Deep learning algorithm for automatic detection of acute ischemic stroke on noncontrast brain CT
Tae Jin Yun, Jin Wook Choi, Hoon Na, Miran Han, Woo Sang Jung, Ji Ye Lee, Roh-Eul Yoo, In Pyeong Hwang, Seung Hong Choi · 2026
Read Deep learning algorithm for automatic detection of acute ischemic stroke on noncontrast brain CT by Tae Jin Yun, Jin Wook Choi, Hoon Na, Miran Han, Woo Sang Jung, Ji Ye Lee, Roh-Eul Yoo, In Pyeong Hwang, Seung Hong Choi (2026) 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-13457881.txt.
Description
Tae Jin Yun and colleagues test an AI aid for spotting acute stroke on plain brain CT in a 2026 multi-reader study. Plain CT is the fastest first scan in stroke, yet small or subtle infarcts elude even skilled readers, delaying treatment. Nine readers, three non-radiologist physicians, three radiologists and three neuroradiologists, reviewed 917 cases with and without AI help in a crossover design.
Alone, the AI reached an area under the curve of about 0.81 with about 74 percent accuracy, about 76 percent sensitivity and about 73 percent specificity. With AI help, reader accuracy rose from about 72 to about 76 percent, with the largest gain for non-radiologists, from about 70 to about 75 percent. Emergency teams gain evidence that AI support narrows the expertise gap for stroke CT, though real-world timing and treatment gains still need prospective proof.
Catalog record
| CREATOR | Tae Jin Yun, Jin Wook Choi, Hoon Na, Miran Han, Woo Sang Jung, Ji Ye Lee, Roh-Eul Yoo, In Pyeong Hwang, Seung Hong Choi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 53 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |