Abstract: A method and system are described for detecting a hypoglycaemic state in a patient. The patient's heart rate is monitored to provide a heart-rate signal. A time-lagged signal is determined as the difference between the heart-rate signal and a time-lagged version of the heart rate-signal. The heart-rate signal is filtered with a low-pass filter to provide a heart-rate trend. An absolute difference between the heart-rate signal and the heart-rate trend is determined to provide an absolute-difference signal. A second time-lagged signal is determined as a difference between the absolute-difference signal and a time-lagged version of the absolute-difference signal. The occurrence of a hypoglycaemic condition is inferred dependent on the time-lagged signal and the second time-lagged signal.