Communications Medicine (Dec 2022)
Deep learning-based age estimation from chest X-rays indicates cardiovascular prognosis
- Hirotaka Ieki,
- Kaoru Ito,
- Mike Saji,
- Rei Kawakami,
- Yuji Nagatomo,
- Kaori Takada,
- Toshiya Kariyasu,
- Haruhiko Machida,
- Satoshi Koyama,
- Hiroki Yoshida,
- Ryo Kurosawa,
- Hiroshi Matsunaga,
- Kazuo Miyazawa,
- Kouichi Ozaki,
- Yoshihiro Onouchi,
- Susumu Katsushika,
- Ryo Matsuoka,
- Hiroki Shinohara,
- Toshihiro Yamaguchi,
- Satoshi Kodera,
- Yasutomi Higashikuni,
- Katsuhito Fujiu,
- Hiroshi Akazawa,
- Nobuo Iguchi,
- Mitsuaki Isobe,
- Tsutomu Yoshikawa,
- Issei Komuro
Affiliations
- Hirotaka Ieki
- Laboratory for Cardiovascular Genomics and Informatics, RIKEN Center for Integrative Medical Sciences
- Kaoru Ito
- Laboratory for Cardiovascular Genomics and Informatics, RIKEN Center for Integrative Medical Sciences
- Mike Saji
- Department of Cardiology, Sakakibara Heart Institute
- Rei Kawakami
- Department of Computer Science, School of Computing, Tokyo Institute of Technology
- Yuji Nagatomo
- Department of Cardiology, Sakakibara Heart Institute
- Kaori Takada
- Department of Radiology, Sakakibara Heart Institute
- Toshiya Kariyasu
- Department of Radiology, Sakakibara Heart Institute
- Haruhiko Machida
- Department of Radiology, Sakakibara Heart Institute
- Satoshi Koyama
- Laboratory for Cardiovascular Genomics and Informatics, RIKEN Center for Integrative Medical Sciences
- Hiroki Yoshida
- Laboratory for Cardiovascular Genomics and Informatics, RIKEN Center for Integrative Medical Sciences
- Ryo Kurosawa
- Laboratory for Cardiovascular Genomics and Informatics, RIKEN Center for Integrative Medical Sciences
- Hiroshi Matsunaga
- Laboratory for Cardiovascular Genomics and Informatics, RIKEN Center for Integrative Medical Sciences
- Kazuo Miyazawa
- Laboratory for Cardiovascular Genomics and Informatics, RIKEN Center for Integrative Medical Sciences
- Kouichi Ozaki
- Laboratory for Cardiovascular Genomics and Informatics, RIKEN Center for Integrative Medical Sciences
- Yoshihiro Onouchi
- Laboratory for Cardiovascular Genomics and Informatics, RIKEN Center for Integrative Medical Sciences
- Susumu Katsushika
- Department of Cardiovascular Medicine, Graduate School of Medicine, The University of Tokyo
- Ryo Matsuoka
- Department of Cardiovascular Medicine, Graduate School of Medicine, The University of Tokyo
- Hiroki Shinohara
- Department of Cardiovascular Medicine, Graduate School of Medicine, The University of Tokyo
- Toshihiro Yamaguchi
- Department of Cardiovascular Medicine, Graduate School of Medicine, The University of Tokyo
- Satoshi Kodera
- Department of Cardiovascular Medicine, Graduate School of Medicine, The University of Tokyo
- Yasutomi Higashikuni
- Department of Cardiovascular Medicine, Graduate School of Medicine, The University of Tokyo
- Katsuhito Fujiu
- Department of Cardiovascular Medicine, Graduate School of Medicine, The University of Tokyo
- Hiroshi Akazawa
- Department of Cardiovascular Medicine, Graduate School of Medicine, The University of Tokyo
- Nobuo Iguchi
- Department of Cardiology, Sakakibara Heart Institute
- Mitsuaki Isobe
- Sakakibara Heart Institute
- Tsutomu Yoshikawa
- Department of Cardiology, Sakakibara Heart Institute
- Issei Komuro
- Department of Cardiovascular Medicine, Graduate School of Medicine, The University of Tokyo
- DOI
- https://doi.org/10.1038/s43856-022-00220-6
- Journal volume & issue
-
Vol. 2,
no. 1
pp. 1 – 12
Abstract
Ieki et al. train a deep learning model to estimate patients’ age from chest X-ray images. X-ray age is found to be an indicator of poor prognosis in patients with heart failure and patients admitted to the intensive care unit with cardiovascular disease.
