A new risk scoring system taking into account the role of chronic diseases in postoperative mortality

A research team at the University of California, Los Angeles created the Comorbid Surgical Risk Assessment (CORE) scale to better account for the role that chronic diseases play in a patient’s risk of death after surgery, allowing surgeons to adjust for a patient’s pre-existing conditions and more easily determine the risk of death.

For almost 40 years, researchers have used two tools, the Charlson Comorbidity Index (CCI) and the Elixhauser Comorbidity Index (ECI), to measure the impact of existing health conditions on patient outcomes. These tools use ICD codes entered by physicians and payers to account for a patient’s disease. However, these tools were not designed for surgical patients and often address chronic conditions that are not relevant to surgical populations. They often extract data from medical records and lack detailed information about pre-existing conditions.

A total of 699,155 patients were used to develop the model, of which 139,831 (20%) constituted the test cohort. Researchers surveyed adults undergoing 62 surgeries in 14 specialties from the 2019 National Inpatient Sample (NIS) using International Classification of Diseases, Revision 10 (ICD-10) codes. They sorted ICD-10 codes for chronic diseases into Clinical Classifications Software Refined (CCSR) groups. They applied CCSR logistic regression with non-zero feature importance to four machine learning algorithms predicting in-hospital mortality and used the result

factors to calculate the Co-occurring Operational Risk Assessment (CORE) score based on a previously approved methodology. The final score ranges from zero, which means the lowest risk, to 100, which means the highest risk.

Health services and outcomes research using retrospective databases continues to constitute a growing proportion of surgical research. Researchers who highlight problems and differences in quality have good intentions. However, without the right tools, it may not be clear whether poor outcomes are independent of pre-existing conditions.

“The advent of novel statistical software and methodology has enabled researchers to leverage large databases to answer questions about health care quality, disparities and outcomes,” said Dr. Nikhil Chervu, a resident physician in the UCLA Department of Surgery and lead author of the study. “However, these databases often aggregate data from medical records and lack detailed information about pre-existing conditions. Without taking into account differences in patients’ chronic diseases, population comparisons may prove ineffective. Including this result in additional studies will further confirm its effectiveness and help improve the analysis of surgical outcomes using large databases.”