Lay summary
Asthma attacks are a leading cause of morbidity and mortality. We have developed a risk prediction algorithm that can predict asthma attacks up to 7 days in advance using data from smartwatches, sending alerts to users when they are at risk of an attack. By receiving these early warnings, individuals can take preventive measures, such as adjusting their medication, to reduce the likelihood of a severe attack. We will co-design the digital asthma attack alert system with New Zealand communities and evaluate its use in a randomised controlled trial. Participants will be randomly assigned to the alert system or standard care and followed up for six months. We will assess the prediction system’s accuracy, feasibility, and impact on health outcomes. The alert system can facilitate proactive and more timely management of asthma potentially leading to reduced asthma-related morbidity, mortality, and healthcare costs, with improved quality of life for patients.