Electrocardiogram Interpretation Using Artificial Intelligence: Diagnosis of Cardiac and Extracardiac Pathologic Conditions. How Far Has Machine Learning Reached?

Artificial intelligence (AI) is already widely used in different fields of medicine, making possible the integration of the paraclinical exams with the clinical findings in patients, for a more accurate and rapid diagnosis and treatment decision. The electrocardiogram remains one of the most important, fastest, cheapest, and noninvasive methods of diagnosis in cardiology, despite the rapid development and progression of the technology. Even if studied a long time ago, it still has a lot of less understood features that, with a better understanding, can give more clues to a correct and prompt diagnosis in a short time. The use of AI in the interpretation of the ECG improved the accuracy and the time to diagnosis in different cardiovascular diseases, and more than this, explaining the decision to make AI diagnosis improved the human understanding of the different features of the ECG that might be considered for a more accurate diagnosis. The purpose of this article is to provide an overview of the most recently published articles about the use of AI in ECG interpretation.

Do depressive and anxiety symptoms influence the quality of life of patients with atrial fibrillation after cryoballoon ablation: a comparison study.

BACKGROUND AND AIMS: One third of patients with atrial fibrillation (AF) suffer from high levels of anxiety and depression, which may significantly impair quality of life (QoL). The purpose of this study was to assess whether depressive and anxiety symptoms before ablation affect the QoL in patients with AF one year after cryoballoon ablation (CBA). METHODS: This single-center retrospective study investigated whether the AF patients with a high Hospital Anxiety and Depression Scale (HADS) score (≥ 8) had worse outcomes than patients with a low pre-ablation HADS score (< 8). The primary outcome was the difference in post-ablation QoL, and the secondary outcome included the difference in pre-ablative QoL, QoL improvement, and self-reported AF. RESULTS: Two hundred ninety-five patients were stratified according to their HADS scores (total, depression, and anxiety). Patients with an elevated HADS total, depression, or anxiety score (≥ 8), had a significantly lower QoL before and 12 months after CBA than patients with a HADS score < 8 (p-value < 0.001 for all groups). All groups improved significantly in QoL after CBA ablation and to a similar extent. Sixty-three percent of the patients reported AF symptoms after the procedure, which was comparable between the cohorts of patients. CONCLUSION: Patients with elevated HADS scores reported a lower QoL compared to participants with low HADS scores at baseline and 12 months after CBA. However, both groups improved in QoL after CBA, irrespective of their depressive and anxiety symptoms.

Randomized trial of intracardiac echocardiography-guided slow pathway ablation.

PURPOSE: Radiofrequency (RF) catheter ablation of the slow pathway (SP) in atrioventricular nodal reentry tachycardia (AVNRT) is highly effective; however, it may require prolonged fluoroscopy and RF time. We postulated that visualization of the SP region with intracardiac echocardiography (ICE) could decrease ablation time, minimize radiation exposure, and facilitate SP ablation compared to the standard, fluoroscopy-guided approach. METHODS: In our study, we randomized 91 patients undergoing electrophysiologic study and SP ablation for AVNRT into 2 groups: fluoroscopy-only (n = 48) or ICE-guided (n = 43) group. Crossover to ICE-guidance was allowed after 8 unsuccessful RF applications. RESULTS: Mapping plus ablation time (mean ± standard deviation: 18.8 ± 16.1 min vs 11.6 ± 15.0 min, p = 0.031), fluoroscopy time (median [interquartile range]: 4.9 [2.93-8.13] min vs. 1.8 [1.2-2.8] min, p < 0.001), and total ablation time (144 [104-196] s vs. 81 [60-159] s, p = 0.001) were significantly shorter in the ICE group. ICE-guidance was associated with reduced radiation exposure (13.2 [8.2-13.4] mGy vs. 3.7 [1.5-5.8] mGy, p < 0.001). The sum of delivered RF energy (3866 [2786-5656] Ws vs. 2283 [1694-4284] Ws, p = 0.002) and number of RF applications (8 [4.25-12.75] vs. 4 [2-7], p = 0.001) were also lower with ICE-guidance. Twelve (25%) patients crossed over to the ICE-guided group. All were treated successfully thereafter with similar number, time, and cumulative energy of RF applications compared to the ICE group. No recurrence occurred during the follow-up. CONCLUSIONS: ICE-guidance during SP ablation significantly reduces mapping and ablation time, radiation exposure, and RF delivery in comparison to fluoroscopy-only procedures. Moreover, early switching to ICE-guided ablation seems to be an optimal choice in challenging cases.