Deep-learning–based non-contrast CT for detecting acute ischemic stroke: a systematic review and HSROC meta-analysis of patient-level diagnostic accuracy
Kalab Yigermal Gete, Asnakew Achaw Ayele · 2025
Read Deep-learning–based non-contrast CT for detecting acute ischemic stroke: a systematic review and HSROC meta-analysis of patient-level diagnostic accuracy by Kalab Yigermal Gete, Asnakew Achaw Ayele (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12706894.txt.
Description
Kalab Yigermal Gete and Asnakew Achaw Ayele present a 2025 review pooling how well deep learning reads plain head scans to catch acute stroke. The plain scan is the first image taken when stroke is suspected, but early signs are faint and easy to miss. Software that flags stroke at the patient level could speed treatment.
The authors searched three databases for studies from 2010 to mid 2025 that tested such software against a sound reference. Sloppy designs, like lesion only reports, were excluded. Two reviewers screened and extracted the data, and bias was graded with a standard tool. A joint statistical model then pooled the accuracy across studies and probed why results varied.
Catalog record
| CREATOR | Kalab Yigermal Gete, Asnakew Achaw Ayele |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |