A Dynamic Prognostic Prediction Method for Colorectal Cancer Liver Metastasis

TL;DR

This paper introduces DyPro, a deep learning model that predicts colorectal cancer liver metastasis outcomes by modeling tumor dynamics over time, improving personalized prognosis accuracy.

Contribution

DyPro uniquely captures longitudinal tumor evolution and multimodal clinical data to enhance postoperative prognostic predictions in CRLM patients.

Findings

DyPro achieves a C-index of 0.755 for overall survival.

DyPro attains an AUC@1y of 0.920 for survival prediction.

DyPro provides quantitative risk cues for clinical decision-making.

Abstract

Colorectal cancer liver metastasis (CRLM) exhibits high postoperative recurrence and pronounced prognostic heterogeneity, challenging individualized management. Existing prognostic approaches often rely on static representations from a single postoperative snapshot, and fail to jointly capture tumor spatial distribution, longitudinal disease dynamics, and multimodal clinical information, limiting predictive accuracy. We propose DyPro, a deep learning framework that infers postoperative latent trajectories via residual dynamic evolution. Starting from an initial patient representation, DyPro generates a 12-step sequence of trajectory snapshots through autoregressive residual updates and integrates them to predict recurrence and survival outcomes. On the MSKCC CRLM dataset, DyPro achieves strong discrimination under repeated stratified 5-fold cross-validation, reaching a C-index of 0.755 for OS and 0.714 for DFS, with OS AUC@1y of 0.920 and OS IBS of 0.143. DyPro provides quantitative risk cues to support adjuvant therapy planning and follow-up scheduling.