scholarly journals Detection of child depression using machine learning methods

PLoS ONE ◽  
2021 ◽  
Vol 16 (12) ◽  
pp. e0261131
Author(s):  
Umme Marzia Haque ◽  
Enamul Kabir ◽  
Rasheda Khanam
Keyword(s):  
Mental Health ◽  
Machine Learning ◽  
Mental Illness ◽  
Children And Adolescents ◽  
Mental Health Problems ◽  
Confusion Matrix ◽  
Model Performance ◽  
Child And Adolescent ◽  
Target Variable ◽  
Depression Detection

Background Mental health problems, such as depression in children have far-reaching negative effects on child, family and society as whole. It is necessary to identify the reasons that contribute to this mental illness. Detecting the appropriate signs to anticipate mental illness as depression in children and adolescents is vital in making an early and accurate diagnosis to avoid severe consequences in the future. There has been no research employing machine learning (ML) approaches for depression detection among children and adolescents aged 4–17 years in a precisely constructed high prediction dataset, such as Young Minds Matter (YMM). As a result, our objective is to 1) create a model that can predict depression in children and adolescents aged 4–17 years old, 2) evaluate the results of ML algorithms to determine which one outperforms the others and 3) associate with the related issues of family activities and socioeconomic difficulties that contribute to depression. Methods The YMM, the second Australian Child and Adolescent Survey of Mental Health and Wellbeing 2013–14 has been used as data source in this research. The variables of yes/no value of low correlation with the target variable (depression status) have been eliminated. The Boruta algorithm has been utilized in association with a Random Forest (RF) classifier to extract the most important features for depression detection among the high correlated variables with target variable. The Tree-based Pipeline Optimization Tool (TPOTclassifier) has been used to choose suitable supervised learning models. In the depression detection step, RF, XGBoost (XGB), Decision Tree (DT), and Gaussian Naive Bayes (GaussianNB) have been used. Results Unhappy, nothing fun, irritable mood, diminished interest, weight loss/gain, insomnia or hypersomnia, psychomotor agitation or retardation, fatigue, thinking or concentration problems or indecisiveness, suicide attempt or plan, presence of any of these five symptoms have been identified as 11 important features to detect depression among children and adolescents. Although model performance varied somewhat, RF outperformed all other algorithms in predicting depressed classes by 99% with 95% accuracy rate and 99% precision rate in 315 milliseconds (ms). Conclusion This RF-based prediction model is more accurate and informative in predicting child and adolescent depression that outperforms in all four confusion matrix performance measures as well as execution duration.

Approaches to Delivering Child and Adolescent Mental Health Services: The South Australian Experience

1995 ◽  
Vol 29 (2) ◽  
pp. 230-237 ◽  
Author(s):  
Michael Gifford Sawyer ◽  
Robert John Kosky
Keyword(s):  
Mental Health ◽  
Mental Health Services ◽  
Health Services ◽  
Children And Adolescents ◽  
Mental Health Problems ◽  
South Australia ◽  
Adolescent Mental Health ◽  
Child And Adolescent ◽  
The South ◽  
Number Of Children

Approximately 10% of children and adolescents experience mental health problems, however only a small proportion receive specialised help. Identifying approaches which can provide a balanced and effective service for the large number of children and adolescents with problems is currently a major challenge for child and adolescent mental health services in Australia. In South Australia, following a review in 1983, child and adolescent services were reorganised into two separate but closely related services. This paper draws on experience in South Australia over the last decade to identify approaches which can be employed in six key areas that significantly influence the effectiveness of child and adolescent mental health services. The paper also describes the specific features which were included in the South Australian child and adolescent mental health service to address these issues.

Child Mental Health in Latin America: Present and Future Epidemiologic Research

2003 ◽  
Vol 33 (3) ◽  
pp. 203-222 ◽  
Author(s):  
Cristiane Duarte ◽  
Christina Hoven ◽  
Carlos Berganza ◽  
Isabel Bordin ◽  
Hector Bird ◽  
...  
Keyword(s):  
Mental Health ◽  
Latin America ◽  
Children And Adolescents ◽  
Latin American ◽  
Mental Health Problems ◽  
Adolescent Mental Health ◽  
Child And Adolescent ◽  
Health Problems ◽  
Prevention And Treatment ◽  
Latin American Countries

