Open AccessRegional Validation and Recalibration of Clinical Predictive Models for Patients With Acute Heart Failure
Author(s) -
Wessler Benjamin S.,
Ruthazer Robin,
Udelson James E.,
Gheorghiade Mihai,
Zannad Faiez,
Maggioni Aldo,
Konstam Marvin A.,
Kent David M.
Publication year - 2017
Publication title -
journal of the american heart association
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.494
H-Index - 85
ISSN - 2047-9980
DOI - 10.1161/jaha.117.006121
Subject(s) - medicine , percentile , generalizability theory , heart failure , guideline , calibration , interquartile range , clinical trial , receiver operating characteristic , intensive care medicine , statistics , mathematics , pathology
Background Heart failure clinical practice guidelines recommend applying validated clinical predictive models ( CPM s) to support decision making. While CPM s are now widely available, the generalizability of heart failure CPM s is largely unknown. Methods and Results We identified CPM s derived in North America that predict mortality for patients with acute heart failure and validated these models in different world regions to assess performance in a contemporary international clinical trial (N=4133) of patients with acute heart failure treated with guideline‐directed medical therapy. We performed independent external validations of 3 CPM s predicting in‐hospital mortality, 60‐day mortality, and 1‐year mortality, respectively. CPM discrimination decreased in all regional validation cohorts. The median change in area under the receiver operating curve was −0.09 (range −0.05 to −0.23). Regional calibration was highly variable (90th percentile of absolute difference between smoothed observed and predicted values range <1% to >50%). Calibration remained poor after global recalibrations; however, region‐specific recalibration procedures significantly improved regional performance (recalibrated 90th percentile of absolute difference range <1% to 5% across all regions and all models). Conclusions Acute heart failure CPM discrimination and calibration vary substantially across different world regions; region‐specific (as opposed to global) recalibration techniques are needed to improve CPM calibration.