Tag: Depression

Posted on

Machine learning-based predictive factor analysis of depression among Chinese adolescents

IntroductionAdolescent depression has emerged as a critical global public health concern, with rising prevalence in China posing severe threats to psychological development and social adaptation. Traditional statistical methods face limitations in capturing complex non-linear relationships and interactions among influencing factors, while machine learning algorithms offer advantages in predictive modeling of mental health disorders.ObjectiveThis study aimed to: (1) compare the performance of seven ML algorithms in classifying low and high depression risk groups among Chinese adolescents; (2) identify key predictive factors from demographic, personality, and PGI-related variables; (3) explore non-linear relationships and interactive effects between critical factors; and (4) explore preliminary threshold values for key factors as potential references for risk identification.MethodsA total of 559 Chinese adolescents completed assessments of demographic characteristics, Big Five personality traits, personal growth initiative, and depression symptoms. Model performance was compared using Friedman tests and Nemenyi post-hoc tests appropriate for correlated cross-validation data. Seven ML algorithms were trained and optimized using 5-fold cross-validation. Feature importance was analyzed via traditional metrics and SHAP values, and SHAP interaction effects were tested using permutation tests. Threshold analysis was conducted using the Youden’s J statistic.ResultsLightGBM outperformed other models with an AUC of 0.834, achieving balanced accuracy, sensitivity, and specificity. Neuroticism emerged as the most robust predictor across all models, followed by proactive change, agreeableness, extraversion, and growth resilience. Demographic factors showed minimal predictive power. SHAP permutation tests confirmed significant interactions between neuroticism and proactive change and between proactive change and agreeableness, whereas no significant interaction was found between neuroticism and agreeableness. Preliminary thresholds were identified for key factors within this sample.ConclusionML algorithms, particularly lightGBM, effectively identify adolescent depression risk, with personality traits and PGI serving as core predictive factors. The findings highlight the value of integrating multi-dimensional variables in depression prediction and provide preliminary references for early intervention. Given the cross-sectional design and lack of external validation, conclusions regarding generalizable cutoffs and causal inference should be made with caution. Targeted strategies focusing on reducing neuroticism and enhancing proactive growth behaviors may mitigate depression vulnerability in Chinese adolescents.
Posted on

Paddy Pimblett on Mental Health Fitness 

MMA Champion Paddy Pimblett’s candid message to young people

In recognition of Mental Health Awareness Month, the Child Mind Institute has launched the Mental Health Fitness campaign — a national call to action highlighting the importance that caring for one’s mental health is just as important as physical health. 

Paddy Pimblett, an English MMA champion, opens up about relying on training to strengthen his body and steady his mind. His message goes beyond sports: structure, purpose, and setting achievable goals can be transformative, especially for young people struggling to feel “good enough.” By speaking candidly about his mental health, he offers a version of strength rooted in resilience, honesty, and showing up for yourself every day.

“I’ve suffered with mental health problems and depression, and I’ve had to get through them. Any kid who’s out there and feels they’re not good enough, just like I did, get some structure in your life. Start doing something where you’ve got a goal at the end of it, so you’re striving to be the best at something. That’s what pushes me on every day.”

About Paddy Pimblett

Paddy Pimblett is an English professional mixed martial artist known for his rising success in the UFC lightweight division. He was named the 2022 Breakthrough Fighter of the Year at the World MMA Awards. Known as Paddy “The Baddy”, Pimblett has built a large following both inside and outside of the Octagon for his entertaining fighting style and his openness about personal struggles and emotional well-being.

About Mental Health Fitness

For decades, we’ve understood that physical fitness doesn’t just happen — it takes skills, regular practice, and a supportive environment. The same is true for mental health. Developed by experts at the Child Mind Institute for three different age groups, our Mental Health Fitness guides have been used by more than 1.8 million students, caregivers, and educators to build emotion regulation skills and resilience. Whether your child is 5 or 15, struggling or thriving, they can learn these skills. And you can practice alongside them. Learn more at Mental Health Fitness.

Related Resources

The post Paddy Pimblett on Mental Health Fitness  appeared first on Child Mind Institute.

Posted on

Correlation of non-suicidal self-injury with SLC6A4 promoter DNA methylation in children and adolescents with bipolar depression

