OBJECTIVE: We sought to characterize unique gene signature patterns associated with worse overall survival (OS) among patients with stage IV colorectal cancer (CRC) using a machine learning (ML) approach. METHODS: Data from the AACR GENIE registry were analyzed for genetic variations (somatic mutations, structural variants and copy number alterations) among patients with CRC. Adult patients (≥18 years) with histologically confirmed stage IV CRC who underwent next-generation sequencing were included. An eXtreme Gradient Boosting (XGBoost) model was developed to predict OS and the relative importance of different genetic alterations was determined using SHapley Additive exPlanations (SHAP) algorithm. RESULTS: Among 688 patients with stage IV CRC, 54.4 % were male (n = 374) with a median age of 55 years (IQR, 46-64). An XGBoost model developed using the 200 most frequent genetic alterations demonstrated good performance to predict OS with a c-index of 0.701 (95 % CI: 0.675-0.726) on 5-fold cross-validation. The model achieved time-dependent AUC of 0.742, 0.757 and 0.793 at 12-, 24- and 36-months, respectively. The SHAP algorithm identified the top 20 genetic alterations most strongly predictive of worse OS among stage IV CRC patients. Based on the 20-gene signature, individuals at high risk had worse 12- and 36-month OS versus low-risk patients (82.6 % vs. 97.1 % and 30.1 % vs. 72.6 %, respectively
p <
0.001). CONCLUSION: The XGBoost ML model identified a unique gene signature that accurately risk stratified stage IV CRC patients. ML models that incorporate molecular information represent an opportunity to predict long-term outcomes and potentially identify novel therapeutic targets for stage IV CRC patients.