Evaluating the benefits of machine learning for diagnosing deep vein thrombosis compared with gold standard ultrasound: a feasibility study
Kerstin Nothnagel, Mohammed Farid Aslam · 2024
Read Evaluating the benefits of machine learning for diagnosing deep vein thrombosis compared with gold standard ultrasound: a feasibility study by Kerstin Nothnagel, Mohammed Farid Aslam (2024) 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-11687269.txt.
Description
A blood clot in a deep leg vein can cause real harm if missed, and the usual expert scan is not always close at hand. Nothnagel and Aslam test whether staff without scan training can capture useful images with a hand probe. An artificial intelligence app guides the probe, and the clips go online for a specialist to read at a distance. Patients with suspected clots had the guided scan and then the standard formal scan for comparison.
Among 91 patients, most of them older women, about one scan in five was left incomplete. Of the rest, most were good enough to read. For those scans the method caught every true clot and was right on most clear veins. About half the patients were low risk and might skip the formal scan. The authors say guided scanning could speed up care and reach into general practice.
Catalog record
| CREATOR | Kerstin Nothnagel, Mohammed Farid Aslam |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 20 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |