Alex: Design, development and evaluation of a digital health assistant for paediatric asthma
Research questions/goals: Poor compliance with medication regimens and insufficient disease monitoring have been shown to be the main factors contributing to deficient disease control in children and adolescents suffering from asthma. Digital health assistants (DHAs) delivered by interactive websites or mobile apps are a potentially suitable tool for remote monitoring of patients. However, current DHA approaches lack sufficient motivation strategies, resulting in the patients’ disengagement. Moreover, current approaches to remote asthma monitoring require regular active patient participation during disease-state-related measurements, which places an additional burden. Our aim is to improve asthma control in children and adolescents by designing and developing a novel, age‐specific, smartphone‐based DHA called “Alex”, capable of regular and sustained remote disease monitoring and patient coaching. Alex will generate age-specific incentives and rewards, ensuring the patients’ long-term engagement with the monitoring schedule. Furthermore, we will test and validate digital ways of assessing the patient’s state than can be measured passively, i.e., not requiring the patient’s active participation. Our platform will also allow for healthcare practitioners to assess their patients’ disease status virtually in real time, and thereby provide therapeutic interventions and/or recommendations in a timely fashion. In particular, in an unprecedented manner, pediatric pulmonologist will be able to assess their patients’ disease state based on the analysis of lung function fluctuations, i.e., taking into account the overall disease dynamics, as opposed to the commonly used approach of only looking at a momentary “snapshot” of the patient’s condition. Following development and implementation of Alex, the project also aims to assess the efficacy of our approach via a randomized controlled trial. Additionally, we will use the data generated in this trial to train machine learning models designed to either predict disease progression, or to generate therapeutic recommendations to be used as an assistance for healthcare providers.
Current main results and/or publications: This four-year project will officially start in December 2022. Our progress will be reported here. Stay tuned!
