A Model-Based Machine Learning Approach to Probing Autonomic Regulation From Nonstationary Vital-Sign Time Series

Abstract

Physiological variables, such as heart rate (HR), blood pressure (BP) and respiration (RESP), are tightly regulated and coupled under healthy conditions, and a break-down in the coupling has been associated with aging and disease. We present an approach that incorporates physiological modeling within a switching linear dynamical systems (SLDS) framework to assess the various functional components of the autonomic regulation through transfer function analysis of nonstationary multivariate time series of vital signs. We validate our proposed SLDS-based transfer function analysis technique in automatically capturing 1) changes in baroreflex gain due to postural changes in a tilt-table study including ten subjects, and 2) the effect of aging on the autonomic control using HR/RESP recordings from 40 healthy adults. Next, using HR/BP time series of more than 450 adult ICU patients, we show that our technique can be used to reveal coupling changes associated with severe sepsis (AUC = 0.74, sensitivity = 0.74, specificity = 0.60). Our findings indicate that reduced HR/BP coupling is significantly associated with severe sepsis even after adjusting for clinical interventions (P <= 0.001). These results demonstrate the utility of our approach in phenotyping complex vital-sign dynamics, and in providing mechanistic hypotheses in terms of break-down of autoregulatory systems under healthy and disease conditions.

A perspective on sepsis pathogenesis, biomarkers and diagnosis: A concise survey

“…Sepsis is prevalent in newborns which makes its early detection extremely important. In Hu, Lee, and Tan (2018), three physiological attributes (Lehman, Mark, & Nemati, 2018) were utilized to predict sepsis which included the following: heart rate, respiratory rate and blood oxygen saturation. The experienced paediatricians at the NICU of Monash Children Hospital utilized these variables to predict the onset of sepsis in preterm infants.…”

Instantaneous Transfer Entropy for the Study of Cardiovascular and Cardio-Respiratory Nonstationary Dynamics

“…Nevertheless, from a theoretical (and philosophical) perspective its not straightforward to discern behaviours of physiological nonlinearity from non-stationarity [57]. It could be possible, in fact, to consider simple, possibly multivariate, linear models with non-stationary transition dynamics [58], or a single nonlinear model with multiple operating regimes [59]. Our approach concerns multivariate, non-stationarity physiological systems as modelled through multivariate linear equations, therefore complying with non-stationarity, linear physiological systems, or nonlinear physiological systems whose nonlinearity is derived from non-stationarity.…”

Multi‐view ensemble learning with empirical kernel for heart failure mortality prediction

“…In recent years, the EHRs data for machine learning analysis have made significant progress in the field of auxiliary medicine . Machine learning allows the algorithm to learn from data and get a model that is more in line with reality . Machine learning technology helps to reduce medical errors and helps solve the problem of excessive medical treatment.…”