During Suicide Prevention Awareness month, public health organizations across the country are launching initiatives focused on raising awareness, combatting stigma, and improving treatment related to mental health issues. Addressing mental health at the community level is, of course, a complex challenge that requires collaboration across disciplines. Yet more and more organizations are recognizing that data and analytics can play a significant part in this effort. Voyatek works closely with public health departments, including NYC Department of Health and Mental Hygiene and Montana Department of Public Health and Human Services helping them leverage data on mental health prevalence and treatment to raise awareness and improve community outcomes. Public health data can help organizations achieve these goals in a number of ways. Let’s examine a few:

Historically, surveys have been the primary tool for understanding population-level health status and outcomes. Surveys are useful because they collect self-reported behavior data that isn’t always captured or included in the information systems that store data about health care services. However, advances in enterprise data management and a growing understanding of the importance of cross-agency data sharing are helping public health officials break down silos and combine survey data with other rich data sources. By combing survey and non-survey data, researchers and health professionals can uncover patterns that are typically more difficult to detect. For example, one study published in the American Journal of Psychiatry concluded that prediction models incorporating both health record information and self-reported survey data substantially outperformed existing suicide risk prediction tools.

Sharing data at scale and providing tools for non-technical users to interpret it was once a years-long, prohibitively expensive endeavor. Today, advances in technology have made it easier than ever before for public health agencies to share data with the public. With cloud technology, common data standards, and self-service analytics and visualization tools, public health agencies can quickly stand up lower-cost, browser-based public health data portals. These solutions allow practitioners, policymakers, and the general public with on-demand access to a range of public health measures on mental health in their communities.

Machine learning and artificial intelligence have revolutionized how health professionals understand mental health trends in their communities. Researchers can now combine vast volumes of data from many different sources–such as patient records, surveys, wearable devices, and social media posts—and leverage machine learning to uncover mental health patterns that might otherwise go unnoticed. Additionally, algorithms can provide insights into how certain mental health conditions affect specific populations, and can help healthcare providers identify locations or demographics in need of suport. One study applied natural language processing to 1.3 million crisis hotline conversations to better understand patterns in youth mental health during the pandemic and help train crisis hotline volunteers on the most effective interventions.  With the use of AI, public health professionals and their service-delivery partners can better understand the underlying causes for mental health issues in their communities and measure the outcomes of specific interventions, which will help them develop more effective strategies to prevent or treat mental health conditions.