Abstract
Background
Treatment selection in patients with advanced non-small cell lung cancer (NSCLC) is based on programmed death-ligand 1 (PD-L1) expression, which is usually scored manually and is subject to intra-/inter-pathologist variability. A PD-L1 clone-agnostic artificial intelligence (AI) model for AI-based measurement of PD-L1 (AIM-PD-L1) was developed and assessed in advanced NSCLC using clinical samples from two Phase 3 trials.
Methods
IMpower110 evaluated atezolizumab versus chemotherapy in PD-L1-positive metastatic, stage IV, squamous/nonsquamous NSCLC. IMpower150 evaluated atezolizumab, carboplatin and paclitaxel, with/without bevacizumab versus carboplatin, paclitaxel, and bevacizumab in patients with metastatic nonsquamous NSCLC. AIM-PD-L1 was developed and deployed on SP263-stained whole slide images (IMpower110, n=509; IMpower150, n=766) for digital scoring of tumor cell (TC) PD-L1 expression and identification of human interpretable features (HIFs) associated with survival outcomes.
Results
Overall percentage agreements between scoring methods for TC ≥50% and ≥1% cutoffs were high. Survival analyses were similar for PD-L1 subgroups between scoring methods at both TC cutoffs. A non-significant improvement in survival outcomes was observed in patients treated with atezolizumab-containing regimens and classified positive by digital scoring but missed by manual scoring. Two HIFs in the cancer epithelium—density of all PD-L1–positive TC and immune cells—were nominally associated with overall survival. Many HIFs were identified to be predictive for significantly improved progression-free survival with atezolizumab-containing regimens versus control.
Conclusions
AIM-PD-L1 digital SP263 PD-L1 scoring is concordant with manual scoring showing similar predictivity for benefit and could potentially be used as a predictive marker for patient stratification and selection for anti-PD-(L)1 therapy.
Authors
- Herbst et al.