Stability and interpretability of penalized logistic regression models for breast cancer risk prediction
Francis Okyere, Michael Nyanney · 2026
Read Stability and interpretability of penalized logistic regression models for breast cancer risk prediction by Francis Okyere, Michael Nyanney (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-0353489.txt.
Description
Francis Okyere and Michael Nyanney published this 2026 statistics study of breast cancer risk models built from tumor measures in a classic Wisconsin data set. They compared three penalized regression methods that shrink or drop predictors, judging not only accuracy but whether repeated samples keep choosing the same tumor features.
All three separated cancer from non-cancer almost perfectly, and more honest risk scores than plain regression. Ridge kept every feature steadily, lasso was sparse but jumpy, and elastic net balanced both. Okyere argues stability checks belong in medical prediction, not accuracy alone.
Catalog record
| CREATOR | Francis Okyere, Michael Nyanney |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 43730 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |