Correlates of past year suicidal thoughts among sexual and gender minority young adults: A machine learning analysis

Factors associated with the use of psychedelics, ketamine and MDMA among sexual and gender minority youths in Canada: a machine learning analysis

BACKGROUND

Substance use is increasing among sexual and gender minority youth (SGMY). This increase may be due to changes in social norms and socialisation, or due to SGMY exploring the potential therapeutic value of drugs such as psychedelics. We identified predictors of psychedelics, MDMA and ketamine use.

METHODS

Data were obtained from 1414 SGMY participants who completed the ongoing longitudinal 2SLGBTQ+ Tobacco Project in Canada between November 2020 to January 2021. We examined the association between 80 potential features (including sociodemographic factors, mental health-related factors and substance use-related factors) with the use of psychedelics, MDMA and ketamine in the past year. Random forest classifier was used to identify the predictors most associated with reported use of these drugs.

RESULTS

18.1% of participants have used psychedelics in the past year; 21.9% used at least one of the three drugs. Cannabis and cocaine use were the predictors most strongly associated with any of these drugs, while cannabis, but not cocaine use, was the one most associated with psychedelic use. Other mental health and 2SLGBTQ+ stigma-related factors were also associated with the use of these drugs.

CONCLUSION

The use of psychedelics, MDMA and ketamine among 2SLGBTQ+ individuals appeared to be largely driven by those who used them together with other drugs. Depression scores also appeared in the top 10 factors associated with these illicit drugs, suggesting that there were individuals who may benefit from the potential therapeutic value of these drugs. These characteristics should be further investigated in future studies.

Latent Heterogeneity of Online Sexual Experiences and Associations With Sexual Risk Behaviors and Behavioral Health Outcomes in Chinese Young Adults: Cross-Sectional Study

BACKGROUND

Online sexual experiences (OSEs) are becoming increasingly common in young adults, but existing papers have reported only on specific types of OSEs and have not shown the heterogeneous nature of the repertoire of OSEs. The use patterns of OSEs remain unclear, and the relationships of OSEs with sexual risk behaviors and behavioral health outcomes have not been evaluated.

OBJECTIVE

This study aimed to examine the latent heterogeneity of OSEs in young adults and the associations with sexual risk behaviors and behavioral health outcomes.

METHODS

The 2021 Youth Sexuality Study of the Hong Kong Family Planning Association phone interviewed a random sample of 1205 young adults in Hong Kong in 2022 (male sex: 613/1205, 50.9%; mean age 23.0 years, SD 2.86 years) on lifetime OSEs, demographic and family characteristics, Patient Health Questionnaire-4 (PHQ-4) scores, sex-related factors (sexual orientation, sex knowledge, and sexual risk behaviors), and behavioral health outcomes (sexually transmitted infections [STIs], drug use, and suicidal ideation) in the past year. Sample heterogeneity of OSEs was analyzed via latent class analysis with substantive checking of the class profiles. Structural equation modeling was used to examine the direct and indirect associations between the OSE class and behavioral health outcomes via sexual risk behaviors and PHQ-4 scores.

RESULTS

The data supported 3 latent classes of OSEs with measurement invariance by sex. In this study, 33.1% (398/1205), 56.0% (675/1205), and 10.9% (132/1205) of the sample were in the abstinent class (minimal OSEs), normative class (occasional OSEs), and active class (substantive OSEs), respectively. Male participants showed a lower prevalence of the abstinent class (131/613, 21.4% versus 263/592, 44.4%) and a higher prevalence of the active class (104/613, 17.0% versus 28/592, 4.7%) than female participants. The normative class showed significantly higher sex knowledge than the other 2 classes. The active class was associated with male sex, nonheterosexual status, higher sex desire and PHQ-4 scores, and more sexual risk behaviors than the other 2 classes. Compared with the nonactive (abstinent and normative) classes, the active class was indirectly associated with higher rates of STIs (absolute difference in percentage points [Δ]=4.8%; P=.03) and drug use (Δ=7.6%; P=.001) via sexual risk behaviors, and with higher rates of suicidal ideation (Δ=2.5%; P=.007) via PHQ-4 scores.

CONCLUSIONS

This study provided the first results on the 3 (abstinent, normative, and active) latent classes of OSEs with distinct profiles in OSEs, demographic and family characteristics, PHQ-4 scores, sex-related factors, and behavioral health outcomes. The active class showed indirect associations with higher rates of STIs and drug use via sexual risk behaviors and higher rates of suicidal ideation via PHQ-4 scores than the other 2 classes. These results have implications for the formulation and evaluation of targeted interventions to help young adults.

Table 2 Fallacy in Descriptive Epidemiology: Bringing Machine Learning to the Table

There is a lack of rigorous methodological development for descriptive epidemiology, where the goal is to describe and identify the most important associations with an outcome given a large set of potential predictors. This has often led to the Table 2 fallacy, where one presents the coefficient estimates for all covariates from a single multivariable regression model, which are often uninterpretable in a descriptive analysis. We argue that machine learning (ML) is a potential solution to this problem. We illustrate the power of ML with an example analysis identifying the most important predictors of alcohol abuse among sexual minority youth. The framework we propose for this analysis is as follows: (1) Identify a few ML methods for the analysis, (2) optimize the parameters using the whole data with a nested cross-validation approach, (3) rank the variables using variable importance scores, (4) present partial dependence plots (PDP) to illustrate the association between the important variables and the outcome, (5) and identify the strength of the interaction terms using the PDPs. We discuss the potential strengths and weaknesses of using ML methods for descriptive analysis and future directions for research. R codes to reproduce these analyses are provided, which we invite other researchers to use.

A Machine Learning Approach Reveals Distinct Predictors of Vaping Dependence for Adolescent Daily and Non-Daily Vapers in the COVID-19 Era

Since 2016, there has been a substantial rise in e-cigarette (vaping) dependence among young people. In this prospective cohort study, we aimed to identify the different predictors of vaping dependence over 3 months among adolescents who were baseline daily and non-daily vapers. We recruited ever-vaping Canadian residents aged 16-25 years on social media platforms and asked them to complete a baseline survey in November 2020. A validated vaping dependence score (0-23) summing up their responses to nine questions was calculated at the 3-month follow-up survey. Separate lasso regression models were developed to identify predictors of higher 3-month vaping dependence score among baseline daily and non-daily vapers. Of the 1172 participants, 643 (54.9%) were daily vapers with a mean age of 19.6 ± 2.6 years and 76.4% (n = 895) of them being female. The two models achieved adequate predictive performance. Place of last vape purchase, number of days a pod lasts, and the frequency of nicotine-containing vaping were the most important predictors for dependence among daily vapers, while race, sexual orientation and reporting treatment for heart disease were the most important predictors in non-daily vapers. These findings have implications for vaping control policies that target adolescents at different stages of vape use.

Conversion therapy, suicidality, and running away: An analysis of transgender youth in the U.S

This study analyzes the relationship between conversion therapy and mental health and wellbeing of transgender youth in the U.S. We create a retrospective panel of transgender youth using the 2015 U.S. Transgender Survey to test how exposure to conversion therapy affects the likelihood of attempting suicide and running away from home. The empirical approach employs a difference-in-differences design. Results indicate that exposure to conversion therapy substantially increases the likelihood a transgender adolescent will attempt suicide and run away. The average treatment effect on treated (ATT) of conversion therapy on having attempted suicide is an increase of 17 percentage points, which amounts to a 55% increase in the risk of attempting suicide, and the ATT on the risk of running away is an increase of 7.8 percentage points, more than doubling the risk of running away. These effects are largest when exposure to conversion therapy occurs at a young age (11-14).

A systems science approach to identifying data gaps in national data sources on adolescent suicidal ideation and suicide attempt in the United States

BACKGROUND

Suicide is currently the second leading cause of death among adolescents ages 10-14, and third leading cause of death among adolescents ages 15-19 in the United States (U.S). Although we have numerous U.S. based surveillance systems and survey data sources, the coverage offered by these data with regard to the complexity of youth suicide had yet to be examined. The recent release of a comprehensive systems map for adolescent suicide provides an opportunity to contrast the content of surveillance systems and surveys with the mechanisms listed in the map.

OBJECTIVE

To inform existing data collection efforts and advance future research on the risk and protective factors relevant to adolescent suicide.

METHODS

We examined data from U.S. based surveillance systems and nationally-representative surveys that included (1) observations for an adolescent population and (2) questions or indicators in the data that identified suicidal ideation or suicide attempt. Using thematic analysis, we evaluated the codebooks and data dictionaries for each source to match questions or indicators to suicide-related risk and protective factors identified through a recently published suicide systems map. We used descriptive analysis to summarize where data were available or missing and categorized data gaps by social-ecological level.

RESULTS

Approximately 1-of-5 of the suicide-related risk and protective factors identified in the systems map had no supporting data, in any of the considered data sources. All sources cover less than half the factors, except the Adolescent Brain Cognitive Development Study (ABCD), which covers nearly 70% of factors.

CONCLUSIONS

Examining gaps in suicide research can help focus future data collection efforts in suicide prevention. Our analysis precisely identified where data is missing and also revealed that missing data affects some aspects of suicide research (e.g., distal factors at the community and societal level) more than others (e.g., proximal factors about individual characteristics). In sum, our analysis highlights limitations in current suicide-related data availability and provides new opportunities to identify and expand current data collection efforts.

SEIR models in the light of Critical Realism - A critique of exaggerated claims about the effectiveness of Covid 19 vaccinations

In a recent modeling study Watson et al. (Lancet Infect Dis 2022;3099:1-10) claim that Covid-19 vaccinations have helped to prevent roughly 14-20 million deaths in 2021. This conclusion is based on an epidemiological susceptible-exposed-infectious-recovered (SEIR) model trained on partially simulated data and yielding a reproduction number distribution which was then applied to a counterfactual scenario in which the efficacy of vaccinations was removed. Drawing on the meta-theory of Critical Realism, we point out several caveats of this model and caution against believing in its predictions. We argue that the absence of vaccinations would have significantly changed the causal tendencies of the system being modelled, yielding a different reproduction number than obtained from training the model on actually observed data. Furthermore, the model omits many important causal factors. Therefore this model, similar to many previous SEIR models, has oversimplified the complex interplay between biomedical, social and cultural dimensions of health and should not be used to guide public health policy. In order to predict the future in epidemic situations more accurately, continuously optimized dynamic causal models which can include the not directly tangible, yet real causal mechanisms affecting public health appear to be a promising alternative to SEIR-type models.

Correlates of wanting to seek help for mental health and substance use concerns by sexual and gender minority young adults during the COVID-19 pandemic: A machine learning analysis

The COVID-19 pandemic has worsened the mental health and substance use challenges among many people who are Two Spirit, lesbian, gay, bisexual, transgender, queer, questioning, and intersex (2SLGBTQI+). We aimed to identify the important correlates and their effects on the predicted likelihood of wanting to seek help among 2SLGBTQI+ young adults for mental health or substance use concerns during the pandemic. A cross-sectional survey was conducted in 2020-2021 among 2SLGBTQI+ young adults aged 16-29 living in two Canadian provinces (Ontario and Quebec). Among 1414 participants, 77% (n = 1089) wanted to seek help for their mental health or substance use concerns during the pandemic, out of these, 69.8% (n = 760) reported delay in accessing care. We built a random forest (RF) model to predict the status of wanting to seek help, which achieved moderately high performance with an area under the receiver operating characteristic curve (AUC) of 0.85. The top 10 correlates of wanting to seek help were worsening mental health, age, stigma and discrimination, and adverse childhood experiences. The interactions of adequate housing with certain sexual orientations, gender identities and mental health challenges were found to increase the likelihood of wanting to seek help. We built another RF model for predicting risk of delay in accessing care among participants who wanted to seek help (n = 1089). The model identified a similar set of top 10 correlates of delay in accessing care but lacked adequate performance (AUC 0.61). These findings can direct future research and targeted prevention measures to reduce health disparities for 2SLGBTQI+ young adults.