An artificial intelligence–enabled ECG algorithm for comprehensive ECG interpretation: Can it pass the ‘Turing test’?

Abstract

OBJECTIVE To develop an artificial intelligence (AI)-enabled electrocardiogram (ECG) algorithm capable of comprehensive, humanlike ECG interpretation and compare its diagnostic performance against conventional ECG interpretation methods. METHODSWe developed a novel AI-enabled ECG (AI-ECG) algorithm capable of complete 12-lead ECG interpretation. It was trained on nearly 2.5 million standard 12-lead ECGs from over 720,000 adult patients obtained at the Mayo Clinic ECG laboratory between 2007 and 2017. We then compared the need for human over-reading edits of the reports generated by the Marquette 12SL automated computer program, AI-ECG algorithm, and final clinical interpretations on 500 randomly selected ECGs from 500 patients. In a blinded fashion, 3 cardiac electrophysiologists adjudicated each interpretation as (1) ideal (ie, no changes needed), (2) acceptable (ie, minor edits needed), or (3) unacceptable (ie, major edits needed).RESULTS Cardiologists determined that on average 202 (13.5%), 123 (8.2%), and 90 (6.0%) of the interpretations required major edits from the computer program, AI-ECG algorithm, and final clinical interpretations, respectively. They considered 958 (63.9%), 1058 (70.5%), and 1118 (74.5%) interpretations as ideal from the computer program, AI-ECG algorithm, and final clinical interpretations, respectively. They considered 340 (22.7%), 319 (21.3%), and 292 (19.5%) interpretations as acceptable from the computer program, AI-ECG algorithm, and final clinical interpretations, respectively.CONCLUSION An AI-ECG algorithm outperforms an existing standard automated computer program and better approximates expert over-read for comprehensive 12-lead ECG interpretation.

Golden Standard or Obsolete Method? Review of ECG Applications in Clinical and Experimental Context

“…Briefly, DL neural network models include specific layers for automatic extraction of feature maps from the input signal and layers providing the output prediction (see Figure 4B ). Thus, DL models can be considered “all-in-one” solutions, analyzing data in a broad context and outperforming most of existing approaches in terms of time and computational requirements, as well as achieved results (e.g., Goodfellow et al, 2016 ; Kashou et al, 2021 ; Ravì et al, 2017 ). Reduced computational demand of the DL decision-making is caused by both the absence of pre-processing steps and fast interpretation of new data once the model is trained.…”

Automated ECG Interpretation—A Brief History from High Expectations to Deepest Networks

“…Publications on the use of AI for 12 lead ECG interpretation are already appearing [60,61]. A recent study by Kashou et al states that their AI-based approach 'outperforms an existing standard automated computer program' and also 'better approximates expert over-read for comprehensive 12 lead ECG interpretation' [62]. Rhythm analysis was included.…”

“…The foregoing suggests that an AI-based system for a complete interpretation of a 12 lead ECG cannot inherently improve on a 12 lead interpretation by cardiologists. Others might disagree with this view based, for example, on one recent report [62]. The same criticism applies to more conventional approaches to automated ECG analysis as shown in the CSE study [35].…”

“…The same could not be said of an AI-based system with identical data input to the logic to check on 'repeatability'. This may explain why cardiologists may not appear to give a performance which is equal to that of the AI-based approach [62].…”

ECG Interpretation: Clinical Relevance, Challenges, and Advances

“…In recent years, the use of AI-enabled ECG (AI-ECG) algorithms for various risk stratification, diagnostic evaluation, and clinical interpretation have emerged. Researchers have shown some algorithms to be capable of rhythm identification [4] and even perform comprehensive 12-lead ECG interpretation [5]. In fact, the accuracy appears to be better than that of the currently implemented ECG software [5].…”