KGEN: A Knowledge-Guided Evolutionary Framework for Feature Selection in Breast Cancer Risk Assessment
- 1School of Mathematics and Computer Science (SMCS), Institute of Business Administration (IBA), Karachi 75270, Pakistan
- 2The Aga Khan University Hospital, Karachi 74800, Pakistan
- 3Faculty of Computer and Information Systems, Islamic University of Madinah, Madinah 42351, Saudi Arabia
Abstract
Choosing which features go into a clinical risk model is not only a statistical problem. A model that is accurate but whose feature list makes no clinical sense will not be trusted by the physicians it is meant to help, and most feature-selection methods still include a clinician’s judgment only as a filter applied after the search, not as part of it. This paper introduces KGEN, a genetic algorithm that builds an oncologist’s feature ratings directly into both the starting population and the fitness function, alongside data-driven importance scores, through one tunable weight. We tested this on 67,858 women from the PLCO Cancer Screening Trial, searching over 75 candidate features, against a matched no-expert control run under an identical search budget. Across four independent runs, expert guidance raised clinical relevance substantially and consistently (0.929–1.000 versus 0.682 for the no-expert control and 0.669–0.720 for four of the five conventional baselines, the exception being BCRAT, whose fixed feature set happens to reach a perfect 1.000; pooled p=0.0019 across sub-populations), while discrimination stayed within the same narrow range as every conventional baseline throughout, and, in three of the four sub-populations, was even modestly but significantly higher than the no-expert control’s: a clinically sensible feature list did not come at the cost of accuracy. The same wide-margin clinical-relevance pattern held on an independent hospital-readmission dataset of 99,343 encounters and an independent breast-cancer gene-expression cohort, each with a small, measurable accuracy trade-off against the strongest conventional baselines. Feature-selection stability across runs was also higher under expert guidance for three of four sub-populations. This suggests that a clinician’s judgment can be built into a search algorithm as a working input, not just a check performed afterward.
Related
- Quadrature Perturbations and High-Order Time Discretization for Prescribed-Feature Evolutionary GTransNet Galerkin Systems
- Linear-Time Multivariate Unsupervised Feature Selection Using Nyström-Based Entropy Approximation
- Learning from pandemics: Feature selection and clustering for robust digital disease nowcasting
- Universal Feature Selection with Noisy Observations and Weak Symmetry Conditions
- Variable Selection for Feature-Based Newsvendor
BibTeX
@article{humayun2026kgen,
title = {{KGEN: A Knowledge-Guided Evolutionary Framework for Feature Selection in Breast Cancer Risk Assessment}},
author = {Saadia Humayun and Tariq Mahmood and Munira Moosajee and Muhammad Shoaib Siddiqui},
journal = {Mathematics},
year = {2026},
month = oct,
doi = {10.3390/math14193591},
url = {https://www.mdpi.com/2227-7390/14/19/3591},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - KGEN: A Knowledge-Guided Evolutionary Framework for Feature Selection in Breast Cancer Risk Assessment
AU - Saadia Humayun
AU - Tariq Mahmood
AU - Munira Moosajee
AU - Muhammad Shoaib Siddiqui
PY - 2026
DA - 2026/10/02
JO - Mathematics
DO - 10.3390/math14193591
UR - https://www.mdpi.com/2227-7390/14/19/3591
AB - Choosing which features go into a clinical risk model is not only a statistical problem. A model that is accurate but whose feature list makes no clinical sense will not be trusted by the physicians it is meant to help, and most feature-selection methods still include a clinician’s judgment only as a filter applied after the search, not as part of it. This paper introduces KGEN, a genetic algorithm that builds an oncologist’s feature ratings directly into both the starting population and the fitness function, alongside data-driven importance scores, through one tunable weight. We tested this on 67,858 women from the PLCO Cancer Screening Trial, searching over 75 candidate features, against a matched no-expert control run under an identical search budget. Across four independent runs, expert guidance raised clinical relevance substantially and consistently (0.929–1.000 versus 0.682 for the no-expert control and 0.669–0.720 for four of the five conventional baselines, the exception being BCRAT, whose fixed feature set happens to reach a perfect 1.000; pooled p=0.0019 across sub-populations), while discrimination stayed within the same narrow range as every conventional baseline throughout, and, in three of the four sub-populations, was even modestly but significantly higher than the no-expert control’s: a clinically sensible feature list did not come at the cost of accuracy. The same wide-margin clinical-relevance pattern held on an independent hospital-readmission dataset of 99,343 encounters and an independent breast-cancer gene-expression cohort, each with a small, measurable accuracy trade-off against the strongest conventional baselines. Feature-selection stability across runs was also higher under expert guidance for three of four sub-populations. This suggests that a clinician’s judgment can be built into a search algorithm as a working input, not just a check performed afterward.
SN - 2227-7390
ER -