Subgroup Analytics and Advanced Semantic Technologies to Enable Personalized Medicine

亚组分析和先进语义技术可实现个性化医疗

• 批准号: 8979535
• 负责人: Daniel Jay Riskin
• 金额: $ 22.47万
• 依托单位: VMT, INC.
• 依托单位国家: 美国
• 财政年份: 2015
• 资助国家: 美国
• 起止时间: 2015-09-10 至 2016-09-09
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/8979535
• 关键词: Accounting; Caring; Clinical; Clinical Data; Clinical Informatics; Clinical Trials; Code; Complex; Computer Assisted; Congresses; Cost Control; Data; Data Element; Electronic Health Record; Electronics; Exclusion Criteria; Goals; Health; Health system; Healthcare; Healthcare Systems; Industry; Informatics; Intervention; Investments; Label; Maps; Measurement; Medicine; Modeling; Natural Language Processing; Outcome; Pathway interactions; Patients; Pharmacologic Substance; Phase; Process; Quality of Care; Randomized Controlled Trials; Rest; Running; Semantics; Small Business Innovation Research Grant; Statutes and Laws; Structure; Subgroup; System; Technology; Time; United States; Work; World Health; base; clinical care; clinical phenotype; cohort; commercialization; cost; data sharing; health data; improved; inclusion criteria; meetings; payment; personalized medicine; population health; public health relevance; randomized trial; standard of care; success

 DESCRIPTION (provided by applicant): United States healthcare is embroiled in a crisis of inconsistent quality and overwhelming cost. Through two administrations, the national healthcare strategy has focused on using data and technology to control costs and improve care. Congress has enacted legislation to encourage measurement of quality, sharing of data, payment based on quality of care, and transparency within the healthcare system. While these goals are bipartisan and lofty, implementation requires both hard work from health systems and robust technology. Industry has developed technologies that incrementally further the national agenda, including electronic health records, computer assisted coding, and population health analytics. Each of these supports workflow within the healthcare system and improves profit margin for healthcare organizations. But, approaches that go beyond workflow, using data to better understand clinical care, are lacking. With newly available electronic health data and a massive increase in processing power, data-driven personalized medicine is just now becoming possible. It will require advanced semantic technologies to understand clinical care strategies that have been tried in the past, but that have unknown efficacy. It will pose informatics challenges in inferring inclusion criteria, interventions, and outcomes from incomplete and poorly structured data. It will require deep clinical understanding to run real-time pragmatic clinical trials based on real world data to understand complex patients. The goal, dependent on Phase I success, is to create the first commercial system to support healthcare in running real-time pragmatic clinical trials using full clinical data. This will augment the standard of care defined by randomized controlled trials to actually tailor therapy for those complex patients that account for the majority of healthcare spends, but for whom complexity precludes tailored randomized trials.

 描述（由申请人提供）：美国医疗保健陷入质量不稳定和成本高昂的危机。通过两届政府，国家医疗保健战略的重点是利用数据和技术来控制成本和改善护理。国会已颁布立法，鼓励医疗保健系统内的质量衡量、数据共享、基于护理质量的支付以及透明度。虽然这些目标是两党共同的崇高目标，但实现需要卫生系统的艰苦努力和强大的技术。工业界已经开发出逐步推进国家议程的技术，包括电子健康记录、计算机辅助编码和人口健康分析。其中每一个都支持医疗保健系统内的工作流程，并提高医疗保健组织的利润率。但是，缺乏超越工作流程、使用数据更好地了解临床护理的方法。随着新可用的电子健康数据和处理能力的大幅提高，数据驱动的个性化医疗现已成为可能。它将需要先进的语义技术来理解过去已经尝试过但效果未知的临床护理策略。它将给从不完整和结构不良的数据推断纳入标准、干预措施和结果带来信息学挑战。需要深入的临床理解才能基于真实世界数据进行实时实用临床试验以了解复杂的患者。取决于第一阶段的成功，目标是创建第一个商业系统，支持医疗保健使用完整的临床数据运行实时实用的临床试验。这将增强随机对照试验定义的护理标准，以便为那些占医疗保健支出大部分的复杂患者量身定制治疗方案，但对于这些患者来说，复杂性妨碍了定制的随机试验。