Search

Objective. Highly comparative time series analysis (HCTSA) is a novel approach involving massive feature extraction using publicly available code from many disciplines. The Prematurity-Related Ventilatory Control (Pre-Vent) observational multicenter prospective study collected bedside monitor data from>700extremely preterm infants to identify physiologic features that predict respiratory outcomes. Approach . We calculated a subset of 33 HCTSA features on>7 M 10 min windows of oxygen saturation (SPO2) and heart rate (HR) from the Pre-Vent cohort to quantify predictive performance. This subset included representatives previously identified using unsupervised clustering on>3500HCTSA algorithms. We hypothesized that the best HCTSA algorithms would compare favorably to optimal PreVent physiologic predictor IH90_DPE (duration per event of intermittent hypoxemia events below 90%). Main Results. The top HCTSA features were from a cluster of algorithms associated with the autocorrelation of SPO2 time series and identified low frequency patterns of desaturation as high risk. These features had comparable performance to and were highly correlated with IH90_DPE but perhaps measure the physiologic status of an infant in a more robust way that warrants further investigation. The top HR HCTSA features were symbolic transformation measures that had previously been identified as strong predictors of neonatal mortality. HR metrics were only important predictors at early days of life which was likely due to the larger proportion of infants whose outcome was death by any cause. A simple HCTSA model using 3 top features outperformed IH90_DPE at day of life 7 (.778 versus .729) but was essentially equivalent at day of life 28 (.849 versus .850). Significance . These results validated the utility of a representative HCTSA approach but also provides additional evidence supporting IH90_DPE as an optimal predictor of respiratory outcomes., (Creative Commons Attribution license.)

Objective: Predictive analytics tools variably take into account data from the electronic medical record, lab tests, nursing charted vital signs and continuous cardiorespiratory monitoring to deliver an instantaneous prediction of patient risk or instability. Few, if any, of these tools reflect the risk to a patient accumulated over the course of an entire hospital stay., Approach: We have expanded on our instantaneous CoMET predictive analytics score to generate the cumulative CoMET score (cCoMET), which sums all of the instantaneous CoMET scores throughout a hospital admission relative to a baseline expected risk unique to that patient., Main Results: We have shown that higher cCoMET scores predict mortality, but not length of stay, and that higher baseline CoMET scores predict higher cCoMET scores at discharge/death. cCoMET scores were higher in males in our cohort, and added information to the final CoMET when it came to the prediction of death., Significance: We have shown that the inclusion of all repeated measures of risk estimation performed throughout a patients hospital stay adds information to instantaneous predictive analytics, and could improve the ability of clinicians to predict deterioration, and improve patient outcomes in so doing., (Creative Commons Attribution license.)

Objective: The goal of predictive analytics monitoring is the early detection of patients at high risk of subacute potentially catastrophic illnesses. An excellent example of a targeted illness is respiratory failure leading to urgent unplanned intubation, where early detection might lead to interventions that improve patient outcomes. Previously, we identified signatures of this illness in the continuous cardiorespiratory monitoring data of intensive care unit (ICU) patients and devised algorithms to identify patients at rising risk. Here, we externally validated three logistic regression models to estimate the risk of emergency intubation developed in Medical and Surgical ICUs at the University of Virginia., Approach: We calculated the model outputs for more than 8000 patients in the University of California-San Francisco ICUs, 240 of whom underwent emergency intubation as determined by individual chart review., Main Results: We found that the AUC of the models exceeded 0.75 in this external population, and that the risk rose appreciably over the 12 h before the event., Significance: We conclude that there are generalizable physiological signatures of impending respiratory failure in the continuous cardiorespiratory monitoring data., (Creative Commons Attribution license.)

Objective. To develop a standardized format for exchanging clinical and physiologic data generated in the intensive care unit. Our goal was to develop a format that would accommodate the data collection pipelines of various sites but would not require dataset-specific schemas or ad-hoc tools for decoding and analysis. Approach. A number of centers had independently developed solutions for storing clinical and physiologic data using Hierarchical Data Format-Version 5 (HDF5), a well-supported standard already in use in multiple other fields. These individual solutions involved design choices that made the data difficult to share despite the underlying common framework. A collaborative process was used to form the basis of a proposed standard that would allow for interoperability and data sharing with common analysis tools. Main Results. We developed the HDF5-based critical care data exchange format which stores multiparametric data in an efficient, self-describing, hierarchical structure and supports real-time streaming and compression. In addition to cardiorespiratory and laboratory data, the format can, in future, accommodate other large datasets such as imaging and genomics. We demonstated the feasibility of a standardized format by converting data from three sites as well as the MIMIC III dataset. Significance. Individual approaches to the storage of multiparametric clinical data are proliferating, representing both a duplication of effort and a missed opportunity for collaboration. Adoption of a standardized format for clinical data exchange will enable the development of a digital biobank, facilitate the external validation of machine learning models and be a powerful tool for sharing multiparametric, high frequency patient level data in multisite clinical trials. Our proposed solution focuses on supporting standardized ontologies such as LOINC allowing easy reading of data regardless of the source and in so doing provides a useful method to integrate large amounts of existing data., (© 2021 Institute of Physics and Engineering in Medicine.)

Objective: The ratio of the partial pressure of arterial oxygen to fraction of inspired oxygen is a key component of the sequential organ failure assessment score that operationally defines sepsis. But, it is calculated infrequently due to the need for the acquisition of an arterial blood gas. So, we sought to find an optimal imputation strategy for the estimation of sepsis-defining hypoxemic respiratory failure using oximetry instead of an arterial blood gas., Approach: We retrospectively studied a sample of non-intubated acute-care patients with oxygen saturation recorded  ⩽10 min before arterial blood sampling (N  =  492 from 2013-2017). We imputed ratios of the partial pressure of arterial oxygen to the fraction of inspired oxygen and sepsis criteria from existing imputation equations (Hill, Severinghaus-Ellis, Rice, and Pandharipande) and compared them with the ratios and sepsis criteria measured from arterial blood gases. We devised a modified model-based equation to eliminate the bias of the results., Main Results: Hypoxemia severity estimates from the Severinghaus-Ellis equation were more accurate than those from other existing equations, but showed significant proportional bias towards under-estimation of hypoxemia severity, especially at oxygen saturations  >96%. Our modified equation eliminated bias and surpassed others on all imputation quality metrics., Significance: Our modified imputation equation, [Formula: see text] is the first one that is free of bias at all oxygen saturations. It resulted in ratios of partial pressure of arterial oxygen to fraction of inspired oxygen and sepsis respiratory criteria closest to those obtained by arterial blood gas testing and is the optimal imputation strategy for non-intubated acute-care patients.

Objective: Predictive analytics monitoring that informs clinicians of the risk for failed extubation would help minimize both the duration of mechanical ventilation and the risk of emergency re-intubation in ICU patients. We hypothesized that dynamic monitoring of cardiorespiratory data, vital signs, and lab test results would add information to standard clinical risk factors., Methods: We report model development in a retrospective observational cohort admitted to either the medical or surgical/trauma ICU that were intubated during their ICU stay and had available physiologic monitoring data (n  =  1202). The primary outcome was removal of endotracheal intubation (i.e. extubation) followed within 48 h by reintubation or death (i.e. failed extubation). We developed a standard risk marker model based on demographic and clinical data. We also developed a novel risk marker model using dynamic data elements-continuous cardiorespiratory monitoring, vital signs, and lab values., Results: Risk estimates from multivariate predictive models in the 24 h preceding extubation were significantly higher for patients that failed. Combined standard and novel risk markers demonstrated good predictive performance in leave-one-out validation: AUC of 0.64 (95% CI: 0.57-0.69) and 1.6 alerts per week to identify 32% of extubations that will fail. Novel risk factors added significantly to the standard model., Conclusion: Predictive analytics monitoring models can detect changes in vital signs, continuous cardiorespiratory monitoring, and laboratory measurements in both the hours preceding and following extubation for those patients destined for extubation failure.

A near-ubiquitous pathology in very low birth weight infants is neonatal apnea, breathing pauses with slowing of the heart and falling blood oxygen. Events of substantial duration occasionally occur after an infant is discharged from the neonatal intensive care unit (NICU). It is not known whether apneas result from a predictable process or from a stochastic process, but the observation that they occur in seemingly random clusters justifies the use of stochastic models. We use a hidden-Markov model to analyze the distribution of durations of apneas and the distribution of times between apneas. The model suggests the presence of four breathing states, ranging from very stable (with an average lifetime of 12 h) to very unstable (with an average lifetime of 10 s). Although the states themselves are not visible, the mathematical analysis gives estimates of the transition rates among these states. We have obtained these transition rates, and shown how they change with post-menstrual age; as expected, the residence time in the more stable breathing states increases with age. We also extrapolated the model to predict the frequency of very prolonged apnea during the first year of life. This paradigm-stochastic modeling of cardiorespiratory control in neonatal infants to estimate risk for severe clinical events-may be a first step toward personalized risk assessment for life threatening apnea events after NICU discharge., Competing Interests: JBD and HL have filed for a patent on the apnea detection algorithm.

Atrial fibrillation (AF) is usually detected by inspection of the electrocardiogram waveform, a task made difficult when the signal is distorted by noise. The RR interval time series is more frequently available and accurate, yet linear and nonlinear time series analyses that detect highly varying and irregular AF are vulnerable to the common finding of frequent ectopy. We hypothesized that different nonlinear measures might capture characteristic features of AF, normal sinus rhythm (NSR), and sinus rhythm (SR) with frequent ectopy in ways that linear measures might not. To test this, we studied 2722 patients with 24 h ECG recordings in the University of Virginia Holter database. We found dynamical phenotypes for the three rhythm classifications. As expected, AF records had the highest variability and entropy, and NSR the lowest. SR with ectopy could be distinguished from AF, which had higher entropy, and from NSR, which had different fractal scaling, measured as higher detrended fluctuation analysis slope. With these dynamical phenotypes, we developed successful classification strategies, and the nonlinear measures improved on the use of mean and variability alone, even after adjusting for age. Final models using all variables had excellent performance, with positive predictive values for AF, NSR and SR with ectopy as high as 97, 98 and 90%, respectively. Since these classifiers can reliably detect rhythm changes utilizing segments as short as 10 min, we envision their application in noisy settings and in personal monitoring devices where only RR interval time series may be available.

Periodic breathing (PB), regular cycles of short apneic pauses and breaths, is common in newborn infants. To characterize normal and potentially pathologic PB, we used our automated apnea detection system and developed a novel method for quantifying PB. We identified a preterm infant who died of sudden infant death syndrome (SIDS) and who, on review of her breathing pattern while in the neonatal intensive care unit (NICU), had exaggerated PB.We analyzed the chest impedance signal for short apneic pauses and developed a wavelet transform method to identify repetitive 10-40 second cycles of apnea/breathing. Clinical validation was performed to distinguish PB from apnea clusters and determine the wavelet coefficient cutoff having optimum diagnostic utility. We applied this method to analyze the chest impedance signals throughout the entire NICU stays of all 70 infants born at 32 weeks' gestation admitted over a two-and-a-half year period. This group includes an infant who died of SIDS and her twin.For infants of 32 weeks' gestation, the fraction of time spent in PB peaks 7-14 d after birth at 6.5%. During that time the infant that died of SIDS spent 40% of each day in PB and her twin spent 15% of each day in PB.This wavelet transform method allows quantification of normal and potentially pathologic PB in NICU patients.

The original observation that reduced heart rate variability (HRV) confers poor prognosis after myocardial infarction has been followed by many studies of heart rate dynamics. We tested the hypothesis that an entropy-based local dynamics measure gave prognostic information in ambulatory patients undergoing 24-h electrocardiography. In this context, entropy is the probability that short templates will find matches in the time series. We studied RR interval time series from 24-h Holter monitors of 1564 consecutive patients over age 39. We generated histograms of the count of templates as a function of the number of templates matches in short RR interval time series, and found characteristic appearance of histograms for atrial fibrillation, sinus rhythm with normal HRV, and sinus rhythm with reduced HRV and premature ventricular contractions (PVCs). We developed statistical models to detect the abnormal dynamic phenotype of reduced HRV with PVCs and fashioned a local dynamics score (LDs) that, after controlling for age, added more prognostic information than other standard risk factors and common HRV metrics, including, to our surprise, the PVC count and the HRV of normal-to-normal intervals. Addition of the LDs to a predictive model using standard risk factors significantly increased the ROC area and the net reclassification improvement was 27%. We conclude that abnormal local dynamics of heart rate confer adverse prognosis in patients undergoing 24-h ambulatory electrocardiography.

Apnea of prematurity is an important and common clinical problem, and is often the rate-limiting process in NICU discharge. Accurate detection of episodes of clinically important neonatal apnea using existing chest impedance (CI) monitoring is a clinical imperative. The technique relies on changes in impedance as the lungs fill with air, a high impedance substance. A potential confounder, however, is blood coursing through the heart. Thus, the cardiac signal during apnea might be mistaken for breathing. We report here a new filter to remove the cardiac signal from the CI that employs a novel resampling technique optimally suited to remove the heart rate signal, allowing improved apnea detection. We also develop an apnea detection method that employs the CI after cardiac filtering. The method has been applied to a large database of physiological signals, and we prove that, compared to the presently used monitors, the new method gives substantial improvement in apnea detection.

We have applied principles of statistical signal processing and nonlinear dynamics to analyze heart rate time series from premature newborn infants in order to assist in the early diagnosis of sepsis, a common and potentially deadly bacterial infection of the bloodstream. We began with the observation of reduced variability and transient decelerations in heart rate interval time series for hours up to days prior to clinical signs of illness. We find that measurements of standard deviation, sample asymmetry and sample entropy are highly related to imminent clinical illness. We developed multivariable statistical predictive models, and an interface to display the real-time results to clinicians. Using this approach, we have observed numerous cases in which incipient neonatal sepsis was diagnosed and treated without any clinical illness at all. This review focuses on the mathematical and statistical time series approaches used to detect these abnormal heart rate characteristics and present predictive monitoring information to the clinician.