Artificial intelligence (AI)-powered diagnostic support for stroke via Telegram bot: preliminary findings
Babatunde Ogunmiloro · 2026
Read Artificial intelligence (AI)-powered diagnostic support for stroke via Telegram bot: preliminary findings by Babatunde Ogunmiloro (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/PMC13523235.txt.
Description
Babatunde Ogunmiloro tests an artificial intelligence stroke aid delivered through a messaging app in a 2026 preliminary study. Expert neuroimaging is scarce in many underserved regions, and early stroke treatment is often missed. Two image models were trained on more than six thousand annotated brain CT scans covering normal scans and two stroke types, then checked on a separate public dataset.
The stronger model reached ninety-nine percent accuracy in internal testing and held up well on external sets, with especially strong detection of bleeding strokes, a distinction that guards against dangerous clot-busting treatment. The chosen model was built into a Telegram bot that answers in real time and deletes uploaded data automatically for privacy. The author acknowledges limits, including slice-level data splitting, and frames the results as preliminary.
Catalog record
| CREATOR | Babatunde Ogunmiloro |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49294 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |