As the population ages, patients’ complexity and the scope of their care is increasing. Over 60% of the population is 65 years of age or older and suffers from multi-morbidity, which is associated with two times as many patient-physician encounters. Yet clinical practice guidelines (CPGs) are developed to treat a single disease. To reconcile these two competing issues, previously we developed a framework for mitigation, i.e., identifying and addressing adverse interactions in multi-morbid patients managed according to multiple CPGs. That framework relies on first-order logic (FOL) to represent CPGs and secondary medical knowledge and FOL theorem proving to establish valid patient management plans. In the work presented here, we leverage our earlier research and simplify the mitigation process by representing it as a planning problem using the Planning Domain Definition Language (PDDL). This new framework, called MitPlan, identifies and addresses adverse interactions using durative planning actions that embody clinical actions (including medication administration and patient testing), supports a physician-defined length of planning horizons, and optimizes plans based on patient preferences and action costs. It supports a variety of criteria when developing management plans, including the total cost of prescribed treatment and the cost of the revisions to be introduced. The solution to MitPlan's planning problem is a sequence of timed actions that are easy to interpret when creating a management plan. We demonstrate MitPlan's capabilities using illustrative and clinical case studies.

随着人口老龄化，患者的复杂性和他们的护理范围正在增加。超过 60% 的人口年龄在 65 岁或以上，并且患有多种疾病，这与医患接触的次数是两倍。然而，临床实践指南 (CPG) 是为治疗单一疾病而制定的。为了调和这两个相互竞争的问题，我们之前开发了一个缓解框架，即识别和解决根据多个 CPG 管理的多病患者的不良相互作用。该框架依赖一阶逻辑 (FOL) 来表示 CPG 和二级医学知识以及 FOL 定理证明来建立有效的患者管理计划。在这里展示的作品中，我们利用我们早期的研究并通过使用规划域定义语言 (PDDL) 将其表示为规划问题来简化缓解过程。这个名为 MitPlan 的新框架使用体现临床行动（包括药物管理和患者测试）的持续计划行动来识别和解决不良相互作用，支持医生定义的计划范围长度，并根据患者偏好和行动成本优化计划。在制定管理计划时，它支持各种标准，包括规定治疗的总成本和要引入的修订成本。MitPlan 计划问题的解决方案是一系列定时操作，这些操作在创建管理计划时易于解释。我们展示了 MitPlan'