Externally Validated Longitudinal GRU Model for Visit-Level 180-Day Mortality Risk in Metastatic Castration-Resistant Prostate Cancer

TL;DR

This study developed and validated a longitudinal GRU-based model to predict 180-day mortality risk in metastatic castration-resistant prostate cancer patients, demonstrating high accuracy and clinical utility using routine clinical data.

Contribution

The paper introduces a novel externally validated GRU model for visit-level mortality prediction in mCRPC, outperforming other architectures in calibration and discrimination.

Findings

GRU model achieved a PR-AUC of 0.87 in external validation.

BMI and systolic blood pressure were key predictors.

Model supports proactive care planning over several months.

Abstract

Metastatic castration-resistant prostate cancer (mCRPC) is a highly aggressive disease with poor prognosis and heterogeneous treatment response. In this work, we developed and externally validated a visit-level 180-day mortality risk model using longitudinal data from two Phase III cohorts (n=526 and n=640). Only visits with observable 180-day outcomes were labeled; right-censored cases were excluded from analysis. We compared five candidate architectures: Long Short-Term Memory, Gated Recurrent Unit (GRU), Cox Proportional Hazards, Random Survival Forest (RSF), and Logistic Regression. For each dataset, we selected the smallest risk-threshold that achieved an 85% sensitivity floor. The GRU and RSF models showed high discrimination capabilities initially (C-index: 87% for both). In external validation, the GRU obtained a higher calibration (slope: 0.93; intercept: 0.07) and achieved an PR-AUC of 0.87. Clinical impact analysis showed a median time-in-warning of 151.0 days for true positives (59.0 days for false positives) and 18.3 alerts per 100 patient-visits. Given late-stage frailty or cachexia and hemodynamic instability, permutation importance ranked BMI and systolic blood pressure as the strongest associations. These results suggest that longitudinal routine clinical markers can estimate short-horizon mortality risk in mCRPC and support proactive care planning over a multi-month window.