学术文献库

The disease trajectory for clinical sepsis, in terms of temporal cytokine and phenotypic dynamics, can be interpreted as a random dynamical system. The ability to make accurate predictions about patient state from clinical measurements has eluded the biomedical community, primarily due to the paucity of relevant and high-resolution data. 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 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. The neural networks converged within 50 epochs for cytokine trajectory predictions and health-metric regressions, with the expected amount of error (due to stochasticity in the simulation). The mapping from a specific cytokine profile to a state-of-health is not unique, and increased levels of inflammation result in less accurate predictions. Due to the propagation of machine learning error combined with computational model stochasticity over time, the network should be re-grounded in reality daily as predictions can diverge from the true model trajectory as the system evolves towards a probabilistic basin of attraction. This work serves as a proof-of-concept for the use of artificial neural networks to predict disease progression in sepsis. This work is not intended to replace a trained clinician, rather the goal is to augment intuition with quantifiable statistical information to help them make the best decisions. We note that this relies on a valid computational model of the system in question as there does not exist sufficient data to inform a machine-learning trained, artificially intelligent, controller.