm entropies and fluctuation index, which delivers 100% classification accuracy, sensitivity and specificity. By using these features, a novel depression diagnostic index is also proposed. This integrated index would assist in quicker and more objective identification of normal and depression EEG signals. The proposed computerized framework and the DDI can help health workers, large enterprises, and product developers build a real-time system.

Utilization of passive visual perception task indetecting patients with major depressive disorder for active health.

Depression is a common emotional and mental disease. At present, doctors' diagnosis mainly depends on the existing evaluation scales and their accumulated experience, lack of objective electrophysiological quantitative evaluation indicators. This study explores the difference in event-related potential (ERP) between patients with depression and healthy controls under the stimulation of multi-dimensional tasks, extracts the characteristic data, and uses a t-test for statistical analysis to provide an objective evaluation index for the clinical diagnosis of depression. Ninety-nine patients in the major depression group (MDD) and thirty patients in the healthy control group (HC) were used to compare the responses to positive, negative, and neutral stimulation, the results showed that there were significant differences between the left and right occipital lobes and one frontal lobe, and the frontal lobe showed lateralization; There were significant differences between the depression group and the healthy control group under multi-dimensional stimulation (P<0.01), and the depression patients were significantly lower than the healthy patients. The results showed that emotional information was processed differently in patients with depression in the early stages of visual face processing. Therefore, EEG indices could be used as an objective index for the early detection of depression. Moreover, according to the instructions before the test, the subject is only asked to recognize visual pictures instead report emotional feelings. Stigma about psychiatric disorders could thus be reduced in this way. The explorations above facilitate designing more accurate and implicit active mental health techniques.

Adolescent Depression Detection Model Based on Multimodal Data of Interview Audio and Text.

Depression is a common mental disease that has a tendency to develop at a younger age. Early detection of depression with psychological intervention may effectively prevent youth suicide. The establishment of the computer-aided model may be efficient for early detection. However, the existing methods of automatic detection for depression mostly rely on unimodal data. Clinical research shows that patients with depression have specificity in speech, text, expression, and other modal data. Multimodal machine learning is emerging but not yet widely used for the detection of psychiatric disorders. The problem of existing multimodal detection models is that only global or local information is considered in feature fusion, which leads to the low accuracy of the depression detection model. Therefore, this study constructs an automatic detection model based on multimodal machine learning for adolescent depression. The proposed method first extracted four features from audio and text globally and locally; then construct a coarse-grained fusion model and fine-grained fusion model base on these four features; and fuse the coarse-grained and the fine-grained fusion model finally. Experiments on the real-world dataset demonstrate that the proposed method could improve the accuracy of depression detection automatically.

Relationship of explicit/implicit self-esteem discrepancies, suicide ideation, and suicide risk in patients with major depressive disorder.

The present study was conducted to explore the associations between explicit self-esteem (ESE), implicit self-esteem (ISE), ESE/ISE discrepancies, depression severity, suicidal ideation (SI), and suicide risk among patients with major depressive disorder (MDD). To this end, 36 MDD patients with SI, 35 MDD patients without SI, and 32 healthy controls were recruited. All participants were interviewed using the Mini International Neuropsychiatric Interview (MINI), and they also completed the Beck Depression Inventory (BDI). The Beck Scale for Suicide Ideation-Chinese Version (BSI-CV) and the Rosenberg Self-Esteem Scale (SES) were used for the analysis. Further, the Implicit Association Test (IAT) was conducted to assess participants' ISE. The study revealed significant differences in ESE among the three groups, F(2, 90)=44.88, p < .001. In particular, the group of MDD patients with SI had the lowest score. The interaction between the size and direction of ESE/ISE discrepancy was associated with depression severity, β=-.50, p=.004, and SI, β=-.39, p=.045. Among the four types of self-esteem, individuals with diminished self-esteem had the highest SI score whereas individuals with low congruent self-esteem had the highest suicide risk score. Based on these findings, the study suggested that diminished self-esteem could help in the early detection of depression and SI. Low-congruent self-esteem may also be considered a screening factor for suicide risk.

Prevalence of depression and suicidal ideation in trauma patients in western Rajasthan

Depression is a common psychiatric disorder in trauma patients. Early detection of depression in a traumatized patients can help alleviate long-term symptoms and adverse effects associated with depression. This study aimed to determine the prevalence of depression and suicidal ideation in trauma patients after one month of injury. Hospital-based cross-sectional study was carried out among 120 individuals with a history of trauma from March 2020 to May 2020. Purposive sampling was used to recruit participants over a specified period. The Beck's Depression Inventory-II (BDI-II) was used to measure depression intensity and suicidal ideation. The statistical analysis was carried out using SPSS version 20. The study included a total of 120 participants. The prevalence of depression was 30% in study participants. In our study, 8 (44.44%) of 18 participants over the age of 60, 30 (36.59%) of 82 male participants, 9 (64.29%) of 14 separated or divorced participants, 17 (45.95%) of 37 illiterate participants, 25 (43.86%) of 57 participants from low socioeconomic backgrounds, and 23 (42.59%) of 54 participants from rural backgrounds had more depression. Twenty (46.51%) out of 43 polytrauma participants, 5 (45.45%) out of 11 participants injured due to violence, 31 (33.70%) out of 92 participants who had a history of more than 48 hrs hospitalization, and 17 (48.57%) out of 35 participants had a history of ICU admission had more depression. Twenty-one participants (58.33%) of the 36 who suffered from depression had suicidal thoughts or intentions. Suicidal ideation and depression were more common in traumatic patients. Physicians' treatment should not be limited to early physical rehabilitation. They must also prioritise early mental rehabilitation in order to avoid long-term issues with mental and physical disabilities.

Factors Associated Depression In Secondary Schools Adolescents In Gombe, North-eastern, Nigeria

Background: Depression is a mood disorder characterised by loss of interest and enjoyment (anhedonia), and reduced energy leading to increased fatigability and diminished activity. Depression is a major contributor to the overall global burden of disease. It has a profound effect on adolescents because those who experience depression at an early age often struggle with depression throughout their lives, and in many cases, early onset of depression predicts more severe depression during adulthood. Objectives: This study aimed to determine the prevalence of depression and associated factors among secondary school adolescents in Gombe, Nigeria. Methodology: Three hundred and ninety-five adolescents aged 13- 18 years were selected using a multistage sampling method. The Beck Depression Inventory-II (BDI-II) was used to assess depression and a structured questionnaire was used to obtain the sociodemographic characteristics of the subjects. Results: The mean age of subjects was 16.2±1.4 years. The prevalence of depression was 37.7% (142/377). Subjects from low socio-economic class (χ2= 30.601, p&lt; 0.001). Subjects with non-parental caregivers were 4.8 times more likely to be depressed than those that had parental caregivers (OR 4.760, CI 1.882-12.04). Depression was significantly higher among subjects from public schools (χ2= 22.698, p&lt; 0.001). Also, the majority of the subjects who failed the exams preceding the study had depression as compared to those that passed the exams (χ2=5.389, p= 0.030). Conclusion: The burden of depression is high among adolescent secondary school students in Gombe. Psychosocial stressors such as low social class, non-parental care, parental divorce and poor academic performance are significant determinants of depression among adolescents. Early detection of depression is recommended as it has a strong relationship with suicidal ideation among adolescents.

Early depression detection in social media based on deep learning and underlying emotions

Depression is a challenge to public health, frequently related to disability and one of the reasons that lead to suicide. Many of the ones who suffer depression use social media to obtain information or even to talk about their problem. Some studies have proposed to detect potentially depressive users in these online environments. However, unsatisfactory effectiveness is still a barrier to practical application. Hence, we propose a method of early detection of depression in social media based on a convolutional neural network in combination with context-independent word embeddings and Early and Late Fusion approaches. These approaches are experimentally evaluated, considering the importance of the underlying emotions encoded in the emoticons. The results show that the proposed method was able to detect potentially depressive users, reaching a precision of 0.76 with equivalent or superior effectiveness in relation to many baselines (F1(0.71)). In addition, the semantic mapping of emoticons allowed to obtain significantly better results, including higher recall and precision with gains of 46.3% and 32.1%, respectively. Regarding the baseline word embedding approach, the higher recall and precision gains of our semantic mapping of emoticons were 14.5% and 40.8%. In terms of overall effectiveness, this work advanced the state-of-the-art, considering both individual embeddings and the fusion-based approaches. Moreover, it is demonstrated that emotions expressed by depressed people and encoded through emoticons are important suggestive evidence of the problem and a valuable asset for early detection.

Research on the Method of Depression Detection by Single-Channel Electroencephalography Sensor.

Depression is a common mental health illness worldwide that affects our quality of life and ability to work. Although prior research has used EEG signals to increase the accuracy to identify depression, the rates of underdiagnosis remain high, and novel methods are required to identify depression. In this study, we built a model based on single-channel, dry-electrode EEG sensor technology to detect state depression, which measures the intensity of depressive feelings and cognitions at a particular time. To test the accuracy of our model, we compared the results of our model with other commonly used methods for depression diagnosis, including the PHQ-9, Hamilton Depression Rating Scale (HAM-D), and House-Tree-Person (HTP) drawing test, in three different studies. In study 1, we compared the results of our model with PHQ-9 in a sample of 158 senior high students. The results showed that the consistency rate of the two methods was 61.4%. In study 2, the results of our model were compared with HAM-D among 71 adults. We found that the consistency rate of state-depression identification by the two methods was 63.38% when a HAM-D score above 7 was considered depression, while the consistency rate increased to 83.10% when subjects showed at least one depressive symptom (including depressed mood, guilt, suicide, lack of interest, retardation). In study 3, 68 adults participated in the study, and the results revealed that the consistency rate of our model and HTP drawing test was 91.2%. The results showed that our model is an effective means to identify state depression. Our study demonstrates that using our model, people with state depression could be identified in a timely manner and receive interventions or treatments, which may be helpful for the early detection of depression.

Machine learning techniques for predicting depression and anxiety in pregnant and postpartum women during the COVID-19 pandemic: a cross-sectional regional study

Background: Maternal depression and anxiety are significant public health concerns that play an important role in the health and well-being of mothers and children. The COVID-19 pandemic, the consequential lockdowns and related safety restrictions worldwide negatively affected the mental health of pregnant and postpartum women. Methods: This regional study aimed to develop a machine learning (ML) model for the prediction of maternal depression and anxiety. The study used a dataset collected from five Arab countries during the COVID-19 pandemic between July to December 2020. The population sample included 3569 women (1939 pregnant and 1630 postpartum) from five countries (Jordan, Palestine, Lebanon, Saudi Arabia, and Bahrain). The performance of seven machine learning algorithms was assessed for the prediction of depression and anxiety symptoms. Results: The Gradient Boosting (GB) and Random Forest (RF) models outperformed other studied ML algorithms with accuracy values of 83.3% and 83.2% for depression, respectively, and values of 82.9% and 81.3% for anxiety, respectively. The Mathew’s Correlation Coefficient was evaluated for the ML models; the Naïve Bayes (NB) and GB models presented the highest performance measures (0.63 and 0.59) for depression and (0.74 and 0.73) for anxiety, respectively. The features’ importance ranking was evaluated, the results showed that stress during pregnancy, family support, financial issues, income, and social support were the most significant values in predicting anxiety and depression. Conclusion: Overall, the study evidenced the power of ML models in predicting maternal depression and anxiety and proved to be an efficient tool for identifying and predicting the associated risk factors that influence maternal mental health. The deployment of machine learning models for screening and early detection of depression and anxiety among pregnant and postpartum women might facilitate the development of health prevention and intervention programs that will enhance maternal and child health in low- and middle-income countries.

Morbidity and Associated Factors of Depressive Disorder in Patients With Parkinson's Disease.

Parkinson's disease (PD) is a progressive, neurodegenerative disorder and is commonly comorbid with depression. The aim of this cross-sectional study was to assess morbidity and associated factors of depression in patients with PD. In total, 181 patients with PD were enrolled and assessed using the Mini-International Neuropsychiatric Interview. Of the sample, 51% had at least one psychiatric diagnosis. The most prevalent psychiatric disorder was depressive disorder (27.6%), followed by rapid eye movement sleep behavior disorder (9.9%), insomnia disorder (8.8%), and adjustment disorder (2.8%). Severity of anxiety, suicide risk, and anxiolytics/hypnotics use were factors associated with depressive disorder in PD patients. Furthermore, severity of anxiety was significantly linked with suicide risk. We suggest that use of a standardized structured interview for early detection of depression in PD patients is crucial. Anxiety, anxiolytics/hypnotics use, depression, and suicide risks are interrelated and warrant clinical concerns regarding PD patients.

Depression Detection by Analyzing Social Media Post of User

Abstract: Nowadays the problem of early depression detection is one of the most important in the field of psychology .Mental health issues are widely accepted as one of the most prominent health challenges in the world, with over 300 million people currently suffering from depression alone. With massive volumes of user-generated data on social networking platforms, researchers are increasingly using machine learning to determine whether this content can be used to detect mental health problems in users. Depression as a disorder has been an excellent concern in our society and has been continuously a hot topic for researchers in the world. Despite the massive quantity of analysis on understanding individual moods together with depression, anxiety, and stress supported activity logs collected by pervasive computing devices like smartphones, foretelling depressed moods continues to be an open question. Social networks analysis is widely applied to address this problem. In this paper, we have proposed a depression analysis and suicidal ideation detection system, for predicting the suicidal acts supported the extent of depression. The present study aims to exploit machine learning techniques for detecting a probable depressed Social Media user his/her Posts. For this purpose, we trained and tested classifiers to differentiate whether a user is depressed or not using features extracted from his/her activities within the posts. classification machine algorithms are used to train and classify it in Different stages of depression on scale of 0-100%. Also, data was collected in the form of posts and were classified into whether the one that tweeted is in depression or not using classification algorithms of Machine Learning In this way Predictive approach for early detection of depression or other mental illnesses. This study’s main contribution is that the exploration a neighborhood of the features and its impact on detecting Depression level. This study aims to develop a deep learning model to classify users with depression via multiple instance learning, which can learn from user-level labels to identify post-level labels. By combining every possibility of posts label category, it can generate temporal posting profiles which can then be used to classify users with depression. This paper shows that there are clear differences in posting patterns between users with depression and non-depression, which is represented through the combined likelihood of posts label category. In this research, machine learning is used to process the scrapped data collected from social media users posts. Natural Language Processing (NLP), classified using BERT algorithm to detect depression potentially in amore convenient and efficient way. Keywords: Machine Learning, NLP, BERT Algorithm, Classification, Social Media Post

Major depressive disorder detection in polytechnic college students

Over 322 million people worldwide are affected by depression, the leading cause of disability. Major depressive disorder (MDD) is the most frequent mental disorder and contributes significantly to the global disease burden. Current depression diagnoses, on the other hand, are beset by issues such as patient denial, clinical experience, and self-report bias. Early detection of depression can assist in lessening or even eliminating its detrimental effects. To help the conventional diagnostic approaches in psychiatry, there has been much research into automated depression prediction in recent years. Automated depression identification based on machine learning techniques can help disorder analysts diagnose depression more effectively. The literature on depression has proven that the acoustic features of a depressed individual vary from a normal individual. This paper aims to identify the minimal acoustic features that can be used to detect depression accurately and propose a majority voting classifier for detecting depression (MVCDD). MVCDD is designed with the base classifiers, including Random Forest Classifier (RFC), Support Vector Classifier (SVC), and Logistic Regression (LR). The experiments are performed on the data collected from the students of Government Polytechnic, Masabtank, Hyderabad, India.

Machine learning techniques for predicting depression and anxiety in pregnant and postpartum women during the COVID-19 pandemic: a cross-sectional regional study.

Background: Maternal depression and anxiety are significant public health concerns that play an important role in the health and well-being of mothers and children. The COVID-19 pandemic, the consequential lockdowns and related safety restrictions worldwide negatively affected the mental health of pregnant and postpartum women. Methods: This regional study aimed to develop a machine learning (ML) model for the prediction of maternal depression and anxiety. The study used a dataset collected from five Arab countries during the COVID-19 pandemic between July to December 2020. The population sample included 3569 women (1939 pregnant and 1630 postpartum) from five countries (Jordan, Palestine, Lebanon, Saudi Arabia, and Bahrain). The performance of seven machine learning algorithms was assessed for the prediction of depression and anxiety symptoms. Results: The Gradient Boosting (GB) and Random Forest (RF) models outperformed other studied ML algorithms with accuracy values of 83.3% and 83.2% for depression, respectively, and values of 82.9% and 81.3% for anxiety, respectively. The Mathew's Correlation Coefficient was evaluated for the ML models; the Naïve Bayes (NB) and GB models presented the highest performance measures (0.63 and 0.59) for depression and (0.74 and 0.73) for anxiety, respectively. The features' importance ranking was evaluated, the results showed that stress during pregnancy, family support, financial issues, income, and social support were the most significant values in predicting anxiety and depression. Conclusion: Overall, the study evidenced the power of ML models in predicting maternal depression and anxiety and proved to be an efficient tool for identifying and predicting the associated risk factors that influence maternal mental health. The deployment of machine learning models for screening and early detection of depression and anxiety among pregnant and postpartum women might facilitate the development of health prevention and intervention programs that will enhance maternal and child health in low- and middle-income countries.

Comparison of classifiers using robust features for depression detection on Bahasa Malaysia speech

Early detection of depression allows rapid intervention and reduce the escalation of the disorder. Conventional method requires patient to seek diagnosis and treatment by visiting a trained clinician. Bio-sensors technology such as automatic depression detection using speech can be used to assist early diagnosis for detecting remotely those who are at risk. In this research, we focus on detecting depression using Bahasa Malaysia language using speech signals that are recorded remotely via subject’s personal mobile devices. Speech recordings from a total of 43 depressed subjects and 47 healthy subjects were gathered via online platform with diagnosis validation according to the Malay beck depression inventory II (Malay BDI-II), patient health questionnaire (PHQ-9) and subject’s declaration of major depressive disorder (MDD) diagnosis by a trained clinician. Classifier models were compared using time-based and spectrum-based microphone independent feature set with hyperparameter tuning. Random forest performed best for male reading speech with 73% accuracy while support vector machine performed best on both male spontaneous speech and female reading speech with 74% and 73% accuracy, respectively. Automatic depression detection on Bahasa Malaysia language has shown to be promising using machine learning and microphone independent features but larger database is necessary for further validation and improving performance.