scholarly journals Explainable Machine Learning Analysis Reveals Gender Differences in the Phenotypic and Neurobiological Markers of Cannabis Use Disorder

2021 ◽  
Author(s):  
Gregory Niklason ◽  
Eric Rawls ◽  
Sisi Ma ◽  
Erich Kummerfeld ◽  
Andrea M. Maxwell ◽  
...  
Keyword(s):  
Mental Health ◽  
Machine Learning ◽  
Risk Factors ◽  
Gender Differences ◽  
Community Sample ◽  
Cannabis Use ◽  
Data Driven ◽  
Cannabis Use Disorder ◽  
Cannabis Dependence ◽  
Human Connectome Project

Background: Cannabis Use Disorder (CUD) has been linked to environmental, personality, mental health, neurocognitive and neurobiological risk factors. While many studies have revealed gender differences in CUD, the relative importance of these complex factors by gender has not been described. Methods: We conducted a data-driven examination of gender differences in CUD in a community sample of young adults (Human Connectome Project [HCP]; n = 1204, 54% female). We employed state-of-the-art machine learning methods [gradient tree boosting, XGBoost] in combination with novel factor ranking tools [SHapley's Additive exPlanations (SHAP)] as an 'explainable machine learning approach' in the multimodal data collected by the HCP (phenotypic and brain data). Results: We were able to successfully classify both cannabis dependence and cannabis use levels. Previously identified environmental, personality, mental health, neurocognitive, and brain factors highly contributed to the classification. Predominantly-male risk factors included personality (high openness), mental health (high externalizing, high childhood conduct disorder, high fear somaticism), neurocognitive (impulsive delay discounting, slow working memory performance) and brain (low hippocampal volume) factors. Conversely, predominantly-female risk factors included environmental (low education level, low instrumental support) factors. Conclusions: Our data-driven analysis of gender differences in the multimodal risk factors underlying cannabis dependence and use levels demonstrate that environmental factors contribute more strongly to CUD in women, whereas individual factors such as personality, mental health and neurocognitive factors have a larger importance in men. This warrants further investigations, and suggests the importance of understanding how these differences relate to the development of effective treatment approaches.

Cannabis use among early adolescents and transdiagnostic mental health risk factors

2021 ◽  
pp. 135910452199463
Author(s):  
Sara Moreno-Mansilla ◽  
Jorge J Ricarte ◽  
David J Hallford
Keyword(s):  
Mental Health ◽  
Risk Factors ◽  
Health Risk ◽  
Suicide Attempts ◽  
Intolerance Of Uncertainty ◽  
Cannabis Use ◽  
Health Risk Factors ◽  
Symptoms Of Depression ◽  
Modifiable Factors ◽  
Wide Range

Introduction: Cannabis is the most widely used psychoactive substance among adolescents worldwide, and the age at which consumption begins to decrease. Cannabis use in adolescents is associated with a wide range of adverse consequences in adulthood including increased vulnerability to psychosis and other mental disorders, as well as suicidal ideation and attempt. The aim of this study is to extend understanding of the link between cannabis use and mental illness by examining whether cannabis use at early ages predicts transdiagnostic variables that are precursors to severe clinical diagnoses. Methods: A descriptive cross-sectional study was conducted. The sample was made up of 605 adolescents from 7th to 9th grades, with a mean age of 13.2 years ( SD = 1.0, 47% girls). The variables evaluated were: anomalous perception of reality, intolerance of uncertainty, rumination, suicide attempt, hopelessness, and symptoms of depression and anxiety. The administration of the questionnaires was carried out in groups of 20 participants under the supervision of a researcher in a unique session of 1 hour. Results: Adolescent cannabis users scored higher on all variables assessed: anomalous perception of reality (Cohen’s d = .60), rumination ( d = .48), intolerance of uncertainty ( d = .11), suicidal attempt (affirmative answer: 25.9% of users vs 7.7% of non-users), hopelessness ( d = .85), symptoms of depression ( d = .80), and anxiety ( d = .39). A binary logistic regression showed that the only variable uniquely related to cannabis use was hopelessness (Wald = 4.560, OR: 1.159, p = .033). Conclusions: Among some mental health risk factors, hopelessness appears uniquely related to cannabis use. Adolescents may use cannabis as a coping strategy for negative thoughts and emotions, or it may be a consequence of cannabis use. Future prevention programs should focus on preventing/treating modifiable factors such as hopelessness, and delaying cannabis use in specific subgroups of adolescents who experience pathologies such as depression or suicide attempts.

Psychosocial and pharmacological treatments for cannabis use disorder and mental health comorbidities: a narrative review

2021 ◽  
pp. 1-12
Author(s):  
Rachel Lees ◽  
Lindsey A. Hines ◽  
Deepak Cyril D'Souza ◽  
George Stothart ◽  
Marta Di Forti ◽  
...  
Keyword(s):  
Mental Health ◽  
Clinical Decision Making ◽  
Treatment Compliance ◽  
Narrative Review ◽  
Cannabis Use ◽  
Psychotic Symptoms ◽  
Motivational Enhancement Therapy ◽  
Cannabis Use Disorder ◽  
Pharmacological Treatments ◽  
Health Comorbidities

Abstract Cannabis is the most widely used illicit drug worldwide, and it is estimated that up to 30% of people who use cannabis will develop a cannabis use disorder (CUD). Demand for treatment of CUD is increasing in almost every region of the world and cannabis use is highly comorbid with mental disorders, where sustained use can reduce treatment compliance and increase risk of relapse. In this narrative review, we outline evidence for psychosocial and pharmacological treatment strategies for CUD, both alone and when comorbid with psychosis, anxiety or depression. Psychosocial treatments such as cognitive behavioural therapy, motivational enhancement therapy and contingency management are currently the most effective strategy for treating CUD but are of limited benefit when comorbid with psychosis. Pharmacological treatments targeting the endocannabinoid system have the potential to reduce cannabis withdrawal and cannabis use in CUD. Mental health comorbidities including anxiety, depression and psychosis hinder effective treatment and should be addressed in treatment provision and clinical decision making to reduce the global burden of CUDs. Antipsychotic medication may decrease cannabis use and cannabis craving as well as psychotic symptoms in patients with CUD and psychosis. Targeted treatments for anxiety and depression when comorbid with CUD are feasible.

Correlates of Youth Suicide Attempters in Australian Community and Clinical Samples

2003 ◽  
Vol 37 (3) ◽  
pp. 286-293 ◽  
Author(s):  
Gregory L. Carter ◽  
Cathy Issakidis ◽  
Kerrie Clover
Keyword(s):  
Mental Health ◽  
Risk Factors ◽  
Substance Use ◽  
Substance Use Disorder ◽  
Suicidal Behaviour ◽  
Clinical Sample ◽  
Community Sample ◽  
Community Control ◽  
Clinical Group ◽  
Health Related

Objective: This study (i) explores differences between a clinical sample of deliberate selfpoisoning (DSP) patients and a community sample who reported previous attempted suicide (AS); and (ii) examines correlates of suicidal behaviour in these groups compared with a community control group (CC) with no suicidal behaviour. Method: The study design was: case–case, case–control and cross-sectional population studies. A clinical sample of DSP (n = 51), a community sample of AS (n = 31) and a community sample with no suicidal behaviour (n = 842) were used, all aged 18–24 years. The DSP and AS groups were compared on several variables and two logistic regression models were developed for risk of (i) DSP and (ii) AS compared to community controls. Results: The adjusted odds ratios for DSP were: female gender (OR = 5.7, CI = 1.7–19.4), anxiety (OR = 7.4, CI = 2.2–25.1), affective (OR = 23.0, CI = 6.9–76.5), or substance-use disorder (OR = 19.2, CI = 5.6–65.4) and greater mental health related disability (OR = 0.5, CI = 0.3–0.7 for 1 SD decrease). For AS the results were: anxiety (OR = 9.4, CI = 1.7–52.8) or substance-use disorder (OR = 3.0, CI = 1.1–8.7) and greater mental health disability (OR = 0.5, CI = 0.4–0.7). Affective disorder was close to significant for the AS group (OR = 4.0, CI = 0.9–17.1). Conclusions: Correlates of DSP/AS were usually more powerful in the clinical group, but showed a similar pattern of psychiatric disorder and disability factors in both groups, supporting a continuum of risk factors across these groups. Interventions based on modifiable risk factors could target the same factors for public health, primary care or hospital populations: anxiety, depression and substance use disorders and mental health related disability.

General Practice Recruitment for People at Risk of Schizophrenia: The Buckingham Experience

2000 ◽  
Vol 34 (1_suppl) ◽  
pp. A131-A136 ◽  
Author(s):  
Ian R. H. Falloon
Keyword(s):  
Mental Health ◽  
Risk Factors ◽  
Primary Care ◽  
At Risk ◽  
General Practice ◽  
Early Detection ◽  
Psychotic Disorders ◽  
Community Sample ◽  
Signs And Symptoms ◽  
Psychotic Episode

