Dataset Information

Atrial fibrillation detection in outpatient electrocardiogram monitoring: An algorithmic crowdsourcing approach

ABSTRACT:

Background

Atrial fibrillation (AFib) is the most common cardiac arrhythmia associated with stroke, blood clots, heart failure, coronary artery disease, and/or death. Multiple methods have been proposed for AFib detection, with varying performances, but no single approach appears to be optimal. We hypothesized that each state-of-the-art algorithm is appropriate for different subsets of patients and provides some independent information. Therefore, a set of suitably chosen algorithms, combined in a weighted voting framework, will provide a superior performance to any single algorithm.

Methods

We investigate and modify 38 state-of-the-art AFib classification algorithms for a single-lead ambulatory electrocardiogram (ECG) monitoring device. All algorithms are ranked using a random forest classifier and an expert-labeled training dataset of 2,532 recordings. The seven top-ranked algorithms are combined by using an optimized weighting approach.

Results

The proposed fusion algorithm, when validated on a separate test dataset consisting of 4,644 recordings, resulted in an area under the receiver operating characteristic (ROC) curve of 0.99. The sensitivity, specificity, positive-predictive-value (PPV), negative-predictive-value (NPV), and F1-score of the proposed algorithm were 0.93, 0.97, 0.87, 0.99, and 0.90, respectively, which were all superior to any single algorithm or any previously published.

Conclusion

This study demonstrates how a set of well-chosen independent algorithms and a voting mechanism to fuse the outputs of the algorithms, outperforms any single state-of-the-art algorithm for AFib detection. The proposed framework is a case study for the general notion of crowdsourcing between open-source algorithms in healthcare applications. The extension of this framework to similar applications may significantly save time, effort, and resources, by combining readily existing algorithms. It is also a step toward the democratization of artificial intelligence and its application in healthcare.

SUBMITTER: Bahrami Rad A

PROVIDER: S-EPMC8594842 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundIn high-dimensional data analysis, the complexity of predictive models can be reduced by selecting the most relevant features, which is crucial to reduce data noise and increase model accuracy and interpretability. Thus, in the field of clinical decision making, only the most relevant features from a set of medical descriptors should be considered when determining whether a patient is healthy or not. This statistical approach known as feature selection can be performed through regression or classification, in a supervised or unsupervised manner. Several feature selection approaches using different mathematical concepts have been described in the literature. In the field of classification, a new approach has recently been proposed that uses the [Formula: see text]-metric, an index measuring separability between different classes in heart rhythm characterization. The present study proposes a filter approach for feature selection in classification using this [Formula: see text]-metric, and evaluates its application to automatic atrial fibrillation detection.MethodsThe stability and prediction performance of the [Formula: see text]-metric feature selection approach was evaluated using the support vector machine model on two heart rhythm datasets, one extracted from the PhysioNet database and the other from the database of Marseille University Hospital Center, France (Timone Hospital). Both datasets contained electrocardiogram recordings grouped into two classes: normal sinus rhythm and atrial fibrillation. The performance of this feature selection approach was compared to that of three other approaches, with the first two based on the Random Forest technique and the other on receiver operating characteristic curve analysis.ResultsThe [Formula: see text]-metric approach showed satisfactory results, especially for models with a smaller number of features. For the training dataset, all prediction indicators were higher for our approach (accuracy greater than 99% for models with 5 to 17 features), as was stability (greater than 0.925 regardless of the number of features included in the model). For the validation dataset, the features selected with the [Formula: see text]-metric approach differed from those selected with the other approaches; sensitivity was higher for our approach, but other indicators were similar.ConclusionThis filter approach for feature selection in classification opens up new methodological avenues for atrial fibrillation detection using short electrocardiogram recordings.

Project description:ImportancePostoperative atrial fibrillation (POAF) occurring after cardiac surgery is associated with adverse outcomes. Whether POAF persists beyond discharge is not well defined.ObjectiveTo determine whether continuous cardiac rhythm monitoring enhances detection of POAF among cardiac surgical patients during the first 30 days after hospital discharge compared with usual care.Design, setting, and participantsThis study is an investigator-initiated, open-label, multicenter, randomized clinical trial conducted at 10 Canadian centers. Enrollment spanned from March 2017 to March 2020, with follow-up through September 11, 2020. As a result of the COVID-19 pandemic, enrollment stopped on July 17, 2020, at which point 85% of the proposed sample size was enrolled. Cardiac surgical patients with CHA2DS2-VASc (congestive heart failure, hypertension, age ≥75 years, diabetes, prior stroke or transient ischemic attack, vascular disease, age 65-74 years, female sex) score greater than or equal to 4 or greater than or equal to 2 with risk factors for POAF, no history of preoperative AF, and POAF lasting less than 24 hours during hospitalization were enrolled.InterventionsThe intervention group underwent continuous cardiac rhythm monitoring with wearable, patch-based monitors for 30 days after randomization. Monitoring was not mandated in the usual care group within 30 days after randomization.Main outcomes and measuresThe primary outcome was cumulative AF and/or atrial flutter lasting 6 minutes or longer detected by continuous cardiac rhythm monitoring or by a 12-lead electrocardiogram within 30 days of randomization. Prespecified secondary outcomes included cumulative AF lasting 6 hours or longer and 24 hours or longer within 30 days of randomization, death, myocardial infarction, ischemic stroke, non-central nervous system thromboembolism, major bleeding, and oral anticoagulation prescription.ResultsOf the 336 patients randomized (163 patients in the intervention group and 173 patients in the usual care group; mean [SD] age, 67.4 [8.1] years; 73 women [21.7%]; median [interquartile range] CHA2DS2-VASc score, 4.0 [3.0-4.0] points), 307 (91.4%) completed the trial. In the intent-to-treat analysis, the primary end point occurred in 32 patients (19.6%) in the intervention group vs 3 patients (1.7%) in the usual care group (absolute difference, 17.9%; 95% CI, 11.5%-24.3%; P < .001). AF lasting 6 hours or longer was detected in 14 patients (8.6%) in the intervention group vs 0 patients in the usual care group (absolute difference, 8.6%; 95% CI, 4.3%-12.9%; P < .001).Conclusions and relevanceIn post-cardiac surgical patients at high risk of stroke, no preoperative AF history, and AF lasting less than 24 hours during hospitalization, continuous monitoring revealed a significant increase in the rate of POAF after discharge that would otherwise not be detected by usual care. Studies are needed to examine whether these patients will benefit from oral anticoagulation therapy.Trial registrationClinicalTrials.gov Identifier: NCT02793895.