Moneyball for Mental Health
Most of us are aware of the revolution in the generation of electronic information known as “big data.” It has been suggested that big data, along with hypothesis-free methods popularized by films such as Moneyball, will allow for an unprecedented growth of knowledge across disciplines, including epidemiology and preventive medicine. While we are a bit more circumspect in our expectations (there is no substitute for survey data in many cases), we do believe that electronic data collected for a fraction of the cost of survey data can work hand-in-hand with research derived from more traditional sources.
We consider our study, published this week in AJPM, to be a great example of the complementarity of big data approaches to mental health research. Previous work had identified mood symptoms as varying in many individuals suffering from depression. Using Google search as a proxy for changing patterns in mental illness, we sought to better understand seasonal patterns via web searches. While we found that patterns of search for mood were indeed linked with seasons, we were surprised to find that this seasonal pattern was replicated across a number of symptom/disease categories. For example, we saw strong seasonal patterns for schizophrenia, a disease for which symptom severity had not been closely associated with seasonal patterns. In contrast, tremendous attention had been given to seasonal birth patterns in schizophrenia. Why? Population surveys readily collect birth date without any added planning, concerns with sensitivity/reliability/validity, or additional budgeting. Since all theories are based on some data, our approach can provide the beginning data stream for theoretical development in mental health.
Clearly, these results are not intended to be definitive. Further research is needed, especially for understanding the link between search patterns and symptomatology. However, intuition suggests that these results are reflective of an important link between the seasons and mental health that goes beyond our previous understanding of these conditions. We believe that this kind of work can continue to cost effectively inform the field on a variety of vital health topics, and ours is just the beginning step.
— John Ayers, PhD, MA