Simpler predictive models provide higher accuracy for ovarian cancer detection
Derrick E. Wood, Joseph Roy, Bari J. Ballew · 2025
Read Simpler predictive models provide higher accuracy for ovarian cancer detection by Derrick E. Wood, Joseph Roy, Bari J. Ballew (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-12716435.txt.
Description
Derrick Wood, Joseph Roy, and Bari Ballew wrote a paper in two thousand twenty-five arguing that simpler models detect ovarian cancer more accurately. Two blood proteins are known markers for the disease, and combining them with a standard regression already gives very high accuracy. A newer, complex model added features from free DNA in blood and claimed gains.
The authors re-examined that model's training data and found a technical flaw. A large share of the cancer samples carried odd chromosome values unlike the rest, which skewed the reported results. After removing those samples, the complex model no longer beat the simple protein-only models. The authors conclude the DNA features are not justified, and that simpler models tend to generalize better.
Catalog record
| CREATOR | Derrick E. Wood, Joseph Roy, Bari J. Ballew |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 44 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |