Pre-Emptive Asthma Risk Notifications Based on Medicament Device Monitoring

A non-transitory computer readable storage medium storing instructions encoded thereon, that, when executed by a processor cause the processor to:

• access a set of historical rescue inhaler usage events for a patient, the set of historical rescue inhaler usage events recorded by a medicament device sensor removably attached to a rescue inhaler unit and configured to monitor medicament usage of the rescue inhaler unit, wherein a historical rescue inhaler usage event is recorded when the rescue inhaler unit dispenses a rescue medication to the patient;
• assign a label representing a known risk score to each historical rescue inhaler usage event of the accessed set;
• determine a patient-specific baseline risk threshold for the patient based on a subset of the accessed set of historical rescue inhaler usage events that occurred within a period of time preceding a current day, wherein the patient-specific baseline risk threshold is determined based on a value representing a percentage of the subset of the rescue inhaler usage events;
• create a training dataset comprising the accessed set of historical rescue inhaler usage events, the label assigned to each historical rescue inhaler usage event, and the patient-specific baseline risk threshold;
• train a machine-learned model to determine the risk score using the training dataset, wherein the machine-learned model is trained to determine the risk score based on a set of input value and the patient-specific baseline risk threshold.