Abstract
BACKGROUND: Mortality after congenital heart surgery is an important metric across benchmarking, quality, and reporting initiatives. All rely on estimates from prior years, and how well these reflect current outcomes is unclear. METHODS: Index operations from The Society of Thoracic Surgeons Congenital Database (2014-2019) were included. Adjusted operative mortality in "past" 4-year and 1-year intervals vs the most recent year ("present") was evaluated using Bayesian hierarchical logistic regression with results presented as odds ratios and 95% credible intervals (CrI). RESULTS: Among 115,699 operations (106 hospitals), overall present observed mortality was 2.5%. Regression to the mean was evident, and individual hospital's present vs past adjusted mortality were only weakly correlated (-0.11 vs past 1-year data, 0.22 vs past 4-year data). A significant relationship was found between past and present mortality only for the group of hospitals in the highest mortality quartile, most prominent for past 4-year data (adjusted odds ratio vs lowest mortality quartile, 2.04; 95% CrI, 1.44-2.80). The proportion of present hospital mortality variation explained by past mortality quartile was 52% (95% CrI, 20%-90%) using past 4-year data and only 27% (95% CrI, 92%-83%) using past 1-year data. Overall 66% of hospitals changed mortality quartiles from past to present (30% by ≥2 quartiles). CONCLUSIONS: Past mortality relates to present primarily for groups of hospitals at the extremes, with past 4-year data more informative than past 1-year data. For individual hospitals, past may differ from present, regression to the mean is common, and many change quartiles. Past mortality should be used thoughtfully and not as the sole factor informing present decision making.