Neves Mariana R, Franke Molly, Mitnick Carole, Ciobanu Nelly, Crudu Valeriu, Furin Jennifer, Cohen Ted, Yaesoubi Reza
Department of Health Policy and Management, Yale School of Public Health, New Haven, USA.
Department of Global Health and Social Medicine, Harvard Medical School, Boston, USA.
medRxiv. 2025 Aug 11:2025.08.07.25333118. doi: 10.1101/2025.08.07.25333118.
For many medical conditions, rapid, reliable, and affordable diagnostic tests are not available, which leads clinicians to base treatment decisions on patient symptoms and history. Although prediction models can estimate disease risk, they typically do not account for the downstream health or cost consequences of acting on their predictions. We developed and evaluated methods that integrate risk prediction with decision modeling to inform personalized, cost-effective treatment recommendations.
We considered two integration methods to maximize the population net monetary benefit (NMB), which summarizes both health and cost outcomes of available actions. In the method, the predicted probability of disease from a risk prediction model is used as input to a decision model. In the method, the decision model relies on the risk prediction model's binary disease classification. We applied these methods to select between two treatment regimens for patients with rifampicin-resistant tuberculosis in Moldova, while accounting for cost, toxicity, and efficacy associated with each regimen.
Both integration methods yielded higher population NMB than standard of care and approaches based on fixed classification thresholds (e.g., 50% or the threshold that maximizes the Youden's index). However, the classification-based approach was less sensitive to whether the model predictions were properly calibrated.
Integrating risk predictions with decision models offers a principled framework for making personalized, value-based treatment decisions. These methods explicitly account for health and cost consequences of treatment choices informed by risk prediction models, improving care quality and resource use in settings with diagnostic uncertainty.
对于许多医疗状况而言，快速、可靠且经济实惠的诊断测试并不存在，这使得临床医生只能依据患者的症状和病史来做出治疗决策。尽管预测模型能够估计疾病风险，但它们通常并未考虑基于其预测采取行动所带来的下游健康或成本后果。我们开发并评估了将风险预测与决策建模相结合的方法，以提供个性化的、具有成本效益的治疗建议。
我们考虑了两种整合方法，以最大化总体净货币效益（NMB），该效益总结了可用行动的健康和成本结果。在 方法中，风险预测模型预测的疾病概率被用作决策模型的输入。在 方法中，决策模型依赖于风险预测模型的二元疾病分类。我们应用这些方法为摩尔多瓦耐利福平结核病患者在两种治疗方案之间进行选择，同时考虑每种方案的成本、毒性和疗效。
两种整合方法产生的总体 NMB 均高于标准治疗以及基于固定分类阈值（例如 50%或使约登指数最大化的阈值）的方法。然而，基于分类的方法对模型预测是否经过适当校准不太敏感。
将风险预测与决策模型相结合为做出个性化的、基于价值的治疗决策提供了一个有原则的框架。这些方法明确考虑了由风险预测模型提供信息的治疗选择所带来的健康和成本后果，在存在诊断不确定性的情况下提高了护理质量和资源利用效率。
