A new Harvey L. Neiman Health Policy Institute study developed a first-of-its-kind comorbidity index predictive of utilization of advanced imaging. The Neiman Imaging Comorbidity Index (NICI) fills a gap in risk-adjustment methods for imaging utilization. This study, published in the Journal of the American College of Radiology, was based on radiology claims for 10.5 million individuals covered by a large commercial payer.

Risk adjustment is a statistical process that helps in unbiased prediction a person’s likely healthcare use and cost. Research of imaging utilization requires adjustment for differences among patients to provide unbiased conclusions; therefore, advancement in risk-adjustment methods can broadly improve research validity. No method has existed to predict, and statistically control for, a person’s likelihood of having advanced imaging using health care claims data, a common data source for health services, policy, and outcomes research.

“There are several comorbidity indexes that use a patient’s diagnosis codes in claims that are used for statistical risk-adjustment. Perhaps the most frequently used is the Charlson comorbidity index (CCI), which was designed to be predictive of mortality in a cancer patient population, not imaging in a broad patient population,” says Eric Christensen, PhD, research director at the Neiman Health Policy Institute. 

Christensen adds, “Absent an imaging-focused comorbidity index to provide risk adjustment, the CCI is commonly used in imaging research. To improve risk adjustment in such studies, we developed the Neiman Imaging Comorbidity Index (NICI) to be specifically predictive of advanced imaging use.”

The NICI, like the CCI and other comorbidity indexes, provides a score based on acute and historical health conditions recorded in an individual’s medical claims, with some conditions having a greater weight than others. This score is then used to statistically control for the differences in patients’ likelihoods of receiving advanced imaging.

“We found that NICI outperformed the CCI in predicting an individual’s chances of receiving advanced imaging. This was true overall and for patients in each of the age groups that were assessed,” says Casey Pelzl, MPH, lead author and senior economics and health services analyst at the Neiman Health Policy Institute. “The NICI is most predictive of imaging use for older individuals who, on average, have more comorbidities recorded in the claims data that were used.”

“In designing the NICI, we balanced the marginal improvement in the ability to predict advanced imaging use from each comorbidity included in the NICI. Because we were able to limit the number of comorbidities included in the NICI, we were left with an index that is far easier to use than the existing indexes such as CCI,” says Pelzl.

She adds, “In the end, the NICI included 9 comorbidities that are statistically correlated with advanced imaging use. In comparison, the CCI has 17 comorbidities, yet the NICI is more predictive of advanced imaging use. This is not a criticism of the CCI, but rather, a benefit of the imaging-specific NICI, a simple and effective tool for researchers.”