Forecasting depression in bipolar disorder.

Bipolar disorder is characterized by recurrent episodes of mania and depression and affects about 1% of the adult population. The condition can have a major impact on an individual's ability to function and is associated with a long-term risk of suicide. In this paper, we report on the use of self-rated mood data to forecast the next week's depression ratings. The data used in the study have been collected using SMS text messaging and comprises one time series of approximately weekly mood ratings for each patient. We find a wide variation between series: some exhibit a large change in mean over the monitored period and there is a variation in correlation structure. Almost half of the time series are forecast better by unconditional mean than by persistence. Two methods are employed for forecasting: exponential smoothing and Gaussian process regression. Neither approach gives an improvement over a persistence baseline. We conclude that the depression time series from patients with bipolar disorder are very heterogeneous and that this constrains the accuracy of automated mood forecasting across the set of patients. However, the dataset is a valuable resource and work remains to be done that might result in clinically useful information and tools.