著者
Jun Komiyama Takehiro Sugiyama Masao Iwagami Miho Ishimaru Yu Sun Hiroki Matsui Keitaro Kume Masaru Sanuki Teruyuki Koyama Genta Kato Yukiko Mori Hiroaki Ueshima Nanako Tamiya
出版者
The Japanese Circulation Society
雑誌
Circulation Reports (ISSN:24340790)
巻号頁・発行日
pp.CR-22-0113, (Released:2023-04-12)
参考文献数
30

Background: Cardiac rehabilitation (CR) is an evidence-based medical service for patients with acute myocardial infarction (AMI); however, its implementation is inadequate. We investigated the provision status and equality of CR by hospitals in Japan using a comprehensive nationwide claims database.Methods and Results: We analyzed data from the National Database of Health Insurance Claims and Specific Health Checkups in Japan for the period April 2014–March 2016. We identified patients aged ≥20 years with postintervention AMI. We calculated hospital-level proportions of inpatient and outpatient CR participation. The equality of hospital-level proportions of inpatient and outpatient CR participation was evaluated using the Gini coefficient. We included 35,298 patients from 813 hospitals for the analysis of inpatients and 33,328 patients from 799 hospitals for the analysis of outpatients. The median hospital-level proportions of inpatient and outpatient CR participation were 73.3% and 1.8%, respectively. The distribution of inpatient CR participation was bimodal; the Gini coefficients of inpatient and outpatient CR participation were 0.37 and 0.73, respectively. Although there were statistically significant differences in the hospital-level proportion of CR participation for several hospital factors, CR certification status for reimbursement was the only visually evident factor affecting the distribution of CR participation.Conclusions: The distributions of inpatient and outpatient CR participation by hospitals were suboptimal. Further research is warranted to determine future strategies.
著者
Ryo Harada Keitaro Kume Kazumasa Horie Takuro Nakayama Yuji Inagaki Toshiyuki Amagasa
出版者
Information Processing Society of Japan
雑誌
IPSJ Transactions on Bioinformatics (ISSN:18826679)
巻号頁・発行日
vol.16, pp.20-27, 2023 (Released:2023-07-25)
参考文献数
48

Eukaryotic genomes contain exons and introns, and it is necessary to accurately identify exon-intron boundaries, i.e., splice sites, to annotate genomes. To address this problem, many previous works have proposed annotation methods/tools based on RNA-seq evidence. Many recent works exploit neural networks (NNs) as their prediction models, but only a few can be used to generate new genome annotation in practice. In this study, we propose AtLASS, a fully automated method for predicting splice sites from genomic and RNA-seq data using attention-based Bi-LSTM (Bidirectional Long Short-Term Memory). We exploit two-stage training on RNA-seq data to address the problem of biased label problem, thereby reducing the false positives. The experiments on the genomes of three species show that the performance of the proposed method itself is comparable to that of existing methods, but we can achieve better performance by combining the outputs of the proposed method and the existing method. The proposed method is the first program specialized in end-to-end splice site prediction using NNs.