An algorithm for determination of rank and degree of contribution of sMRI volumetric features in depression detection

Brain volume changes at structural level appear to have utmost importance in depression biomarkers studies. However, these brain volumetric findings have very minimal utilization in depression detection studies at individual level. Thus, this paper presents an evaluation of volumetric features to identify the relevant/optimal features for the detection of depression. An algorithm is presented for determination of rank and degree of contribution (DoC) of structural magnetic resonance imaging (sMRI) volumetric features. The algorithm is based on the frequencies of each feature contribution toward the desired accuracy limit. Forty-four volumetric features from various brain regions were adopted for evaluation. From DoC analysis, the DoC of each volumetric feature for depression detection is calculated and the features that dominate the contribution are determined.

Degree of contribution (DoC) feature selection algorithm for structural brain MRI volumetric features in depression detection

Accurate detection of depression at an individual level using structural magnetic resonance imaging (sMRI) remains a challenge. Brain volumetric changes at a structural level appear to have importance in depression biomarkers studies. An automated algorithm is developed to select brain sMRI volumetric features for the detection of depression.

Evaluation of feature selection algorithms for detection of depression from brain sMRI scans

Detection of depression from structural MRI (sMRI) scans is relatively new in the mental health diagnosis. Such detection requires processes including image acquisition and pre-processing, feature extraction and selection, and classification. Identification of a suitable feature selection (FS) algorithm will facilitate the enhancement of the detection accuracy by selection of important features. In the field of depression study, there are very limited works that evaluate feature selection algorithms for sMRI data. This paper investigates the performance of four algorithms for FS of volumetric attributes in sMRI scans. The algorithms are One Rule (OneR), Support Vector Machine (SVM), Information Gain (IG) and ReliefF. The performances of the algorithms are determined through a set of experiments on sMRI brain scans. An experimental procedure is developed to measure the performance of the tested algorithms. The result of the evaluation of the FS algorithms is discussed by using a number of analyses.

Investigating machine learning techniques for detection of depression using structural MRI volumetric features

Structural MRI offers anatomical details and high sensitivity to pathological changes. It can demonstrate certain patterns of brain changes present at a structural level. Research to date has shown that volumetric analysis of brain regions has importance in depression detection. However, such analysis has had very minimal use in depression detection studies at individual level. Optimally combining various brain volumetric features/attributes, and summarizing the data into a distinctive set of variables remain difficult. This study investigates machine learning algorithms that automatically identify relevant data attributes for depression detection. Different machine learning techniques are studied for depression classification based on attributes extracted from structural MRI (sMRI) data. The attributes include volume calculated from whole brain, white matter, grey matter and hippocampus. Attributes subset selection is performed aiming to remove redundant attributes using three filtering methods and one hybrid method, in combination with ranker search algorithms. The highest average classification accuracy, obtained by using a combination of both SVM-EM and IG-Random Tree algorithms, is 85.23%. The classification approach implemented in this study can achieve higher accuracy than most reported studies using sMRI data, specifically for detection of depression.

Automated detection of depression from brain structural magnetic resonance imaging (sMRI) scans

 Automated sMRI-based depression detection system is developed whose components include acquisition and preprocessing, feature extraction, feature selection, and classification. The core focus of the research is on the establishment of a new feature selection algorithm that quantifies the most relevant brain volumetric feature for depression detection at an individual level.

An empirical comparison of classification algorithms for diagnosis of depression from brain sMRI scans

To be diagnostically effective, structural magnetic resonance imaging (sMRI) must reliably distinguish a depressed individual from a healthy individual at individual scans level. One of the tasks in the automated diagnosis of depression from brain sMRI is the classification. It determines the class to which a sample belongs (i.e., depressed/not depressed, remitted/not-remitted depression) based on the values of its features. Thus far, very limited works have been reported for identification of a suitable classification algorithm for depression detection. In this paper, different types of classification algorithms are compared for effective diagnosis of depression. Ten independent classification schemas are applied and a comparative study is carried out. The algorithms are: Naïve Bayes, Support Vector Machines (SVM) with Radial Basis Function (RBF), SVM Sigmoid, J48, Random Forest, Random Tree, Voting Feature Intervals (VFI), LogitBoost, Simple KMeans Classification Via Clustering (KMeans) and Classification Via Clustering Expectation Minimization (EM) respectively. The performances of the algorithms are determined through a set of experiments on sMRI brain scans. An experimental procedure is developed to measure the performance of the tested algorithms. A classification accuracy evaluation method was employed for evaluation and comparison of the performance of the examined classifiers.

Depressão em hospital geral: avaliação do desepenho de escalas de rastreamento e desenvolvimento de instrumento para uso na rotina assistencial

O presente estudo desenvolve-se numa perspectiva prática, visando à integração de conhecimentos gerados pela pesquisa a atividades assistenciais no hospital geral universitário, dirigindo-se, especificamente, à questão da detecção da depressão. A depressão é um problema de saúde pública no mundo inteiro, transtorno mental de alta prevalência, com elevado custo para os sistemas de saúde. Entre pacientes clínicos e cirúrgicos, hospitalizados, aumenta a complexidade dos tratamentos, implica maior morbidade e mortalidade, importando também no aumento do tempo e dos custos das internações. Por outro lado, a depressão é subdiagnosticada. Este estudo, originado de um projeto cujo objetivo foi criar um instrumento para a detecção de depressão, utilizável na rotina assistencial, a partir da avaliação do desempenho de escalas de rastreamento já existentes, desdobra-se em três artigos. O primeiro, já aceito para publicação em revista indexada internacionalmente, é a retomada de estudos anteriores, realizados no final da década de 1980. É apresentada a comparação da detecção de depressão, realizada por médicos não-psiquiatras e por enfermeiros, no Hospital de Clínicas de Porto Alegre (HCPA), em 1987 e em 2002. O segundo artigo apresenta o processo de construção da nova escala, a partir da seleção de itens de outras escalas já validadas, utilizando modelos logísticos de Rasch. A nova escala, composta por apenas seis itens, exige menos tempo para sua aplicação. O terceiro artigo é um estudo de avaliação de desempenho da nova escala, denominada Escala de Depressão em Hospital Geral (EDHG), realizado em uma outra amostra de pacientes adultos clínicos e cirúrgicos internados no HCPA. O segundo e terceiro artigos já foram encaminhados para publicação internacional. Esses estudos, realizados em unidades de internação clínicas e cirúrgicas do Hospital de Clínicas de Porto Alegre, permitiram as seguintes conclusões: a) comparando-se os achados de 1987 com os de 2002, a prevalência de depressão e o seu diagnóstico, em pacientes adultos clínicos e cirúrgicos internados, mantêm-se nos mesmos níveis; b) foi possível selecionar um conjunto de seis itens, que constituíram a nova Escala de Depressão em Hospital Geral (EDHG), baseando-se no desempenho individual de cada um dos 48 itens componentes de outras três escalas (BDI, CESD e HADS); c) a EDHG apresentou desempenho semelhante aos das escalas que lhe deram origem, usando o PRIME-MD como padrão-ouro, com a vantagem de ter um pequeno número de itens, podendo constituir-se num dispositivo de alerta para detecção de depressão na rotina de hospital geral.

Detection of acute coronary occlusion in patients with acute coronary syndromes presenting with isolated ST-segment depression

This study sought to determine whether 80-lead body surface potential mapping (BSPM) would improve detection of acute myocardial infarction (AMI) and occluded culprit artery in patients presenting with ST-segment depression (STD) only on 12-lead ECG.

The early detection of postpartum depression: midwives and nurses trial a checklist

Objective: To evaluate the use of a standard pen-and-paper test versus the use of a checklist for the early identification of women at risk of postpartum depression and to investigate the experiences of nurses in using the checklist.

Design: A prospective cohort design using repeated measures.

Setting: The booking-in prenatal clinic at a regional hospital in Victoria, Australia, and the community-based postpartum maternal and child health service.

Participants: 107 pregnant women over 20 years of age.

Main Measures: Postpartum Depression Prediction Inventory (PDPI), Postpartum Depression Screening Scale (PDSS), Edinburgh Postnatal Depression Scale (EPDS), demographic questionnaire, and data on the outcome from the midwives and nurses.

Results: The PDPI identified 45% of the women at risk of depression during pregnancy and 30% postpartum. The PDSS and EPDS both identified the same 8 women (10%), who scored highly for depression at the 8-week postpartum health visit. Nurses provided 80% of the women with anticipatory guidance on postpartum depression in the prenatal period and 46% of women at the 8-week postpartum health visit. Nurse counseling or anticipatory guidance was provided for 60% of the women in the prenatal period.

Conclusion: The PDPI was found to be a valuable checklist by many nurses involved in this research, particularly as a way of initiating open discussion with women about postpartum depression. It correlated strongly with both the PDSS and the EPDS, suggesting that it is useful as an inventory to identify women at risk of postpartum depression.

Early detection of depression and associated risk factors in adults with mild/moderate intellectual disability

The aim of this study was to determine the presentation and risk factors for depression in adults with mild/moderate intellectual disability (ID). A sample of 151 adults (83 males and 68 females) participated in a semi-structured interview. According to results on the Beck Depression Inventory II, 39.1% of participants evinced symptoms of depression (2 severe, 14 moderate, and 43 mild). Sadness, self-criticism, loss of energy, crying, and tiredness appeared to be the most frequent indicators of depression or risk for depression. A significant difference was found between individuals with and without symptoms of depression on levels of automatic negative thoughts, downward social comparison and self-esteem. Automatic negative thoughts, quality and frequency of social support, self-esteem, and disruptive life events significantly predicted depression scores in people with mild/moderate ID, accounting for 58.1% of the variance.