Tumor Center Regensburg/ University of Regensburg, Institute for Quality Control and Health Services Research, Regensburg, Germany.
Department of Health Technology and Services Research, Technical Medical Centre, University of Twente, P.O. Box 217, 7500 AE, Enschede, The Netherlands.
BMC Med Res Methodol. 2022 Sep 10;22(1):239. doi: 10.1186/s12874-022-01718-2.
Risk-prediction tools allow classifying individuals into risk groups based on risk thresholds. Such risk categorization is often used to inform screening schemes by offering screening only to individuals at increased risk of harmful events. Adding information concerning an individual's risk development over time would allow assessing not just who to screen but also when to screen. This paper illustrates the value of personalised, time-dependent risk predictions to optimize risk-based screening schemes.
In a simulation analysis, two different time-dependent risk-based screening approaches are compared to another risk-based, but time-independent approach regarding their impact on screening efficiency. For this purpose, 81 scenarios featuring 5000 patients with five consecutive annual risk estimations for a hypothetical disease D are simulated, using different parameters to model disease progression and risk distribution. This simulation analysis is validated using a real-world clinical case study based on German breast cancer patients and the INFLUENCE-nomogram for locoregional breast cancer recurrence.
If individual risk estimations were used to personalise screening for a disease D aiming at detecting a 90% of curable cases, more than 20% of screening examinations could be avoided relative to a conventional uninformed approach, depending on the simulated scenario. Whereas an individual but time-independent approach is associated with acceptable saving potentials in case of a relatively homogenous risk distribution, the time-dependent approaches are superior when the complexity of a scenario increases. With slowly progressing diseases, risk-accumulation over time needs to be considered to achieve the highest screening efficiency on population level, for rapidly progressing diseases, an interval-specific approach is superior. The possible benefits of time-dependent risk-based screening were confirmed in the real-world clinical case study.
Appropriate approaches to use time-dependent risk predictions may considerably enhance screening efficiency on individual and population level. Therefore, predicting risk development over time should be supported by future prediction tools and be incorporated in decision algorithms.
风险预测工具可以根据风险阈值将个体分类到风险组中。这种风险分类通常用于通过仅向处于有害事件风险增加的个体提供筛查来告知筛查计划。添加有关个体随时间推移的风险发展的信息将不仅允许评估要筛查的对象，还允许评估何时进行筛查。本文说明了个性化、随时间变化的风险预测在优化基于风险的筛查计划方面的价值。
在模拟分析中，两种不同的基于时间的风险筛查方法与另一种基于风险但时间独立的方法进行了比较，以评估它们对筛查效率的影响。为此，使用不同的参数模拟了 5000 名患有假设疾病 D 的患者的 81 个场景，这些参数用于模拟疾病进展和风险分布。使用基于德国乳腺癌患者和 INFLUENCE-局部区域乳腺癌复发风险预测图的真实临床案例研究对该模拟分析进行了验证。
如果使用个体风险估计值来个性化筛查疾病 D，以检测 90%的可治愈病例，与传统的无信息方法相比，取决于模拟场景，可避免超过 20%的筛查检查。虽然个体但时间独立的方法在风险分布相对均匀的情况下与可接受的节省潜力相关，但随着场景复杂性的增加，时间相关方法更具优势。对于进展缓慢的疾病，需要考虑随时间的风险积累，以在人群水平上实现最高的筛查效率，对于进展迅速的疾病，特定间隔的方法更具优势。真实世界临床案例研究证实了基于时间的风险筛查的可能益处。
适当的方法可以利用时间相关的风险预测来显著提高个体和人群水平的筛查效率。因此，未来的预测工具应支持随时间推移预测风险发展，并将其纳入决策算法中。
