Selection of self-reported data in our study cohort, finally containing 2,374 patients. Number of retained self-reports after each filtering criteria given in box. In this study, some of the reports were cleaned and retrospectively analysed to train prognostic models. To this end, only those reports in which the patient did not report an exacerbation event were used (n = 49,122).ⁱⁱ We then randomly assigned reports from 19.2% (13,111/68,139) of the patients to a holdout test set.