Active Surveillance (AS) for prostate cancer is a management option that continually monitors early disease and considers intervention if progression occurs. A robust method to incorporate “live” updates of progression risk during follow-up has hitherto been lacking. To address this, we developed a deep learning-based individualised longitudinal survival model using Dynamic-DeepHit-Lite (DDHL) that learns data-driven distribution of time-to-event outcomes. Further refining outputs, we used a reinforcement learning approach (Actor-Critic) for temporal predictive clustering (AC-TPC) to discover groups with similar time-to-event outcomes to support clinical utility. We applied these methods to data from 585 men on AS with longitudinal and comprehensive follow-up (median 4.4 years). Time-dependent C-indices and Brier scores were calculated and compared to Cox regression and landmarking methods. Both Cox and DDHL models including only baseline variables showed comparable C-indices but the DDHL model performance improved with additional follow-up data. With 3 years of data collection and 3 years follow-up the DDHL model had a C-index of 0.79 (±0.11) compared to 0.70 (±0.15) for landmarking Cox and 0.67 (±0.09) for baseline Cox only. Model calibration was good across all models tested. The AC-TPC method further discovered 4 distinct outcome-related temporal clusters with distinct progression trajectories. Those in the lowest risk cluster had negligible progression risk while those in the highest cluster had a 50% risk of progression by 5 years. In summary, we report a novel machine learning approach to inform personalised follow-up during active surveillance which improves predictive power with increasing data input over time.

前列腺癌的主动监测 (AS) 是一种管理选项，可以持续监测早期疾病并在出现进展时考虑干预。迄今为止，缺乏一种在随访期间纳入进展风险“实时”更新的稳健方法。为了解决这个问题，我们使用 Dynamic-DeepHit-Lite (DDHL) 开发了一个基于深度学习的个性化纵向生存模型，该模型学习数据驱动的事件时间结果分布。进一步细化输出，我们使用强化学习方法 (Actor-Critic) 进行时间预测聚类 (AC-TPC)，以发现具有相似事件时间结果的组，以支持临床效用。我们将这些方法应用于来自 585 名患有 AS 的男性的数据，并进行了纵向和全面的随访（中位数 4.4 年）。计算了与时间相关的 C 指数和 Brier 分数，并与 Cox 回归和界标方法进行了比较。仅包括基线变量的 Cox 和 DDHL 模型都显示出可比较的 C 指数，但 DDHL 模型的性能随着额外的后续数据而提高。经过 3 年的数据收集和 3 年的随访，DDHL 模型的 C 指数为 0.79 (±0.11)，而标志性 Cox 为 0.70 (±0.15)，仅基线 Cox 为 0.67 (±0.09)。模型校准在所有测试的模型中都很好。AC-TPC 方法进一步发现了 4 个不同的结果相关时间簇，具有不同的进展轨迹。最低风险集群的进展风险可以忽略不计，而最高风险集群的进展风险为 50% 到 5 年。总之，