Matthew M Churpek1, Richa Adhikari2, Dana P Edelson2. 1. Department of Medicine, University of Chicago, Chicago, IL, United States. Electronic address: matthew.churpek@uchospitals.edu. 2. Department of Medicine, University of Chicago, Chicago, IL, United States.
Abstract
AIM: Early detection of clinical deterioration on the wards may improve outcomes, and most early warning scores only utilize a patient's current vital signs. The added value of vital sign trends over time is poorly characterized. We investigated whether adding trends improves accuracy and which methods are optimal for modelling trends. METHODS: Patients admitted to five hospitals over a five-year period were included in this observational cohort study, with 60% of the data used for model derivation and 40% for validation. Vital signs were utilized to predict the combined outcome of cardiac arrest, intensive care unit transfer, and death. The accuracy of models utilizing both the current value and different trend methods were compared using the area under the receiver operating characteristic curve (AUC). RESULTS: A total of 269,999 patient admissions were included, which resulted in 16,452 outcomes. Overall, trends increased accuracy compared to a model containing only current vital signs (AUC 0.78 vs. 0.74; p<0.001). The methods that resulted in the greatest average increase in accuracy were the vital sign slope (AUC improvement 0.013) and minimum value (AUC improvement 0.012), while the change from the previous value resulted in an average worsening of the AUC (change in AUC -0.002). The AUC increased most for systolic blood pressure when trends were added (AUC improvement 0.05). CONCLUSION: Vital sign trends increased the accuracy of models designed to detect critical illness on the wards. Our findings have important implications for clinicians at the bedside and for the development of early warning scores.
AIM: Early detection of clinical deterioration on the wards may improve outcomes, and most early warning scores only utilize a patient's current vital signs. The added value of vital sign trends over time is poorly characterized. We investigated whether adding trends improves accuracy and which methods are optimal for modelling trends. METHODS:Patients admitted to five hospitals over a five-year period were included in this observational cohort study, with 60% of the data used for model derivation and 40% for validation. Vital signs were utilized to predict the combined outcome of cardiac arrest, intensive care unit transfer, and death. The accuracy of models utilizing both the current value and different trend methods were compared using the area under the receiver operating characteristic curve (AUC). RESULTS: A total of 269,999 patient admissions were included, which resulted in 16,452 outcomes. Overall, trends increased accuracy compared to a model containing only current vital signs (AUC 0.78 vs. 0.74; p<0.001). The methods that resulted in the greatest average increase in accuracy were the vital sign slope (AUC improvement 0.013) and minimum value (AUC improvement 0.012), while the change from the previous value resulted in an average worsening of the AUC (change in AUC -0.002). The AUC increased most for systolic blood pressure when trends were added (AUC improvement 0.05). CONCLUSION: Vital sign trends increased the accuracy of models designed to detect critical illness on the wards. Our findings have important implications for clinicians at the bedside and for the development of early warning scores.
Authors: Gabriel J Escobar; Juan Carlos LaGuardia; Benjamin J Turk; Arona Ragins; Patricia Kipnis; David Draper Journal: J Hosp Med Date: 2012-03-22 Impact factor: 2.960
Authors: Bechien U Wu; Olaf J Bakker; Georgios I Papachristou; Marc G Besselink; Kathryn Repas; Hjalmar C van Santvoort; Venkata Muddana; Vikesh K Singh; David C Whitcomb; Hein G Gooszen; Peter A Banks Journal: Arch Intern Med Date: 2011-04-11
Authors: Gary B Smith; David R Prytherch; Paul Meredith; Paul E Schmidt; Peter I Featherstone Journal: Resuscitation Date: 2013-01-04 Impact factor: 5.262
Authors: Amber M Sawyer; Eli N Deal; Andrew J Labelle; Chad Witt; Steven W Thiel; Kevin Heard; Richard M Reichley; Scott T Micek; Marin H Kollef Journal: Crit Care Med Date: 2011-03 Impact factor: 7.598
Authors: Thomas C Bailey; Yixin Chen; Yi Mao; Chenyang Lu; Gregory Hackmann; Scott T Micek; Kevin M Heard; Kelly M Faulkner; Marin H Kollef Journal: J Hosp Med Date: 2013-02-25 Impact factor: 2.960
Authors: Marilyn Rantz; Lorraine J Phillips; Colleen Galambos; Kari Lane; Gregory L Alexander; Laurel Despins; Richelle J Koopman; Marjorie Skubic; Lanis Hicks; Steven Miller; Andy Craver; Bradford H Harris; Chelsea B Deroche Journal: J Am Med Dir Assoc Date: 2017-07-12 Impact factor: 4.669
Authors: Matthew M Churpek; Kyle A Carey; Nino Dela Merced; James Prister; John Brofman; Dana P Edelson Journal: Crit Care Med Date: 2019-12 Impact factor: 7.598
Authors: Alvin D Jeffery; Mary S Dietrich; Daniel Fabbri; Betsy Kennedy; Laurie L Novak; Joseph Coco; Lorraine C Mion Journal: Am J Crit Care Date: 2018-09 Impact factor: 2.228
Authors: Sarah Collins Rossetti; Chris Knaplund; Dave Albers; Abdul Tariq; Kui Tang; David Vawdrey; Natalie H Yip; Patricia C Dykes; Jeffrey G Klann; Min Jeoung Kang; Jose Garcia; Li-Heng Fu; Kumiko Schnock; Kenrick Cato Journal: AMIA Annu Symp Proc Date: 2020-03-04
Authors: Eske K Aasvang; Helge B D Sørensen; Christian S Meyhoff; Mikkel Elvekjaer; Rasmus M Olsen; Celeste M Porsbjerg; Jens-Ulrik Jensen; Camilla Haahr-Raunkjær Journal: J Clin Monit Comput Date: 2019-11-11 Impact factor: 2.502