scholarly journals Detection of Minor and Major Depression through Voice as a Biomarker Using Machine Learning

2021 ◽  
Vol 10 (14) ◽  
pp. 3046
Author(s):  
Daun Shin ◽  
Won Ik Cho ◽  
C. Hyung Keun Park ◽  
Sang Jin Rhee ◽  
Min Ji Kim ◽  
...  
Keyword(s):  
Machine Learning ◽  
Major Depression ◽  
Depressive Episode ◽  
Small Sample Size ◽  
Structured Interview ◽  
Small Sample ◽  
Minor Depression ◽  
Voice Change ◽  
Depressed Group ◽  
Depressive Episodes

Both minor and major depression have high prevalence and are important causes of social burden worldwide; however, there is still no objective indicator to detect minor depression. This study aimed to examine if voice could be used as a biomarker to detect minor and major depression. Ninety-three subjects were classified into three groups: the not depressed group (n = 33), the minor depressive episode group (n = 26), and the major depressive episode group (n = 34), based on current depressive status as a dimension. Twenty-one voice features were extracted from semi-structured interview recordings. A three-group comparison was performed through analysis of variance. Seven voice indicators showed differences between the three groups, even after adjusting for age, BMI, and drugs taken for non-psychiatric disorders. Among the machine learning methods, the best performance was obtained using the multi-layer processing method, and an AUC of 65.9%, sensitivity of 65.6%, and specificity of 66.2% were shown. This study further revealed voice differences in depressive episodes and confirmed that not depressed groups and participants with minor and major depression could be accurately distinguished through machine learning. Although this study is limited by a small sample size, it is the first study on voice change in minor depression and suggests the possibility of detecting minor depression through voice.

Investigating the Dynamics of Suicidal Ideation

Crisis ◽  
2018 ◽  
Vol 39 (1) ◽  
pp. 65-69 ◽  
Author(s):  
Nina Hallensleben ◽  
Lena Spangenberg ◽  
Thomas Forkmann ◽  
Dajana Rath ◽  
Ulrich Hegerl ◽  
...  
Keyword(s):  
Suicidal Ideation ◽  
Small Sample Size ◽  
Unipolar Depression ◽  
Small Sample ◽  
History Of ◽  
Severity Of Depression ◽  
Ecological Momentary ◽  
Depressive Episodes ◽  
Ema Method ◽  
Shed Light

Abstract. Background: Although the fluctuating nature of suicidal ideation (SI) has been described previously, longitudinal studies investigating the dynamics of SI are scarce. Aim: To demonstrate the fluctuation of SI across 6 days and up to 60 measurement points using smartphone-based ecological momentary assessments (EMA). Method: Twenty inpatients with unipolar depression and current and/or lifetime suicidal ideation rated their momentary SI 10 times per day over a 6-day period. Mean squared successive difference (MSSD) was calculated as a measure of variability. Correlations of MSSD with severity of depression, number of previous depressive episodes, and history of suicidal behavior were examined. Results: Individual trajectories of SI are shown to illustrate fluctuation. MSSD values ranged from 0.2 to 21.7. No significant correlations of MSSD with several clinical parameters were found, but there are hints of associations between fluctuation of SI and severity of depression and suicidality. Limitations: Main limitation of this study is the small sample size leading to low power and probably missing potential effects. Further research with larger samples is necessary to shed light on the dynamics of SI. Conclusion: The results illustrate the dynamic nature and the diversity of trajectories of SI across 6 days in psychiatric inpatients with unipolar depression. Prediction of the fluctuation of SI might be of high clinical relevance. Further research using EMA and sophisticated analyses with larger samples is necessary to shed light on the dynamics of SI.

scholarly journals Longitudinal assessment of S100B serum levels and clinical factors in youth patients with mood disorders

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Aleksandra Rajewska-Rager ◽  
Monika Dmitrzak-Weglarz ◽  
Pawel Kapelski ◽  
Natalia Lepczynska ◽  
Joanna Pawlak ◽  
...  
Keyword(s):  
Mood Disorders ◽  
Calcium Binding ◽  
Clinical Symptoms ◽  
Small Sample Size ◽  
Serum Levels ◽  
Small Sample ◽  
Drop Out ◽  
Control Group ◽  
Longitudinal Assessment ◽  
Depressed Group

AbstractMood disorders have been discussed as being in relation to glial pathology. S100B is a calcium-binding protein, and a marker of glial dysfunctions. Although alterations in the S100B expression may play a role in various central nervous system diseases, there are no studies on the potential role of S100B in mood disorders in adolescents and young adults . In a prospective two-year follow-up study, peripheral levels of S100B were investigated in 79 adolescent/young adult patients (aged 14–24 years), diagnosed with mood disorders and compared with 31 healthy control subjects. A comprehensive clinical interview was conducted which focused on clinical symptoms and diagnosis change. The diagnosis was established and verified at each control visit. Serum S100B concentrations were determined. We detected: lower S100B levels in medicated patients, compared with those who were drug-free, and healthy controls; higher S100B levels in a depressed group with a family history of affective disorder; correlations between age and medication status; sex-dependent differences in S100B levels; and lack a of correlation between the severity of depressive or hypo/manic symptoms. The results of our study indicate that S100B might be a trait-dependent rather than a state-dependent marker. Due to the lack of such studies in the youth population, further research should be performed. A relatively small sample size, a lack of exact age-matched control group, a high drop-out rate.

Work stress as a risk factor for major depressive episode(s)

2004 ◽  
Vol 35 (6) ◽  
pp. 865-871 ◽  
Author(s):  
JIANLI WANG
Keyword(s):  
Multivariate Analysis ◽  
Risk Factor ◽  
Major Depression ◽  
Work Stress ◽  
Depressive Episode ◽  
Major Depressive Episode ◽  
Working Population ◽  
Major Depressive ◽  
Major Depressive Episodes ◽  
Depressive Episodes

Background. Major depression is a prevalent mental disorder in the general population, with a multi-factorial etiology. However, work stress as a risk factor for major depression has not been well studied.Method. Using a longitudinal study design, this analysis investigated the association between the levels of work stress and major depressive episode(s) in the Canadian working population, aged 18 to 64 years. Data from the longitudinal cohort of the Canadian National Population Health Survey (NPHS) were used (n=6663). The NPHS participants who did not have major depressive episodes (MDE) at baseline (1994–1995 NPHS) were classified into four groups by the quartile values of the baseline work stress scores. The proportion of MDE of each group was calculated using the 1996–1997 NPHS data.Results. The first three quartile groups had a similar risk of MDE. Those who had a work stress score above the 75th percentile had an elevated risk of MDE (7·1%). Using the 75th percentile as a cut-off, work stress was significantly associated with the risk of MDE in multivariate analysis (odds ratio=2·35, 95% confidence interval 1·54–3·77). Other factors associated with MDE in multivariate analysis included educational level, number of chronic medical illnesses and child and adulthood traumatic events. There was no evidence of effect modification between work stress and selected sociodemographic, clinical and psychosocial variables.Conclusions. Work stress is an independent risk factor for the development of MDE in the working population. Strategies to improve working environment are needed to keep workers mentally healthy and productive.

scholarly journals MLW-gcForest: A Multi-Weighted gcForest Model for Cancer Subtype Classification by Methylation Data

2019 ◽  
Vol 9 (17) ◽  
pp. 3589 ◽  
Author(s):  
Yunyun Dong ◽  
Wenkai Yang ◽  
Jiawen Wang ◽  
Juanjuan Zhao ◽  
Yan Qiang
Keyword(s):  
Machine Learning ◽  
Small Sample Size ◽  
Small Sample ◽  
The Cancer Genome Atlas ◽  
High Dimensionality ◽  
Methylation Data ◽  
Learning Methods ◽  
Cancer Subtypes ◽  
Machine Learning Methods

Effective cancer treatment requires a clear subtype. Due to the small sample size, high dimensionality, and class imbalances of cancer gene data, classifying cancer subtypes by traditional machine learning methods remains challenging. The gcForest algorithm is a combination of machine learning methods and a deep neural network and has been indicated to achieve better classification of small samples of data. However, the gcForest algorithm still faces many challenges when this method is applied to the classification of cancer subtypes. In this paper, we propose an improved gcForest algorithm (MLW-gcForest) to study the applicability of this method to the small sample sizes, high dimensionality, and class imbalances of genetic data. The main contributions of this algorithm are as follows: (1) Different weights are assigned to different random forests according to the classification ability of the forests. (2) We propose a sorting optimization algorithm that assigns different weights to the feature vectors generated under different sliding windows. The MLW-gcForest model is trained on the methylation data of five data sets from the cancer genome atlas (TCGA). The experimental results show that the MLW-gcForest algorithm achieves high accuracy and area under curve (AUC) values for the classification of cancer subtypes compared with those of traditional machine learning methods and state of the art methods. The results also show that methylation data can be effectively used to diagnose cancer.

scholarly journals Sacred groves as potential ecotourism sites at Tolon and Diare in Northern Region, Ghana

2020 ◽  
Vol 1 (3) ◽  
pp. 195-215
Author(s):  
Benjamin Makimilua Tiimub ◽  
◽  
Richard Amankwah Kuffour ◽  
Richard Wonnsibe Tiimob ◽  
Cletus Ankrah Kuuyeni ◽  
...  
Keyword(s):  
Small Sample Size ◽  
Target Population ◽  
Structured Interview ◽  
Northern Region ◽  
Small Sample ◽  
Northern Ghana ◽  
Sacred Grove ◽  
Sacred Groves ◽  
Management Measures ◽  
Land Use Plan

Purpose: Relic plant communities commonly referred as “sacred groves” in Ghana and comparatively anywhere are ecologically, genetically important resources indigenously protected as “abodes of gods or ancestral habitats” through traditional or religious beliefs and taboos. This study mainly evaluated the potentials of sacred groves for development as tourist sites at Tolon and Diare in the Northern Region of Ghana. Research methodology: Data was collected using semi structured interview questionnaire aided by vegetation survey, observational field walk through the Jaagbo and Tindangung Sacred Groves to screen natural features of the destinations and determine its potential for ecotourism. Findings: Potential areas for visitor amateurism such as the wonderful baobab tree, crocodile pond, misty stone bird sanctuary, were identified in both groves. About 220 different species of plants were identified in the entire groves. The study further discovered that with effective management measures in place, the ecotourism potentials of these sacred groves will optimize if developed to attract visitors and generate income for sustainable socio-economic development of the adjoining communities in northern Ghana. Limitations: Although the target population was above 200 people, relatively small sample size (≤ 36%), could be chosen since the opinion leaders considered the groves as sacred and were less prepared to divulge information about them. Islam and Christianity rather counteracted certain beliefs of the traditional people who adopted local measures to enhance sustainability of these sites for ecotourism functions. Contribution: The study advocates the adoption of bylaws to promote sustainable management of the sacred groves for sustainable benefits. Keywords: Jaagbo, Tindangung, Sacred grove, Crocodile pond, Bird sanctuary, Traditional bylaws, Land use plan

scholarly journals Service Quality of Traditional and Islamic Commercial Banks in Bangladesh

2021 ◽  
pp. 7-16
Author(s):  
Shohel Rana ◽  
Imran Ahmed Shakeer
Keyword(s):  
Service Quality ◽  
Commercial Banks ◽  
Small Sample Size ◽  
Secondary Data ◽  
Structured Interview ◽  
Small Sample ◽  
Primary Data ◽  
Significant Difference ◽  
Practical Implications

Purpose: This study aims to know the service quality of the different private commercial banks operating in Bangladesh with the rapid advancement in information technology and provide some guidelines to improve their service qualities. Methodology: The study used both primary and secondary data to support the objective. Primary data were collected from 240 customers, of whom 120 customers are from traditional private commercial banks and the rest from private Islamic commercial banks operating in Bangladesh using a structured interview schedule, naming SERVQUAL. The study used a convenience sampling method to select respondents. Secondary data were collected from different journals, newspaper articles, books, and various published sources. An independent samples t-test was conducted in the test of the hypothesis. Findings: This study found a significant difference between the traditional and Islamic commercial banks’ service quality and added that the study area’s customers/clients are not fully satisfied with either traditional private commercial banks or Islamic banks. However, Islamic commercial banks are showing a relatively better picture. Research Limitations: The Study is limited to Bangladesh’s small marginal market and a small sample size of only 240 respondents, which cannot sufficiently reflect the large population’s actual scenario. Practical Implications: The Study will help manage the traditional and Islamic commercial banks and policymakers to improve their service quality and improve monitoring efficiency. Originality/value: The Study extensively identified some factors to improve the traditional and Islamic commercial banks’ service quality for both the banks’ and policymakers’ management. In this regard, the critical factors can be the number of employees and the number of counters, increasing ATM services, ensuring faster services, flexible loan disbursement policy, sufficient floor space, suitable sitting arrangements, and improved online services.

scholarly journals Gambling Habits of People With Parkinson’s Disease: An Exploratory Study

2017 ◽  
Author(s):  
Dominic Nadeau ◽  
Isabelle Giroux ◽  
Martine Simard ◽  
Christian Jacques ◽  
Nicolas Dupré
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Impulse Control ◽  
Small Sample Size ◽  
Structured Interview ◽  
Small Sample ◽  
Slot Machines ◽  
Gambling Problem ◽  
Maladie De Parkinson ◽  
Gambling Activities

The development of pathological gambling (PG) among people with Parkinson’s disease (PD) is increasingly reported. The intake of dopamine agonists is most often associated with the emergence of this addiction. Although it is known that gambling habits contribute to the onset of gambling problems in the general population, these habits have not yet been studied in individuals with PD. Thus, this study aimed to explore gambling habits in people with PD. Twenty-five individuals with PD and 8 caregivers participated. Thirteen gamblers took part in a semi-structured interview regarding their gambling habits and the presence of a gambling problem and other impulse-control disorders. The results show that gamblers mainly play lotteries and slot machines. Most gamble for pleasure, but some reported wanting to win money to finance a cure for their PD. None of the gamblers involved a caregiver in their gambling activities and no gambler currently presented a gambling problem. However, 2 at-risk gamblers reported having developed a gambling problem in the past. This study sheds light on factors that may contribute to the development of PG among patients with PD, namely, the emergence of new reasons for gambling after a PD diagnosis, erroneous beliefs about gambling, and discretion about gambling habits. Prevention strategies are discussed in view of these results. However, given the small sample size, further studies examining the gambling habits of people with PD are required.RésuméDe plus en plus, on observe le développement du jeu pathologique (JP) chez les personnes atteintes de la maladie de Parkinson (MP). La prise d’agonistes de la dopamine est le plus souvent associée à l’émergence de cette dépendance. Bien qu’il soit connu que les habitudes de jeu contribuent à l’apparition de problèmes de jeu dans la population en général, ces habitudes n’ont pas encore été étudiées chez les personnes atteintes de la maladie de Parkinson (MP). Dans cette optique, cette étude explore les habitudes de jeu chez les personnes atteintes de la MP. Vingt-cinq personnes atteintes de la maladie de Parkinson et huit soignants y ont participé. Treize joueurs ont participé à une entrevue semi-structurée concernant leurs habitudes de jeu et la présence d’un problème de jeu et d’autres troubles liés au contrôle des impulsions. Les résultats montrent que les joueurs jouent principalement aux loteries et aux machines à sous. La plupart jouent par plaisir, mais certains ont déclaré vouloir gagner de l’argent pour financer une thérapie contre la maladie. Aucun des joueurs n’avait avec lui un fournisseur de soins dans ses activités de jeu et aucun joueur ne présentait actuellement de problème de jeu. Cependant, deux joueurs à risque ont déclaré en avoir développé un par le passé. Cette étude met en lumière les facteurs qui peuvent contribuer au développement du jeu pathologique chez les personnes atteintes de Parkinson, à savoir l’émergence de nouvelles raisons pour le jeu après un diagnostic de MP, les croyances erronées sur le jeu et la discrétion sur les habitudes de jeu. Compte tenu de ces résultats, des stratégies de prévention sont analysées. Cependant, étant donné la petite taille de l’échantillon, d’autres études examinant les habitudes de jeu des personnes atteintes de cette maladie sont nécessaires.

scholarly journals An investigation on the factors affecting machine learning classifications in gamma-ray astronomy

2020 ◽  
Vol 492 (4) ◽  
pp. 5377-5390 ◽  
Author(s):  
Shengda Luo ◽  
Alex P Leung ◽  
C Y Hui ◽  
K L Li
Keyword(s):  
Machine Learning ◽  
Gamma Ray ◽  
Small Sample Size ◽  
Classification Performance ◽  
Small Sample ◽  
Classification Model ◽  
Machine Learning Techniques ◽  
Large Area ◽  
Actual Performance ◽  
Statistical Fluctuations

ABSTRACT We have investigated a number of factors that can have significant impacts on the classification performance of gamma-ray sources detected by Fermi Large Area Telescope (LAT) with machine learning techniques. We show that a framework of automatic feature selection can construct a simple model with a small set of features that yields better performance over previous results. Secondly, because of the small sample size of the training/test sets of certain classes in gamma-ray, nested re-sampling and cross-validations are suggested for quantifying the statistical fluctuations of the quoted accuracy. We have also constructed a test set by cross-matching the identified active galactic nuclei (AGNs) and the pulsars (PSRs) in the Fermi-LAT 8-yr point source catalogue (4FGL) with those unidentified sources in the previous 3rd Fermi-LAT Source Catalog (3FGL). Using this cross-matched set, we show that some features used for building classification model with the identified source can suffer from the problem of covariate shift, which can be a result of various observational effects. This can possibly hamper the actual performance when one applies such model in classifying unidentified sources. Using our framework, both AGN/PSR and young pulsar (YNG)/millisecond pulsar (MSP) classifiers are automatically updated with the new features and the enlarged training samples in 4FGL catalogue incorporated. Using a two-layer model with these updated classifiers, we have selected 20 promising MSP candidates with confidence scores $\gt 98{{\ \rm per\ cent}}$ from the unidentified sources in 4FGL catalogue that can provide inputs for a multiwavelength identification campaign.

Superimposition of acute depressive episode on chronic neurotic symptoms: one of the reasons for refractoriness of depression

1994 ◽  
Vol 9 (6) ◽  
pp. 307-308
Author(s):  
F Okada ◽  
M Daiguji
Keyword(s):  
Mental Health ◽  
Major Depression ◽  
Panic Disorder ◽  
Personality Disorders ◽  
Depressive Episode ◽  
Major Depressive Episode ◽  
Minor Depression ◽  
Major Depressive ◽  
Collaborative Program ◽  
Double Depression

Keller and Shapiro (1982) reported that 26% of the first 101 patients who entered the National Institute of Mental Health (NIMH)-Clinical Research Branch Collaborative Program on the Psychobiology of Depression (Katz and Klerman, 1979; Katz et al, 1979) with a major depressive episode were found to have a pre-existing chronic minor depression of at least 2 years’ duration. They labeled this Phenomenon “double depression„ (Keller and Shapiro, 1982). Furthermore, patients with panic disorder almost universally suffer from major depression at some time in the course of their disorder (Coryell et al, 1988; Stein and Uhde, 1988; Vollrath et al, 1990). “Double diagnosis„, or identification of psychotic or related syndromes, co-existing with personality disorders, have received much attention in the literature in recent years (Sanderson et al, 1990; Torgersen, 1990; Barsky et al, 1992). Much of the research on comorbidity between depressive and anxiety disorders has been summarized in two edited volumes (Kendall and Watson, 1989; Maser and Cloninger, 1990).

Sign in / Sign up

Export Citation Format

Share Document