From the Department of Medical Statistics, London School of Hygiene and Tropical Medicine, London, United Kingdom.
Medical Research Council (MRC) Biostatistics Unit, University of Cambridge, Cambridge, United Kingdom.
Epidemiology. 2019 Jan;30(1):29-37. doi: 10.1097/EDE.0000000000000920.
Cystic fibrosis (CF) is an inherited, chronic, progressive condition affecting around 10,000 individuals in the United Kingdom and over 70,000 worldwide. Survival in CF has improved considerably over recent decades, and it is important to provide up-to-date information on patient prognosis.
The UK Cystic Fibrosis Registry is a secure centralized database, which collects annual data on almost all CF patients in the United Kingdom. Data from 43,592 annual records from 2005 to 2015 on 6181 individuals were used to develop a dynamic survival prediction model that provides personalized estimates of survival probabilities given a patient's current health status using 16 predictors. We developed the model using the landmarking approach, giving predicted survival curves up to 10 years from 18 to 50 years of age. We compared several models using cross-validation.
The final model has good discrimination (C-indexes: 0.873, 0.843, and 0.804 for 2-, 5-, and 10-year survival prediction) and low prediction error (Brier scores: 0.036, 0.076, and 0.133). It identifies individuals at low and high risk of short- and long-term mortality based on their current status. For patients 20 years of age during 2013-2015, for example, over 80% had a greater than 95% probability of 2-year survival and 40% were predicted to survive 10 years or more.
Dynamic personalized prediction models can guide treatment decisions and provide personalized information for patients. Our application illustrates the utility of the landmarking approach for making the best use of longitudinal and survival data and shows how models can be defined and compared in terms of predictive performance.
囊性纤维化（CF）是一种遗传性、慢性、进行性疾病，影响英国约 10000 人，全球超过 70000 人。近年来，CF 的生存率有了显著提高，因此提供有关患者预后的最新信息非常重要。
英国囊性纤维化登记处是一个安全的集中式数据库，收集了英国几乎所有 CF 患者的年度数据。使用 2005 年至 2015 年的 6181 名患者的 43592 份年度记录的数据，开发了一个动态生存预测模型，该模型使用 16 个预测因子，根据患者当前的健康状况，提供个性化的生存概率估计。我们使用定标法开发模型，为 18 至 50 岁的患者提供长达 10 年的预测生存曲线。我们使用交叉验证比较了几种模型。
最终模型具有良好的区分度（2 年、5 年和 10 年生存率预测的 C 指数分别为 0.873、0.843 和 0.804）和低预测误差（Brier 分数分别为 0.036、0.076 和 0.133）。它根据当前状况识别出短期和长期死亡风险低和高的个体。例如，对于 2013-2015 年 20 岁的患者，超过 80%的患者有大于 95%的 2 年生存率，40%的患者预计能存活 10 年或更长时间。
动态个性化预测模型可以指导治疗决策，并为患者提供个性化信息。我们的应用说明了定标法在充分利用纵向和生存数据方面的效用，并展示了如何根据预测性能定义和比较模型。
