.png){kind=icon}
.png){kind=icon}
Return
Current progress and obstacles for automated classification of causes of death based on death certificates: A systematic review
.png){kind=icon}
PRE
AI
C
Q
S
S
R
K
DOI：10.1016/j.ijmedinf.2026.106549.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Systematically reviewed studies on automated cause of death classification in a recent six-year period. • Deep learning and rule-based approaches are the most popular methodologies, with the former being rapidly developed. . • The performance varied substantially within and between studies, influenced by the settings and quality of data. • Deep learning models have potential although their performance needs to improve for infrequent causes of death. • Appropriate pre-training may enhance classification performance.
Journal
IF:
4.1
Papers:
4.5K
Citations:
1.1W
Organization
Cited Papers