Automatic detection of ECG electrode misplacement: a tale of two algorithms

Abstract

Artifacts in an electrocardiogram (ECG) due to electrode misplacement can lead to wrong diagnoses. Various computer methods have been developed for automatic detection of electrode misplacement. Here we reviewed and compared the performance of two algorithms with the highest accuracies on several databases from PhysioNet. These algorithms were implemented into four models. For clean ECG records with clearly distinguishable waves, the best model produced excellent accuracies (> = 98.4%) for all misplacements except the LA/LL interchange (87.4%). However, the accuracies were significantly lower for records with noise and arrhythmias. Moreover, when the algorithms were tested on a database that was independent from the training database, the accuracies may be poor. For the worst scenario, the best accuracies for different types of misplacements ranged from 36.1% to 78.4%. A large number of ECGs of various qualities and pathological conditions are collected every day. To improve the quality of health care, the results of this paper call for more robust and accurate algorithms for automatic detection of electrode misplacement, which should be developed and tested using a database of extensive ECG records.

Implementation of Artifact Detection in Critical Care: A Methodological Review

“…This increases false alarm rates in monitors [36][37][38], which leads to staff desensitization [30,39,40]. Clinicians cannot rely on analysing artifact-laden monitor data [41], which in the past has resulted in incorrect diagnoses [33,42]; unnecessary therapy; surgery and iatrogenic diseases [32]. Independent research groups have developed a variety of post processing techniques to address the problem of artifacts in OEM monitor data.…”

Detection of Unicolor ECG Electrode Reversals in Standard 12-Lead ECG

“…Numerous approaches were proposed for the automated detection of limb ECG electrode reversals: -Left arm (L) and left leg (F) reversal was examined by P wave amplitude [2] and QRS, P-axes [3]; -Right arm (R) and right leg (N) reversal was detected by observing flat line ECG in lead II [4]; -Various L/R/F/N reversals were detected using the direction of P-loop inscription and/or frontal P-axis [5]; frontal QRS-axis [6]; lead reconstruction using redundancy of information in 8 independent leads [7]; morphological measurements of QRS, P-wave amplitudes, frontal axis and clockwise vector loop rotation, combined with redundancy features [8]; maximal and minimal QRS, T-wave voltages in leads I, II, III [9]; correlation coefficients, comparing limb leads to V6 [10]; gathering the features described in [3] and [7] for a more robust and accurate performance [11].…”

Integration of Artifact Detection in Clinical Decision Support Systems

“…samples. Table IV shows Table V shows that the best achievable result (Sn, FAR) = (80,39) is obtained when MedWW = 10 and CEDDT = 10, where Sn ≥ 80%. If Sn is only required to be ≥ 75%, then the best achievable performance becomes (Sn, FAR) = (75,32) when MedWW = 15 and CEDDT = 12, as shown in Table VI.…”

“…Clinicians cannot rely on analyzing artifact-laden data [79]. This has previously resulted in incorrect diagnoses [77,80]; unnecessary therapy; surgery and iatrogenic diseases [76]. Independent research groups have developed a variety of post processing techniques to address the problem of artifacts in OEM monitor data.…”

“…Figures Figure 4-8 Figure 4-9 show the linear and radar plots of Sn and FAR for this experiment respectively. (80,50) with CEDDT = 12. With Sn ≥ 75%, the best achievable result for (Sn, FAR) = (78,47) with CEDDT = 20.…”