The role of computerized diagnostic proposals in the interpretation of the 12-lead electrocardiogram by cardiology and non-cardiology fellows

Novotný, Tomáš; Bond, Raymond; Andršová, Irena; Koc, Lumír; Šišáková, Martina; Finlay, Dewar; Guldenring, Daniel; Špinar, Jindřich; Malik, Marek

doi:10.1016/j.ijmedinf.2017.02.007

Cited by 22 publications

(15 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these findings have been limited to single-lead ECGs 12 or fall short in providing complete 12-lead ECG interpretation. 13,14 Our AI-ECG algorithm is capable of comprehensive 12-lead ECG interpretation consistent with those provided by board-certified cardiologists on nearly 2.5 million standard 12-lead ECGs from over 720,000 adult patients. In recent work, we demonstrated that an AI-ECG algorithm could generate 66 structured diagnostic codes from a spectrum of uncommon and complex to normal ECG features (eg, primary and secondary rhythms, axis deviation, chamber enlargement/hypertrophy, atrioventricular and intraventricular conduction delay, myocardial ischemia, waveform abnormalities, clinical disorders, and pacemaker activity).…”

Section: Clinical Valuementioning

confidence: 82%

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

Kashou

Mulpuru

Deshmukh

et al. 2021

Cardiovascular Digital Health Journal

View full text Add to dashboard Cite

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.

show abstract

Section: Clinical Valuementioning

confidence: 82%

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

Kashou

Mulpuru

Deshmukh

et al. 2021

Cardiovascular Digital Health Journal

View full text Add to dashboard Cite

show abstract

“…It helps the experienced over-reader inadvertently avoid missing diagnoses and it improves the less experienced reader's performance. This was nicely documented by Novotny, et al [6], who demonstrated that diagnostic prompting improved interpretive accuracy substantially by both cardiology and non-cardiology fellows. For example, when multiple correct and incorrect diagnostic statements were presented, the over-readers were able to distinguish well between correct and incorrect statements, and they improved their diagnostic accuracy over their interpretations without availability of automated diagnostic statements by approximately 30%…”

Section: Automated Ecg Interpretation Is Beneficial Even In Major Hosmentioning

confidence: 67%

“…They also showed that the general practitioner using prompting from interpretive software further improved his/her detection of AF (92% sensitivity and 91% specificity). 6 Reader prompting is one of the greatest benefits of algorithmic interpretation. It helps the experienced over-reader inadvertently avoid missing diagnoses and it improves the less experienced reader's performance.…”

Section: Automated Ecg Interpretation Is Beneficial Even In Major Hosmentioning

confidence: 99%

Debatable issues in automated ECG reporting

Macfarlane

Mason

Kligfield

et al. 2017

Journal of Electrocardiology

View full text Add to dashboard Cite

2 Highlights Four areas of topical interest in automated ECG reporting were debated at the 2017 International Society of Computerized Electrocardiology (ISCE) conference. These included the value of automated ECG interpretation, real time ambulatory ECG monitoring, ECG imaging and single channel ECG rhythm interpretation  Advantages and disadvantages were elaborated in each of the four topics.3 AbstractAlthough automated ECG analysis has been available for many years, there are some aspects which require to be re-assessed with respect to their value while newer techniques which are worthy of review are beginning to find their way into routine use. At the annual International Society of Computerized Electrocardiology conference held in April, 2017, four areas in particular were debated. These were a) automated 12 lead resting ECG analysis; b) real time out of hospital ECG monitoring; c) ECG imaging; and d) single channel ECG rhythm interpretation.One speaker presented the positive aspects of each technique and another outlined the more negative aspects. Debate ensued. There were many positives set out for each technique but equally, more negative features were not in short supply, particularly for out of hospital ECG monitoring.4

show abstract

“…When they are accurate, they have been shown to increase the accuracy of physician overread, but when inaccurate, they have been shown to lead physicians astray. This has been shown for cardiology fellows [15], for emergency physicians [16], and also for fully trained cardiologists, for whom the presence of an automated interpretation resulted in lower accuracy because automated errors were not corrected [17].…”

Section: Discussionmentioning

confidence: 94%

A deep neural network for 12-lead electrocardiogram interpretation outperforms a conventional algorithm, and its physician overread, in the diagnosis of atrial fibrillation

Smith

Rapin²,

Li³

et al. 2019

IJC Heart & Vasculature

View full text Add to dashboard Cite

BackgroundAutomated electrocardiogram (ECG) interpretations may be erroneous, and lead to erroneous overreads, including for atrial fibrillation (AF). We compared the accuracy of the first version of a new deep neural network 12-Lead ECG algorithm (Cardiologs®) to the conventional Veritas algorithm in interpretation of AF.Methods24,123 consecutive 12-lead ECGs recorded over 6 months were interpreted by 1) the Veritas® algorithm, 2) physicians who overread Veritas® (Veritas® + physician), and 3) Cardiologs® algorithm. We randomly selected 500 out of 858 ECGs with a diagnosis of AF according to either algorithm, then compared the algorithms' interpretations, and Veritas® + physician, with expert interpretation. To assess sensitivity for AF, we analyzed a separate database of 1473 randomly selected ECGs interpreted by both algorithms and by blinded experts.ResultsAmong the 500 ECGs selected, 399 had a final classification of AF; 101 (20.2%) had ≥1 false positive automated interpretation. Accuracy of Cardiologs® (91.2%; CI: 82.4–94.4) was higher than Veritas® (80.2%; CI: 76.5–83.5) (p < 0.0001), and equal to Veritas® + physician (90.0%, CI:87.1–92.3) (p = 0.12). When Veritas® was incorrect, accuracy of Veritas® + physician was only 62% (CI 52–71); among those ECGs, Cardiologs® accuracy was 90% (CI: 82–94; p < 0.0001). The second database had 39 AF cases; sensitivity was 92% vs. 87% (p = 0.46) and specificity was 99.5% vs. 98.7% (p = 0.03) for Cardiologs® and Veritas® respectively.ConclusionCardiologs® 12-lead ECG algorithm improves the interpretation of atrial fibrillation.

show abstract

The role of computerized diagnostic proposals in the interpretation of the 12-lead electrocardiogram by cardiology and non-cardiology fellows

Cited by 22 publications

References 13 publications

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

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

Debatable issues in automated ECG reporting

A deep neural network for 12-lead electrocardiogram interpretation outperforms a conventional algorithm, and its physician overread, in the diagnosis of atrial fibrillation

Contact Info

Product

Resources

About