Clinical rating scales are the golden standard for assessing the severity of depressive and manic symptoms in patients with bipolar disorder. However, they are time consuming and require a trained professional to be accurate. Automatic daily estimates of these ratings based on smartphone self-assessments can potentially help support disease monitoring and identify individuals with high risk of relapse to enable early intervention and treatment.
Smartphone-based self-assessment of symptoms in mental health settings has many advantages over traditional paper-based methods, including making data available for immediate and automatic analysis. Self-reported mood scores have previously been shown to correlate with clinical ratings of depression and mania, but in this new study, the self-assessments are used to produce estimates of clinical severity ratings, which can easily be interpreted by clinicians.
The statistical methods used in the analysis are designed to be transparent and includes uncertainty in the estimated values to improve interpretability of the results, which is crucial in a clinical setting. Furthermore, the estimated uncertainty intervals can be utilised to quantify the probability of observing alarmingly high ratings and thus be used to identify individuals with a high risk of relapse who are in need of assistance.
These promising results show that it is feasible to produce daily estimates of clinical severity ratings of depression and mania from smartphone-based self-assessments and the proposed methods can potentially be implemented to improve and automate continuous disease monitoring and treatment among out-patients with bipolar disorder.
You can view the full publication here