New Risk Scoring System Considers Role of Chronic Illness in Post-Surgery Mortality

Image: The new score better accounts for the role chronic illness plays in a patient’s risk of mortality after the operation (Photo courtesy of 123RF)

For nearly four decades, researchers have relied on two tools—the Charlson Comorbidity Index (CCI) and the Elixhauser Comorbidity Index (ECI)—to assess the impact of existing health conditions on patient outcomes. These indices utilize International Classification of Diseases (ICD) codes, entered by healthcare professionals and medical billers, to account for patient illness. However, these tools were not specifically designed for surgical patients and often focused on chronic illnesses that may not be directly relevant to surgical populations. They also tend to capture data from medical billing records, which lack detailed insights into pre-existing health conditions. To address these limitations, researchers have now developed a new risk-scoring system that better accounts for how chronic illnesses affect a patient's risk of mortality after surgery, enabling surgeons to adjust for patients' pre-existing conditions and more accurately determine mortality risk.

The Comorbid Operative Risk Evaluation (CORE) score was created by a research team from UCLA Health (Los Angeles, CA, USA), using data from 699,155 patients, with 139,831 (20%) comprising the testing cohort. The researchers analyzed adults undergoing 62 different operations across 14 specialties, using data from the 2019 National Inpatient Sample (NIS) and ICD, 10th Revision (ICD-10) codes. They categorized ICD-10 codes for chronic diseases into Clinical Classifications Software Refined (CCSR) groups. The team applied logistic regression on CCSR groups with non-zero feature importance across four machine learning algorithms to predict in-hospital mortality, and used the resulting coefficients to calculate the CORE score based on previously validated methodology. The final score ranges from zero, indicating the lowest risk, to 100, representing the highest risk, according to the study published in the Annals of Surgery.

“The advent of novel statistical software and methodology have enabled researchers to exploit large databases to answer questions of healthcare quality, disparities, and outcomes,” said Dr. Nikhil Chervu, a resident physician in the UCLA Department of Surgery and the study’s lead author. “These databases, however, often capture data from medical billing records and lack nuanced information regarding pre-existing health conditions. Without addressing differences in patients' chronic illnesses, population comparisons may fall flat. Incorporation of this score in additional research will further validate its use and help improve analysis of surgical outcomes using large databases.”