Dataset Information

Interpretation of a 12-Lead Electrocardiogram by Medical Students: Quantitative Eye-Tracking Approach.

ABSTRACT:

Background

Accurate interpretation of a 12-lead electrocardiogram (ECG) demands high levels of skill and expertise. Early training in medical school plays an important role in building the ECG interpretation skill. Thus, understanding how medical students perform the task of interpretation is important for improving this skill.

Objective

We aimed to use eye tracking as a tool to research how eye fixation can be used to gain a deeper understanding of how medical students interpret ECGs.

Methods

In total, 16 medical students were recruited to interpret 10 different ECGs each. Their eye movements were recorded using an eye tracker. Fixation heatmaps of where the students looked were generated from the collected data set. Statistical analysis was conducted on the fixation count and duration using the Mann-Whitney U test and the Kruskal-Wallis test.

Results

The average percentage of correct interpretations was 55.63%, with an SD of 4.63%. After analyzing the average fixation duration, we found that medical students study the three lower leads (rhythm strips) the most using a top-down approach: lead II (mean=2727 ms, SD=456), followed by leads V1 (mean=1476 ms, SD=320) and V5 (mean=1301 ms, SD=236). We also found that medical students develop a personal system of interpretation that adapts to the nature and complexity of the diagnosis. In addition, we found that medical students consider some leads as their guiding point toward finding a hint leading to the correct interpretation.

Conclusions

The use of eye tracking successfully provides a quantitative explanation of how medical students learn to interpret a 12-lead ECG.

SUBMITTER: Tahri Sqalli M

PROVIDER: S-EPMC8554676 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ImportanceMillions of clinicians rely daily on automated preliminary electrocardiogram (ECG) interpretation. Critical comparisons of machine learning-based automated analysis against clinically accepted standards of care are lacking.ObjectiveTo use readily available 12-lead ECG data to train and apply an explainability technique to a convolutional neural network (CNN) that achieves high performance against clinical standards of care.Design, setting, and participantsThis cross-sectional study was conducted using data from January 1, 2003, to December 31, 2018. Data were obtained in a commonly available 12-lead ECG format from a single-center tertiary care institution. All patients aged 18 years or older who received ECGs at the University of California, San Francisco, were included, yielding a total of 365 009 patients. Data were analyzed from January 1, 2019, to March 2, 2021.ExposuresA CNN was trained to predict the presence of 38 diagnostic classes in 5 categories from 12-lead ECG data. A CNN explainability technique called LIME (Linear Interpretable Model-Agnostic Explanations) was used to visualize ECG segments contributing to CNN diagnoses.Main outcomes and measuresArea under the receiver operating characteristic curve (AUC), sensitivity, and specificity were calculated for the CNN in the holdout test data set against cardiologist clinical diagnoses. For a second validation, 3 electrophysiologists provided consensus committee diagnoses against which the CNN, cardiologist clinical diagnosis, and MUSE (GE Healthcare) automated analysis performance was compared using the F1 score; AUC, sensitivity, and specificity were also calculated for the CNN against the consensus committee.ResultsA total of 992 748 ECGs from 365 009 adult patients (mean [SD] age, 56.2 [17.6] years; 183 600 women [50.3%]; and 175 277 White patients [48.0%]) were included in the analysis. In 91 440 test data set ECGs, the CNN demonstrated an AUC of at least 0.960 for 32 of 38 classes (84.2%). Against the consensus committee diagnoses, the CNN had higher frequency-weighted mean F1 scores than both cardiologists and MUSE in all 5 categories (CNN frequency-weighted F1 score for rhythm, 0.812; conduction, 0.729; chamber diagnosis, 0.598; infarct, 0.674; and other diagnosis, 0.875). For 32 of 38 classes (84.2%), the CNN had AUCs of at least 0.910 and demonstrated comparable F1 scores and higher sensitivity than cardiologists, except for atrial fibrillation (CNN F1 score, 0.847 vs cardiologist F1 score, 0.881), junctional rhythm (0.526 vs 0.727), premature ventricular complex (0.786 vs 0.800), and Wolff-Parkinson-White (0.800 vs 0.842). Compared with MUSE, the CNN had higher F1 scores for all classes except supraventricular tachycardia (CNN F1 score, 0.696 vs MUSE F1 score, 0.714). The LIME technique highlighted physiologically relevant ECG segments.Conclusions and relevanceThe results of this cross-sectional study suggest that readily available ECG data can be used to train a CNN algorithm to achieve comparable performance to clinical cardiologists and exceed the performance of MUSE automated analysis for most diagnoses, with some exceptions. The LIME explainability technique applied to CNNs highlights physiologically relevant ECG segments that contribute to the CNN's diagnoses.

Project description:Abstract Background We have demonstrated that a neural network is able to predict a person’s age from the electrocardiogram (ECG) [artificial intelligence (AI) ECG age]. However, some discrepancies were observed between ECG-derived and chronological ages. We assessed whether the difference between AI ECG and chronological age (Age-Gap) represents biological ageing and predicts long-term outcomes. Methods and results We previously developed a convolutional neural network to predict chronological age from ECGs. In this study, we used the network to analyse standard digital 12-lead ECGs in a cohort of 25 144 subjects ≥30 years who had primary care outpatient visits from 1997 to 2003. Subjects with coronary artery disease, stroke, and atrial fibrillation were excluded. We tested whether Age-Gap was correlated with total and cardiovascular mortality. Of 25 144 subjects tested (54% females, 95% Caucasian) followed for 12.4 ± 5.3 years, the mean chronological age was 53.7 ± 11.6 years and ECG-derived age was 54.6 ± 11 years (R2 = 0.79, P < 0.0001). The mean Age-Gap was small at 0.88 ± 7.4 years. Compared to those whose ECG-derived age was within 1 standard deviation (SD) of their chronological age, patients with Age-Gap ≥1 SD had higher all-cause and cardiovascular disease (CVD) mortality. Conversely, subjects whose Age-Gap was ≤1 SD had lower all-cause and CVD mortality. Results were unchanged after adjusting for CVD risk factors and other survival influencing factors. Conclusion The difference between AI ECG and chronological age is an independent predictor of all-cause and cardiovascular mortality. Discrepancies between these possibly reflect disease independent biological ageing. Graphical Abstract In subjects without baseline cardiovascular disease, an older artificial intelligence (AI)-derived electrocardiogram (ECG) Age (AI-ECG age) compared to chronological age was associated with increased all-cause and cardiovascular mortality. Subjects, where the reverse was true, had lower mortality. Discrepancies between chronological age and ECG-derived age possibly reflect disease independent biological ageing.