ICES: Small: Collaborative Research: Data-driven mechanisms in healthcare

ICES：小型：协作研究：医疗保健中的数据驱动机制

• 批准号: 1216011
• 负责人: Mohsen Bayati
• 金额: $ 20万
• 依托单位: Stanford University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2012
• 资助国家: 美国
• 起止时间: 2012-09-01 至 2015-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1216011&HistoricalAwards=false
• 关键词: ICES; Small; Collaborative; Research; Data

The main objective of the project is to develop and study new incentive and reimbursement mechanisms within the context of the delivery of medical care. The project takes a game-theoretic perspective, with the main players being the government, health plans, healthcare providers, and patients. Some of the design goals of the mechanisms are to motivate the parties involved to improve healthcare quality while controlling costs. Among others, the study will try to extend the algorithmic game theory framework to address the unique challenges that occur in the context of healthcare. A key goal of the study is understanding the extent to which utilizing electronically available medical records may enable new mechanisms in the context of healthcare. In particular, the project studies potential advantages of high quality risk-adjustment schemes that are empowered by the application of machine learning to medical data.In recent years, much of the focus in the US public policy debate has been given to problems surrounding providing and sustaining healthcare services. One of the key problems the US healthcare system faces is that of aligning incentives among the various stakeholders - the government, health plans, care providers, and patients - to ensure favorable outcomes and efficient resource utilization. The study will use tools from algorithms and game theory to develop new alignment strategies. In particular, the study will look at ways in which the collection and data-mining of electronic health records may be used to provide better incentives for the stakeholders, and lead to better overall care at lower cost.

该项目的主要目标是在提供医疗服务的范围内制定和研究新的奖励和偿还机制。该项目采用了博弈论的观点，主要参与者是政府，健康计划，医疗保健提供者和患者。这些机制的一些设计目标是激励有关各方在控制成本的同时提高医疗质量。除其他外，该研究将尝试扩展算法博弈论框架，以解决医疗保健领域出现的独特挑战。该研究的一个关键目标是了解利用电子病历在医疗保健方面可能实现新机制的程度。特别是，该项目研究通过将机器学习应用于医疗数据而增强的高质量风险调整方案的潜在优势。近年来，美国公共政策辩论的大部分焦点都集中在围绕提供和维持医疗服务的问题上。美国医疗体系面临的关键问题之一是协调不同利益相关者--政府、医疗计划、医疗服务提供者和患者--之间的激励措施，以确保有利的结果和有效的资源利用。这项研究将使用算法和博弈论的工具来开发新的对齐策略。特别是，该研究将探讨如何利用电子健康记录的收集和数据挖掘为利益相关者提供更好的激励，并以更低的成本提供更好的整体护理。