RT Journal Article
SR Electronic
T1 Discovery of signatures of fatal neonatal illness in vital signs using highly comparative time-series analysis
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2021.03.26.437138
DO 10.1101/2021.03.26.437138
A1 Justin C Niestroy
A1 J Randall Moorman
A1 Maxwell A Levinson
A1 Sadnan Al Manir
A1 Timothy W Clark
A1 Karen D Fairchild
A1 Douglas E Lake
YR 2021
UL http://biorxiv.org/content/early/2021/09/07/2021.03.26.437138.abstract
AB Objective To seek new signatures of illness in heart rate and oxygen saturation vital signs from Neonatal Intensive Care Unit (NICU), we implemented highly comparative time-series analysis to discover features of all-cause mortality in the next 7 days.Design We collected 0.5Hz heart rate and oxygen saturation vital signs of infants in the University of Virginia NICU from 2009 to 2019. We applied 4988 algorithmic operations from 11 mathematical families to random daily ten-minute segments. We clustered the results and selected a representative from each, and examined multivariable logistic regression models.Setting Neonatal ICUPatients 5957 NICU infants; 205 died.Measurements and main results 3555 operations were usable; 20 cluster medoids held more than 81% of the information. A multivariable model had AUC 0.83. Five algorithms outperformed others: moving threshold, successive increases, surprise, and random walk. We computed provenance of the computations and constructed a software library with links to the data.Conclusions Highly comparative time-series analysis revealed new vital sign measures to identify NICU patients at the highest risk of death in the next week.Competing Interest StatementJRM and DEL own stock in Medical Predictive Science Corporation, Charlottesville, VA; JRM owns stock and is an officer of Advanced Medical Predictive Devices, Diagnostics and Displays, Charlottesville, VA.