All Times ET
Keywords: Wearables, biosensors, clustering, clinical trials, heart failure, machine learning
As human demographics continue to trend toward elderly, especially in advanced economies, the treatment of illness becomes more salient. Across many therapeutic areas, researchers examine potential treatments while incorporating novel technologies in an effort to prolong the years in which quality of life is achieved for patients around the world. In the area of cardiovascular disease, wearable and biosensor data is becoming increasingly used in order to compliment data traditionally collected from clinical trials. This paper discusses a case study from a recent clinical trial in which accelerometry data from wearable devices were analyzed using k-means clustering to aggregate the patients and examine their baseline clinical characteristics. Unique clinical phenotypes were identified within the patient clusters. Furthermore, the results of this clustering analysis of patients can be used to assess whether heterogeneous clinical subgroups of patients exist as well as further guide the clinical development program.