Using Smartphone Survey Data and Machine Learning to Identify Situational and Contextual Risk Factors for HIV Risk Behavior Among Men Who Have Sex with Men Who Are Not on PrEP
“Just-in-time” interventions (JITs) delivered via smartphones have considerable potential for reducing HIV risk behavior by providing pivotal support at key times prior to sex. However, these programs depend on a thorough understanding of when risk behavior is likely to occur to inform the timing of JITs. It is also critical to understand the most important momentary risk factors that may precede HIV risk behavior, so that interventions can be designed to address them. Applying machine learning (ML) methods to ecological momentary assessment data on HIV risk behaviors can help answer both questions. Eighty HIV-negative men who have sex with men (MSM) who were not on PrEP completed a daily diary survey each morning and an experience sampling survey up to six times per day via a smartphone application for 30 days. Random forest models achieved the highest area under the curve (AUC) values for classifying high-risk condomless anal sex (CAS). These models achieved 80% specificity at a sensitivity value of 74%. Unsurprisingly, the most important contextual risk factors that aided in classification were participants’ plans and intentions for sex, sexual arousal, and positive affective states. Findings suggest that survey data collected throughout the day can be used to correctly classify about three of every four high-risk CAS events, while incorrectly classifying one of every five non-CAS days as involving high-risk CAS. A unique set of risk factors also often emerge prior to high-risk CAS events that may be useful targets for JITs.
KeywordsHIV Sexual behavior Men who have sex with men Machine learning Ecological momentary assessment
This manuscript was supported by P01AA019072 (to PM) and L30AA023336 (to TW) from the National Institute on Alcohol Abuse and Alcoholism.
Compliance with Ethical Standards
Conflict of Interest
The authors declare that they have no conflict of interest.
Research Involving Human Participants and/or Animals
All procedures in this study were approved by the Brown University Institutional Review Board.
All participants in this study provided informed consent prior to enrollment.
- Bae, S., Ferreira, D., Suffoletto, B., Puyana, J. C., Kurtz, R., Chung, T., & Dey, A. K. (2017). Detecting drinking episodes in young adults using smartphone-based sensors. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 1, 5.Google Scholar
- Bi, J., Sun, J., Wu, Y., Tennen, H., & Armeli, S. (2013). A machine learning approach to college drinking prediction and risk factor identification. ACM Transactions on Intelligent Systems and Technology (TIST), 4, 72.Google Scholar
- Centers for Disease Control and Prevention. (2013). HIV prevention: progress to date. Atlanta: U.S. Department of Health and Human Services.Google Scholar
- Centers for Disease Control and Prevention. (2016a). Lifetime risk of HIV diagnosis. Retrieved from: https://www.cdc.gov/nchhstp/newsroom/2016/croi-press-release-risk.html.
- Centers for Disease Control and Prevention. (2016b). Trends in HIV diagnoses, 2005–2014. Retrieved from: http://www.webcitation.org/6vAPQZG6c.
- Centers for Disease Control and Prevention. (2016c). As many as 185,000 new HIV infections in the U.S. could be prevented by expanding testing, treatment, PrEP. Retrieved from: https://www.cdc.gov/nchhstp/newsroom/2016/croi-press-release-prevention.html.
- Centers for Disease Control and Prevention. (2017). HIV among African American gay and bisexual men. Atlanta: National Center for HIV/AIDS, Viral Hepatitis, STD, and TB Prevention.Google Scholar
- Choe, E. K., Lee, N. B., Lee, B., Pratt, W., & Kientz, J. A. (2014). Understanding quantified-selfers’ practices in collecting and exploring personal data. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (pp. 1143–1152). New York: ACM.Google Scholar
- Dey, A. K., Wac, K., Ferreira, D., Tassini, K., Hong, J. H., & Ramos, J. (2011). Getting closer: an empirical investigation of the proximity of user to their smart phones. Proceedings of the 13th International Conference on Ubiquitous Computing (pp. 163–172). New York: ACM.Google Scholar
- Etchings, J. A. (2017). Strategies in biomedical data science: driving force for innovation. Hoboken: John Wiley & Sons.Google Scholar
- Goldstein, S. P., Evans, B. C., Flack, D., Juarascio, A., Manasse, S., Zhang, F., & Forman, E. M. (2017). Return of the JITAI: applying a just-in-time adaptive intervention framework to the development of m-health solutions for addictive behaviors. International Journal of Behavioral Medicine, 24, 673–682.CrossRefPubMedPubMedCentralGoogle Scholar
- Google Developers. (2018). Google APIs for Android: detected activity. Retrieved from: http://www.webcitation.org/72BzwQGD0.
- Grov, C., Rendina, H. J., Ventuneac, A., & Parsons, J. T. (2016). Sexual behavior varies between same-race and different-race partnerships: a daily diary study of highly sexually active Black, Latino, and White gay and bisexual men. Archives of Sexual Behavior, 45, 1453–1462.CrossRefPubMedGoogle Scholar
- Hosek, S., Landovitz, R., Rudy, B., Kapogiannis, B., Siberry, G., & Rutledge, B. (2016). An HIV pre-exposure prophylaxis (PrEP) demonstration project and safety study for adolescent MSM ages 15–17 in the United States (ATN 113). Paper presented at the International AIDS Conference.Google Scholar
- Intille, S., Haynes, C., Maniar, D., Ponnada, A., & Manjourides, J. (2016). μEMA: microinteraction-based ecological momentary assessment (EMA) using a smartwatch. Paper presented at the proceedings of the 2016 ACM international joint conference on pervasive and ubiquitous computing.Google Scholar
- LiKamWa, R., Liu, Y., Lane, N. D., & Zhong, L. (2013). Moodscope: building a mood sensor from smartphone usage patterns. Paper presented at the proceeding of the 11th annual international conference on Mobile systems, applications, and services.Google Scholar
- Mayer, K., Maloney, K., Levine, K., King, D., Grasso, C., Krakower, D., & Boswell, S. (2016). HIV infection and PrEP use are independently associated with diagnoses of bacterial sexually transmitted infections in men accessing care at a Boston community health center. Paper presented at the ID week, New Orleans, LA.Google Scholar
- Nahum-Shani, I., Smith, S. N., Spring, B. J., Collins, L. M., Witkiewitz, K., Tewari, A., & Murphy, S. A. (2017). Just-in-time adaptive interventions (JITAIs) in mobile health: key components and design principles for ongoing health behavior support. Annals of Behavioral Medicine, 52, 446–462.Google Scholar
- Newcomb, M. E., & Mustanski, B. (2013). Diaries for observation or intervention of health behaviors: factors that predict reactivity in a sexual diary study of men who have sex with men. Annals of Behavioral Medicine, 47, 325–334.Google Scholar
- Paolillo, E. W., Obermeit, L. C., Tang, B., Depp, C. A., Vaida, F., Moore, D. J., & Moore, R. C. (2018). Smartphone-based ecological momentary assessment (EMA) of alcohol and cannabis use in older adults with and without HIV infection. Addictive Behaviors, 83, 102–108.Google Scholar
- Parsons, J. T., Rendina, H. J., Grov, C., Ventuneac, A., & Mustanski, B. (2015). Accuracy of highly sexually active gay and bisexual men's predictions of their daily likelihood of anal sex and its relevance for intermittent event-driven HIV Pre-Exposure Prophylaxis. Journal of Acquired Immune Deficiency Syndromes (JAIDS), 68, 449–455.Google Scholar
- Puterman, E. (2009). Bringing risk prevention into the bedroom: sex motives and risky behaviors in men who have sex with men. Doctoral dissertation, University of British Columbia.Google Scholar
- Shiffman, S., Stone, A. A., & Hufford, M. R. (2008). Ecological momentary assessment. Annual Review of Clinical Psychology, 4, 1–32 Retrieved from: http://www.ncbi.nlm.nih.gov/pubmed/18509902.
- Shoaib, M., Bosch, S., Scholten, H., Havinga, P. J., & Incel, O. D. (2015). Towards detection of bad habits by fusing smartphone and smartwatch sensors. 2015 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops) (pp. 591–596). St. Louis: IEEE.Google Scholar
- Siegler, A., Mouhanna, F., Giler, R., McCallister, S., Yeung, H., Jones, J., … Sullivan, P. S. (2018). Distribution of active PrEP prescriptions and the PrEP-to-need ratio, US, Q2 2017. Paper presented at the conference on retroviruses and opportunistic infections (CROI), Boston, MA.Google Scholar
- Smyth, J. M., & Heron, K. E. (2016). Is providing mobile interventions" just-in-time" helpful? An experimental proof of concept study of just-in-time intervention for stress management. Paper presented at IEEE Wireless Health 2016 (pp. 1–7). Retrieved from: https://sites.psu.edu/shadelab/files/2016/11/Smyth_Heron_2016_JIT_IEEE-1vleki4.pdf.
- Sobell, L. C., & Sobell, M. B. (1992). Timeline follow-back measuring alcohol consumption (pp. 41-72): Springer.Google Scholar
- Spruijt-Metz, D., Hekler, E., Saranummi, N., Intille, S., Korhonen, I., Nilsen, W., et al. (2015). Building new computational models to support health behavior change and maintenance: new opportunities in behavioral research. Translational Behavioral Medicine, 5, 335–346.CrossRefPubMedPubMedCentralGoogle Scholar
- Stone, A. A., & Shiffman, S. (1994). Ecological momentary assessment (EMA) in behavorial medicine. Annals of Behavioral Medicine, 16, 199–202.Google Scholar
- Swendeman, D., Ramanathan, N., Baetscher, L., Medich, M., Scheffler, A., Comulada, W. S., & Estrin, D. (2015). Smartphone self-monitoring to support self-management among people living with HIV: perceived benefits and theory of change from a mixed-methods, randomized pilot study. Journal of Acquired Immune Deficiency Syndromes (JAIDS), 69, S80–S91.Google Scholar
- US Public Health Service. (2018). Preexposure prophylaxis for the prevention of HIV infection in the United States - 2017 update. New York: US Department of Health and Human Services.Google Scholar
- Wray, T. B., Merrill, J., & Monti, P. M. (2015). Using ecological momentary assessment (EMA) to assess situation-level risk factors for heavy drinking and alcohol-related consequences. Alcohol Research & Health, 36, 19–27.Google Scholar
- Wray, T. B., Adia, A. C., Pérez, A. E., Simpanen, E. M., Woods, L.-A., Celio, M. A., & Monti, P. M. (2018). Timeline: A web application for assessing the timing and details of health behaviors. The American Journal of Drug and Alcohol Abuse, 45, 141–150. https://doi.org/10.1080/00952990.2018.1469138.
- Wray, T. B., Celio, M. A., Pérez, A. E., DiGuiseppi, G. T., Carr, D. J., Woods, L. A., & Monti, P. M. (2019). Causal effects of alcohol intoxication on sexual risk intentions and condom negotiation skills among high-risk men who have sex with men (MSM). AIDS and Behavior, 23, 161–174.Google Scholar
- Yang, C., Linas, B., Kirk, G., Bollinger, R., Chang, L., Chander, G., … & Latkin, C. (2015). Feasibility and acceptability of smartphone-based ecological momentary assessment of alcohol use among African American men who have sex with men in Baltimore. JMIR mHealth and uHealth, 3, e67.Google Scholar