In the Australian private healthcare sector there is a growing pressure to reduce unplanned hospital readmissions, i.e., readmissions related to the initial indexed visit that were unexpected within 28 days of discharge, which are considered a quality of care indicator as well as a major cost driver1. The Australian Institute for Health and Welfare (AIHW) focuses on reducing unplanned readmissions post specific surgical procedures. Hysterectomy has been identified as the cause of the 2nd highest unplanned readmission within these procedures2; yet no model to predict unplanned readmissions following a hysterectomy exists. Australia has one of the highest rates of hysterectomy (27,586 procedures a year) in benign diseases as compared to other OECD countries3. Hence, this study focusses on developing a suitable predictive model which has lessons for other cases and contexts of unplanned readmissions.

Learning Objective: to be able to:
-assess suitable analytic models to apply to health data sets
-manage imbalanced data sets
-distingusih between different modles and their relative merits


Daniel Reischl, Friedrich Alexander University
Lehrstuhl Bodendorf Eigner, Friedrich Alexander University
Freimut Bodendorf, Friedrich Alexander University
Jonathan Schaffer, Cleveland Clinic
Nilmini Wickramasinghe (Presenter)
Epworth & Swinburne

Presentation Materials: