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 (www.cs.wayne.edu/~reddy/projects/health/).
