Classification of recurrence status after surgical treatment of chronic subdural hemorrhage – A machine learning approach

Hussam Hamou, Julius Kernbach, Hani Ridwan, Kimberley Fay-Rodrian, Hans Clusmann, Anke Hoellig, Michael Veldeman · 2026

Read Classification of recurrence status after surgical treatment of chronic subdural hemorrhage – A machine learning approach by Hussam Hamou, Julius Kernbach, Hani Ridwan, Kimberley Fay-Rodrian, Hans Clusmann, Anke Hoellig, Michael Veldeman (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/plos-pone-0346756.txt.

Description

Hussam Hamou and colleagues test machine learning for predicting brain bleed relapse in a 2026 PLOS ONE study. Chronic subdural hematoma is a slow blood collection under the skull covering, and surgery is followed by relapse needing a second operation in a share of cases. Predicting relapse could focus follow-up scans on those at risk.

The team studied five hundred and sixty-four surgery patients at one center and trained three model types on thirty-one routine variables. The best model scored only modestly on held-out patients and was overconfident in its single-patient risks. At a cautious threshold it could spare scans for only about a third of non-relapse patients. Relapse likely depends on factors routine records miss.

Catalog record

CREATORHussam Hamou, Julius Kernbach, Hani Ridwan, Kimberley Fay-Rodrian, Hans Clusmann, Anke Hoellig, Michael Veldeman
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE81100
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0346756

Browse the full library · About the Tower of Babel