Key result
Hybrid machine learning model detects cardiac arrhythmias from single-lead ECGs with ~99% F1 score.
Why the study?
Computer-assisted single-lead ECG interpretation helps clinicians flag arrhythmias in acutely ill patients, but critical scrutiny of novel detection algorithms in external real-world data sets was lacking.
Does a hybrid machine learning model accurately classify eight common cardiac arrhythmias from real-world single-lead ECG signals compared with expert human annotators in acutely ill patients receiving home hospital care?
Cross-Sectional (n=423)
Yes
Does a hybrid machine learning model accurately classify eight common cardiac arrhythmias from real-world single-lead ECG signals compared with expert human annotators in acutely ill patients receiving home hospital care?
A hybrid machine learning algorithm combining signal filtration and a deep neural network accurately classified eight common cardiac arrhythmias from noisy real-world single-lead ECG patch data in acutely ill home-hospitalized patients, achieving an overall F1 Score of 99.0% with a 0.2% false positive rate.
Answers are grounded in this paper and cite their sources.
May support arrhythmia detection in home-hospital care; leaves open prospective outcome validation before clinical adoption.
Background Computer-assisted interpretation of single-lead ECG is the preliminary method for clinicians to flag and further evaluate an arrhythmia of clinical importance for acutely ill patients. Critical scrutiny of novel detection algorithms is lacking, particularly in external real-world data sets. This study’s objective was to evaluate a hybrid machine learning model’s ability to classify eight arrhythmias from a single-lead ECG signal from acutely ill patients. Methods This cross-sectional external retrospective evaluation of a previously trained hybrid machine learning model against an ECG reading team in the setting of home hospital care (acute care delivered at home substituting for traditional hospital care) draws from patients admitted at two hospitals in Boston, Massachusetts, USA between 12 June 2017 and 23 November 2019. We calculated classifier statistics for each arrhythmia, all arrhythmias and strips where the model identified normal sinus rhythm. Results The model analysed 2 680 162 min of single-lead ECG data from 423 patients and identified 691 478 arrhythmias. Patients had a mean age of 70 years (SD, 18), 60% were female and 45% were white. For any arrhythmia, the model had a sensitivity of 98%, a specificity of 100%, an accuracy of 98%, a positive predictive value of 100%, a negative predictive value of 93% and an F 1 Score of 99%. Performance was best for pause (F 1 Score, 99%) and worst for paroxysmal supraventricular tachycardia (F 1 Score, 92%). The model’s false positive rate for any arrhythmia was 0.2%, ranging from 0.4% for pause to 7.2% for paroxysmal supraventricular tachycardia. The false negative rate for any arrhythmia was 1.9%. Conclusions A hybrid machine learning model was effective at classifying common cardiac arrhythmias from a single-lead ECG in real-world data.
No takes yet. Share an insight, caveat, or question.
Mitchell et al. (2023) conducted a cross-sectional in Acutely ill patients receiving home hospital care requiring continuous ECG monitoring for arrhythmias (n=423). Hybrid machine learning ECG interpretation model (RhythmAnalytics, Biofourmis) vs. Expert ECG reading team (certified cardiac and rhythm analysis technicians reviewed by a cardiologist) was evaluated on Diagnostic performance (F1 Score, sensitivity, specificity, accuracy, PPV, NPV) for detecting any arrhythmia from 1-minute single-lead ECG strips (95% CI 98.78-99.19). The hybrid machine learning model classified any cardiac arrhythmia from single-lead ECGs with an F1 Score of 99.0%, sensitivity of 98.1%, and specificity of 99.8%.
Synapse has enriched 10 related papers. Consider them for comparative context: