JMIR Publications

ABSTRACT

Background:

Home Hospitalization is widely accepted as a cost-effective alternative to conventional hospitalization in selected patients. A recent analysis of the home hospitalization and early discharge (HH/ED) program at Hospital Clínic de Barcelona, over a 10-year period (2006-2015), demonstrated high levels of acceptance by patients and professionals, as well as health-value generation at provider and at health system levels. However, health risk assessment was identified as an unmet need with potential to enhance clinical decision making.

Objective:

To generate, and assess, predictive models of mortality and in-hospital admission at entry and at HH/ED discharge.

Methods:

Predictive modelling of mortality and in-hospital admission was done in two different scenarios: at entry into the HH/ED program and at discharge, from January 2009 to December 2015. Multisource predictive variables including: standard clinical data, patients’ functional features and population-health information were considered.

Results:

We studied 1925 HH/ED patients applying a random forest classifier because it showed best performance. Results of the Area Under the Receiver Operating Characteristic Curve (ROC AUC) for prediction of mortality were 0.88 and 0.89, at entry and at home hospitalization discharge, respectively; and, for in-hospital admission, 0.71 and 0.70, respectively.

Conclusions:

Results showed potential for feeding clinical decision support systems aiming at supporting health professionals for inclusion of candidates into the HH/ED program, as well as to guide transitions toward community-based care at HH discharge.