Machine learning prediction of germline BRCA1/2 pathogenic variants in patients with ovarian cancer
Giovanni Innella, Giulia Erini, Antonio De Leo, Lea Godino, Luca Caramanna, Simona Ferrari, Sara Miccoli, Anna Myriam Perrone, Claudio Zamagni, Pierandrea De Iaco, Daniela Turchetti, Paola Rucci · 2025
Read Machine learning prediction of germline BRCA1/2 pathogenic variants in patients with ovarian cancer by Giovanni Innella, Giulia Erini, Antonio De Leo, Lea Godino, Luca Caramanna, Simona Ferrari, Sara Miccoli, Anna Myriam Perrone, Claudio Zamagni, Pierandrea De Iaco, Daniela Turchetti, Paola Rucci (2025) 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-12766824.txt.
Description
Giovanni Innella and eleven co-authors test whether software can flag ovarian cancer patients likely to carry a faulty breast cancer gene, in a 2025 paper. Inherited damage in the BRCA1 or BRCA2 genes changes treatment and family advice, but gene testing everyone is costly. A good guess from routine chart data could target testing well.
The team fed the records of 648 tested patients into three learning methods. A boosting method did best, calling the overall answer right about eighty-five percent of the time. Family history of ovarian cancer drove the guesses most, then tumor type and the patient's own breast cancer history. Age at diagnosis helped a little; tumor stage added nothing.
Catalog record
| CREATOR | Giovanni Innella, Giulia Erini, Antonio De Leo, Lea Godino, Luca Caramanna, Simona Ferrari, Sara Miccoli, Anna Myriam Perrone, Claudio Zamagni, Pierandrea De Iaco, Daniela Turchetti, Paola Rucci |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 18 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |