HOSPITAL Score
Determine risk of avoidable hospital readmission
The HOSPITAL Score is a validated prediction tool to identify patients at a high risk of potentially avoidable hospital readmission. It is intended to allow hospitals to assign extra discharge & care transition services to those patients most likely to be readmitted.
The scoring system is designed to predict the 30-day risk of potential avoidable readmission.
The formula has a C statistic of 0.72, performing similarly to other prediction models. It is validated in a large, international population and can be calculated prior to discharge from hospital. As well, it identifies 30-day readmissions that are potentially avoidable, rather than including unavoidable readmissions.
The model includes 7 variables: low hemoglobin at discharge, discharge from an Oncology service, low sodium on discharge, procedure during hospital stay, urgent/emergent admission, number of hospital admission and length of stay.
- [1]Donzé J, Aujesky D, Williams D, Schnipper JL.: Potentially avoidable 30-day hospital readmissions in medical patients: derivation and validation of a prediction model.JAMA Internal Medicine 2013 April 22, 173 (8): 632-8
- [2]Donzé D Jacques et al.: International Validity of the HOSPITAL Score to Predict 30-Day Potentially Avoidable Hospital Readmissions.JAMA Intern Med. 2016;176(4):496-502.
Results
Real-time automated computation
The HOSPITAL Score is a validated prediction tool to identify patients at a high risk of potentially avoidable hospital readmission. It is intended to allow hospitals to assign extra discharge & care transition services to those patients most likely to be readmitted.
The scoring system is designed to predict the 30-day risk of potential avoidable readmission.
The formula has a C statistic of 0.72, performing similarly to other prediction models. It is validated in a large, international population and can be calculated prior to discharge from hospital. As well, it identifies 30-day readmissions that are potentially avoidable, rather than including unavoidable readmissions.
The model includes 7 variables: low hemoglobin at discharge, discharge from an Oncology service, low sodium on discharge, procedure during hospital stay, urgent/emergent admission, number of hospital admission and length of stay.
- [1]Donzé J, Aujesky D, Williams D, Schnipper JL.: Potentially avoidable 30-day hospital readmissions in medical patients: derivation and validation of a prediction model.JAMA Internal Medicine 2013 April 22, 173 (8): 632-8
- [2]Donzé D Jacques et al.: International Validity of the HOSPITAL Score to Predict 30-Day Potentially Avoidable Hospital Readmissions.JAMA Intern Med. 2016;176(4):496-502.