Trends in leading causes of hospitalisation of adults with diabetes in England from 2003 to 2018: an epidemiological analysis of linked primary care records

Abstract

Background: Diabetes leads to a wide range of established vascular and metabolic complications that has resulted in the implementation of diverse prevention programmes across high-income countries. Diabetes has also been associated with an increased risk of a broader set of conditions including cancers, liver disease, and common infections. We aimed to examine the trends in a broad set of cause-specific hospitalisations in individuals with diabetes in England from 2003 to 2018.

Methods: In this epidemiological analysis, we identified 309 874 individuals 18 years or older with diabetes (type 1 or 2) in England from the Clinical Practice Research Datalink linked to Hospital Episode Statistics inpatient data from 2003 to 2018. We generated a mixed prevalent and incident diabetes study population through serial cross sections and follow-up over time. We used a discretised Poisson regression model to estimate annual cause-specific hospitalisation rates in men and women with diabetes across 17 cause groupings. We generated a 1:1 age-matched and sex-matched population of individuals without diabetes to compare cause-specific hospitalisation rates in those with and without diabetes.

Findings: Hospitalisation rates were higher for all causes in persons with diabetes than in those without diabetes throughout the study period. Diabetes itself and ischaemic heart disease were the leading causes of excess (defined as absolute difference in the rate in the populations with and without diabetes) hospitalisation in 2003. By 2018, non-infectious and non-cancerous respiratory conditions, non-diabetes-related cancers, and ischaemic heart disease were the most common causes of excess hospitalisation across men and women. Hospitalisation rates of people with diabetes declined and causes of hospitalisation changed. Almost all traditional diabetes complication groups (vascular diseases, amputations, and diabetes) decreased, while conditions non-specific to diabetes (cancers, infections, non-infectious and non-cancerous respiratory conditions) increased. These differing trends represented a change in the cause of hospitalisation, such that the traditional diabetes complications accounted for more than 50% of hospitalisation in 2003, but only approximately 30% in 2018. In contrast, the proportion of hospitalisations due to respiratory infections between the same time period increased from 3% to 10% in men and from 4% to 12% in women.

Interpretations: Changes in the composition of excess risk and hospitalisation burden in those with diabetes means that preventative and clinical measures should evolve to reflect the diverse set of causes that are driving persistent excess hospitalisation in those with diabetes.

Funding: Wellcome Trust.

Figure 1

Absolute change in adjusted hospitalisation rates by cause grouping from 2003 to 2018 in those with and without diabetes The ends of the arrow tails represent hospitalisation rates in 2003 and the tips of the arrow heads represent hospitalisation rates in 2018.

Figure 2

Absolute change in adjusted cause-specific hospitalisation rates from 2003 to 2018 in men and women with diabetes The ends of the arrow tails represent hospitalisation rates in 2003 and the tips of the arrow heads represent hospitalisation rates in 2018.

Figure 3

Hospitalisation rates due to diabetes-specific complications (A and B) and other causes (C) in men and women with diabetes from 2003 to 2018 *Non-infectious, non-cancerous.

Figure 4

Proportional contribution to hospitalisation burden of leading cause-specific diseases in people with diabetes from 2003 to 2018