Machine learning techniques for detecting electrode misplacement and interchanges when recording ECGs: A systematic review and meta-analysis

Abstract

Introduction: Electrode misplacement and interchange errors are known problems when recording the 12-lead electrocardiogram (ECG). Automatic detection of these errors could play an important role for improving clinical decision making and outcomes in cardiac care. The objectives of this systematic review and meta-analysis is to 1) study the impact of electrode misplacement on ECG signals and ECG interpretation, 2) to determine the most challenging electrode misplacements to detect using machine learning (ML), 3) to analyse the ML performance of algorithms that detect electrode misplacement or interchange according to sensitivity and specificity and 4) to identify the most commonly used ML technique for detecting electrode misplacement/interchange. This review analysed the current literature regarding electrode misplacement/interchange recognition accuracy using machine learning techniques. Method: A search of three online databases including IEEE, PubMed and ScienceDirect identified 228 articles, while 3 articles were included from additional sources from co-authors. According to the eligibility criteria, 14 articles were selected. The selected articles were considered for qualitative analysis and meta-analysis. Results: The articles showed the effect of lead interchange on ECG morphology and as a consequence on patient diagnoses. Statistical analysis of the included articles found that machine learning performance is high in detecting electrode misplacement/interchange except left arm/left leg interchange. Conclusion: This review emphasises the importance of detecting electrode misplacement detection in ECG diagnosis and the effects on decision making. Machine learning shows promise in detecting lead misplacement/interchange and highlights an opportunity for developing and operationalising deep learning algorithms such as convolutional neural network (CNN) to detect electrode misplacement/interchange.

Artificial intelligence and its impact on the domains of universal health coverage, health emergencies and health promotion: An overview of systematic reviews

“…2 . There is an intermediate group including diseases of the circulatory system (N = 9) [65] , [66] , [67] , [68] , [69] , [70] , [71] , [72] , [73] , diseases of the musculoskeletal system (N = 8) [74] , [75] , [76] , [77] , [78] , [79] , [80] , [81] , diseases of the digestive system (N = 7) [82] , [83] , [84] , [85] , [86] , [87] , [88] and the nervous system (N = 7) [89] , [90] , [91] , [92] , [93] , [94] , [95] . There are a few reviews focused on other categories such as diseases of respiratory system (N = 4) [96] , [97] , [98] , [99] , visual system (N = 3) [100] , [101] , [102] and the other chapters include only one or two systematic reviews [103] , [104] , [105] , [106] , [107] , [108] , [109] , [110] , [111] , [112] , [113] , [114] , [115] , [116] .…”

“…The effective management of public health systems is a multifactorial responsibility with a wide range of actors and effects. Like any other medical act, the provision of care services at a populational level involves the screening and diagnosis of certain conditions, the treatment and the follow-up of those conditions [71] , [95] , [115] . In this context, the use of AI has demonstrated that it can provide powerful tools to support and inform decisions and even automate tasks to aid clinicians, epidemiologists and policy makers on the most efficient strategies to promote health at a population level [137] , including the current COVID-19 pandemic [125] .…”

Current trends and opportunities in the methodology of electrodermal activity measurement

“…In addition to the potential for improving insight and trustworthiness of developed models, these methods may also help determine which signal features are important and explain patterns that are uncovered by the machine learning process. While these methods have demonstrated promising results in the aid of ECG classification (Rjoob K et al, 2020;Jo YY et al, 2021), we could not find any published works on explainable AI methods applied on EDA data at the time of this review.…”

Wireless IoT Networks Security and Lightweight Encryption Schemes- Survey

“…In general, these detection algorithms have had high results for peripheral electrodes; however, inversion detection of precordial electrodes is less accurate, with values ranging from sensitivities of 20% to 99% [11]. The first study that used lead correlation to detect electrode exchanges automatically is that of Jekova [12], which revealed a high correlation between adjacent precordial electrodes that goes in descending order as one moves away towards the other electrodes.…”

“…Modern methods of interchange detection are based on the use of Machine Learning, as is the use of Decision Trees, Artificial Neural Networks, Amplitude Thresholds, and Support Vector Machines [11]. These methods possess variable and inconsistent Sensitivities (Se) and Specificities (Sp), finding Se = 44.…”