Methods and systems are described for providing output based on detection ofanxiety in a subject. Output is provided, dependent on an anxiety indicationthatrepresents a current or expected level of anxiety in the subject. Aphysiologicalsignal is received, representing physiological information from the subject. Acontext signal is also received. A user state detector determines a currentuserstate from a plurality of possible user states, based on the context signal.Aninteractive multiple model (IMM) filter is used to determine, using thephysiologicalsignal, a statistical prediction of anxiety in each of the possible userstates. Ananxiety detector is used to output the anxiety indication, based on aweighting ofthe statistical predictions using the determined current user state.