Objective The process of detecting people at high risk of schizophrenia from a community sample is a major challenge for prevention of psychotic disorders. The aim of this paper is to describe early detection procedures that can be implemented in primary care settings. Methods A selected literature review is supplemented by experiences and data obtained during the Buckingham Integrated Mental Health Care Project. Results General medical practitioners have been favoured as the agents most likely to prove helpful in detecting the key risk factors that predict the onset of schizophrenic disorders, as well as in recognising the earliest signs and symptoms of these conditions. However, the practical problems of screening for multiple and subtle risk factors in general practice are substantial, and general practitioners (GPs) often have difficulty recognising the earliest signs of a psychotic episode. A range of strategies to assist GPs detect early signs of psychosis in their patients are considered. Conclusions It is feasible to implement primary care setting early detection procedures for people at risk of schizophrenia. Implementation is aided by the use of a brief screening questionnaire, training sessions and case supervision; and increased collaboration with mental health services and other community agencies.

scholarly journals Precision Mental Health Care for Cannabis Use Disorder: Utility of a bioSocial Cognitive Theory to Inform Treatment

2021 ◽  
Vol 12 ◽  
Author(s):  
Matthew J. Gullo ◽  
Zoë E. Papinczak ◽  
Gerald F. X. Feeney ◽  
Ross McD. Young ◽  
Jason P. Connor
Keyword(s):  
Risk Factors ◽  
Cognitive Theory ◽  
Preliminary Evidence ◽  
Cannabis Use ◽  
Social Risk ◽  
Cannabis Use Disorder ◽  
Social Risk Factors ◽  
Psychological Mechanisms ◽  
Wide Range ◽  
Drug Refusal

Globally, cannabis is the most frequently used controlled substance after alcohol and tobacco. Rates of cannabis use are steadily increasing in many countries and there is emerging evidence that there is likely to be greater risk due to increased concentrations of delta-9-tetrahydrocannabinol (THC). Cannabis use and Cannabis Use Disorder (CUD) has been linked to a wide range of adverse health outcomes. Several biological, psychological, and social risk factors are potential targets for effective evidence-based treatments for CUD. There are no effective medications for CUD and psychological interventions are the main form of treatment. Psychological treatments based on Social Cognitive Theory (SCT) emphasize the importance of targeting 2 keys psychological mechanisms: drug outcome expectancies and low drug refusal self-efficacy. This mini-review summarizes the evidence on the role of these mechanisms in the initiation, maintenance, and cessation of cannabis use. It also reviews recent evidence showing how these psychological mechanisms are affected by social and biologically-based risk factors. A new bioSocial Cognitive Theory (bSCT) is outlined that integrates these findings and implications for psychological cannabis interventions are discussed. Preliminary evidence supports the application of bSCT to improve intervention outcomes through better targeted treatment.

Longitudinal course of mental health symptoms among veterans with and without cannabis use disorder.

2021 ◽  
Author(s):  
Nicholas A. Livingston ◽  
Stacey L. Farmer ◽  
Colin T. Mahoney ◽  
Brian P. Marx ◽  
Terence M. Keane
Keyword(s):  
Mental Health ◽  
Cannabis Use ◽  
Cannabis Use Disorder ◽  
Mental Health Symptoms ◽  
Health Symptoms ◽  
Longitudinal Course

scholarly journals Brain structural changes in cannabis dependence: association with MAGL

2019 ◽  
Vol 25 (12) ◽  
pp. 3256-3266 ◽  
Author(s):  
Peter Manza ◽  
Kai Yuan ◽  
Ehsan Shokri-Kojori ◽  
Dardo Tomasi ◽  
Nora D. Volkow
Keyword(s):  
White Matter ◽  
Spatial Patterns ◽  
Cortical Thickness ◽  
Gray Matter ◽  
Acid Amide ◽  
Cannabis Use ◽  
Brain Atlas ◽  
Cannabis Dependence ◽  
Human Connectome Project ◽  
Postmortem Brain Tissue

AbstractCannabis use is rising, yet there is poor understanding of biological processes that might link chronic cannabis use to brain structural abnormalities. To lend insight into this topic, we examined white matter microstructural integrity and gray matter cortical thickness/density differences between 89 individuals with cannabis dependence (CD) and 89 matched controls (64 males, 25 females in each group) from the Human Connectome Project. We tested whether cortical patterns for expression of genes relevant for cannabinoid signaling (from Allen Human Brain Atlas postmortem tissue) were associated with spatial patterns of cortical thickness/density differences in CD. CD had lower fractional anisotropy than controls in white matter bundles innervating posterior cingulate and parietal cortex, basal ganglia, and temporal cortex. The CD group also had significantly less gray matter thickness and density in precuneus, relative to controls. Sibling-pair analysis found support for causal and graded liability effects of cannabis on precuneus structure. Spatial patterns of gray matter differences in CD were significantly associated with regional differences in monoacylglycerol lipase (MAGL) expression in postmortem brain tissue, such that regions with higher MAGL expression (but not fatty-acid amide hydrolase or FAAH) were more vulnerable to cortical thinning. In sum, chronic cannabis use is associated with structural differences in white and gray matter, which was most prominent in precuneus and associated white matter tracts. Regions with high MAGL expression, and therefore with potentially physiologically restricted endogenous cannabinoid signaling, may be more vulnerable to the effects of chronic cannabis use on cortical thickness.