PurposeTo investigate the association between non-suicidal self-injury (NSSI) and DNA methylation of the SLC6A4 promoter region in individuals diagnosed with bipolar depression.Patients and methodsA total of 48 children and adolescent patients meeting ICD-10 criteria for bipolar disorder with current depressive episodes (Hamilton Depression Rating Scale-24 score >20) were recruited, and stratified into two groups according to the presence or absence of non-suicidal self-injurious (NSSI) behavior(NSSI group and non-NSSI group). Negative life events were evaluated using the Adolescent Self-Rating Life Events Checklist (ASLEC). The methylation levels of five CpG sites within the SLC6A4 promoter region were determined by pyrosequencing, and mRNA expression was assessed by quantitative reverse transcription polymerase chain reaction (qRT-PCR).ResultsIn 48 adolescents with bipolar depression, the two groups were comparable in age, gender, education, only-child status, family history of mental illness, and disease course (all p > 0.05). Compared with the non-NSSI group, the NSSI group showed significantly lower CpG2 methylation at the SLC6A4 promoter, higher SLC6A4 mRNA expression, and higher ASLEC scores. The other four CpG sites showed no significant differences. Spearman’s correlation revealed a strong negative association between CpG2 methylation and mRNA expression (ρ = -0.547, p < 0.001). Two logistic regression models both fit the data well. Higher CpG2 methylation was a protective factor against NSSI (OR = 0.131, p = 0.021), while higher mRNA expression was a risk factor (OR = 10.957, p = 0.015). ASLEC scores and interaction terms were not significant.ConclusionThese preliminary findings suggest that lower CpG2 methylation and higher SLC6A4 mRNA expression are each independently associated with NSSI in adolescents with bipolar depression. Stressful life events were higher in the NSSI group, but did not significantly moderate these associations in the current sample. Given the small sample size and cross-sectional design, the results should be viewed as exploratory and require replication in larger studies.
Posted on
<![CDATA[See how overlooked birth trauma can mimic postpartum depression.]]>
Posted on

Neurocognitive function among individuals with problematic social media use

BackgroundWith the development of technology and the internet, social networks gained momentum quickly and play a central role in daily activities. Despite this, there is a public health concern over excessive or problematic social media use. There is also a debate whether excessive social media use should be considered as a behavioral addiction characterized by impulsivity or an impulse control disorder characterized by compulsivity. The goal of this study is to use neurocognitive tasks to investigate impulsivity and compulsivity among excessive social media users compared with non-excessive users.MethodThe study included 79 participants (age range 18 to 37), divided into two groups: 34 participants who excessively use social media (Mean Age = 23.03, SD = 2.71) and 45 participants who do not excessively use social media (Mean Age = 25.47, SD = 4.3). Participants filled out a demographic questionnaire, questionnaires on social media use, impulsivity, compulsivity, anxiety, and depression. They performed computerized cognitive tasks: GO/NO-GO (with Facebook and traffic sign pictures), Experimental Delay Discounting (EDT), and the Wisconsin Card Sorting Test (WCST).ResultsExcessive users of social media exhibited a lower ability to delay gratification on the EDT, indicating impulsivity. They made fewer non-perseverative errors on the WCST, which indicated high flexibility and test shifting, which is a contradicting evidence for compulsivity. Furthermore, on the GO/NO-GO task, individuals who excessively use social media made more omission errors in response to the “Facebook” sign compared to traffic signs (GO condition), indicating impaired selective attention. Finally, they also showed higher subjective ratings of anxiety, depression, impulsivity, and compulsivity.DiscussionThe results of this study provide evidence for impulsivity indicated by delay discounting tendency, which supports the behavioral addiction model, impaired selection attention and lack of evidence for compulsivity in excessive social media users. Further research on neurocognitive function in excessive social media users is required in order to determine whether it should be considered a behavioral addiction or an impulse control disorder.
Posted on

Psychological inflexibility and resilience in anxiety: insights from machine-learning and robust mediation-based models

IntroductionPsychological inflexibility (PI) has been associated with anxiety symptoms, while resilience serves as a protective factor; however, their roles and interrelationship remain poorly understood. We investigated the role of PI on anxiety-related symptoms while assessing the mediating role of resilience and testing the moderating effect of sex and psychiatric history.MethodsFrom April to July 2021, an online protocol employing self-reported measures assessed PI (Acceptance and Action Questionnaire), resilience dimensions (Resilience Scale for Adults), and anxiety-related symptoms (Generalized Anxiety Disorder (GAD) Scale; Depression, Anxiety, and Stress Scales). A model generation approach, using machine-learning and robust mediation-based models, was applied to investigate the relationships between these constructs.ResultsIn a sample of 313 adults (72.20% females; 39.29 ± 11.81 years), Random Forest analysis indicated PI and the resilience dimensions perception of self (R-PS) and planned future (R-PF) as the strongest predictors of anxiety-related symptoms. PI showed a positive direct association with GAD, anxiety, and stress (respectively β = 0.28, β = 0.07, β = 0.20, p ≤ 0.001). Significant indirect associations emerged: PI–Stress regarding R-PS (β = 0.08, p = 0.004), PI–Anxiety regarding R-PF (β = 0.03; p = 0.03), PI–GAD (β = 0.08, p = 0.001) and PI–Stress (β = 0.11, p < 0.001) regarding R-PS and R-PF together.DiscussionThese findings highlight the importance of PI and resilience as interconnected processes underlying mental health outcomes. Additionally, they suggest that psychological intervention programs targeting PI, along with resilience, could foster healthier strategies for coping with anxiety-related symptoms.