Impact of Computer-Interpreted ECGs on the Accuracy of Healthcare Professionals

Kashou, Anthony H.; Noseworthy, Peter A.; Beckman, Thomas J.; Anavekar, Nandan S.; Cullen, Michael W.; Angstman, Kurt B.; Sandefur, Benjamin J.; Shapiro, Brian P.; Wiley, Brandon M.; Kates, Andrew M.; Huneycutt, David; Braisted, Andrew C.; Manoukian, Steven V.; Kerwin, Shannon; Young, Brian A.; Rowlandson, Ian; Beard, John; Baranchuk, Adrián; O’Brien, Kevin; Knohl, Stephen J.; May, Adam M.

doi:10.1016/j.cpcardiol.2023.101989

Cited by 4 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the lack of routine ECG screening (Van Der Werf et al, 2010) and reliance on manual measurements or automatic estimations by ECG analysis software, leads to unrecognized or misjudged diagnoses of LQT syndrome. Of note, a correct determination of the QT interval is not homogeneous, even by clinical experts (Kashou et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

A MATLAB algorithm to automatically estimate the QT interval and other ECG parameters and validation using a machine learning approach in congenital long-QT syndrome

Tzvi-Minker,

Dittmann,

Keck

et al. 2023

Preprint

View full text Add to dashboard Cite

ObjectiveWe present a novel MATLAB®algorithm designed to automatically estimate the QT interval as well as other parameters in digital electrocardiograms (ECGs) of patients with congenital long QT syndrome (LQTS).BackgroundNormal myocardial repolarization and the QT interval (i.e., the duration from the beginning of the QRS complex to the end of the T wave) are crucial markers for arrhythmogenesis, diagnosis and monitoring of LQTS. Manual measurement is time consuming and prone to physician’s variability and potential errors, necessitating an efficient and precise automated approach.MethodsOur algorithm implements Lepeschkin’s tangent method to determine the T-wave end and, subsequently, the QT interval. Based on this, the algorithm additionally calculates other ECG parameters and T-wave characteristics: T-peak to T-end, Twave area, T-wave duration and R-peak to T-peak amplitude ratio. The results are two-fold validated: (1) against expert measurement of the QT interval (QT_GS), as well as (2) against the algorithm results of the ECG machine used (QT_MU). Machine-learning methods are applied to investigate the accuracy of the estimated parameters by our algorithm in a cohort of 363 LQT1 patients.ResultsEstimation of T-wave end, the QT interval and other ECG parameters by our algorithm was successful in at least one of the three ECG channels in 362 out of 363 patients (99.7%). On the other hand, the ECG machine-based QT_MU algorithm could estimate the QT interval only in 245/363 (95.3%) of recordings. Individual differences between the developed MATLAB®algorithm in assessment of the QT and QT_GS were 10-fold more accurate to differences between QT_MU and QT_GS. Applying an optimizable Ensemble classifier on 30 ECG parameters extracted by our MATLAB®algorithm had an accuracy of 74.91% and area under the curve (AUC) of 0.82 in classifying LQTS patients with a prolonged QTc interval (upon QT_GS) from those with a normal QTc interval.ConclusionThe presented MATLAB®-based algorithm offers a robust and reliable approach to automatic QT interval estimation and QTc calculation in LQTS patients, potentially improving diagnostic precision and patient management. The results suggest that integrating further ECG parameters can assist with clinical assessment of LQTS patients. Future development will focus on integration into mainstream ECG devices and broadening the applicability to other arrhythmic conditions.

show abstract

Section: Introductionmentioning

confidence: 99%