Optimized Gene Selection Using Nomadic People and Salp Swarm Algorithms for Cancer Detection
Computational method selects gene combinations for cancer detection with high accuracy, though clinical testing remains needed.
This computational study proposed a hybrid swarm intelligence approach (NPO + enhanced SSA) for gene selection in cancer detection, achieving 91-97% accuracy on five public gene expression datasets with substantial feature reduction. While results are promising on public benchmarks, the study lacks prospective clinical validation and relies solely on in silico data.
What the study was
- Study design
- Computational/in silico machine learning feature selection study
- Population
- 5 public gene expression datasets (LUAD, GSE2034 breast, GBM, GSE2109 ovarian, COAD)
- Category
- Diagnostics
- Maturity
- Exploratory
- Journal
- IEEE Transactions on Computational Biology and Bioinformatics
Why it surfaced
In silico only; no prospective validation; benchmark datasets only; capped per non-human model rule.
A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.