November 2, 2026 · Mayo Clinic proceedings · DOI: 10.1016/j.mayocp.2026.06.029

Feature Selection and Machine Learning Strategies to Develop a Minimal Bioassay for Cholangiocarcinoma Subtype.

Listen to this summary

This study asks whether a cheap, clinically feasible RNA sequencing assay can reproduce the molecular subtyping of cholangiocarcinoma that normally requires costly multiomic (RNA, protein, and phosphoprotein) profiling. Using feature selection and machine learning on 249 tumors from Mayo Clinic and Fudan University, the authors found that a panel of just 20 RNA transcripts, classified with gradient boosted trees, achieved 83.8% accuracy and an AUC of 0.961 on reserved test data. The results suggest that combining feature selection with machine learning can make multiomic-based subtyping practical for routine clinical use.

Ellen L Larson, Erik Jessen, Dong-Gi Mun, Jennifer L Tomlinson, Amro M Abdelrahman, Danielle M Carlson, Hojjat Salehinejad, Rory L Smoot

This is one of 33,000+ journals available on OSLR. Try it free for 14 days.

Free 14-day trial. 33,000+ journals. Cancel anytime.

14-day free trial. No commitment.

“

"Oslr has become part of my weekly routine on my day off. The clinical relevance of the summaries is outstanding — I'd rate it 9/10. Being able to consume research hands-free is a huge advantage for busy physicians."

Dr. Jennifer Thompson

Dr. Jennifer Thompson

Portland, OR

Stay current without falling behind

33,000+ journals. 3-minute audio summaries. Free for 14 days.

Download on the App StoreGet it on Google Play