Distributed, Collaborative Intelligent Agents for Proactive Post-Marketing Drug S

描述（由申请人提供）：全国范围内的医疗保健系统和保险公司定期根据有关药物的益处、风险和成本的证据来决定将哪些药物纳入或排除在其处方集中。有效药物选择的一个主要障碍是缺乏足够的关于药物（尤其是新药）安全性的公开信息。非常需要在医疗机构中运行的计算机化系统，该系统可以在将新药引入处方集后提供持续、主动的监测并及时识别潜在的安全问题。这样的系统可以带来更安全的药物使用政策、更具成本效益的处方决策、更好的医疗保健以及更早发现药物不良反应（ADR）。这种技术对改善国家药物监测系统的影响将是显而易见的，因为 ADR 会使患者的医疗状况复杂化、增加发病率并导致死亡（美国每年约有 7,000 例死亡归因于 ADR）。目前，为这些决策提供信息的安全问题证据主要由 FDA 的上市后监测系统 MedWatch(tm) 生成。 MedWatch(tm) 是一个被动系统，依赖于自愿、自发的报告。由于该系统受到低报告率和缓慢积累足够事件以进行关键分析的限制，因此在识别和从市场上撤回有问题的药物或在其上贴上黑框警告标签方面会出现延迟。这些延误导致了不必要的死亡、发病和医疗费用。 我们建议开发一个名为 ADRMonitor 的创新的基于团队的代理系统，用于主动监控和检测涉及医疗机构预期或潜在 ADR 的信号对。每个 ADRMonitor 用户（例如医生和药物安全官员）都将拥有自己的软件代理，该代理可通过互联网访问并扮演两个角色：协助用户做出决策，并与其他团队成员的代理进行协作。该方法的一个关键特征是代理将持续、自主地相互协作。他们预测队友的信息需求并主动共享信息，以便用户可以及时收到有关信号对的警报。 为了证明可行性，我们计划在这个为期两年的试点项目中开发 ADRMonitor 原型，该项目将由我们的多学科团队协作开展。我们的初步设计和分析表明所提出的方法是有前途的。拟议的工作代表了在本研究工作后期开发更全面的 ADRMonitor 的关键的第一步，该监测器将使用信号对来检测 ADR，并将所得系统扩展到覆盖一个地区或全国范围内的医疗保健。所提出的方法本质上是通用的，可以适用于其他重要的应用，例如生物恐怖主义监视。 公共卫生相关性：非常需要在医疗机构中运行的计算机化系统，该系统可以在将新药引入处方集后提供持续、主动的监测并及时识别潜在的安全问题。这样的系统可以带来更安全的药物使用政策、更具成本效益的处方决策、更好的医疗保健以及更早发现药物不良反应（ADR）。这种技术对改善国家药物监测系统的影响将是显而易见的，因为 ADR 会使患者的医疗状况复杂化、增加发病率并导致死亡（美国每年约有 7,000 例死亡归因于 ADR）。

DESCRIPTION (provided by applicant): Healthcare systems and insurers nationwide regularly make decisions regarding which drugs to include or exclude from their formularies based on evidence concerning benefits, risks, and costs of the medications. A major barrier to effective drug selection is the lack of sufficient published information on the safety of drugs, particularly new drugs. A computerized system operating at healthcare facilities that could provide continuous, active surveillance and timely identification of potential safety issues following the introduction of a new drug to a formulary is highly desirable. Such a system could lead to safer drug use policy, more cost-effective formulary decisions, better healthcare, and earlier detection of adverse drug reactions (ADRs). The implications of such technology for improving a national drug surveillance system will be apparent because ADRs can complicate the patient's medical condition, increase morbidity, and result in death (about 7,000 deaths per year in the U.S. were attributed to ADRs). At present, evidence on safety issues that would inform these decisions is generated primarily by the FDA's post-marketing surveillance system MedWatch(tm). MedWatch(tm) is a passive system that depends on voluntary, spontaneous reports. Because the system is limited by low reporting rates and the slow accumulation of sufficient events to enable a critical analysis, delays occur in the identification and withdrawal of problematic drugs from the market or labeling them with black box warnings. These delays have resulted in unnecessary mortality, morbidity, and costs of healthcare. We propose to develop an innovative team-based agent system, named ADRMonitor, for actively monitoring and detecting signal pairs implicating anticipated or potential ADRs at a healthcare facility. Each ADRMonitor user (e.g., physicians and drug safety officers) will have his/her own software agent that is accessible via the Internet and plays two roles -- assisting the user in his/her decision-making, and collaborating with agents of other team members. A key feature of the proposed approach is that the agents will continuously and autonomously collaborate with one another. They anticipate information needs of their teammates and share information proactively so that the users can be alerted timely about signal pairs. To demonstrate the feasibility, we plan to develop a prototype of ADRMonitor in this two-year pilot project, which will be undertaken collaboratively by our multidisciplinary team. Our preliminary design and analysis show the proposed methodology to be promising. The proposed effort represents a critical first step toward a subsequent development of a more comprehensive ADRMonitor in later phases of this research endeavor that would use the signal pairs to detect ADRs and expand the resultant system to cover healthcare in a region or across the country. The proposed methodology is general in nature and can be adapted for other important applications such as bioterrorism surveillance. PUBLIC HEALTH RELEVANCE: A computerized system operating at healthcare facilities that could provide continuous, active surveillance and timely identification of potential safety issues following the introduction of a new drug to a formulary is highly desirable. Such a system could lead to safer drug use policy, more cost-effective formulary decisions, better healthcare, and earlier detection of adverse drug reactions (ADRs). The implications of such technology for improving a national drug surveillance system will be apparent because ADRs can complicate the patient's medical condition, increase morbidity, and result in death (about 7,000 deaths per year in the U.S. were attributed to ADRs).