Abstract
Introduction: Disease states are being characterized at finer and finer levels of resolution via biomarker or gene expression profiles, while at the same time. Machine learning (ML) is increasingly used to analyze and potentially classify or predict the behavior of biological systems based on such characterization. As ML applications are extremely data-intensive, given the relative sparsity of biomedical data sets ML training of artificial neural networks (ANNs) often require the use of synthetic training data. Agent-based models (ABMs) that incorporate known biological mechanisms and their associated stochastic properties are a potential means of generating synthetic data. Herein we present an example of ML used to train an artificial neural network (ANN) as a surrogate system used to predict the time evolution of an ABM focusing on the clinical condition of sepsis.Methods: The disease trajectories for clinical sepsis, in terms of temporal cytokine and phenotypic dynamics, can be interpreted as a random dynamical system. The Innate Immune Response Agent-based Model (IIRABM) is a well-established model that utilizes known cellular and molecular rules to simulate disease trajectories corresponding to clinical sepsis. We have utilized two distinct neural network architectures, Long Short-Term Memory and Multi-Layer Perceptron, to take a time sequence of five measurements of eleven IIRABM simulated serum cytokine concentrations as input and to return both the future cytokine trajectories as well as an aggregate metric representing the patient’s state of health.Results: The ANNs predicted model trajectories with the expected amount of error, due to stochasticity in the simulation, and recognizing that the mapping from a specific cytokine profile to a state-of-health is not unique. The Multi-Layer Perceptron neural network, generated predictions with a more accurate forecasted trajectory cone.Discussion: This work serves as a proof-of-concept for the use of ANNs to predict disease progression in sepsis as represented by an ABM. The findings demonstrate that multicellular systems with intrinsic stochasticity can be approximated with an ANN, but that forecasting a specific trajectory of the system requires sequential updating of the system state to provide a rolling forecast horizon.
Highlights
Disease states are being characterized at finer and finer levels of resolution via biomarker or gene expression profiles, while at the same time
Toward that end we present an investigation of the ability of trained artificial neural networks (ANNs) to forecast the dynamic behavior of a complex biomedical Agent-based models (ABMs) used to simulate acute systemic inflammation and the clinical condition of sepsis
The sum of cytokine concentrations is a coarse metric that roughly represents the amount of inflammation and inflammatory signaling present in the model. This is analogous to what is seen clinically – patients that see ostensibly identical insults/infections/injuries will invariably present a range of responses, in terms of temporal cytokine profiles or other clinical physiological observables. This figure illustrates a key difference between the structure of the noise in the Innate Immune Response Agent-based Model (IIRABM) and the stochastic structure in a stochastic differential equation; the noise present in the IIRABM varies spatio-temporally and cannot be represented with a closed-form analytical expression
Summary
Disease states are being characterized at finer and finer levels of resolution via biomarker or gene expression profiles, while at the same time. As ML is extremely data-intensive, training is often augmented by the use of synthetic data; it is crucial that the generated surrogate/synthetic data effectively replicates the underlying generative process of the real-world system being learned This issue is less important for such static tasks such as image recognition/classification but takes on considerable importance if time-series/dynamic processes (and functions) are being analyzed. The need to effectively generate synthetic data is accentuated in biomedical applications, where, in general, biomedical data sets are relatively sparse, in terms of time series data needed to predict or forecast the dynamic course of disease This sparsity is further accentuated when molecular-level biomarker panels are proposed as the means of disease characterization, as currently this information can only be acquired through invasive blood sampling. There is an inherent tension between the desire for a finer-grained characterization of disease state and limitations in terms of both availability of such data and the ability to correlate these detailed representations to the physiological derangements present clinically
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
