The population is a union of health and hospital workers in the Northeast, whose self-insured trust fund administers comprehensive health benefits to the members, their spouses and children. The fund covers all medically necessary hospital, medical, maternity, behavioral health and pharmacy services, and maintains their own claims data repository. There were 226,157 individuals who were eligible for benefits for at least 11 months between January–December 2009; of those, 185,294 (86.2%) remained eligible for at least 11 months from January–December 2010. Overall 18.1% (n = 40,862) did not remain eligible for reasons such as retirement or dependent children reaching the maximum age of eligibility. This analysis focuses on the 181,764 beneficiaries who were consistently eligible for benefits over at least 22 months in 2009 and 2010, who also received DCG codes. (Sightlines DxCG Risk Solutions V 3.0, Verisk Health Inc)

Beneficiary age and gender were available. Comorbidity was assessed through the Charlson comorbidity index [19]. Different weights are assigned for specific conditions and the weights are added to find the index for a specific patient (e.g., a patient with depression, COPD and lymphoma would have a weight of 4) (Table 1). Data on use of warfarin was not available.

The comorbidity index was assessed from claims data for services provided between January and December 2009; each claim had at least one primary ICD-9 diagnosis code and up to three secondary codes. The comorbidity index was assessed using the Deyo strategy [23]. The comorbidity index for the first year was computed for all diagnoses recorded in all of the claims during the first year. 10.2% had no claims in 2009; of those, 63% were adults and 37% children. Among adults, of those who had no claims in 2009, 53% also had none in 2010. Among children, 43% of those who had no claims in 2009 also had none in 2010. Costs were zero for those without claims.

The prospective DCG model utilizes claims data and age, sex, diagnoses and their interactions to predict future costs; the 2009 prospective DCG was used to predict 2010 cost [24]. Mental health disorders encompassed the ICD-9 codes 290–316 other than depression (290.13, 296.20–296.36; 296.82; 298.0; 201.11; 301.12; 309.0–309.1 or 311) and dementia (290, 290.4–290.43, 331, 331.19, 331.2 or 331.82).

Claims data was used to document the cost and utilization of services among these consistently eligible beneficiaries. The type and place of service were available. The prior year hospitalization was the actual number of hospitalizations. Total amount paid for all services including inpatient, outpatient, emergency room, laboratory tests, behavioral health and prescription drugs for January–December 2010 were evaluated.

To compare the costs for those with a given chronic disease versus those with that disease and other comorbid diseases, an adjusted comorbidity index was calculated by subtracting the Charlson comorbidity weight for that disease from the total comorbidity score. For example, patients with congestive heart failure (CHF) who have an adjusted index score of zero have only CHF, while those with an index of one or more have other illnesses as well.

Four predictors of subsequent yearly costs (i.e., prior year costs, prior year hospitalization, prior year comorbidity and prior year DCG) were compared using four different analytic approaches: a two part regression modeling strategy often used in econometric analysis; quantile regression to predict the upper 5% and 10% of the cost distribution; logistic regression to predict whether a specific individual would be in the upper 5% or 10% cost strata using positive predictive value; and receiver operating characteristic (ROC) analysis to evaluate sensitivity and specificity. Since cost data was skewed by both high cost patients and by those with zero costs, standard regression could not be used. Age, gender and mental health were controlled for in all regressions. There was no data on race/ethnicity in the claims; however, the beneficiaries are predominately Black and Latino. The data did not include the specific location where the beneficiaries received services.

Figure 1 shows the distribution of beneficiaries according to the adjusted comorbidity index for the specific chronic diseases. Those with an adjusted comorbidity index of zero have only the specific chronic disease. Regardless of specific chronic disease, most patients had low comorbidity. Only a small proportion of patients with any specific chronic disease had high comorbidity. (See Table S2 in File S1 for numbers of patients in each category.)

Figure 2 shows the adjusted comorbidity index and total costs. As the index increased, total yearly cost increased significantly, regardless of the specific chronic disease (P<.001). At lower comorbidity, the costs did not differ significantly for different chronic diseases.

Overall 6.4% of adults and 2.0% of children were hospitalized. Table 3 shows hospitalization rates according to comorbidity. As comorbidity index increased, the proportion of beneficiaries hospitalized once, twice or three or more times increased significantly (P<.001). Patients with higher comorbidity had more hospitalizations (p<.001) and more repeated hospitalizations (p<.001). Table 3 also shows the costs for beneficiaries according to the comorbidity index and the number of hospitalizations. Costs steadily rose with increasing comorbidity index (p<.001) and increasing hospitalizations (p<.001).

The only mental or behavioral health conditions in the comorbidity index are depression and dementia. 0.9% of the beneficiaries had dementia, and only 2.9% of adults (average age 45.2) and 1.0% of children (average age 13.8) had a diagnosis of depression. In total, 4.9% of adults (average age 45.2) and 1.0% of children (average age 11.3 years) had another mental health diagnosis. Overall, 5.9% of beneficiaries who had a mental health diagnosis (other than depression or dementia) accounted for 11.0% of the costs (p<.001). The frequency of a mental health diagnosis increased with increasing levels of comorbidity. For those with a comorbidity index of 0–1, 5% had a mental health diagnosis; comorbidity of 2–3, 8.8%; comorbidity of 4, 9.4%; comorbidity 5–7, 10.2% and those ≥8, 14.1%. At each level of comorbidity, those with mental health diagnoses had significantly increased costs (p<.001).

Table 4 shows predictions of the 2010 total expenditure from regressions that included either prior year costs, prior year comorbidity index, prior year hospitalization or the DCG prospective risk score. Total costs in 2009 were $4,256 for adults and $1,410 for children, very similar to those in 2010. Overall 5.6% of adults and 2.3% of children were hospitalized in 2009, also very similar to 2010; most of the adults and children were hospitalized only once. The mean prospective DCG score in 2009 was 1.6±2.2.

Overall, 9.7% of beneficiaries had zero costs in 2010. Those with lower comorbidity (p<.001), without a mental health diagnosis (p<.001), men (p<.001), and those with zero costs in 2009 (p<.001) were more likely to have zero costs in 2010. In adults, prior year costs explained 31% of the variance, while the comorbidity index and prospective DCG each explained 20%; prior hospitalization explained only 11%. In children, prior costs explained 20% of the variance, and the comorbidity index explained 17% of the variance, while prospective DCG and prior hospitalization explained 7%. Each model in Table 4 is controlled for age, gender and mental health diagnosis. Random effects for zip code and fixed effects for employer type were not significant and were omitted from the regression models in Table 4.

Table 5 shows the results of quantile regressions for predicting the top 5^th and 10^th percentile of costs for both adults and children. Prior year costs, prior year comorbidity, prior year DCG, and prior year hospitalizations were all evaluated as predictors of upper 5% and upper 10% of subsequent (2010) costs in separate models controlling for age, gender and mental health diagnosis. In adults, the comorbidity index was equivalent to DCG and prior cost in predicting the top 5% and 10% of cost, while prior hospitalization had much lower ability to identify such patients. In children, the comorbidity index, prior costs, and DCG also had similar predictive ability for the top 5% and 10% of costs. Table S3 in File S1 shows the percent of patients in each prior year comorbidity rank who fell into the upper 0.5%, 1.0%, 2.0%, 5.0%, and 10% of subsequent year costs. Since there is a monotonic gradient of increasing costs with increasing comorbidity, the findings are not contingent on a specific cutoff.

Another approach to classification assessed how likely it was for an individual to be in the top 5% and 10% of 2010 costs based on prior year characteristics. Table S4 in File S1 shows the positive predictive values for predicting 2010 costs from bootstrapping using prior year costs, prior year comorbidity, prior year hospitalizations and prior year DCG to predicting membership in the top 5% and 10% of 2010 cost, controlling for age, gender and mental health diagnosis. Prior year comorbidity had a slightly higher positive predictive value for identifying those who would become a member of the top 5% and 10% subsequent year cost than hospitalization and both are better than prior year costs and prior year DCG score. The positive predictive values are relatively stable across the top 5% and 10% cost groups. With respect to the ROC analysis, the comorbidity index achieved almost identical area under the curve as prospective DCG and prior cost in predicting the top 5% and 10% of subsequent costs, these three measures are slightly better than prior years hospitalization. The small difference between the findings for positive predictive value and area under the curve is that the positive predictive value depends on the prevalence of high costs as well as on sensitivity and specificity. Each model in Table 5 is controlled for age, gender and mental health diagnosis. Again, in this set of regression models random effects for zip code and fixed effects for employer type were not significant and were omitted from the regression models in Table 5.

These results were obtained from analysis of a specific population and cannot be directly compared to the explanatory power of other published cost models, in part because any analysis of costs, including this one, encompass differentials in provider pricing. However, contrasting the different models in this population provides a context for evaluating the predictive ability of prior comorbidity, prior cost, prospective DCG and prior hospitalizations to predict subsequent costs in the same population. The comorbidity index could not be calculated for the 10% who did not have claims in the first year.

In addition, the comorbidity index has not been independently validated in children, although it has been used in some pediatric studies [34]–[36]. The comorbidity index does not capture a variety of conditions unique to pediatrics. Although children who have illnesses that in the index do accumulate higher costs, further modification would be required to adapt it to the chronic conditions unique to children. It should also be noted that supply side factors were not considered in this analysis.

To be successful in reducing health care expenditures, interventions have to identify the patients who are most likely to have sustained high costs. If not targeted precisely toward such patients, interventions will cost more than they will save. This was the experience with disease management interventions [37]–[40]. Studies have shown that both prior costs and prior hospitalization overestimate subsequent health care utilization and neither reliably identifies those who have stable high costs from year to year [3], [6]. Likely as a result, intervention programs that have targeted beneficiaries using these definitions have not demonstrated savings [3], [41]. Thus, to date, most interventions have not been successful in reducing costs in patients with multiple chronic diseases. Our hypothesis is that they did not efficiently target the patients at highest risk of high future costs.

Focused on adults, a comorbidity index ≥5 identifies 5% of patients who will have 17.5% of costs; or comorbidity index ≥4 identifies 9.3% of patients who will incur 25.6% of costs. A recent study using the VA criteria found that 32% of patients had 65% of costs [42]. The issue is the tradeoffs between the percent of patients and the percent of possible reduction in future costs.

This study used the comorbidity index calculated for patients from claims data from the prior year to predict subsequent year costs and contrasted it with commonly used predictors of cost including prior hospitalization, prior costs, and DCG. Prior costs and prior DCG usually require 12 months of claims data, which generally creates a lag time of 6–18 months [43]. Accordingly, such data cannot be used to identify risk for high costs among patients for whom health plans or employers have no prior utilization data, including those who may gain insurance under the Affordable Care Act. Prior hospitalization might be ascertainable at the time of enrollment but clearly affords less explanatory power.

Importantly, the Charlson comorbidity index can also be documented prospectively by a short questionnaire as well as through claims or chart data. For more than 20 years, we and others have ascertained the comorbidity index in less than 10 minutes through interview in person or by telephone [44], [45].