Benchmark RadarOncoTraj
OncoTraj is a public benchmark for predicting acquired resistance to first-line osimertinib in EGFR-mutant non-small-cell lung cancer. It provides a harmonized dataset of 813 patients from three real-world sources, with locked splits, an evaluation harness, and six baselines, defining three tasks: 12-month progression classification, time-to-progression regression, and resistance mechanism classification.
- Released
- 2026-06-09
- Readiness
- Runnable
- Primary field
- Health & Life Sciences
Why it matters
OncoTraj fills the gap of a standardized, public evaluation for longitudinal resistance prediction, offering reproducible baseline results and leakage-audited splits. It provides a practical means to compare models and highlights the limitation of single-timepoint features, guiding future data collection and algorithm development.
Motivation
Resistance to first-line osimertinib in EGFR-mutant non-small-cell lung cancer (NSCLC) is the canonical example of predictable clonal evolution under therapeutic pressure, yet no public benchmark exists for training or evaluating computational models on the corresponding longitudinal patient trajectories.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.