Fig. 5From: Exploring different research questions via complex multi-state models when using registry-based repeated prescriptions of antidepressants in women with breast cancer and a matched population comparison groupBidirectional multi-state structure approach. Probability of being in a medication cycle at time t since the start of the follow-up (a), Probability of being in a medication cycle (solid) or being in a medication discontinuation period (dash) as a function of time t since entering a medication cycle (b)Back to article page