Search

Abstract We sought to validate the ability of a novel handheld ultrasound device with an artificial intelligence program (AI-POCUS) that automatically assesses left ventricular ejection fraction (LVEF). AI-POCUS was used to prospectively scan 200 patients in two Japanese hospitals. Automatic LVEF by AI-POCUS was compared to the standard biplane disk method using high-end ultrasound machines. After excluding 18 patients due to infeasible images for AI-POCUS, 182 patients (63 ± 15 years old, 21% female) were analyzed. The intraclass correlation coefficient (ICC) between the LVEF by AI-POCUS and the standard methods was good (0.81, p 0.80), AI-POCUS tended to underestimate LV volumes for larger LV (overall bias 42.1 mL for end-diastolic volume). These trends were mitigated with a newer version of the software tuned using increased data involving larger LVs, showing similar correlations (ICC > 0.85). In this real-world multicenter study, AI-POCUS showed accurate LVEF assessment, but careful attention might be necessary for volume assessment. The newer version, trained with larger and more heterogeneous data, demonstrated improved performance, underscoring the importance of big data accumulation in the field.

Key Clinical Message Familial cryptogenic stroke associated with atrial septal defect and patent foramen ovale is rare. The presence of a family history of cryptogenic stroke may lead to the requirement for careful follow‐up for younger family members.

The generalization of deep neural network algorithms to a broader population is an important challenge in the medical field. We aimed to apply self-supervised learning using masked autoencoders (MAEs) to improve the performance of the 12-lead electrocardiography (ECG) analysis model using limited ECG data. We pretrained Vision Transformer (ViT) models by reconstructing the masked ECG data with MAE. We fine-tuned this MAE-based ECG pretrained model on ECG-echocardiography data from The University of Tokyo Hospital (UTokyo) for the detection of left ventricular systolic dysfunction (LVSD), and then evaluated it using multi-center external validation data from seven institutions, employing the area under the receiver operating characteristic curve (AUROC) for assessment. We included 38,245 ECG-echocardiography pairs from UTokyo and 229,439 pairs from all institutions. The performances of MAE-based ECG models pretrained using ECG data from UTokyo were significantly higher than that of other Deep Neural Network models across all external validation cohorts (AUROC, 0.913-0.962 for LVSD, p < 0.001). Moreover, we also found improvements for the MAE-based ECG analysis model depending on the model capacity and the amount of training data. Additionally, the MAE-based ECG analysis model maintained high performance even on the ECG benchmark dataset (PTB-XL). Our proposed method developed high performance MAE-based ECG analysis models using limited ECG data.

Objectives The clinical outcomes of transcatheter aortic valve replacement (TAVR) in patients with aortic stenosis (AS) and concomitant active cancer remain insufficiently explored. This study aimed to assess the midterm outcomes of TAVR in patients diagnosed with AS and active cancer.Methods Data from the OCEAN-TAVI, a prospective Japanese registry of TAVR procedures, was analysed to compare prognoses and clinical outcomes in patients with and without active cancer at the time of TAVR.Results Of the 2336 patients who underwent TAVR from October 2013 to July 2017, 89 patients (3.8%) had active cancer, whereas 2247 did not. Among patients with active cancer, 49 had limited-stage cancer (stage 1 or 2). The prevalent cancers identified before TAVR were colon (21%), prostate (18%), lung (15%), liver (11%) and breast (9%). Although the periprocedural complications and 30-day mortality rates were comparable between the groups, the 3-year survival rate after TAVR was notably lower in patients with active cancer (64.7%) than in those without active cancer (74.7%; p=0.016). Nevertheless, the 3-year survival rate of patients with limited-stage cancer (stage 1 or 2) did not significantly differ from those without cancer (70.6% vs 74.7%, p=0.50).Conclusions The patients with active cancer exhibited significantly reduced midterm survival rates. However, no distinct disparity existed in those with limited-stage cancer (stage 1 or 2). Although TAVR is a viable treatment in patients with AS with active cancer, the type and stage of cancer and prognosis should be carefully weighed in the decision-making process.