Show simple item record

dc.contributor.authorLee, Jinseok
dc.contributor.authorMcManus, David D.
dc.contributor.authorMerchant, Sneh
dc.contributor.authorChon, Ki H.
dc.date2022-08-11T08:09:24.000
dc.date.accessioned2022-08-23T16:29:18Z
dc.date.available2022-08-23T16:29:18Z
dc.date.issued2012-06-01
dc.date.submitted2013-01-02
dc.identifier.citation<p>Jinseok Lee; McManus, D.D.; Merchant, S.; Chon, K.H.; , "Automatic Motion and Noise Artifact Detection in Holter ECG Data Using Empirical Mode Decomposition and Statistical Approaches," <em>Biomedical Engineering, IEEE Transactions on</em> , vol.59, no.6, pp.1499-1506, June 2012<br />doi: 10.1109/TBME.2011.2175729 <a href="http://dx.doi.org/10.1109/TBME.2011.2175729" target="_blank">Link to article on publisher's site</a></p>
dc.identifier.issn0018-9294 (Linking)
dc.identifier.doi10.1109/TBME.2011.2175729
dc.identifier.pmid22086485
dc.identifier.urihttp://hdl.handle.net/20.500.14038/37216
dc.description.abstractWe present a real-time method for the detection of motion and noise (MN) artifacts, which frequently interferes with accurate rhythm assessment when ECG signals are collected from Holter monitors. Our MN artifact detection approach involves two stages. The first stage involves the use of the first-order intrinsic mode function (F-IMF) from the empirical mode decomposition to isolate the artifacts' dynamics as they are largely concentrated in the higher frequencies. The second stage of our approach uses three statistical measures on the F-IMF time series to look for characteristics of randomness and variability, which are hallmark signatures of MN artifacts: the Shannon entropy, mean, and variance. We then use the receiver-operator characteristics curve on Holter data from 15 healthy subjects to derive threshold values associated with these statistical measures to separate between the clean and MN artifacts' data segments. With threshold values derived from 15 training data sets, we tested our algorithms on 30 additional healthy subjects. Our results show that our algorithms are able to detect the presence of MN artifacts with sensitivity and specificity of 96.63% and 94.73%, respectively. In addition, when we applied our previously developed algorithm for atrial fibrillation (AF) detection on those segments that have been labeled to be free from MN artifacts, the specificity increased from 73.66% to 85.04% without loss of sensitivity (74.48%-74.62%) on six subjects diagnosed with AF. Finally, the computation time was less than 0.2 s using a MATLAB code, indicating that real-time application of the algorithms is possible for Holter monitoring.
dc.language.isoen_US
dc.relation<a href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=pubmed&cmd=Retrieve&list_uids=22086485&dopt=Abstract">Link to Article in PubMed</a>
dc.relation.urlhttp://dx.doi.org/10.1109/TBME.2011.2175729
dc.subject*Algorithms
dc.subject*Artifacts
dc.subjectAtrial Fibrillation
dc.subjectComputer Systems
dc.subjectDiagnosis, Computer-Assisted
dc.subjectElectrocardiography, Ambulatory
dc.subjectHumans
dc.subjectMotion
dc.subjectPattern Recognition, Automated
dc.subjectReproducibility of Results
dc.subjectSensitivity and Specificity
dc.subjectSignal-To-Noise Ratio
dc.subjectBiomedical Engineering and Bioengineering
dc.subjectCardiology
dc.titleAutomatic motion and noise artifact detection in Holter ECG data using empirical mode decomposition and statistical approaches
dc.typeJournal Article
dc.source.journaltitleIEEE transactions on bio-medical engineering
dc.source.volume59
dc.source.issue6
dc.identifier.legacycoverpagehttps://escholarship.umassmed.edu/meyers_pp/631
dc.identifier.contextkey3560236
html.description.abstract<p>We present a real-time method for the detection of motion and noise (MN) artifacts, which frequently interferes with accurate rhythm assessment when ECG signals are collected from Holter monitors. Our MN artifact detection approach involves two stages. The first stage involves the use of the first-order intrinsic mode function (F-IMF) from the empirical mode decomposition to isolate the artifacts' dynamics as they are largely concentrated in the higher frequencies. The second stage of our approach uses three statistical measures on the F-IMF time series to look for characteristics of randomness and variability, which are hallmark signatures of MN artifacts: the Shannon entropy, mean, and variance. We then use the receiver-operator characteristics curve on Holter data from 15 healthy subjects to derive threshold values associated with these statistical measures to separate between the clean and MN artifacts' data segments. With threshold values derived from 15 training data sets, we tested our algorithms on 30 additional healthy subjects. Our results show that our algorithms are able to detect the presence of MN artifacts with sensitivity and specificity of 96.63% and 94.73%, respectively. In addition, when we applied our previously developed algorithm for atrial fibrillation (AF) detection on those segments that have been labeled to be free from MN artifacts, the specificity increased from 73.66% to 85.04% without loss of sensitivity (74.48%-74.62%) on six subjects diagnosed with AF. Finally, the computation time was less than 0.2 s using a MATLAB code, indicating that real-time application of the algorithms is possible for Holter monitoring.</p>
dc.identifier.submissionpathmeyers_pp/631
dc.contributor.departmentMeyers Primary Care Institute
dc.contributor.departmentDepartment of Medicine, Division of Cardiovascular Medicine
dc.source.pages1499-506


This item appears in the following Collection(s)

Show simple item record