Benchmarking changepoint detection algorithms on cardiac time series

arXiv:2404.12408v1 Announce Type: new
Abstract: The pattern of state changes in a biomedical time series can be related to health or disease. This work presents a principled approach for selecting a changepoint detection algorithm for a specific task, such as disease classification. Eight key algorithms were compared, and the performance of each algorithm was evaluated as a function of temporal tolerance, noise, and abnormal conduction (ectopy) on realistic artificial cardiovascular time series data. All algorithms were applied to real data …

abstract algorithm algorithms arxiv benchmarking biomedical classification cs.lg detection disease health key performance series state stat.ml time series type work