Lower KCCQ-12 scores predict hospitalization, death in outpatient HF care

During outpatient heart failure (HF) care, patients with lower scores in the Kansas City Cardiomyopathy Questionnaire-12 (KCCQ-12) are at greater risk of hospitalizations and mortality, suggests a study. Moreover, those with scores <25 appear to have the highest risk.

“Noncompletion of the KCCQ-12 was itself associated with worse outcomes,” the investigators said.

A total of 4,406 patients were assigned the KCCQ-12 in HF clinics from July 2019 through March 2024, of whom 2,888 (66 percent) completed at least one questionnaire. The median KCCQ Overall Summary (OS) score was 59.4.

KCCQ-OS scores <25 significantly correlated with higher adjusted risks of 90-day hospitalization (odds ratio [OR], 3.49, 95 percent confidence interval [CI], 2.50‒4.90) and cumulative mortality (hazard ratio [HR], 3.09, 95 percent CI, 2.29‒4.17) compared with scores ≥75.

Compared with other clinical, demographic, and laboratory variables, the KCCQ-OS score stood out as the most important factor for predicting 90-day hospitalizations in the XGBoost model (area under the receiver-operating characteristic curve, 0.760, 95 percent CI, 0.706‒0.811) and cumulative mortality in the random survival forest model (C-index, 0.783, 95 percent CI, 0.742‒0.824).

Notably, patients who did not complete the KCCQ-12 questionnaire showed an increased risk of 90-day hospitalization (OR, 1.72, 95 percent CI, 1.46‒2.02) and 1-year mortality (HR, 1.52, 95 percent CI, 1.25‒1.84) after adjusting for variables in the primary analysis.

“The KCCQ-OS score was the dominant predictor of 90-day hospitalizations and cumulative mortality in machine learning models, supporting the KCCQ-12 as a prognostic tool in routine clinical practice,” the investigators said.

In this study, logistic regression and Cox proportional hazards models were used to explore the multivariable-adjusted associations. The investigators used XGBoost and random survival forest machine learning models to assess KCCQ-OS feature importance in predicting 90-day hospitalizations and mortality, respectively.