Automated detection of atrial fibrillation using long short-term memory network with RR interval signals. (1st November 2018)

• Record Type: Journal Article
• Authors: Faust, Oliver; Shenfield, Alex; Kareem, Murtadha; San, Tan Ru; Fujita, Hamido; Acharya, U. Rajendra
• Is Part Of: Computers in biology and medicine. Volume 102(2018)
• Page Start: 327
• Page End: 335
• Publication Date: 2018-11-01
• Subjects: Deep learning -- Recurrent neural network -- Heart rate -- Atrial fibrillation; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2018.07.001
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Atrial Fibrillation (AF), either permanent or intermittent (paroxysnal AF), increases the risk of cardioembolic stroke. Accurate diagnosis of AF is obligatory for initiation of effective treatment to prevent stroke. Long term cardiac monitoring improves the likelihood of diagnosing paroxysmal AF. We used a deep learning system to detect AF beats in Heart Rate (HR) signals. The data was partitioned with a sliding window of 100 beats. The resulting signal blocks were directly fed into a deep Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM). The system was validated and tested with data from the MIT-BIH Atrial Fibrillation Database. It achieved 98.51% accuracy with 10-fold cross-validation (20 subjects) and 99.77% with blindfold validation (3 subjects). The proposed system structure is straight forward, because there is no need for information reduction through feature extraction. All the complexity resides in the deep learning system, which gets the entire information from a signal block. This setup leads to the robust performance for unknown data, as measured with the blind fold validation. The proposed Computer-Aided Diagnosis (CAD) system can be used for long-term monitoring of the human heart. To the best of our knowledge, the proposed system is the first to incorporate deep learning for AF beat detection. Highlights: Importance: For the first time deep learning was used to detect Atrial Fibrillation based on heart rate signals. Data: The system was validated and tested with data from the MIT-BIH Atrial Fibrillation Database. Performance: The system achieved 98.51% accuracy with 10-fold cross-validation and 99.77% with blindfold validation. Simplicity: Partition the heart rate signal with a sliding window of 100 beats. Feed the resulting data blocks to the deep learning system.