Alteration of the P-wave non-linear dynamics near the onset of paroxysmal atrial fibrillation

Clinical applicability of an artificial intelligence prediction algorithm for early prediction of non-persistent atrial fibrillation

Background and aims

It is difficult to document atrial fibrillation (AF) on ECG in patients with non-persistent atrial fibrillation (non-PeAF). There is limited understanding of whether an AI prediction algorithm could predict the occurrence of non-PeAF from the information of normal sinus rhythm (SR) of a 12-lead ECG. This study aimed to derive a precise predictive AI model for screening non-PeAF using SR ECG within 4 weeks.

Methods

This retrospective cohort study included patients aged 18 to 99 with SR ECG on 12-lead standard ECG (10 seconds) in Ewha Womans University Medical Center for 3 years. Data were preprocessed into three window periods (which are defined with the duration from SR to non-PeAF detection) - 1 week, 2 weeks, and 4 weeks from the AF detection prospectively. For experiments, we adopted a Residual Neural Network model based on 1D-CNN proposed in a previous study. We used 7,595 SR ECGs (extracted from 215,875 ECGs) with window periods of 1 week, 2 weeks, and 4 weeks for analysis.

Results

The prediction algorithm showed an AUC of 0.862 and an F1-score of 0.84 in the 1:4 matched group of a 1-week window period. For the 1:4 matched group of a 2-week window period, it showed an AUC of 0.864 and an F1-score of 0.85. Finally, for the 1:4 matched group of a 4-week window period, it showed an AUC of 0.842 and an F1-score of 0.83.

Conclusion

The AI prediction algorithm showed the possibility of risk stratification for early detection of non-PeAF. Moreover, this study showed that a short window period is also sufficient to detect non-PeAF.

Pathological Heart Rate Regulation in Apparently Healthy Individuals

Cardiovascular diseases are the leading cause of morbidity and mortality in adults worldwide. There is one common pathophysiological aspect present in all cardiovascular diseases-dysfunctional heart rhythm regulation. Taking this aspect into consideration for cardiovascular risk predictions opens important research perspectives, allowing for the development of preventive treatment techniques. The aim of this study was to find out whether certain pathologically appearing signs in the heart rate variability (HRV) of an apparently healthy person, even with high HRV, can be defined as biomarkers for a disturbed cardiac regulation and whether this can be treated preventively by a drug-free method. This multi-phase study included 218 healthy subjects of either sex, who consecutively visited the physician at Gesundheit clinic because of arterial hypertension, depression, headache, psycho-emotional stress, extreme weakness, disturbed night sleep, heart palpitations, or chest pain. In study phase A, baseline measurement to identify individuals with cardiovascular risks was done. Therefore, standard HRV, as well as the new cardiorhythmogram (CRG) method, were applied to all subjects. The new CRG analysis used here is based on the recently introduced LF drops and HF counter-regulation. Regarding the mechanisms of why these appear in a steady-state cardiorhythmmogram, they represent non-linear event-based dynamical HRV biomarkers. The next phase of the study, phase B, tested whether the pathologically appearing signs identified via CRG in phase A could be clinically influenced by drug-free treatment. In order to validate the new CRG method, it was supported by non-linear HRV analysis in both phase A and in phase B. Out of 218 subjects, the pathologically appearing signs could be detected in 130 cases (60%), p < 0.01, by the new CRG method, and by the standard HRV analysis in 40 cases (18%), p < 0.05. Thus, the CRG method was able to detect 42% more cases with pathologically appearing cardiac regulation. In addition, the comparative CRG analysis before and after treatment showed that the pathologically appearing signs could be clinically influenced without the use of medication. After treatment, the risk group decreased eight-fold-from 130 people to 16 (p < 0.01). Therefore, progression of the detected pathological signs to structural cardiac pathology or arrhythmia could be prevented in most of the cases. However, in the remaining risk group of 16 apparently healthy subjects, 8 people died due to all-cause mortality. In contrast, no other subject in this study has died so far. The non-linear parameter which is able to quantify the changes in CRGs before versus after treatment is FWRENYI4 (symbolic dynamic feature); it decreased from 2.85 to 2.53 (p < 0.001). In summary, signs of pathological cardiac regulation can be identified by the CRG analysis of apparently healthy subjects in the early stages of development of cardiac pathology. Thus, our method offers a sensitive biomarker for cardiovascular risks. The latter can be influenced by non-drug treatments (acupuncture) to stop the progression into structural cardiac pathologies or arrhythmias in most but not all of the patients. Therefore, this could be a real and easy-to-use supplemental method, contributing to primary prevention in cardiology.

