Machine learning and cancer survival: analysis of the Registro Hospitalar de Câncer do Estado de São Paulo
Fernando Henrique de Albuquerque Maia, Lucas Buk Cardoso, Simone Aldrey Angelo, Yasmin Pacheco Gil Bonilha, Adeylson Guimarães Ribeiro, Maria Paula Curado, Gisele Aparecida Fernandes, Alexandre Dias Porto Chiavegatto, Vanderlei Cunha Parro, Tatiana Natasha Toporcov, Fernando Henrique de Albuquerque Maia, Lucas Buk Cardoso, Simone Aldrey Angelo, Yasmin Pacheco Gil Bonilha, Adeylson Guimarães Ribeiro, Maria Paula Curado, Gisele Aparecida Fernandes, Alexandre Dias Porto Chiavegatto, Vanderlei Cunha Parro, Tatiana Natasha Toporcov · 2026
Read Machine learning and cancer survival: analysis of the Registro Hospitalar de Câncer do Estado de São Paulo by Fernando Henrique de Albuquerque Maia, Lucas Buk Cardoso, Simone Aldrey Angelo, Yasmin Pacheco Gil Bonilha, Adeylson Guimarães Ribeiro, Maria Paula Curado, Gisele Aparecida Fernandes, Alexandre Dias Porto Chiavegatto, Vanderlei Cunha Parro, Tatiana Natasha Toporcov, Fernando Henrique de Albuquerque Maia, Lucas Buk Cardoso, Simone Aldrey Angelo, Yasmin Pacheco Gil Bonilha, Adeylson Guimarães Ribeiro, Maria Paula Curado, Gisele Aparecida Fernandes, Alexandre Dias Porto Chiavegatto, Vanderlei Cunha Parro, Tatiana Natasha Toporcov (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/PMC13398606.txt.
Description
Fernando Henrique de Albuquerque Maia and colleagues race six survival-learning algorithms on São Paulo state cancer registry data. Their 2026 study covers the five most common cancers in the hospital registry: breast, prostate, lung, colorectal and cervix. Machine learning promises sharper survival forecasts than classic statistics, but which algorithm wins depends on the cancer.
An XGBoost model using accelerated failure time took the best concordance scores for breast, lung, colorectal and cervix cancers, reaching 0.7845 for breast cases in the results shown. Gradient boosting won for prostate cancer instead, at 0.7574 on the same yardstick. Clinical stage stood out as the strongest predictor everywhere, a sanity anchor for the algorithms' rankings.
Catalog record
| CREATOR | Fernando Henrique de Albuquerque Maia, Lucas Buk Cardoso, Simone Aldrey Angelo, Yasmin Pacheco Gil Bonilha, Adeylson Guimarães Ribeiro, Maria Paula Curado, Gisele Aparecida Fernandes, Alexandre Dias Porto Chiavegatto, Vanderlei Cunha Parro, Tatiana Natasha Toporcov, Fernando Henrique de Albuquerque Maia, Lucas Buk Cardoso, Simone Aldrey Angelo, Yasmin Pacheco Gil Bonilha, Adeylson Guimarães Ribeiro, Maria Paula Curado, Gisele Aparecida Fernandes, Alexandre Dias Porto Chiavegatto, Vanderlei Cunha Parro, Tatiana Natasha Toporcov |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 87529 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |