Clinical Edge

Summaries of Must-Read Clinical Literature, Guidelines, and FDA Actions

Clinical Predictive Models for Patients with HF

J Am Heart Assoc; ePub 2017 Nov 18; Wessler, et al

Acute heart failure clinical predictive model (CPM) discrimination and calibration vary across different world regions, with regional-specific recalibration techniques needed to improve CPM calibration, a recent study suggests. CPMs in North American that predict mortality for patients with acute heart failure were identified and researchers validated these models in different world regions to assess performance in a contemporary international clinical trial of 4,133 patients with acute heart failure treated with guideline-directed medical therapy. Independent external validations of 3 CPMs predicting in-hospital mortality, 60-day mortality, and 1-year mortality were performed. Among the findings:

  • CPM discrimination decreased in all regional validation cohorts.
  • The median change in area under the receiver operating curve was ‒0.09.
  • Regional calibration was highly variable.
  • Calibration remained poor after global recalibrations; however, region-specific recalibration procedures significantly improved regional performance.

Citation:

Wessler BS, Ruthazer R, Udelson JE, et al. Regional validation and recalibration of clinical predictive models for patients with acute heart failure. [Published online ahead of print November 18, 2017]. J Am Heart Assoc. doi:10.1161/JAHA.117.006121.