apply a set of rules to first patient parameter data sensed by the insertable cardiac monitor for a first determination that sudden cardiac arrest of the patient is occurring or has occurred;

determine a confidence level of the first determination that sudden cardiac arrest of the patient is occurring or has occurred;

determine that one or more context criteria of the first determination are satisfied based at least in part on the determined confidence level being below a threshold;

change a mode of sensing a common patient parameter between the first patient parameter data and second patient parameter data in response to satisfaction of the one or more context criteria;

activate another device to sense at least one patient parameter that is not included in the first patient parameter data in response to satisfaction of the one or more context criteria, the another device being other than the insertable cardiac monitor, and the another device being in physical proximity and external to the patient; and

apply a machine learning model to the second patient parameter data for a second determination that sudden cardiac arrest of the patient is occurring or has occurred in response to the satisfaction of the one or more context criteria,

wherein the first patient parameter data and the second patient parameter data each include the common patient parameter, and the second patient parameter data further comprises the at least one patient parameter that is not included in the first patient parameter data.