Key result
The LightGBM machine learning model effectively differentiated sinus rhythm from atrial fibrillation using 12-lead ECG power spectral features, achieving an average F1-score of 0.988.
Why the study?
AF diagnosis largely relies on healthcare professional proficiency, and real-time identification of paroxysmal AF is hindered by a lack of automated techniques.
Does a machine learning algorithm accurately detect atrial fibrillation based on power spectral features of 12-lead ECGs?
Cross-Sectional
Does a machine learning algorithm accurately detect atrial fibrillation based on power spectral features of 12-lead ECGs?
Effect estimate: F1-score 0.988
The LightGBM machine learning model can accurately detect atrial fibrillation from 12-lead ECG power spectral features, achieving an F1-score of 0.988.
Should not yet change practice for AF detection; leaves open prospective validation of ML algorithms on 12-lead ECGs.
BACKGROUND Atrial fibrillation (AF) represents a hazardous cardiac arrhythmia that significantly elevates the risk of stroke and heart failure. Despite its severity, its diagnosis largely relies on the proficiency of health care professionals. At present, the real-time identification of paroxysmal AF is hindered by the lack of automated techniques. Consequently, a highly effective machine learning algorithm specifically designed for AF detection could offer substantial clinical benefits. We hypothesized that machine learning algorithms have the potential to identify and extract features of AF with a high degree of accuracy, given the intricate and distinctive patterns present in electrocardiogram (ECG) recordings of AF. OBJECTIVE This study aims to develop a clinically valuable machine learning algorithm that can accurately detect AF and compare different leads’ performances of AF detection. METHODS We used 12-lead ECG recordings sourced from the 2020 PhysioNet Challenge data sets. The Welch method was used to extract power spectral features of the 12-lead ECGs within a frequency range of 0.083 to 24.92 Hz. Subsequently, various machine learning techniques were evaluated and optimized to classify sinus rhythm (SR) and AF based on these power spectral features. Furthermore, we compared the effects of different frequency subbands and different lead selections on machine learning performances. RESULTS The light gradient boosting machine (LightGBM) was found to be the most effective in classifying AF and SR, achieving an average F₁-score of 0.988 across all ECG leads. Among the frequency subbands, the 0.083 to 4.92 Hz range yielded the highest F₁-score of 0.985. In interlead comparisons, aVR had the highest performance (F₁=0.993), with minimal differences observed between leads. CONCLUSIONS In conclusion, this study successfully used machine learning methodologies, particularly the LightGBM model, to differentiate SR and AF based on power spectral features derived from 12-lead ECGs. The performance marked by an average F₁-score of 0.988 and minimal interlead variation underscores the potential of machine learning algorithms to bolster real-time AF detection. This advancement could significantly improve patient care in intensive care units as well as facilitate remote monitoring through wearable devices, ultimately enhancing clinical outcomes.
No takes yet. Share an insight, caveat, or question.
Chuang et al. (2023) conducted a cross-sectional in Atrial fibrillation. LightGBM machine learning model was evaluated on Classification of sinus rhythm and atrial fibrillation (F1-score 0.988). The LightGBM machine learning model effectively differentiated sinus rhythm from atrial fibrillation using 12-lead ECG power spectral features, achieving an average F1-score of 0.988.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: