Machine Learning Applications in Mental Health and Substance Use Research Among the LGBTQ2S+ Population: Scoping Review

Abstract

Background A high risk of mental health or substance addiction issues among sexual and gender minority populations may have more nuanced characteristics that may not be easily discovered by traditional statistical methods. Objective This review aims to identify literature studies that used machine learning (ML) to investigate mental health or substance use concerns among the lesbian, gay, bisexual, transgender, queer or questioning, and two-spirit (LGBTQ2S+) population and direct future research in this field. Methods The MEDLINE, Embase, PubMed, CINAHL Plus, PsycINFO, IEEE Xplore, and Summon databases were searched from November to December 2020. We included original studies that used ML to explore mental health or substance use among the LGBTQ2S+ population and excluded studies of genomics and pharmacokinetics. Two independent reviewers reviewed all papers and extracted data on general study findings, model development, and discussion of the study findings. Results We included 11 studies in this review, of which 81% (9/11) were on mental health and 18% (2/11) were on substance use concerns. All studies were published within the last 2 years, and most were conducted in the United States. Among mutually nonexclusive population categories, sexual minority men were the most commonly studied subgroup (5/11, 45%), whereas sexual minority women were studied the least (2/11, 18%). Studies were categorized into 3 major domains: web content analysis (6/11, 54%), prediction modeling (4/11, 36%), and imaging studies (1/11, 9%). Conclusions ML is a promising tool for capturing and analyzing hidden data on mental health and substance use concerns among the LGBTQ2S+ population. In addition to conducting more research on sexual minority women, different mental health and substance use problems, as well as outcomes and future research should explore newer environments, data sources, and intersections with various social determinants of health.

Scoping review of guidance on cessation interventions for electronic cigarettes and dual electronic and combustible cigarettes use

“…The database search strategy was reviewed and improved by incorporating suggestions from all authors. We did not use support from any information specialist because of previous experiences of conducting similar searches by the research team [37][38][39][40] and budget limitation.…”

Sex trouble: Sex/gender slippage, sex confusion, and sex obsession in machine learning using electronic health records

“…Sex/gender slippage and presumption of concordance can have significant negative consequences in areas where transgender people face higher risks than cisgender people, like mental health problems. 87 For example, Walsh et al. used EHR data to analyze suicide risk, incorporating gender data because “demographics such as age and gender are known risk factors for suicidal behavior.” 88 In the study, gender was found to be a significant factor in prediction of suicide attempts.…”

“…14,20,22 Research from Reisner et al suggests that there is a trade off between the number of patients/individuals and the availability of gender identity information, as many large databases used for population-level studies (e.g., datasets using driver's licenses for demographics) do not include gender identity. 87,99 Even in healthcare systems considered to be leading in this area, gender identity data may be missing for upwards of 75% of patients. 22 When the data are present, information about how the data were collected may not be available (e.g., self-reported, taken from health insurance records, written down by intake staff, etc.).…”

Use of Machine Learning Tools in Evidence Synthesis of Tobacco Use Among Sexual and Gender Diverse Populations: Algorithm Development and Validation

“…NLP is dedicated to deciphering and comprehending how computers interpret human language, equipping them to analyze extensive data sets of natural language [ 14 - 16 ]. While NLP tools have garnered considerable recognition in biomedical research [ 4 - 10 ], aiding in tasks such as disease surveillance (eg, COVID-19) and diagnosing using medical records [ 17 - 23 ], their potential to expedite near real-time synthesis of evidence in tobacco control research remains untapped [ 24 ].…”