A novel framework for predicting patients at risk of readmission

Rathi, M. 2015. A novel framework for predicting patients at risk of readmission. PhD thesis University of Westminster Department of Computer Science

TitleA novel framework for predicting patients at risk of readmission
TypePhD thesis
AuthorsRathi, M.
Abstract

Uncertainty in decision-making for patients’ risk of re-admission arises due to non-uniform data and lack of knowledge in health system variables. The knowledge of the impact of risk factors will provide clinicians better decision-making and in reducing the number of patients admitted to the hospital. Traditional approaches are not capable to account for the uncertain nature of risk of hospital re-admissions. More problems arise due to large amount of uncertain information. Patients can be at high, medium or low risk of re-admission, and these strata have ill-defined boundaries. We believe that our model that adapts fuzzy regression method will start a novel approach to handle uncertain data, uncertain relationships between health system variables and the risk of re-admission. Because of nature of ill-defined boundaries of risk bands, this approach does allow the clinicians to target individuals at boundaries. Targeting individuals at boundaries and providing them proper care may provide some ability to move patients from high risk to low risk band. In developing this algorithm, we aimed to help potential users to assess the patients for various risk score thresholds and avoid readmission of high risk patients with proper interventions. A model for predicting patients at high risk of re-admission will enable interventions to be targeted before costs have been incurred and health status have deteriorated. A risk score cut off level would flag patients and result in net savings where intervention costs are much higher per patient. Preventing hospital re-admissions is important for patients, and our algorithm may also impact hospital income.

Year2015
FileRathi_Manisha_thesis.pdf

Related outputs

A risk analysis method for assessing risks based on interval-valued fuzzy number
Rathi, M. and Chaussalet, T.J. 2012. A risk analysis method for assessing risks based on interval-valued fuzzy number. in: 2012 IEEE International conference on computational intelligence and computing research (ICCIC), 18-20 December 2012, Coimbatore, India IEEE .

Predicting hospital resource utilization: a fuzzy regression approach
Rathi, M. and Chaussalet, T.J. 2012. Predicting hospital resource utilization: a fuzzy regression approach. High Tech Human Touch: Proceedings of the 38th ORAHS conference. University of Twente, The Netherlands. 16-20 July 2012

Permalink - https://westminsterresearch.westminster.ac.uk/item/9x22z/a-novel-framework-for-predicting-patients-at-risk-of-readmission


Share this
Tweet
Email