Publications by authors named "Hirotaka Ieki"
Atrial fibrillation (AF) is a common cardiac arrhythmia resulting in increased risk of stroke. Despite highly heritable etiology, our understanding of the genetic architecture of AF remains incomplete. Here we performed a genome-wide association study in the Japanese population comprising 9,826 cases among 150,272 individuals and identified East Asian-specific rare variants associated with AF.
View Article and Find Full Text PDFDeep learning-based age estimation from chest X-rays indicates cardiovascular prognosis.
Commun Med (Lond)
December 2022
Article Synopsis
- - Recent research has focused on using AI to estimate age and disease status from medical images, but age estimation from chest X-rays (CXRs) has not been extensively studied yet.
- - A deep neural network was trained on over 100,000 CXRs to estimate patient age, and it was applied to two groups of hospitalized patients with heart failure and cardiovascular disease.
- - The estimated age from CXRs (X-ray age) correlated strongly with actual age and was linked to worse clinical outcomes, indicating that X-ray age can help clinicians assess and manage cardiovascular conditions more effectively.
Article Synopsis
- Deep learning models can effectively analyze electrocardiograms (ECGs) to detect left ventricular (LV) dysfunction, enhancing diagnostic accuracy for cardiologists.
- A study involved training a convolutional neural network on 23,801 ECGs, achieving a high accuracy of 94.5% in identifying LV dysfunction in a separate test set of 7,196 ECGs.
- When cardiologists used the model's output, their accuracy increased from 78% to 88%, demonstrating significant improvement in identifying LV dysfunction with the model's assistance.
Article Synopsis
- - The study developed a deep learning algorithm to identify subclinical cardiac sarcoidosis (CS) from echocardiographic movies, addressing challenges in early diagnosis.
- - Researchers trained two 3D convolutional neural networks (3D-CNN) on a dataset of 302 echocardiographic movies, comparing a pretrained algorithm to a non-pretrained one; results showed the pretrained algorithm had a higher accuracy (AUC 0.842 vs. 0.724) similar to that of cardiologists.
- - Findings suggest that using a 3D-CNN with transfer learning could be an effective method for detecting CS, particularly focusing on the mitral valve area in echocardiographic images.
To elucidate the genetics of coronary artery disease (CAD) in the Japanese population, we conducted a large-scale genome-wide association study of 168,228 individuals of Japanese ancestry (25,892 cases and 142,336 controls) with genotype imputation using a newly developed reference panel of Japanese haplotypes including 1,781 CAD cases and 2,636 controls. We detected eight new susceptibility loci and Japanese-specific rare variants contributing to disease severity and increased cardiovascular mortality. We then conducted a trans-ancestry meta-analysis and discovered 35 additional new loci.
View Article and Find Full Text PDFArticle Synopsis
- An error was identified in the article "Diagnosing Heart Failure from Chest X-Ray Images Using Deep Learning."
- The issue specifically pertains to Figure 5 on page 784 of the publication.
- The authors provided a replacement for the incorrect figure to correct the error.
Article Synopsis
- * A dataset of 952 chest X-ray images was analyzed, with cardiologists verifying and relabeling images to ensure accuracy, resulting in a final set of 638 images for analysis.
- * The study achieved an 82% accuracy rate in diagnosing heart failure, utilizing methods like data augmentation and transfer learning, while also employing heatmaps to visualize the machine's decision-making process.
Background: Genome-wide association studies provided many biological insights into coronary artery disease (CAD), but these studies were mainly performed in Europeans. Genome-wide association studies in diverse populations have the potential to advance our understanding of CAD.
Methods: We conducted 2 genome-wide association studies for CAD in the Japanese population, which included 12 494 cases and 28 879 controls and 2808 cases and 7261 controls, respectively.
• Spontaneous mitral chordal rupture is a complication in hypertrophic cardiomyopathy (HCM). • Mitral chordal rupture in HCM causes deterioration in heart failure. • Symptoms improved when left ventricular outflow tract (LVOT) obstruction disappeared.
View Article and Find Full Text PDFIntroduction: Previous studies have indicated that the ratio of pulmonary artery (PA) to ascending aorta (Ao) diameter as measured by computed tomography (PA/Ao) is strongly associated with pulmonary artery pressure. However, the clinical significance of PA/Ao in heart failure (HF) has not been fully characterized. We sought to investigate the prognostic impact of PA/Ao in HF.
View Article and Find Full Text PDF