SHB: Type I (EXP): Rehospitalization Analytics: Modeling and Reducing the Risks of Rehospitalization

住院治疗占美国每年2万亿美元医疗保健费用的30%以上。多达20%或更多的住院发生在前一次出院后30天内。这种再住院治疗不仅昂贵，而且可能有害，最重要的是，它们通常是可以预防的。为再住院风险高的目标患者群体提供特殊护理可以显著提高避免再住院的机会。估计在患者住院期间收集的临床数据的预测能力并有效地从这样的不同患者记录进行预测需要新的分析模型。该项目开发了一个“再住院分析”框架，可以使用广泛的电子健康记录来识别、表征和降低患者再住院的风险。具体而言，该项目的研究目标是：（i）集成模型，其可以有效地利用多个异质患者信息源，并且在仅存在少量患者记录的情况下在不同医院和患者组之间传递所获得的关于再住院的知识，（ii）在临床数据中存在固有概念漂移的情况下对风险估计进行预测的新颖的可适应的时间敏感模型，以及（iii）新的正则化方法，其可以有效地提取人群特异性风险因子，尽管存在多重相关性和分组的分类临床预测因子。使用在底特律的亨利福特健康系统收集的心力衰竭患者记录来评估该方法。所提出的模型的性能进行了比较，对国家的最先进的统计和临床工具，目前应用于风险prediction.This项目的目的是提供一个全面的，准确的，及时的再住院风险评估，并有可能针对特定的高风险患者更积极的治疗。在这个项目中开发的预测模型可以被广泛采用，并具有全国性的影响，因为源数据往往是在医院。这有可能通过减少急性加重来改善患者的生活，并通过减少住院次数来降低整体医疗保健成本。本项目中开发的计算模型也可应用于其他慢性病，这些慢性病的利用率很高，并可从改善干预/资源的目标中受益。该项目的教育目标是培养数据分析和医疗信息学领域的下一代跨学科研究人员。该项目的进展情况和研究结果通过项目网站（http：//www.cs.wayne.edu/projects/health/）传播。

Hospitalizations account for more than 30% of the $2 trillion annual cost of healthcare in the United States. As many as 20% or more of all hospital admissions occur within 30 days of a previous discharge. Such rehospitalizations are not only expensive but are also potentially harmful, and most importantly, they are often preventable. Providing special care for a targeted group of patients who are at a high risk of rehospitalization can significantly improve the chances of avoiding rehospitalization. Estimating the predictive power of the clinical data collected during the hospitalization of a patient and effectively making predictions from such diverse patient records requires new analytical models. This project develops a 'rehospitalization analytics' framework that can identify, characterize and reduce the risks of rehospitalization for patients using a wide range of electronic health records. Specifically, the research objectives of this project are to develop: (i) integrated models that can effectively leverage multiple heterogeneous patient information sources and transfer the acquired knowledge about rehospitalization between different hospitals and patient groups in the presence of only few patient records, (ii) novel adaptable time-sensitive models that make predictions of the risk estimates in the presence of inherent concept drifts in the clinical data, and (iii) new regularization methods that can effectively extract the population-specific risk factors despite the presence of multiple correlations and grouped categorical clinical predictors. The methods are evaluated using heart failure patient records collected at the Henry Ford Health System in Detroit. The performance of the proposed models is compared against the state-of-the-art statistical and clinical tools that are currently applied for risk prediction.This project aims to provide a comprehensive, accurate, and timely assessment of risk of rehospitalizations, and has the potential to direct more aggressive treatments towards specific high-risk patients. Predictive models developed in this project could be widely adopted and have nation-wide impact because the source data is often available at the hospitals. This has the potential to improve the lives of patients, by reducing exacerbations, and reducing overall health care costs by reducing the number of hospitalizations. The computational models developed in this project could also be applied to other chronic diseases that have high rates of utilization and could benefit from improved targeting of intervention/resources. The educational objective of this project is to train the next generation of interdisciplinary researchers in the fields of data analytics and healthcare informatics. The progress of the project and the research findings are disseminated via the project website (http://www.cs.wayne.edu/~reddy/projects/health/).