Trends in 30-day readmissions following hospitalisation for heart failure by sex, socioeconomic status and ethnicity

Abstract

Background: Reducing the high patient and economic burden of early readmissions after hospitalisation for heart failure (HF) has become a health policy priority of recent years.

Methods: An observational study linking Hospital Episode Statistics to socioeconomic and death data in England (2002-2018). All first hospitalisations with a primary discharge code for HF were identified. Quasi-poisson models were used to investigate trends in 30-day readmissions by age, sex, socioeconomic status and ethnicity.

Findings: There were 698,983 HF admissions, median age 81 years [IQR 14].In-hospital deaths reduced by 0.7% per annum (pa), whilst additional deaths at 30-days remained stable at 5%. Age adjusted 30-day readmissions (21% overall), increased by 1.4% pa (95% CI 1.3-1.5). Readmissions for HF (6%) and 'other cardiovascular disease (CVD)' (3%) remained stable, but readmissions for non-CVD causes (12%) increased at a rate of 2.6% (2.4-2.7) pa. Proportions were similar by sex but trends diverged by ethnicity. Black groups experienced an increase in readmissions for HF (1.8% pa, interaction-p 0.03) and South Asian groups had more rapidly increasing readmission rates for non-CVD causes (interaction-p 0.04). Non-CVD readmissions were also more prominent in the least (15%; 15-15) compared to the most affluent group (12%; 12-12). Strongest predictors for HF readmission were Black ethnicity and chronic kidney disease, whilst cardiac procedures were protective. For non-CVD readmissions, strongest predictors were non-CVD comorbidities, whilst cardiologist care was protective.

Interpretation: In HF, despite readmission reduction policies, 30-day readmissions have increased, impacting the least affluent and ethnic minority groups the most.

Funding: NIHR.

Keywords: AF, Atrial fibrillation; CI, Confidence Interval; COPD, Chronic obstructive pulmonary disease; CRT, Cardiac resynchronisation therapy; CVA, Cerebrovascular accident; CVD, Cardiovascular disease; HES, Hospital Episode Statistics; HF, Heart failure; Heart failure; ICD, Implantable cardioverter defibrillator; IHD, Ischaemic heart disease; IMD, Index of Multiple Deprivation; MI, Myocardial infarction; ONS, Office of National Statistics; PCI, Percutaneous coronary intervention; Readmission; hospitalisation.

Fig. 1

Top ten causes of readmission by time period. The charts show the percentages of specific causes of admission, for each time period. Percentages are calculated using the number of readmissions for each of the causes, out of the total number of readmissions. Only the top ten are displayed and they are presented in descending order of prevalence. Causes with * are unique to that time period.

Fig. 2

Plot of trends in probability of in-hospital death, 30-day readmission (split by cause) and/or 30-day death over time. The figure shows the predicted proportions of events for all index admissions with HF, during the study time window (1st January 2002 and 31st December 2018). All predictions are made at the mean age 79 years. With the exception of in-hospital deaths, all proportions are estimated using the sum of first event within 30-days of discharge from hospital as the numerator and all live discharges as the denominator.

Fig. 3

Predictors of readmission by cause. The graphs show the result of logistic models for each readmission cause with all of the variables. Variables that did not contribute sufficiently to the fit (based on AIC) with a backwards step procedure were removed (shaded in grey) and the remaining odds ratios were plotted. Variables are in bold if the point estimate for the odds ratio is <0.8 or > 1.25. Age spline coefficients were removed to ease interpretation.