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

2026-01-27

AI Summary

This study addresses the lack of reliable short-term mortality risk prediction tools for patients with metastatic castration-resistant prostate cancer (mCRPC) by developing and externally validating a 180-day mortality risk prediction model using only routine clinical variables from two phase III clinical trial cohorts. By excluding right-censored observations and applying an 85% sensitivity threshold, the authors present the first external validation of a longitudinal gated recurrent unit (GRU)–based model in mCRPC. The GRU model demonstrated superior performance (calibration slope: 0.93; intercept: 0.07; PR-AUC: 0.87), providing early warnings for high-risk patients an average of 151 days in advance (triggering 18.3 alerts per 100 clinic visits). This enables prospective care planning over multiple months and identifies body mass index and systolic blood pressure as key predictive factors.

Technology Category

• Machine Learning: Probabilistic Circuits and Graphical Models
• Reasoning under Uncertainty: Relational Probabilistic Models
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• mCRPC
• 180-day mortality risk
• longitudinal data
• visit-level prediction
• external validation

Innovation

• Gated Recurrent Unit
• longitudinal modeling
• external validation
• short-term mortality prediction
• visit-level risk assessment