- 著者
- Yasuhiro Hamatani Yasuko Takada Yoshihiro Miyamoto Yukie Kawano Yuta Anchi Tatsuhiro Shibata Atsushi Suzuki Mitsunori Nishikawa Hiroto Ito Masashi Kato Tsuyoshi Shiga Yoshihiro Fukumoto Chisato Izumi Satoshi Yasuda Hisao Ogawa Yasuo Sugano Toshihisa Anzai
- 出版者
- The Japanese Circulation Society
- 雑誌
- Circulation Journal (ISSN:13469843)
- 巻号頁・発行日
- pp.CJ-19-0225, (Released:2020-01-25)
- 参考文献数
- 25
- 被引用文献数
- 17
Background:Palliative care is highly relevant for patients with heart failure (HF), and there is a need for quantitative information on quality of care. Accordingly, this study aimed to develop a set of quality indicators (QIs) for palliative care of HF patients, and to conduct a practical pilot measurement of the proposed QIs in clinical practice.Methods and Results:We used a modified Delphi technique, a consensus method that involves a comprehensive literature review, face-to-face multidisciplinary panel meeting, and anonymous rating in 2 rounds. A 15-member multidisciplinary expert panel individually rated each potential indicator on a scale of 1 (lowest) to 9 (highest) for appropriateness. All indicators receiving a median score ≥7 without significant disagreement were included in the final set of QIs. Through the consensus-building process, 35 QIs were proposed for palliative care in HF patients. Practical measurement in HF patients (n=131) from 3 teaching hospitals revealed that all of the proposed QIs could be obtained retrospectively from medical records, and the following QIs had low performance (<10%): “Intervention by multidisciplinary team”, “Opioid therapy for patients with refractory dyspnea”, and “Screening for psychological symptoms”.Conclusions:The first set of QIs for palliative care of HF patients was developed and could clarify quantitative information and might improve the quality of care.
- 著者
- Yasuhiro Hamatani Yasuko Takada Yoshihiro Miyamoto Yukie Kawano Yuta Anchi Tatsuhiro Shibata Atsushi Suzuki Mitsunori Nishikawa Hiroto Ito Masashi Kato Tsuyoshi Shiga Yoshihiro Fukumoto Chisato Izumi Satoshi Yasuda Hisao Ogawa Yasuo Sugano Toshihisa Anzai
- 出版者
- The Japanese Circulation Society
- 雑誌
- Circulation Journal (ISSN:13469843)
- 巻号頁・発行日
- vol.84, no.4, pp.584-591, 2020-03-25 (Released:2020-03-25)
- 参考文献数
- 25
- 被引用文献数
- 13 17
Background:Palliative care is highly relevant for patients with heart failure (HF), and there is a need for quantitative information on quality of care. Accordingly, this study aimed to develop a set of quality indicators (QIs) for palliative care of HF patients, and to conduct a practical pilot measurement of the proposed QIs in clinical practice.Methods and Results:We used a modified Delphi technique, a consensus method that involves a comprehensive literature review, face-to-face multidisciplinary panel meeting, and anonymous rating in 2 rounds. A 15-member multidisciplinary expert panel individually rated each potential indicator on a scale of 1 (lowest) to 9 (highest) for appropriateness. All indicators receiving a median score ≥7 without significant disagreement were included in the final set of QIs. Through the consensus-building process, 35 QIs were proposed for palliative care in HF patients. Practical measurement in HF patients (n=131) from 3 teaching hospitals revealed that all of the proposed QIs could be obtained retrospectively from medical records, and the following QIs had low performance (<10%): “Intervention by multidisciplinary team”, “Opioid therapy for patients with refractory dyspnea”, and “Screening for psychological symptoms”.Conclusions:The first set of QIs for palliative care of HF patients was developed and could clarify quantitative information and might improve the quality of care.
- 著者
- Motoki Amagasaki Hiroki Oyama Yuichiro Fujishiro Masahiro Iida Hiroaki Yasuda Hiroto Ito
- 出版者
- Information Processing Society of Japan
- 雑誌
- IPSJ Transactions on System LSI Design Methodology (ISSN:18826687)
- 巻号頁・発行日
- vol.13, pp.69-71, 2020 (Released:2020-08-13)
- 参考文献数
- 7
Graph neural networks are a type of deep-learning model for classification of graph domains. To infer arithmetic functions in a netlist, we applied relational graph convolutional networks (R-GCN), which can directly treat relations between nodes and edges. However, because original R-GCN supports only for node level labeling, it cannot be directly used to infer set of functions in a netlist. In this paper, by considering the distribution of labels for each node, we show a R-GCN based function inference method and data augmentation technique for netlist having multiple functions. According to our result, 91.4% accuracy is obtained from 1, 000 training data, thus demonstrating that R-GCN-based methods can be effective for graphs with multiple functions.