Chronic Obstructive Pulmonary Disease (COPD) is a progressive chronic disease, predicted to become the third leading cause of death by 2030. COPD patients are at risk of sudden and acute worsening of symptoms, reducing the patient's quality of life and leading to hospitalization. We present the results of a pilot study with 18 COPD patients using an m-Health system, based on a tablet computer and pulse oximeter, for a period of six months. For prioritizing patients for clinical review, a data-driven approach has been developed which generates personalized alerts using the electronic symptom diary, pulse rate, blood oxygen saturation, and respiratory rate derived from oximetry data. This work examines the advantages of multivariate novelty detection over univariate approaches and shows the benefit of including respiratory rate as a predictor.