UNSTRUCTURED
Acute exacerbations of chronic obstructive pulmonary disease (AECOPD) are associated with high mortality, morbidity and poor quality of life and constitute a substantial burden to patients and healthcare systems. New approaches to prevent or reduce the severity of AECOPD are urgently needed. Internationally, this has prompted increased interest in the potential of remote patient monitoring (RPM) and digital medicine. RPM refers to the direct transmission of patient-reported outcomes, physiological, and functional data including heart rate, weight, blood pressure, oxygen saturation, physical activity, and lung function (spirometry) directly to healthcare professionals through automation, web-based data entry or phone-based data entry. Machine learning has the potential to enhance RPM in COPD by increasing the accuracy and precision of AECOPD prediction systems. Here we conduct a dual systematic review of RPM randomised controlled trials (RCT) in AECOPD and machine learning studies combined with RPM to predict AECOPD. We review the evidence and concepts behind RPM and machine learning and go on to discuss the strengths, limitations, and clinical utility of available systems. We have generated a list of recommendations needed to deliver patient and healthcare system benefits. RPM, and in particular the incorporation of machine learning appears to have the potential to improve the predictive capabilities of RPM for AECOPD significantly. Advances in RPM and machine learning require a greater focus on patient co-design, identification and clinical validation of the optimal physiological, behavioural and environmental sensors. This focus should ultimately result in randomised controlled trials set against usual care to provide an evidence base for their safety, efficacy and cost-effectiveness which could, once present transform outcomes through the widespread implementation of new approaches to care.