This site is not optimized for Internet Explorer 8 (or older).

Please upgrade to a newer version of Internet Explorer or use an alternate browser such as Chrome or Firefox.

Novel Machine Learning Approach to Identify Preoperative Risk Factors Associated With Super-Utilization of Medicare Expenditure Following Surgery

Thursday, August 15, 2019

Submitted by


J. Madison Hyer, Aslam Ejaz, Diamantis I. Tsilimigras, Anghela Z. Paredes, Rittal Mehta, Timothy M. Pawlik

Using a machine learning algorithm, resource utilization among more than 1 million Medicare patients undergoing one of 6 operations including CABG and lung resection was analyzed.  Super users comprised 4.8% of the cohort but consumed 31.7% of the resources.  Risk factors for super use included paraplegia/hemiplegia, weight loss, and CHF combined with chronic kidney disease. 

Add comment

Log in or register to post comments