000097056 001__ 97056
000097056 005__ 20210820090352.0
000097056 0247_ $$2doi$$a10.1088/1361-6579/ab553a
000097056 0248_ $$2sideral$$a117013
000097056 037__ $$aART-2019-117013
000097056 041__ $$aeng
000097056 100__ $$aLlamedo Mariano
000097056 245__ $$aAssessment of automatic strategies for combining QRS detections by multiple algorithms in multiple leads
000097056 260__ $$c2019
000097056 5060_ $$aAccess copy available to the general public$$fUnrestricted
000097056 5203_ $$aObjective: To develop and evaluate an algorithm for the selection of the best-performing QRS detections from multiple algorithms and ECG leads. Approach: The detections produced by several publicly available single-lead QRS detectors are segmented in 20 s consecutive windows; then a statistical model is trained to estimate a quality metric that is used to rank each 20 s segment of detections. The model describes each heartbeat in terms of six features calculated from the RR interval series, and one feature proportional to the number of heartbeats detected in other leads in a neighborhood of the current heartbeat. With the highest ranked segments, we defined several lead selection strategies (LSS) that were evaluated in a set of 1754 ECG recordings from 14 ECG databases. The LSS proposed were compared with simple strategies such as selecting lead II or the first lead available in a recording. The performance was calculated in terms of the average sensitivity, positive predictive value, and F score. Main results: The best-performing LSS, based on wavedet algorithm, achieved an F score of 98.7, with sensitivity S¿¿=¿¿99.2 and positive predictive value P¿¿=¿¿98.3. The F score for the simpler strategy using the same algorithm was 92.7. The LSS studied in this work have been made available in an open-source toolbox to ease the reproducibility and result comparison. Significance: The results suggest that the use of LSS is convenient for purposes of selecting the best heartbeat locations among those provided by different detectors in different leads, obtaining better results than any of the algorithms individually.
000097056 536__ $$9info:eu-repo/grantAgreement/ES/MINECO/TEC2016-75458-R$$9info:eu-repo/grantAgreement/ES/DGA-FEDER/T39-17R-BSICoS
000097056 540__ $$9info:eu-repo/semantics/openAccess$$aby-nc-nd$$uhttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
000097056 590__ $$a2.309$$b2019
000097056 591__ $$aBIOPHYSICS$$b39 / 71 = 0.549$$c2019$$dQ3$$eT2
000097056 591__ $$aPHYSIOLOGY$$b43 / 81 = 0.531$$c2019$$dQ3$$eT2
000097056 591__ $$aENGINEERING, BIOMEDICAL$$b49 / 87 = 0.563$$c2019$$dQ3$$eT2
000097056 592__ $$a0.702$$b2019
000097056 593__ $$aBiomedical Engineering$$c2019$$dQ2
000097056 593__ $$aBiophysics$$c2019$$dQ2
000097056 593__ $$aPhysiology$$c2019$$dQ3
000097056 593__ $$aPhysiology (medical)$$c2019$$dQ3
000097056 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion
000097056 700__ $$0(orcid)0000-0002-7503-3339$$aMartínez Cortés, Juan Pablo$$uUniversidad de Zaragoza
000097056 7102_ $$15008$$2800$$aUniversidad de Zaragoza$$bDpto. Ingeniería Electrón.Com.$$cÁrea Teoría Señal y Comunicac.
000097056 773__ $$g40 (2019), 114002  [11 pp.]$$pPhysiol. meas.$$tPHYSIOLOGICAL MEASUREMENT$$x0967-3334
000097056 8564_ $$s979103$$uhttps://zaguan.unizar.es/record/97056/files/texto_completo.pdf$$yPostprint
000097056 8564_ $$s344027$$uhttps://zaguan.unizar.es/record/97056/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint
000097056 909CO $$ooai:zaguan.unizar.es:97056$$particulos$$pdriver
000097056 951__ $$a2021-08-20-08:38:38
000097056 980__ $$aARTICLE