Constructing an Adapted Cascade of Diabetes Care Using Inpatient Admissions Data: Cross-sectional Study

The diabetes mellitus cascade of care has been constructed to evaluate diabetes care at a population level by determining the percentage of individuals diagnosed and linked to care as well as their reported glycemic control.

We sought to adapt the cascade of care to an inpatient-only setting using the electronic health record (EHR) data of 81,633 patients with type 2 diabetes.

In this adaptation, linkage to care was defined as prescription of diabetes medications within 3 months of discharge, and control was defined as hemoglobin A_1c (HbA_1c) below individual target levels, as these are the most reliably captured items in the inpatient setting. We applied the cascade model to assess differences in demographics and percent loss at each stage of the cascade; we then conducted two-sample chi-square equality of proportions tests for each demographic. Based on findings in the previous literature, we hypothesized that women, Black patients, younger patients (<45 years old), uninsured patients, and patients living in an economically deprived area called the Promise Zone would be disproportionately unlinked and uncontrolled. We also predicted that patients who received inpatient glycemic care would be more likely to reach glycemic control.

We found that out of 81,633 patients, 28,716 (35.2%) were linked to care via medication prescription. Women and younger patients were slightly less likely to be linked to care than their male and older counterparts, while Black patients (n=19,141, 23.4% of diagnosed population vs n=6741, 23.5% of the linked population) were as proportionately part of the linked population as White patients (n=58,291, 71.4% of diagnosed population vs n=20,402, 71.0% of the linked population). Those living in underserved communities (ie, the Promise Zone) and uninsured patients were slightly overrepresented (n=6789, 8.3% of diagnosed population vs n=2773, 9.7% of the linked population) in the linked population as compared to patients living in wealthier zip codes and those who were insured. Similar patterns were observed among those more likely to reach glycemic control via HbA_1c. However, conclusions are limited by the relatively large amount of missing glycemic data.

We conclude that inpatient EHR data do not adequately capture the care cascade as defined in the outpatient setting. In particular, missing data in this setting may preclude assessment of glycemic control. Future work should integrate inpatient and outpatient data sources to complete the picture of diabetes care.