Qualitative Evaluation of an Artificial Intelligence–Based Clinical Decision Support System to Guide Rhythm Management of Atrial Fibrillation: Survey Study

Postoperative atrial fibrillation (POAF) after cardiac surgery: clinical practice review

Postoperative atrial fibrillation (POAF) after cardiac surgery is associated with elevated morbidity and mortality. Although current prediction models have limited efficacy, several perioperative interventions can reduce patients' risk of POAF. These begin with preoperative medications, including beta-blockers and amiodarone. Moreover, patients should be screened for preexisting atrial fibrillation (AF) so that concomitant surgical ablation and left atrial appendage occlusion can be performed in appropriate candidates. Intraoperative interventions such as posterior pericardiectomy can reduce mediastinal fluid accumulation, which is a trigger for POAF. Furthermore, many preventive strategies for POAF are implemented in the immediate postoperative period. Initiating beta-blockers, amiodarone, or both is reasonable for most patients. Overdrive atrial pacing, colchicine, and steroids have been used by some, although the evidence base is less robust. For patients with POAF, rate-control and rhythm-control strategies have comparable outcomes. Decision-making regarding anticoagulation should recognize that the stroke risk associated with POAF appears to be lower than that for general nonvalvular AF. The evidence that oral anticoagulation reduces stroke risk is less clear for POAF patients than for patients with general nonvalvular AF. Given that POAF tends to be shorter-lived and is associated with greater bleeding risks in the perioperative period, decisions regarding anticoagulation should be individualized. Finally, wearable technology and machine learning algorithms for better predicting and managing POAF appear to be coming soon. These technologies and a comprehensive clinical program could meaningfully reduce the incidence of this common complication.

Improved diagnostic performance of insertable cardiac monitors by an artificial intelligence-based algorithm

AIMS

The increasing use of insertable cardiac monitors (ICM) produces a high rate of false positive (FP) diagnoses. Their verification results in a high workload for caregivers. We evaluated the performance of an artificial intelligence (AI)-based ILR-ECG Analyzer™ (ILR-ECG-A). This machine-learning algorithm reclassifies ICM-transmitted events to minimize the rate of FP diagnoses, while preserving device sensitivity.

METHODS AND RESULTS

We selected 546 recipients of ICM followed by the Implicity™ monitoring platform. To avoid clusterization, a single episode per ICM abnormal diagnosis (e.g. asystole, bradycardia, atrial tachycardia (AT)/atrial fibrillation (AF), ventricular tachycardia, artefact) was selected per patient, and analyzed by the ILR-ECG-A, applying the same diagnoses as the ICM. All episodes were reviewed by an adjudication committee (AC) and the results were compared. Among 879 episodes classified as abnormal by the ICM, 80 (9.1%) were adjudicated as 'Artefacts', 283 (32.2%) as FP, and 516 (58.7%) as 'abnormal' by the AC. The algorithm reclassified 215 of the 283 FP as normal (76.0%), and confirmed 509 of the 516 episodes as abnormal (98.6%). Seven undiagnosed false negatives were adjudicated as AT or non-specific abnormality. The overall diagnostic specificity was 76.0% and the sensitivity was 98.6%.

CONCLUSION

The new AI-based ILR-ECG-A lowered the rate of FP ICM diagnoses significantly while retaining a > 98% sensitivity. This will likely alleviate considerably the clinical burden represented by the review of ICM events.