Development and validation of the Immune Profile Score (IPS), a novel multi-omic algorithmic assay for stratifying outcomes in a real-world cohort of advanced solid cancer patients treated with immune checkpoint inhibitors

Background: Immune checkpoint inhibitors (ICIs) have transformed the oncology treatment landscape. Despite substantial improvements for some patients, the majority do not benefit from ICIs, indicating a need for predictive biomarkers to better inform treatment decisions. Methods: A de-identified pan-cancer cohort from the Tempus multimodal real-world database was used for the development and validation of the Immune Profile Score (IPS) algorithm leveraging Tempus xT (648 gene DNA panel) and xR (RNAseq). The cohort consisted of advanced stage cancer patients treated with any ICI-containing regimen as the first or second line of therapy. The IPS model was developed utilizing a machine learning framework that includes tumor mutational burden (TMB) and 8 RNA-based biomarkers as features. Results: IPS-High patients demonstrated significantly longer overall survival (OS) compared to IPS-Low patients (HR=0.45, 90% CI [0.40-0.52]). IPS was consistently prognostic in PD-L1 (positive/negative), TMB (high/low), microsatellite status (MSS/MSI), and regimen (ICI only/ICI + other) subgroups. In a subgroup of TMB-Low patients who received ICI-only therapy (n=323), IPS-high patients had longer survival than IPS-Low patients (HR=0.41 [0.30-0.57]). In a subgroup of MSS patients who received ICI only therapy in LOT1, IPS-High patients had longer survival than IPS-Low patients (HR=0.33 [0.24-0.45]). Additionally, IPS remained significant in multivariable models controlling for TMB, MSI, and PD-L1, with IPS HRs of 0.49 [0.42-0.56], 0.47 [0.41-0.53], and 0.45 [0.38-0.53] respectively. In an exploratory predictive utility analysis of the subset of patients (n=345) receiving first-line (1L) chemotherapy (CT) and second-line (2L) ICI, there was no significant effect of IPS for time to next treatment on CT in L1 (HR=1.06 [0.85-1.33]). However, there was a significant effect of IPS for OS on ICI in L2 (HR=0.63 [0.46-0.86]). A test of interaction was statistically significant (p<0.01). Conclusions: Our results demonstrate that IPS is a generalizable multi-omic biomarker that can be widely utilized clinically as a prognosticator of ICI based regimens.