scholarly journals Identification of risk factors for involuntary psychiatric hospitalization: using environmental socioeconomic data and methods of machine learning to improve prediction

2020 ◽  
Vol 20 (1) ◽  
Author(s):  
O. Karasch ◽  
M. Schmitz-Buhl ◽  
R. Mennicken ◽  
J. Zielasek ◽  
E. Gouzoulis-Mayfrank
Keyword(s):  
Mental Health ◽  
Machine Learning ◽  
Risk Factors ◽  
Prediction Model ◽  
Psychiatric Hospitalization ◽  
Previous Analysis ◽  
Psychiatric Hospitals ◽  
Data Set ◽  
Interaction Detection ◽  
Socioeconomic Data

Abstract Background The purpose of this study was to identify factors associated with a high risk of involuntary psychiatric in-patient hospitalization both on the individual level and on the level of mental health services and the socioeconomic environment that patients live in. Methods The present study expands on a previous analysis of the health records of 5764 cases admitted as in-patients in the four psychiatric hospitals of the Metropolitan City of Cologne, Germany, in the year 2011 (1773 cases treated under the Mental Health Act and 3991 cases treated voluntarily). Our previous analysis had included medical, sociodemographic and socioeconomic data of every case and used a machine learning-based prediction model employing chi-squared automatic interaction detection (CHAID). Our current analysis attempts to improve the previous one through (1) optimizing the machine learning procedures (use of a different type of decision-tree prediction model (Classification and Regression Trees (CART) and application of hyperparameter tuning (HT)), and (2) the addition of patients’ environmental socioeconomic data (ESED) to the data set. Results Compared to our previous analysis, model fit was improved. Main diagnoses of an organic mental or a psychotic disorder (ICD-10 groups F0 and F2), suicidal behavior upon admission, admission outside of regular service hours and absence of outpatient treatment prior to admission were confirmed as powerful predictors of detention. Particularly high risks were shown for (1) patients with an organic mental disorder, specifically if they were retired, admitted outside of regular service hours and lived in assisted housing, (2) patients with suicidal tendencies upon admission who did not suffer from an affective disorder, specifically if it was unclear whether there had been previous suicide attempts, or if the affected person lived in areas with high unemployment rates, and (3) patients with psychosis, specifically those who lived in densely built areas with a large proportion of small or one-person households. Conclusions Certain psychiatric diagnoses and suicidal tendencies are major risk factors for involuntary psychiatric hospitalization. In addition, service-related and environmental socioeconomic factors contribute to the risk for detention. Identifying modifiable risk factors and particularly vulnerable risk groups should help to develop suitable preventive measures.

scholarly journals Gender differences in the structure of risk for alcohol use disorder in adolescence and young adulthood

2015 ◽  
Vol 45 (14) ◽  
pp. 3047-3058 ◽  
Author(s):  
K. T. Foster ◽  
B. M. Hicks ◽  
W. G. Iacono ◽  
M. McGue
Keyword(s):  
Risk Factors ◽  
Gender Differences ◽  
Alcohol Use ◽  
Psychosocial Factors ◽  
Internalizing Symptoms ◽  
Alcohol Use Disorder ◽  
Community Sample ◽  
Risk Exposure ◽  
Deviant Peer Affiliation ◽  
Adolescent Risk

Background.Gender differences in the prevalence of alcohol use disorder (AUD) have motivated the separate study of its risk factors and consequences in men and women. However, leveraging gender as a third variable to help account for the association between risk factors and consequences for AUD could elucidate etiological mechanisms and clinical outcomes.Method.Using data from a large, community sample followed longitudinally from 17 to 29 years of age, we tested for gender differences in psychosocial risk factors and consequences in adolescence and adulthood after controlling for gender differences in the base rates of AUD and psychosocial factors. Psychosocial factors included alcohol use, other drug use, externalizing and internalizing symptoms, deviant peer affiliation, family adversity, academic problems, attitudes and use of substances by a romantic partner, and adult socio-economic status.Results.At both ages of 17 and 29 years, mean levels of psychosocial risks and consequences were higher in men and those with AUD. However, the amount of risk exposure in adolescence was more predictive of AUD in women than men. By adulthood, AUD consequences were larger in women than men and internalizing risk had a stronger relationship with AUD in women at both ages.Conclusions.Despite higher mean levels of risk exposure in men overall, AUD appears to be a more severe disorder in women characterized by higher levels of adolescent risk factors and a greater magnitude of the AUD consequences among women than men. Furthermore, internalizing symptoms appear to be a gender-specific risk factor for AUD in women.

Sign in / Sign up

Export Citation Format

Share Document