Deep learning for early detection of Zenker’s diverticulum based on swallowing sound analysis
Daniel Ostler-Mildner, Alissa Jell, Matthias Seibold, Hubertus Feussner, Simone Graf, Dirk Wilhelm, Jonas Fuchtmann · 2026
Read Deep learning for early detection of Zenker’s diverticulum based on swallowing sound analysis by Daniel Ostler-Mildner, Alissa Jell, Matthias Seibold, Hubertus Feussner, Simone Graf, Dirk Wilhelm, Jonas Fuchtmann (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-13553711.txt.
Description
Daniel Ostler-Mildner and colleagues built a sound-based screening tool for a throat pouch disorder that often goes undiagnosed for years, publishing the work in 2026. Zenker's diverticulum causes swallowing trouble, yet confirming it usually needs a specialist centre and video X-ray, which smaller clinics may lack. The team recorded neck sounds during swallowing with a portable device, gathering data from 23 patients and 27 healthy volunteers.
Their two-stage deep learning model first spots swallows in the recordings, then sorts each swallow as healthy or pathological. Patient-level accuracy reached about 89 percent, with a similarly strong balance of precision and recall. The authors present the approach as a first noninvasive screen that could speed referral, cut diagnostic delays, and lower costs in swallowing care.
Catalog record
| CREATOR | Daniel Ostler-Mildner, Alissa Jell, Matthias Seibold, Hubertus Feussner, Simone Graf, Dirk Wilhelm, Jonas Fuchtmann |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |