Discovery of signatures of fatal neonatal illness in vital signs using highly comparative time-series analysis

Abstract

Objective: Signatures of illness in vital signs of Neonatal Intensive Care Unit (NICU) patients can inform on future adverse events and outcomes. We implemented highly comparative time-series analysis to discover features and predictive analytics tools for all-cause mortality in the next 7 days, using the ubiquitous HR and SpO2 vital sign data from bedside monitors. Design: We populated a Time Series Commons with the complete HR and SpO2 data from all infants in the University of Virginia NICU from 2009 to 2019. We calculated the results of applying over 80 members of 11 mathematical families to random ten-minute segments of 0.5Hz data each day for each infant, with varying parameter sets, resulting in 4998 algorithmic operations on each infant. We used an unsupervised mutual information-based method to cluster the results, and we selected a single representative operation from each cluster. We used our FAIRSCAPE framework to compute a detailed provenance of all computations, and we constructed a complete software library with links to the analyzed data for reproducibility and reuse. We made multivariable logistic regression models using the lasso to assay the usefulness of the algorithms. Setting: Neonatal ICU. Patients: 5957 NICU infants, of whom 206 died. Measurements and main results: 3555 algorithmic operations returned usable results. Twenty representative operations, selected from each of 20 unsupervised clusters, held more than 81% of the information predicting death. A multivariable model had an AUC of 0.81 for predicting death in the next 7 days. In addition, five algorithms outperformed others: moving threshold, successive increases, surprise, and a random walk model. Conclusions: Highly comparative time-series analysis revealed new vital sign metrics to identify NICU patients at the highest risk of death in the next week. This approach can facilitate the discovery of signatures of impending, potentially actionable, clinical decompensation in monitored patients.

Heart Rate and Pulse Oximetry Dynamics in the First Week after Birth in Neonatal Intensive Care Unit Patients and the Risk of Cerebral Palsy

“…An additional benefit of a CP biomarker is identifying, within the inherently high-risk group of NICU infants, those at highest risk of CP for allocation of early intervention therapies during the NICU stay. 39…”

“…An additional benefit of a CP biomarker is identifying, within the inherently high-risk group of NICU infants, those at highest risk of CP for allocation of early intervention therapies during the NICU stay. 39 Ethical Approval Ethical approval was provided by the Institutional Review Board of University of Virginia in advance of implementation. The waiver of consent was approved.…”

Evidence Graphs: Supporting Transparent and FAIR Computation, with Defeasible Reasoning on Data, Methods, and Results

“…In developing and validating our approach, we performed a very large-scale time series analysis of ten years of vital signs time series data from the Neonatal Intensive Care Unit (NICU) at the University of Virginia Hospital, collected on 5,957 infants. This extended proof-of-concept was a significant research study in its own right, in which NICU time series were analyzed using 80 different algorithms in 11 mathematical families from diverse domains [69]. Computations were performed over a period of 15 months, in various stages, using the FAIRSCAPE microservices framework [64], producing an evidence graph of 17,996 nodes [70].…”

The principles of whole-hospital predictive analytics monitoring for clinical medicine originated in the neonatal ICU

“…We note the promise of a comprehensive strategy of Fulcher and coworkers that they named highly comparative time-series analysis 55 , 56 . Our recent work points to a reduced set of calculations on heart rate and oxygen saturation time series that captures many facets of cardiopulmonary physiology in premature infants 57 .…”