TY - JOUR
T1 - Validation of a venous thromboembolism prediction algorithm for pediatric trauma
T2 - A national trauma data bank (NTDB) analysis
AU - Cunningham, Aaron J.
AU - Dewey, Elizabeth
AU - Hamilton, Nicholas A.
AU - Schreiber, Martin A.
AU - Krishnaswami, Sanjay
AU - Jafri, Mubeen A.
N1 - Publisher Copyright:
© 2020 Elsevier Inc.
PY - 2020/6
Y1 - 2020/6
N2 - Purpose: We sought to validate a risk model to predict venous thromboembolism (VTE) in pediatric trauma through an analysis of a contemporary cohort in the National Trauma Data Bank (NTDB). Study design: Prospective internal validation was performed in 10 randomly stratified samples of children (age 0–17 years) from the NTDB 2013–2016. Model discrimination was determined by calculation of the c-statistic (AUC), and calibration was evaluated through analysis of observed to expected (O:E) ratio. Recalibration was performed with application of a mixed-effects logistic regression. Model parameters were reestimated based on recalibration. Results: Retrospective review identified 481,485 pediatric trauma patients with 729 (0.2%) episodes of VTE. Discriminatory ability of the model in all random cohorts was significant with AUC > 0.93 (p < 0.001). Inadequate calibration was noted in 4 of 10 cohorts and the entire dataset (p < 0.001) with an O:E ratio of 1.79. Model recalibration resulted in similar discrimination (AUC = 0.95) with improved calibration (O:E ratio = 1.33, p < 0.0001). Conclusion: Pediatric trauma prediction models can provide useful data for VTE risk stratification in injured children, but these models must be validated and calibrated prior to use. Recalibration of the model in question resulted in improved accuracy in a contemporary NTDB dataset. These data provide an appropriately calibrated and validated model for clinical use. Level of evidence: II — Prospective internal validation of a multivariable prediction model.
AB - Purpose: We sought to validate a risk model to predict venous thromboembolism (VTE) in pediatric trauma through an analysis of a contemporary cohort in the National Trauma Data Bank (NTDB). Study design: Prospective internal validation was performed in 10 randomly stratified samples of children (age 0–17 years) from the NTDB 2013–2016. Model discrimination was determined by calculation of the c-statistic (AUC), and calibration was evaluated through analysis of observed to expected (O:E) ratio. Recalibration was performed with application of a mixed-effects logistic regression. Model parameters were reestimated based on recalibration. Results: Retrospective review identified 481,485 pediatric trauma patients with 729 (0.2%) episodes of VTE. Discriminatory ability of the model in all random cohorts was significant with AUC > 0.93 (p < 0.001). Inadequate calibration was noted in 4 of 10 cohorts and the entire dataset (p < 0.001) with an O:E ratio of 1.79. Model recalibration resulted in similar discrimination (AUC = 0.95) with improved calibration (O:E ratio = 1.33, p < 0.0001). Conclusion: Pediatric trauma prediction models can provide useful data for VTE risk stratification in injured children, but these models must be validated and calibrated prior to use. Recalibration of the model in question resulted in improved accuracy in a contemporary NTDB dataset. These data provide an appropriately calibrated and validated model for clinical use. Level of evidence: II — Prospective internal validation of a multivariable prediction model.
KW - Pediatric trauma
KW - Prediction algorithm
KW - Validation
KW - Venous thromboembolism
UR - http://www.scopus.com/inward/record.url?scp=85082826860&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85082826860&partnerID=8YFLogxK
U2 - 10.1016/j.jpedsurg.2020.02.032
DO - 10.1016/j.jpedsurg.2020.02.032
M3 - Article
C2 - 32247600
AN - SCOPUS:85082826860
SN - 0022-3468
VL - 55
SP - 1127
EP - 1133
JO - Journal of pediatric surgery
JF - Journal of pediatric surgery
IS - 6
ER -