Prediction of pacemaker-induced cardiomyopathy using a convolutional neural network based on clinical findings prior to pacemaker implantation.

Risk factors for pacemaker-induced cardiomyopathy (PICM) have been previously reported, including a high burden of right ventricular pacing, lower left ventricular ejection fraction, a wide QRS duration, and left bundle branch block before pacemaker implantation (PMI). However, predicting the development of PICM remains challenging. This study aimed to use a convolutional neural network (CNN) model, based on clinical findings before PMI, to predict the development of PICM. Out of a total of 561 patients with dual-chamber PMI, 165 (mean age 71.6 years, 89 men [53.9%]) who underwent echocardiography both before and after dual-chamber PMI were enrolled. During a mean follow-up period of 1.7 years, 47 patients developed PICM. A CNN algorithm for prediction of the development of PICM was constructed based on a dataset prior to PMI that included 31 variables such as age, sex, body mass index, left ventricular ejection fraction, left ventricular end-diastolic diameter, left ventricular end-systolic diameter, left atrial diameter, severity of mitral regurgitation, severity of tricuspid regurgitation, ischemic heart disease, diabetes mellitus, hypertension, heart failure, New York Heart Association class, atrial fibrillation, the etiology of bradycardia (sick sinus syndrome or atrioventricular block) , right ventricular (RV) lead tip position (apex, septum, left bundle, His bundle, RV outflow tract), left bundle branch block, QRS duration, white blood cell count, haemoglobin, platelet count, serum total protein, albumin, aspartate transaminase, alanine transaminase, estimated glomerular filtration rate, sodium, potassium, C-reactive protein, and brain natriuretic peptide. The accuracy, sensitivity, specificity, and area under the curve of the CNN model were 75.8%, 55.6%, 83.3% and 0.78 respectively. The CNN model could accurately predict the development of PICM using clinical findings before PMI. This model could be useful for screening patients at risk of developing PICM, ensuring timely upgrades to physiological pacing to avoid missing the optimal intervention window.

The estimated glomerular filtration rate predicts pacemaker-induced cardiomyopathy.

Clinical predictors for pacemaker-induced cardiomyopathy (PICM) (e.g., a wide QRS duration and left bundle branch block at baseline) have been reported. However, factors involved in the development of PICM in patients with preserved left ventricular ejection fraction (LVEF) remain unknown. This study aimed to determine the risk factors for PICM in patients with preserved LVEF. The data of 113 patients (average age: 71.3 years; men: 54.9%) who had echocardiography before and after pacemaker implantation (PMI) among 465 patients undergoing dual-chamber PMI were retrospectively analyzed. Thirty-three patients were diagnosed with PICM (18.0/100 person-years; 95% CI 12.8-25.2). A univariate Cox regression analysis showed that an estimated glomerular filtration rate (eGFR) ≤ 30 mL/min/1.73 m2 (HR 3.47; 95% CI 1.48-8.16) and a past medical history of coronary artery disease (CAD) (HR 2.76; 95% CI 1.36-5.60) were significantly associated with the onset of PICM. After adjusting for clinical variables, an eGFR ≤ 30 mL/min/1.73 m2 (HR 2.62; 95% CI 1.09-6.29) and a medical history of CAD (HR 2.32; 95% CI 1.13-4.80) were independent risk factors for developing PICM. A medical history of CAD and low eGFR are independent risk factors for PICM in patients with preserved LVEF at baseline. These results could be helpful in predicting a decreased LVEF by ventricular pacing before PMI. Close follow-up by echocardiography is recommended to avoid a delay in upgrading to physiological pacing, such as cardiac resynchronization therapy or conduction system pacing.

Seasonal Variations in the Incidence of Ischemic Stroke, Extracranial and Intracranial Hemorrhage in Atrial Fibrillation Patients.

BACKGROUND: Ischemic stroke (IS) and major bleeding, which are serious adverse events in patients with atrial fibrillation (AF), could have seasonal variations, but there are few reports.Methods and Results:In the Shinken Database 2004-2016 (n=22,018), 3,581 AF patients (average age, 63.5 years; 2,656 men, 74.2%; 1,388 persistent AF, 38.8%) were identified. Median CHADS2and HAS-BLED scores were both 1 point. Oral anticoagulants were prescribed for 2,082 (58.1%) patients (warfarin, 1,214; direct oral anticoagulants [DOACs], 868). Incidence and observation period (maximum 3 years) of IS, extracranial hemorrhage (ECH), and intracranial hemorrhage (ICH) were counted separately for the northern hemisphere seasons. During the mean follow-up period of 2.4 years, there were totals of 90 IS, 73 ECH, and 33 ICH cases. The respective incidence rates per 1,000 patient-years in spring, summer, autumn, and winter were 8.5, 8.8, 7.5, and 16.8 for IS, 7.2, 9.7, 3.8, and 13.1 for ECH, and 2.7, 1.9, 3.8, and 7.0 for ICH. The number of patients with DOACs relatively increased among those with ECH in summer. CONCLUSIONS: Significant seasonal variations were observed for IS, ECH, and ICH events in AF patients, and were consistently the highest in winter. A small peak of ECH was observed in summer, which seemed, in part, to be related to increased DOAC use.