Prediction of heart failure hospitalizations with wearable activity monitors

activity monitor;heart failure;metrics;physical activity count;fragmentation;entropy;temporal analysis;not listed

Li, XiminZipunnikov, Vadim ;

Johns Hopkins University

关键词: activity monitor;    heart failure;    metrics;    physical activity count;    fragmentation;    entropy;    temporal analysis;    not listed;   

Others  :  https://jscholarship.library.jhu.edu/bitstream/handle/1774.2/37239/Appendix.pdf?sequence=2&isAllowed=y

瑞士|英语

来源: JOHNS HOPKINS DSpace Repository

【 摘 要 】

Sixty one patients of the Advanced Cardiac Care Center of Columbia University Medical Center diagnosed with congestive heart failure (CHF) wore Actical, an accelerometer device that continuously recorded physical activity over a seven to nine months period. Over the course of the study, twenty two subjects were either hospitalized or had an emergency room visit. The goal of this thesis is to explore whether ambulatory monitoring of physical activity with accelerometers predicts clinically relevant adverse events in CHF patients. We introduce novel actigraphy summaries and identify prevalent patterns that explain roughly 60 of all CHF related episodes. These patterns can be detected as early as two months to three weeks prior to an episode.