Key result
A deep neural network model using RR interval variations was not superior to a random forest algorithm using heart rate variability parameters for forecasting atrial fibrillation onset.
Why the study?
Machine learning algorithms can forecast atrial fibrillation episodes in patients in sinus rhythm, but they do not provide relevant information about underlying pathophysiology.
Does a deep neural network model improve the forecasting of atrial fibrillation compared to a random forest model using HRV and premature beats?
Observational (n=10,484)
Does a deep neural network model improve the forecasting of atrial fibrillation compared to a random forest model using HRV and premature beats?
A deep neural network model did not outperform a random forest algorithm using HRV parameters for forecasting AF onset, suggesting HRV plays a predominant role in triggering AF.
Background The identification of patients still in sinus rhythm who will present one month later an atrial fibrillation episode is possible using machine learning (ML) techniques. However, these new ML algorithms do not provide any relevant information about the underlying pathophysiology. Purpose To compare the predictive performance for forecasting AF between a machine learning algorithm and other parameters whose pathophysiological mechanisms are known to play a role in the triggering of arrhythmias (i.e. the count of premature beats (PB) and heart rate variability (HRV) parameters) Material and methods We conducted a retrospective study from an outpatient clinic. 10484 Holter ECG recordings were screened. 250 analysable AF onsets were labelled. We developed a deep neural network model composed of convolutional neural network layers and bidirectional gated recurrent units as recurrent neural network layers that was trained for the forecast of paroxysmal AF episodes, using RR intervals variations. This model works like a black box. For comparison purposes, we used a “random forest” (RF) model of ML to obtain forecast results using HRV parameters with and without PB. This model allows the evaluation of the relevance of HRV parameters and of PB used for the forecast. We calculated the area under the curve of the receiving operating characteristic curve for the different time windows counted in RR intervals before the AF onset. Results As shown in the table, the forecasting value of the deep neural network model (ML) was not superior to the random forest algorithm. Prediction value of both decreased when analyzing the RR intervals further away from the onset of AF Conclusions These results suggest that HRV plays a predominant role in triggering AF episodes and that premature beats could add minor information. Moreover, the closer the window from AF onset, the better the accuracy, regardless of the method used. Such detection algorithms once implemented in pacemakers, might prove useful to prevent AF onset by changing pacing sequence while patients would still be in sinus rhythm, however this remains to be demonstrated Funding Acknowledgement Type of funding source: None
No takes yet. Share an insight, caveat, or question.
Grégoire et al. (2020) conducted an observational in Atrial fibrillation (n=10,484). Deep neural network model using RR intervals variations vs. Random forest model using HRV parameters with and without premature beats was evaluated on Forecasting of paroxysmal atrial fibrillation episodes (Area under the curve). A deep neural network model using RR interval variations was not superior to a random forest algorithm using heart rate variability parameters for forecasting atrial fibrillation onset.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: