JMIR Publications

ABSTRACT

Background:

Sexual and gender minority (SGM) individuals are at heightened risk for substance use and sexually transmitted infections than their non-SGM peers. Collecting mobile phone usage data passively may open new opportunities for personalizing interventions, as behavioral risks could be identified without user input.

Objective:

Our objective was to determine whether passively sensed mobile phone data can be used to identify substance use and sexual risk behaviors for STI and HIV transmission among young SGM who have sex with men.

Methods:

We developed a mobile phone app to collect participants’ messaging, location, and app use data. Based on community-engaged qualitative research, we trained a machine learning model to identify risk behaviors for STI and HIV transmission, such as condomless anal sex, number of sexual partners, and methamphetamine use. We validated these behaviors using self-report and evaluated their association with mobile phone use data.

Results:

We recruited 82 SGM young people who have sex to use our data collection app, and among those users, our model was highly predictive of methamphetamine use and having 6+ sexual partners (F1 scores 0.83 and 0.69 respectively). The model was less predictive of condomless anal sex (F1 score 0.38). Overall, text-based features were found to be most predictive, but app use and location data improved the results, particularly for detecting 6+ sexual partners.

Conclusions:

Our results show that passively collected mobile phone data may be useful in detecting sexual risk behaviors. Expanding data collection may improve the results further, as certain behaviors, such as injection drug use, were quite rare in the study sample. These models may be used to personalize STI and HIV prevention as well as substance use harm reduction interventions.