Artificial Intelligence–Assisted Amphiregulin and Epiregulin IHC Predicts Panitumumab Benefit in RAS Wild-Type Metastatic Colorectal Cancer

Abstract

Purpose High tumor mRNA levels of the EGFR ligands, amphiregulin (AREG) and epiregulin (EREG) are associated with anti-EGFR agent response in metastatic colorectal cancer (mCRC). However, ligand RNA assays have not been adopted into routine practice due to issues with analytical precision and practicality. We investigated whether AREG/EREG immunohistochemistry (IHC) could predict benefit from the anti-EGFR agent, panitumumab. Experimental Design Artificial intelligence algorithms were developed to assess AREG/EREG IHC in 274 patients from the PICCOLO trial of irinotecan+/-panitumumab (Ir vs IrPan) in RAS wild-type (-wt) mCRC. The primary endpoint was progression-free survival (PFS). Secondary endpoints were Response Evaluation Criteria in Solid Tumors (RECIST) response rate (RR) and overall survival (OS). Models were repeated adjusting separately for BRAF mutation status and primary tumor location (PTL). Results High ligand expression was associated with significant PFS benefit from IrPan compared with Ir (8·0 vs 3·2 months; HR 0·54, 95% CI 0·37-0·79; p=0·001); whereas low ligand expression was not (3·4 vs 4·4 months; HR 1·05, 95% CI 0·74-1·49; p=0·78). The ligand-treatment interaction was significant (pinteraction=0·02) and remained significant after adjustment for BRAF-mutation status and PTL. Likewise, RECIST RR was significantly improved in patients with high ligand expression (IrPan vs Ir: 48% vs 6%; p<0·0001) but not those with low ligand expression (25% vs 14%; p=0·10) (pinteraction=0·01). The effect on OS was similar but not statistically significant. Conclusion AREG/EREG IHC identified patients who benefitted from the addition of panitumumab to irinotecan chemotherapy. IHC is a practicable assay that may be of use in routine practice.