Objective: This report reviews population studies of child and adolescent mental health carried out in Latin America over the past 15 years. Also considered is the issue of how to meet the needs of children and adolescents who may present mental health problems in Latin America, given that most of them live in poverty in economies that are underdeveloped, providing limited resources. Method: Ten studies from six different countries were identified that employed some form of randomized sampling method and used standardized instruments for assessment. The authors present a summary of the main characteristics of these studies, highlighting methodological features that may account for differences in the rates obtained. Results: Overall, a similar pattern of prevalence and risk factors for mental health problems in children and adolescents in Latin American countries emerged. Moreover, rates of disorders in these children are similar to the 15 to 20% found in other countries. These findings are similar to those observed when adult mental health problems are considered. Prevention and treatment strategies are discussed and the peculiarities of the delivery of mental health services for children and adolescents are explored. Conclusions: Future research needs to focus on understanding of resilience and formal and informal mental health delivery systems of care available in different Latin American countries. Such research has high potential for ameliorating the prevention and treatment of child and adolescent mental health problems in this region of the world.

Comparison of the Prevalence of Mental Health Problems in Deaf and Hearing Children and Adolescents in Australia

2010 ◽  
Vol 44 (4) ◽  
pp. 351-357 ◽  
Author(s):  
Maria D. Remine ◽  
P. Margaret Brown
Keyword(s):  
Mental Health ◽  
Children And Adolescents ◽  
Prevalence Rate ◽  
Mental Health Problems ◽  
Child And Adolescent ◽  
Health Problems ◽  
Demographic Characteristics ◽  
Self Report ◽  
Deaf Children ◽  
Hearing Children

Objective: The aims of the present study were to (i) identify the prevalence rate and nature of mental health problems in a group of Australian deaf children and adolescents and compare these to those reported for the Australian hearing population; and (ii) identify specific demographic characteristics that may typify deaf children and adolescents with mental health problems. Method: Sixty-six parents of deaf children and adolescents aged 6–18 years, their teachers and 38 adolescents participated in the study. Data related to mental health problems were collected using the Child Behaviour Checklist and Youth Self-Report. Data related to demographic characteristics were obtained via parent and teacher surveys. Results: The overall prevalence rate of mental health problems reported by parents and adolescents in the present study is comparable to that of the Australian hearing population. Parents in the present study, however, reported significantly more concerns on the social problem and thought problem scales than did Australian parents of hearing children and adolescents. There were also significant differences between the prevalence and nature of mental health problems as reported by the deaf adolescents in the present study when compared to deaf adolescents in another Australian study. These differences appear to be explained by differences in the preferred communication mode of the participants in the two studies. Conclusions: The known heterogeneity within the Australian deaf child and adolescent population with respect to preferred mode of communication has important implications not only for the appropriate selection and use of psychiatric instruments in assessing child and adolescent mental health but also for the accurate reporting of the prevalence and nature of mental health problems within this population.

Chronic Mental Illness and the Changing Scope of Intervention Strategies, Diagnosis, and Treatment in Child and Adolescent Population

2019 ◽  
pp. 556-567
Author(s):  
Bhavuk Garg ◽  
Prerna Khanna ◽  
Amit Khanna
Keyword(s):  
Mental Health ◽  
Mental Illness ◽  
Mental Health Problems ◽  
Significant Proportion ◽  
Treatment Strategies ◽  
Child And Adolescent ◽  
Health Problems ◽  
Diagnosis And Treatment ◽  
Chronic Mental Illness ◽  
Adolescent Population

A significant proportion of the Child and Adolescent population suffer from a psychological or psychiatric disorder. It is estimated that at least 20% of the child and adolescent population is affected mental health problems and largely this is undetected. Some of the mental health problems are severe and disabling and tend to be chronic in nature. Childhood forms an important phase in the development period of life during which one develops physically, emotionally, socially, intellectually and morally. Chronic and severe mental health problems in children impact the overall development of the child thereby leading to significant and lifelong disability. The scope of this chapter has been narrowed to include two important chronic mental illness in children mainly Schizophrenia and Bipolar Mood Disorder. The Authors will discuss the clinical features, course, outcome and treatment strategies. Special issues in children are also discussed in terms of diagnosis and treatment.

scholarly journals The Current situation of Child and adolescent psychological problems and intervention in China

2016 ◽  
Vol 7 (3) ◽  
pp. 15-17 ◽  
Author(s):  
Wenyan Jiao ◽  
Lin Liu ◽  
Rui Li ◽  
Na Zhao
Keyword(s):  
Mental Health ◽  
Children And Adolescents ◽  
Psychological Health ◽  
Mental Health Problems ◽  
Mental Disease ◽  
Adolescent Mental Health ◽  
Child And Adolescent ◽  
Health Problems ◽  
Current Situation ◽  
Psychological Problems

In China, the psychological health problems of children and adolescents have been more and more serious recently. The psychological disorders not only have a lot of adverse effects for children and adolescents, but also were an important source of mental disease in adulthood. In order to make more people understand this serious problem, this paper summarized the current situation of child and adolescent mental health problems in China and the risk factors for child and adolescent mental health problems; additionally, the interventions of child and adolescent psychological problems were also reviewed in this paper.Asian Journal of Medical Sciences Vol. 7(3) 2016 15-17

Supporting Parents of Children with Serious Mental Health Problems

2017 ◽  
pp. 135-144
Author(s):  
Kylie Burke
Keyword(s):  
Mental Health ◽  
Mental Illness ◽  
Children And Adolescents ◽  
Serious Mental Illness ◽  
Well Being ◽  
Adolescent Mental Health ◽  
Child And Adolescent ◽  
Parenting Interventions ◽  
Treatment Services ◽  
Treatment Gains

Serious mental illness affects between 10% and 20% of children and adolescents, significantly representing the world’s children and adolescents. Parents are a critical protective factor in their child’s treatment and recovery from serious mental illness. They support the child during treatment, manage symptom reduction, maintain treatment gains, and promote their child’s development and well-being. Parenting a child or adolescent with serious mental illness places significant strain and burden on them. This chapter discusses evidence-based parenting interventions (e.g., the Triple P—Positive Parenting Program) within the child and adolescent mental health context and their potential to be flexibly and sustainably incorporated into existing usual treatment services. The need is highlighted for researchers, policy-makers, and service providers to focus on developing child- and family-focused mental health policy and better processes for conducting high-quality research that examines specific and combined contributions of parenting interventions within child and adolescent mental health services.

Chronic Mental Illness and the Changing Scope of Intervention Strategies, Diagnosis, and Treatment in Child and Adolescent Population

2017 ◽  
pp. 258-269
Author(s):  
Bhavuk Garg ◽  
Prerna Khanna ◽  
Amit Khanna
Keyword(s):  
Mental Health ◽  
Mental Illness ◽  
Mental Health Problems ◽  
Significant Proportion ◽  
Treatment Strategies ◽  
Child And Adolescent ◽  
Health Problems ◽  
Diagnosis And Treatment ◽  
Chronic Mental Illness ◽  
Adolescent Population

A significant proportion of the Child and Adolescent population suffer from a psychological or psychiatric disorder. It is estimated that at least 20% of the child and adolescent population is affected mental health problems and largely this is undetected. Some of the mental health problems are severe and disabling and tend to be chronic in nature. Childhood forms an important phase in the development period of life during which one develops physically, emotionally, socially, intellectually and morally. Chronic and severe mental health problems in children impact the overall development of the child thereby leading to significant and lifelong disability. The scope of this chapter has been narrowed to include two important chronic mental illness in children mainly Schizophrenia and Bipolar Mood Disorder. The Authors will discuss the clinical features, course, outcome and treatment strategies. Special issues in children are also discussed in terms of diagnosis and treatment.

scholarly journals Psychiatric hospital treatment of children and adolescents in New South Wales, Australia: 12-year trends

BJPsych Open ◽  
2016 ◽  
Vol 2 (1) ◽  
pp. 1-5 ◽  
Author(s):  
Philip Hazell ◽  
Titia Sprague ◽  
Joanne Sharpe
Keyword(s):  
Mental Health ◽  
Children And Adolescents ◽  
Mental Health Problems ◽  
New South ◽  
New South Wales ◽  
Child And Adolescent ◽  
Hospital Treatment ◽  
Temporary Increase ◽  
South Wales ◽  
Health Districts

BackgroundIt is preferable that children and adolescents requiring in-patient care for mental health problems are managed in age-appropriate facilities. To achieve this, nine specialist Child and Adolescent Mental Health Services (CAMHS) in-patient units have been commissioned in New South Wales (NSW) since 2002.AimsTo examine trends in child and adolescent in-patient admissions since the opening of these CAMHS units.MethodAnalysis of separation data for under 18-year-olds to CAMHS, adult mental health and paediatric units for the period 2002 to 2013 in NSW, comparing districts with and without specialist CAMHS units.ResultsSeparations from CAMHS, adult and paediatric units rose with time, but there was no interaction between time and health district type (with/without CAMHS unit). Five of eight health districts experienced increased separations of under 18-year-olds from adult units in the year of opening a CAMHS unit. Separations from related paediatric units increased in three of seven health districts.ConclusionsOpening CAMHS units may be followed by a temporary increase in separations of young people from adult units, but it does not influence the flow of patients to non-CAMHS facilities in the longer term.

scholarly journals An Explainable Machine Learning Approach for COVID-19 Impact on Mood State of Children and Adolescents during the 1st Lockdown in Greece

2021 ◽  
Author(s):  
Charis Ntakolia ◽  
Dimitrios Priftis ◽  
Mariana Charakopoulou-Travlou ◽  
Ioanna Rannou ◽  
Konstantina Magklara ◽  
...  
Keyword(s):  
Mental Health ◽  
Machine Learning ◽  
Children And Adolescents ◽  
Mental Health Problems ◽  
Mood State ◽  
Selection Process ◽  
World Health ◽  
Children And Adolescent ◽  
Health Organization ◽  
Almost All

The global spread of COVID-19 led the World Health Organization to declare a pandemic on 11 March 2020. To decelerate this spread, countries have taken strict measures that affected the lifestyle and economy. Various studies have been focused on the identification of COVID-19 impact to mental health of children and adolescents via traditional statistical approaches. However, a machine learning methodology must be developed to explain the main factors that contribute to the change of mood state of children and adolescents during the first lockdown. Therefore, to this study an explainable machine learning pipeline is presented focusing on children and adolescents in Greece, where a strict lockdown was imposed. The target group consists of children and adolescents, recruited from children and adolescent mental health services, who present mental health problems diagnosed before the pandemic. The proposed methodology imposes: (i) data collection via questionnaires; (ii) a clustering process to identify the groups of subjects with amelioration, deterioration and stability to their mood state; (iii) a feature selection process to identify the most informative features that contribute to mood state prediction; (iv) a decision-making process based on an experimental evaluation among classifiers; (v) calibration of the best performing model and (v) a post-hoc interpretation of the features’ impact on the best performing model. The results showed that a blend of heterogeneous features from almost all feature categories is necessary to increase our understanding regarding the effect of COVID-19 pandemic on the mood state of children and adolescents.

scholarly journals An Explainable Machine Learning Approach for COVID-19’s Impact on Mood States of Children and Adolescents during the First Lockdown in Greece

Healthcare ◽  
2022 ◽  
Vol 10 (1) ◽  
pp. 149
Author(s):  
Charis Ntakolia ◽  
Dimitrios Priftis ◽  
Mariana Charakopoulou-Travlou ◽  
Ioanna Rannou ◽  
Konstantina Magklara ◽  
...  
Keyword(s):  
Mental Health ◽  
Machine Learning ◽  
Children And Adolescents ◽  
Mental Health Problems ◽  
Mood State ◽  
Selection Process ◽  
World Health ◽  
Children And Adolescent ◽  
Health Organization ◽  
Almost All

The global spread of COVID-19 led the World Health Organization to declare a pandemic on 11 March 2020. To decelerate this spread, countries have taken strict measures that have affected the lifestyles and economies. Various studies have focused on the identification of COVID-19’s impact on the mental health of children and adolescents via traditional statistical approaches. However, a machine learning methodology must be developed to explain the main factors that contribute to the changes in the mood state of children and adolescents during the first lockdown. Therefore, in this study an explainable machine learning pipeline is presented focusing on children and adolescents in Greece, where a strict lockdown was imposed. The target group consists of children and adolescents, recruited from children and adolescent mental health services, who present mental health problems diagnosed before the pandemic. The proposed methodology imposes: (i) data collection via questionnaires; (ii) a clustering process to identify the groups of subjects with amelioration, deterioration and stability to their mood state; (iii) a feature selection process to identify the most informative features that contribute to mood state prediction; (iv) a decision-making process based on an experimental evaluation among classifiers; (v) calibration of the best-performing model; and (vi) a post hoc interpretation of the features’ impact on the best-performing model. The results showed that a blend of heterogeneous features from almost all feature categories is necessary to increase our understanding regarding the effect of the COVID-19 pandemic on the mood state of children and adolescents.

Sign in / Sign up

Export Citation Format

Share Document