Warning signals for mental health problems in at-risk young adults may be informed by momentary emotions reported by the general population: A novel application of the principles of statistical process control

Abstract

Statistical process control (SPC) was recently introduced as a method for detecting person-specific warning signals for mental ill-health. Such warning signals occur when a person's repeatedly assessed emotions exceed a control limit. This control limit should in principle be based on the same person's emotions in a healthy period. As such data are often unavailable, this preregistered study investigated whether general population data can be used instead to estimate control limits. We used data from the HowNutsAreTheDutch study, in which adults from the general population (N = 746) rated their emotions three times a day for 1 month. Based on these data, we computed control limits according to the exponentially weighted moving average (EWMA) and Shewhart SPC methods. Next, we investigated how often young adults with versus without persistent mental health problems from the TRAILS TRANS-ID study (N = 100)–who rated their emotions daily for 6 months–reported scores beyond these general population-based control limits. Generally, warning signals occurred more often in young adults with persistent mental health problems compared to healthy young adults (p < 0.05). The predictive performance of SPC did not consistently improve when control limits were conditioned on individuals' age, sex, and depressive symptoms, nor differ between methods (EWMA vs. Shewhart). The different emotions that were monitored, however, affected SPC performance, so that for most settings, warning signs in feeling tired and upset were worse for detecting mental-ill health compared to warning signs in other emotions (e.g., feeling nervous, relaxed, etc.).  It follows that warning signs in individual's emotions can perhaps be monitored using relatively generic norms, derived from the general population, opening up new avenues for research and low-threshold clinical application.