A FEATURE SELECTION-BASED ALGORITHM FOR DETECTION OF ATRIAL FIBRILLATION USING SHORT-TERM ECG

In the presence of premature atrial contraction (PAC), premature ventricular contraction (PVC) or other ectopic beats, RR intervals (RRIs) may be disturbed, which results in other types of heart disease being misdiagnosed as atrial fibrillation (AF). In this study, a low-complexity AF detection method based on short ECG is proposed, which includes RRIs modification and feature selection. The extracted RRIs are used to determine whether the potential RRI interference exists and to modify it. Next, based on the modified RRIs, the features are evaluated and selected by the methods of correlation criterion, Fisher criterion, and minimum redundancy maximum relevance criterion. Finally, filtered features are classified by the artificial neural network (ANN). The algorithm is validated in a test set including 2332 AF, 313 normal (NOR), 239 atrioventricular block (IAVB), 81 left bundle branch block (LBBB), 624 right bundle branch block (RBBB), 426 PAC and 564 PVC. Compared with the previous detection method of AF based on the RRIs, the proposed method achieved an overall sensitivity of 94.04% and an overall specificity of 86.74%. The specificity of the test set containing only AF and NOR is up to 99.04%. Meanwhile, the overall false-positive rate (FPR) of PAC and PVC can be reduced by 9.19%. While ensuring accuracy, this method effectively reduces the probability of misdiagnosis of PVC and PAC as AF. It is an automatic detection method of AF suitable for inter-patient clinical short-term ECG.

Usefulness of P-Wave Duration and Morphologic Variability to Identify Patients Prone to Paroxysmal Atrial Fibrillation

Few data are available on the assessment of P-wave beat-to-beat morphology variability and its ability to identify patients prone to paroxysmal atrial fibrillation (AF) occurrence. Aim of this study was to determine whether electrocardiographic (ECG) parameters resulting from the beat-to-beat analysis of P wave in ECG recorded during sinus rhythm could be indicators of paroxysmal AF susceptibility. ECGs of 76 consecutive patients including 36 patients with history of AF and no overt structural cardiac abnormalities and a control group of 40 healthy patients without history of AF were analyzed. After preprocessing, features based on P waves and RR intervals were extracted from lead II of a 5-minute ECG recorded during sinus rhythm. The discriminative power of the extracted features was assessed. Among extracted features, the most discriminative ones to identify patients with paroxysmal episodes of AF were the mean P-wave duration and the SD of beat-to-beat Euclidean distance between P waves (an indicator of beat-to-beat P-wave morphologic variability). Patients with history of AF presented a significantly longer P-wave duration (125 ± 18 vs 110 ± 8 ms, p <0.001) and higher variability of P-wave morphology over time (beat-to-beat Euclidean distance: 0.11 ± 0.07 vs 0.076 ± 0.02, p <0.01) compared to patients without history of AF. Combination of P-wave duration and standard deviation of beat-to-beat Euclidean distance led to an accuracy of 88% in the discrimination between the 2 groups of patients. In conclusion, combination of P-wave duration and beat-to-beat Euclidean distance between P waves efficiently discriminates patients with history of AF and no overt structural cardiac abnormalities from healthy age-matched subjects, and it might be used as an effective tool to identify patients prone to paroxysmal AF occurrence.