Prediction of cancer-associated thrombosis by machine learning: results from the Vienna Cancer and Thrombosis Study

T. Hoberstorfer, C.P. Spielvogel, C. Englisch, N. Vladic, S. Nopp, F. Moik, M. Preusser, I. Pabinger, C. Ay · 2026

Read Prediction of cancer-associated thrombosis by machine learning: results from the Vienna Cancer and Thrombosis Study by T. Hoberstorfer, C.P. Spielvogel, C. Englisch, N. Vladic, S. Nopp, F. Moik, M. Preusser, I. Pabinger, C. Ay (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-13235454.txt.

Description

T. Hoberstorfer and colleagues tested in 2026 whether machine learning can better predict blood clots in people with cancer. Clots in veins are a frequent, serious complication of cancer and its treatment. Data came from a long-running Vienna cohort of more than two thousand patients followed for clot events. Six classification models learned from clinical details and many laboratory measurements.

Performance of the best model, an enhanced logistic regression, was modest at both six months and two years. Its discrimination matched established risk scores rather than beating them in the validation. Strongest contributors included an inherited clotting mutation, a personal history of clots, and certain tumour types such as pancreatic cancer. Newly diagnosed cancer also raised predicted risk in the model. The authors conclude that adding extensive biomarker panels to machine learning did not improve prediction in this cohort.

Catalog record

CREATORT. Hoberstorfer, C.P. Spielvogel, C. Englisch, N. Vladic, S. Nopp, F. Moik, M. Preusser, I. Pabinger, C. Ay
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE34 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13235454

Browse the full library · About the Tower of Babel