Adaptive Pulse Segmentation and Artifact Detection in Photoplethysmography for Mobile Applications

Adaptive Pulse Segmentation and Artifact Detection in Photoplethysmography for Mobile Applications. Karlen, W., Ansermino, J., M., & Dumont, G., A. In Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pages 3131-4, 8, 2012.
abstract bibtex 7 downloads

Abstract—Pulse oximeters non-invasively measure heart rate and oxygen saturation and have great potential for predicting critical illness. The photoplethysmogram (PPG) recorded from pulse oximeters is often corrupted with artifacts that can render the vital signs obtained inaccurate. We present a novel real-time algorithm for segmentation of the PPG into pulses and classification of artifacts. The line segmentation algorithm operates in the time domain and extracts morphological fea- tures of the PPG. These features are characterized as lines which are classified as pulses and artifacts using adaptive thresholds. The algorithm was evaluated using the Complex System Laboratory (CSL) Benchmark data set. A sensitivity of 98.93% and positive predictive value of 96.68% have been obtained, which compares very favorably with the benchmark algorithm. The novel algorithm is currently being implemented into mobile phone pulse oximeters

@inproceedings{
 title = {Adaptive Pulse Segmentation and Artifact Detection in Photoplethysmography for Mobile Applications},
 type = {inproceedings},
 year = {2012},
 keywords = {Adaptive filtering,Biomedical signal classification,Signals and systems},
 pages = {3131-4},
 month = {8},
 city = {San Diego},
 id = {560145ab-7673-31e2-967a-cb9f54692441},
 created = {2021-11-19T08:04:10.548Z},
 file_attached = {true},
 profile_id = {6d353feb-efe4-367e-84a2-0815eb9ca878},
 last_modified = {2022-09-04T18:12:03.246Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Karlen2012},
 folder_uuids = {f1f67efc-95a7-4f1a-b181-c3670c667a34,d25bf112-04e3-4db2-9a05-346bfdcbbda2},
 private_publication = {false},
 abstract = {Abstract—Pulse oximeters non-invasively measure heart rate and oxygen saturation and have great potential for predicting critical illness. The photoplethysmogram (PPG) recorded from pulse oximeters is often corrupted with artifacts that can render the vital signs obtained inaccurate. We present a novel real-time algorithm for segmentation of the PPG into pulses and classification of artifacts. The line segmentation algorithm operates in the time domain and extracts morphological fea- tures of the PPG. These features are characterized as lines which are classified as pulses and artifacts using adaptive thresholds. The algorithm was evaluated using the Complex System Laboratory (CSL) Benchmark data set. A sensitivity of 98.93% and positive predictive value of 96.68% have been obtained, which compares very favorably with the benchmark algorithm. The novel algorithm is currently being implemented into mobile phone pulse oximeters},
 bibtype = {inproceedings},
 author = {Karlen, Walter and Ansermino, J Mark and Dumont, Guy A.},
 booktitle = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society}
}

Downloads: 7