Pi Selina, Rutter Carolyn M, Pineda-Antunez Carlos, Chen Jonathan H, Goldhaber-Fiebert Jeremy D, Alarid-Escudero Fernando
Department of Biomedical Data Science, School of Medicine, Stanford University, Palo Alto, CA.
Hutch Institute for Cancer Outcomes Research, Biostatistics Program, Public Health Sciences Division, Fred Hutch Cancer Center, Seattle, WA.
medRxiv. 2025 May 13:2025.05.12.25327470. doi: 10.1101/2025.05.12.25327470.
Simulation models inform health policy decisions by integrating data from multiple sources and forecasting outcomes when there is a lack of comprehensive evidence from empirical studies. Such models have long supported health policy for cancer, the first or second leading cause of death in over 100 countries. Discrete-event simulation (DES) and Bayesian calibration have gained traction in the field of Decision Science because they enable efficient and flexible modeling of complex health conditions and produce estimates of model parameters that reflect real-world disease epidemiology and data uncertainty given model constraints. This uncertainty is then propagated to model-generated outputs, enabling decision makers to determine the optimal strategy to recommend, assess confidence in the recommendation, and estimate the value of collecting additional information. However, there is limited end-to-end guidance on structuring a DES model for cancer progression, estimating its parameters using Bayesian calibration, and applying the calibration outputs to policy evaluation and other downstream tasks. To fill this gap, we introduce the Model for ancer nterventions and opulation ealth in (DESCIPHR), an open-source framework and codebase integrating a flexible DES model for the natural history of cancer, Bayesian calibration for parameter estimation, and screening strategy evaluation. We also introduce an automated method to generate data-informed parameter prior distributions and enhance the accuracy and flexibility of a neural network emulator-based Bayesian calibration algorithm. We anticipate that the adaptable DESCIPHR modeling template will facilitate the construction of future decision models evaluating the risks and benefits of health interventions.
模拟模型通过整合来自多个来源的数据并在缺乏实证研究的全面证据时预测结果，为卫生政策决策提供信息。此类模型长期以来一直为癌症卫生政策提供支持，癌症是100多个国家的首要或第二大死因。离散事件模拟（DES）和贝叶斯校准在决策科学领域越来越受欢迎，因为它们能够对复杂的健康状况进行高效灵活的建模，并生成反映真实世界疾病流行病学和给定模型约束下数据不确定性的模型参数估计值。然后，这种不确定性会传播到模型生成的输出中，使决策者能够确定推荐的最优策略、评估对该推荐的信心，并估计收集更多信息的价值。然而，在构建用于癌症进展的DES模型、使用贝叶斯校准估计其参数以及将校准输出应用于政策评估和其他下游任务方面，端到端的指导有限。为了填补这一空白，我们引入了癌症干预与人群健康模型（DESCIPHR）——一个开源框架和代码库，它集成了一个用于癌症自然史的灵活DES模型、用于参数估计的贝叶斯校准以及筛查策略评估。我们还引入了一种自动方法来生成基于数据的参数先验分布，并提高基于神经网络模拟器的贝叶斯校准算法的准确性和灵活性。我们预计，适应性强的DESCIPHR建模模板将有助于构建未来评估健康干预措施风险和益处的决策模型。
