Prediction of the development of depression and post-traumatic stress disorder in sexually abused children using a random forest classifier

Prevalence and correlates of depressive disorders in commercially sexual exploited children: A cross-sectional study in Mombasa, Kenya

BACKGROUND

Commercial sexual exploitation of children (CSEC) is a global concern and is among the common forms of sexual violence against children. In Kenya, about 32 % of girls and 16 % of boys experience sexual violence before the age of 18 years. While much has been written about the impact of child sexual exploitation, there's little on the prevalence of depressive disorders among CSE children.

OBJECTIVES

This study was conducted to assess the prevalence and correlates of depressive disorders among CSE children in Mombasa, Kenya.

PARTICIPANTS AND SETTING

The study was conducted among CSE children (10-17 years) in Mombasa County.

METHODS

A cross-sectional study conducted between May 2021 and June 2022. A total of 409 CSE children were enrolled, using a case management approach. Data was collected using the child identification tool and the Patient Health Questionnaire (PHQ-9), at the first counselling session to determine the prevalence of depression levels.

RESULTS

Of the 409 children, 367 (90 %) were girls while 42 (10 %) were boys. The mean age was 15 years (10-17) (SD = 1.4, t = 0.765). In 286 (70 %) 'Depression unlikely' was recorded, while 123 (30 %) 'Depression likelihood.' Prevalence of mild to severe depression was significantly higher in girls than boys (p = 0.002). Other determinants of depression were having a primary level of education (p = 0.03) and being an orphan. (p = 0.03).

CONCLUSION

It is important to prioritize mental health interventions such as screening and early diagnosis of mental health among CSE children in order to prevent and manage both short and long term effects.

Machine learning methods to discriminate posttraumatic stress disorder: A protocol of systematic review and meta-analysis

Introduction

Recent years have witnessed a persistent threat to public mental health, especially during and after the COVID-19 pandemic. Posttraumatic stress disorder (PTSD) has emerged as a pivotal concern amidst this backdrop. Concurrently, machine learning (ML) techniques have progressively applied in the realm of mental health. Therefore, our present undertaking seeks to provide a comprehensive assessment of studies employing ML methods that use diverse data modalities on the classification of people with PTSD.

Methods and analysis

In pursuit of pertinent studies, we will search both English and Chinese databases from January 2000 to May 2022. Two researchers will independently conduct screening, extract data and assess study quality. We intend to employ the assessment framework introduced by Luis Francisco Ramos-Lima in 2020 for quality evaluation. Rate, standard error and 95% CIs will be utilized for effect size measurement. A Cochran's Q test will be applied to assess heterogeneity. Subgroup and sensitivity analysis will further elucidate the source of heterogeneity and funnel plots and Egger's test will detect publication bias.

Ethics and dissemination

This systematic review and meta-analysis does not encompass patient interactions or engagements with healthcare providers. The outcomes of this research will be disseminated through scholarly channels, including presentations at scientific conferences and publications in peer-reviewed journals.PROSPERO registration number CRD42023342042.

CXCL8 delivered by plasma-derived exosomes induces the symptoms of post-traumatic stress disorder through facilitating astrocyte-neuron communication

Extracellular vesicles (EVs) play an important role in post-traumatic stress disorder (PTSD). This study is aimed to investigate the possible molecular mechanism of CD63 mediating CXCL8 delivery via EVs to affect astrocyte-neuron communication in PTSD. The neuron-derived EVs (NDEVs) and astrocyte-derived EVs (ADEVs) were isolated from plasma in PTSD patients. Next, the uptake of EVs by neurons was assessed. Following determination of the interaction between CD63 and CXCL8, gain- and loss-of-function experiments were performed in astrocytes. Finally, a PTSD mouse model was established using the single prolonged stress and electric foot shock to confirm the effects of plasma-derived EVs delivering CXCL8 on anxiety- and depression-like behaviors in PTSD mice. EVs derived from plasma of PTSD patients aggravated anxiety- and depression-like behaviors in PTSD mice. CXCL8 was a key gene upregulated in both NDEVs and ADEVs from plasma of PTSD patients, which could be delivered into EVs by CD63. Meanwhile, CXCL8 was also highly expressed in plasma-derived EVs. In vivo experiments also verified that plasma-derived EVs could enhance astrocyte-neuron communication by delivering CXCL8, and silencing of CXCL8 ameliorated anxiety- and depression-like behaviors in PTSD mice. Taken together, CD63 promotes delivery of CXCL8 via EVs to induce PTSD by enhancing astrocyte-neuron communication, suggesting the potential of CD63 mediating delivery of CXCL8 via EVs as a therapeutic target for PTSD.

Improved Stress Classification Using Automatic Feature Selection from Heart Rate and Respiratory Rate Time Signals

Time-series features are the characteristics of data periodically collected over time. The calculation of time-series features helps in understanding the underlying patterns and structure of the data, as well as in visualizing the data. The manual calculation and selection of time-series feature from a large temporal dataset are time-consuming. It requires researchers to consider several signal-processing algorithms and time-series analysis methods to identify and extract meaningful features from the given time-series data. These features are the core of a machine learning-based predictive model and are designed to describe the informative characteristics of the time-series signal. For accurate stress monitoring, it is essential that these features are not only informative but also well-distinguishable and interpretable by the classification models. Recently, a lot of work has been carried out on automating the extraction and selection of times-series features. In this paper, a correlation-based time-series feature selection algorithm is proposed and evaluated on the stress-predict dataset. The algorithm calculates a list of 1578 features of heart rate and respiratory rate signals (combined) using the tsfresh library. These features are then shortlisted to the more specific time-series features using Principal Component Analysis (PCA) and Pearson, Kendall, and Spearman correlation ranking techniques. A comparative study of conventional statistical features (like, mean, standard deviation, median, and mean absolute deviation) versus correlation-based selected features is performed using linear (logistic regression), ensemble (random forest), and clustering (k-nearest neighbours) predictive models. The correlation-based selected features achieved higher classification performance with an accuracy of 98.6% as compared to the conventional statistical feature’s 67.4%. The outcome of the proposed study suggests that it is vital to have better analytical features rather than conventional statistical features for accurate stress classification.

A Review of Machine Learning and Deep Learning Approaches on Mental Health Diagnosis

Combating mental illnesses such as depression and anxiety has become a global concern. As a result of the necessity for finding effective ways to battle these problems, machine learning approaches have been included in healthcare systems for the diagnosis and probable prediction of the treatment outcomes of mental health conditions. With the growing interest in machine and deep learning methods, analysis of existing work to guide future research directions is necessary. In this study, 33 articles on the diagnosis of schizophrenia, depression, anxiety, bipolar disorder, post-traumatic stress disorder (PTSD), anorexia nervosa, and attention deficit hyperactivity disorder (ADHD) were retrieved from various search databases using the preferred reporting items for systematic reviews and meta-analysis (PRISMA) review methodology. These publications were chosen based on their use of machine learning and deep learning technologies, individually assessed, and their recommended methodologies were then classified into the various disorders included in this study. In addition, the difficulties encountered by the researchers are discussed, and a list of some public datasets is provided.

The practice of psychological well-being education model for poor university students from the perspective of positive psychology

Poor university students are a special group. Social development provides many positive factors for poor university students' personality and psychological development, but negative factors are also accompanied by them, which affect the psychological health of poor university students. University students are in a period of rapid physical and mental development, and it is an important issue that colleges and universities need to solve psychological well-being education. We hope to find out the aspects that can be studied in the irregularity of various factors that affect college students' mental health. BP neural network is a typical model of artificial neural network. Based on the BP algorithm and the fuzzy comprehensive evaluation of the psychological well-being prediction system for poor university students, this paper systematically summarizes the concept of psychological well-being, the factors that affect psychological well-being, and the related research done by predecessors on psychological well-being. Using the international psychological well-being scale SCL-90 to comprehensively consider the psychological well-being status of poor university students and select the optimized BP algorithm to establish a psychological well-being prediction model, and implement it and compare it with other models to reflect its superiority. Data were collected and analyzed by means of a questionnaire. The regression model was used to analyze the relationship between mindfulness, rumination and psychological well-being. The mediation index fitted by the model reached 0.9. The model can reflect the real situation of the data, that is, rumination plays a partial mediating role in the effect of mindfulness on psychological well-being. The introduction of this psychological prediction model into the psychological well-being education of poor university students not only helps to improve the educational concept and expand the educational approach, but also helps to achieve the goal of psychological well-being education for poor university students, thereby promoting the improvement of the psychological quality of poor university students.

Predicting depression among rural and urban disabled elderly in China using a random forest classifier

With global aging, the number of elderly with physical disabilities is also increasing. Compared with the ordinary elderly, the elderly who lose their independence are more likely to have the symptoms of depression. Reducing depression may help to alleviate the disability process of those who find themselves in the disabled stages. Therefore, the purpose of this study is to explore the predictive effects of demographic characteristics, health behavior, health status, family relations, social relations, and subjective attitude on depression in rural and urban disabled elderly to improve early depression symptom recognition.A total of 1460 older adults aged 60 and disabled were selected from China Family Panel Studies (CFPS). Depression was assessed according to The Center for Epidemiologic Studies Depression Scale (CES-D). This paper used the random forest classifier to predict the depression of the disabled elderly from six aspects: demographic characteristics, health status, health behavior, family relationship, and social relationship. The prediction model was established based on 70% of the training set and 30% of the test set. The depression rate of rural disabled elderly was 57.67%, and that of urban disabled elderly was 44.59%. The mean values of the 10-k cross-validated results were 0.71 in rural areas and 0.70 in urban areas. AUC:0.71, specificity: 65.3%, sensitivity: 80.6% for rural disabled elderly with depression; AUC:0.78, specificity: 78.1%, sensitivity: 64.2% for urban disabled elderly with depression, respectively. There are apparent differences in the top ten predictors between rural and urban disabled elderly. The common predictors were self-rated health, changing in perceived health, disease or accidence experience within the past 2 weeks, life satisfaction, trusting people, BMI, and having trust in the future. Non-common predictors were chronic diseases, neighborly relations, total medical expenses within 1 year, community emotion, sleep duration, and family per capita income. Using random forest data to predict the depression of the disabled elderly may lead to early detection of depression.

Using random forest to detect multiple inherited metabolic diseases simultaneously based on GC-MS urinary metabolomics

Inborn errors of metabolism, also known as inherited metabolic diseases (IMDs), are related to genetic mutations and cause corresponding biochemical metabolic disorder of newborns and even sudden infant death. Timely detection and diagnosis of IMDs are of great significance for improving survival of newborns. Here we propose a strategy for simultaneously detecting six types of IMDs via combining GC-MS technique with the random forest algorithm (RF). Clinical urine samples from IMD and healthy patients are analyzed using GC-MS for acquiring metabolomics data. Then, the RF model is established as a multi-classification tool for the GC-MS data. Compared with the models built by artificial neural network and support vector machine, the results demonstrated the RF model has superior performance of high specificity, sensitivity, precision, accuracy, and matthews correlation coefficients on identifying all six types of IMDs and normal samples. The proposed strategy can afford a useful method for reliable and effective identification of multiple IMDs in clinical diagnosis.

Can the adverse childhood experiences (ACEs) checklist be utilized to predict emergency department visits among children and adolescents?

Background

Extensive literature has shown an association of Adverse Childhood Experiences (ACEs) with adverse health outcomes; however, its ability to predict events or stratify risks is less known. Individuals with mental illness and ACE exposure have been shown to visit emergency departments (ED) more often than those in the general population. This study thus examined the ability of the ACEs checklist to predict ED visits within the subsequent year among children and adolescents presenting to mental health clinics with pre-existing mental health issues.

Methods

The study analyzed linked data (n = 6100) from two databases provided by Alberta Health Services (AHS). The Regional Access and Intake System (RAIS 2016–2018) database provided data on the predictors (ACE items, age, sex, residence, mental health program type, and primary diagnosis) regarding children and adolescents (aged 0–17 years) accessing addiction and mental health services within Calgary Zone, and the National Ambulatory Care Reporting System (NACRS 2016–2019) database provided data on ED visits. A 25% random sample of the data was reserved for validation purposes. Two Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression models, each employing a different method to tune the shrinkage parameter lambda (namely cross-validated and adaptive) and performing 10-fold cross-validation for a set of 100 lambdas in each model were examined.

Results

The adaptive LASSO model had a slightly better fit in the validation dataset than the cross-validated model; however, it still demonstrated poor discrimination (AUC 0.60, sensitivity 37.8%, PPV 49.6%) and poor calibration (over-triaged in low-risk and under-triaged in high-risk subgroups). The model’s poor performance was evident from an out-of-sample deviance ratio of − 0.044.

Conclusion

The ACEs checklist did not perform well in predicting ED visits among children and adolescents with existing mental health concerns. The diverse causes of ED visits may have hindered accurate predictions, requiring more advanced statistical procedures. Future studies exploring other machine learning approaches and including a more extensive set of childhood adversities and other important predictors may produce better predictions. Furthermore, despite highly significant associations being observed, ACEs may not be deterministic in predicting health-related events at the individual level, such as general ED use.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12874-021-01392-w.