A community challenge to predict clinical outcomes after immune checkpoint blockade in non-small cell lung cancer

: Mason Mike, Lapuente-Santana Óscar, Halkola Anni S., Wang Wenyu, Mall Raghvendra, Xiao Xu, Kaufman Jacob, Fu Jingxin, Pfeil Jacob, Banerjee Jineta, Chung Verena, Chang Han, Chasalow Scott D., Lin Hung Ying, Chai Rongrong, Yu Thomas, Finotello Francesca, Mirtti Tuomas, Mäyränpää Mikko I., Bao Jie, Verschuren Emmy W., Ahmed Eiman I., Ceccarelli Michele, Miller Lance D., Monaco Gianni, Hendrickx Wouter R. L., Sherif Shimaa, Yang Lin, Tang Ming, Gu Shengqing Stan, Zhang Wubing, Zhang Yi, Zeng Zexian, Das Sahu Avinash, Liu Yang, Yang Wenxian, Bedognetti Davide, Tang Jing, Eduati Federica, Laajala Teemu D., Geese William J., Guinney Justin, Szustakowski Joseph D., Vincent Benjamin G., Carbone David P.

Publisher: BioMed Central

: 2024

: Journal of Translational Medicine

: 190

: 22

: 1

: 1479-5876

DOI: https://doi.org/10.1186/s12967-023-04705-3

: https://translational-medicine.biomedcentral.com/articles/10.1186/s12967-023-04705-3

: https://research.utu.fi/converis/portal/detail/Publication/387386055

Background

Predictive biomarkers of immune checkpoint inhibitor (ICI) efficacy are currently lacking for non-small cell lung cancer (NSCLC). Here, we describe the results from the Anti–PD-1 Response Prediction DREAM Challenge, a crowdsourced initiative that enabled the assessment of predictive models by using data from two randomized controlled clinical trials (RCTs) of ICIs in first-line metastatic NSCLC.

Methods

Participants developed and trained models using public resources. These were evaluated with data from the CheckMate 026 trial (NCT02041533), according to the model-to-data paradigm to maintain patient confidentiality. The generalizability of the models with the best predictive performance was assessed using data from the CheckMate 227 trial (NCT02477826). Both trials were phase III RCTs with a chemotherapy control arm, which supported the differentiation between predictive and prognostic models. Isolated model containers were evaluated using a bespoke strategy that considered the challenges of handling transcriptome data from clinical trials.

Results

A total of 59 teams participated, with 417 models submitted. Multiple predictive models, as opposed to a prognostic model, were generated for predicting overall survival, progression-free survival, and progressive disease status with ICIs. Variables within the models submitted by participants included tumor mutational burden (TMB), programmed death ligand 1 (PD-L1) expression, and gene-expression–based signatures. The best-performing models showed improved predictive power over reference variables, including TMB or PD-L1.

Conclusions

This DREAM Challenge is the first successful attempt to use protected phase III clinical data for a crowdsourced effort towards generating predictive models for ICI clinical outcomes and could serve as a blueprint for similar efforts in other tumor types and disease states, setting a benchmark for future studies aiming to identify biomarkers predictive of ICI efficacy.

Trial registration

CheckMate 026; NCT02041533, registered January 22, 2014. CheckMate 227; NCT02477826, registered June 23, 2015.

s12967-023-04705-3.pdf