Deep-learning cardiac motion analysis for human survival prediction
- Submitting institution
-
The University of Birmingham
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 73868462
- Type
- D - Journal article
- DOI
-
10.1038/s42256-019-0019-2
- Title of journal
- Nature Machine Intelligence
- Article number
- -
- First page
- 95
- Volume
- 1
- Issue
- 2
- ISSN
- 2522-5839
- Open access status
- Exception within 3 months of publication
- Month of publication
- February
- Year of publication
- 2019
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
10
- Research group(s)
-
-
- Citation count
- 45
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work proposes a deep learning technique to predict human survival by tracking heart motion using cardiac MRI. It is significant because (1) the new technology is by far the most precise prediction of future cardiac events and allows doctors to interpret the output results from it; and (2) the technology correctly predicts a patient’s prognosis 75% of the time and outperforms doctors’ measurements. World-leading researchers such as Prof Sanjiv Narayan (Stanford) and Prof James Duncan (Yale) have taken up the work. Moreover, this work has recently led to a 5-year research grant (~£1m) from the British Heart Foundation.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -