Dataset Information

Examining the controllability of sepsis using genetic algorithms on an agent-based model of systemic inflammation.

ABSTRACT: Sepsis, a manifestation of the body's inflammatory response to injury and infection, has a mortality rate of between 28%-50% and affects approximately 1 million patients annually in the United States. Currently, there are no therapies targeting the cellular/molecular processes driving sepsis that have demonstrated the ability to control this disease process in the clinical setting. We propose that this is in great part due to the considerable heterogeneity of the clinical trajectories that constitute clinical "sepsis," and that determining how this system can be controlled back into a state of health requires the application of concepts drawn from the field of dynamical systems. In this work, we consider the human immune system to be a random dynamical system, and investigate its potential controllability using an agent-based model of the innate immune response (the Innate Immune Response ABM or IIRABM) as a surrogate, proxy system. Simulation experiments with the IIRABM provide an explanation as to why single/limited cytokine perturbations at a single, or small number of, time points is unlikely to significantly improve the mortality rate of sepsis. We then use genetic algorithms (GA) to explore and characterize multi-targeted control strategies for the random dynamical immune system that guide it from a persistent, non-recovering inflammatory state (functionally equivalent to the clinical states of systemic inflammatory response syndrome (SIRS) or sepsis) to a state of health. We train the GA on a single parameter set with multiple stochastic replicates, and show that while the calculated results show good generalizability, more advanced strategies are needed to achieve the goal of adaptive personalized medicine. This work evaluating the extent of interventions needed to control a simplified surrogate model of sepsis provides insight into the scope of the clinical challenge, and can serve as a guide on the path towards true "precision control" of sepsis.

SUBMITTER: Cockrell RC

PROVIDER: S-EPMC5813897 | biostudies-literature | 2018 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Examining the controllability of sepsis using genetic algorithms on an agent-based model of systemic inflammation.

Cockrell Robert Chase RC An Gary G

PLoS computational biology 20180215 2

Sepsis, a manifestation of the body's inflammatory response to injury and infection, has a mortality rate of between 28%-50% and affects approximately 1 million patients annually in the United States. Currently, there are no therapies targeting the cellular/molecular processes driving sepsis that have demonstrated the ability to control this disease process in the clinical setting. We propose that this is in great part due to the considerable heterogeneity of the clinical trajectories that const ...[more]

PMID: 29447154

Similar Datasets

Project description:Introduction: Accounting for biological heterogeneity represents one of the greatest challenges in biomedical research. Dynamic computational and mathematical models can be used to enhance the study and understanding of biological systems, but traditional methods for calibration and validation commonly do not account for the heterogeneity of biological data, which may result in overfitting and brittleness of these models. Herein we propose a machine learning approach that utilizes genetic algorithms (GAs) to calibrate and refine an agent-based model (ABM) of acute systemic inflammation, with a focus on accounting for the heterogeneity seen in a clinical data set, thereby avoiding overfitting and increasing the robustness and potential generalizability of the underlying simulation model. Methods: Agent-based modeling is a frequently used modeling method for multi-scale mechanistic modeling. However, the same properties that make ABMs well suited to representing biological systems also present significant challenges with respect to their construction and calibration, particularly with respect to the selection of potential mechanistic rules and the large number of associated free parameters. We have proposed that machine learning approaches (such as GAs) can be used to more effectively and efficiently deal with rule selection and parameter space characterization; the current work applies GAs to the challenge of calibrating a complex ABM to a specific data set, while preserving biological heterogeneity reflected in the range and variance of the data. This project uses a GA to augment the rule-set for a previously validated ABM of acute systemic inflammation, the Innate Immune Response ABM (IIRABM) to clinical time series data of systemic cytokine levels from a population of burn patients. The genome for the GA is a vector generated from the IIRABM's Model Rule Matrix (MRM), which is a matrix representation of not only the constants/parameters associated with the IIRABM's cytokine interaction rules, but also the existence of rules themselves. Capturing heterogeneity is accomplished by a fitness function that incorporates the sample value range ("error bars") of the clinical data. Results: The GA-enabled parameter space exploration resulted in a set of putative MRM rules and associated parameterizations which closely match the cytokine time course data used to design the fitness function. The number of non-zero elements in the MRM increases significantly as the model parameterizations evolve toward a fitness function minimum, transitioning from a sparse to a dense matrix. This results in a model structure that more closely resembles (at a superficial level) the structure of data generated by a standard differential gene expression experimental study. Conclusion: We present an HPC-enabled machine learning/evolutionary computing approach to calibrate a complex ABM to complex clinical data while preserving biological heterogeneity. The integration of machine learning, HPC, and multi-scale mechanistic modeling provides a pathway forward to more effectively representing the heterogeneity of clinical populations and their data.

Project description:The study of the pathogenesis of breast cancer is challenged by the long time-course of the disease process and the multi-factorial nature of generating oncogenic insults. The characterization of the longitudinal pathogenesis of malignant transformation from baseline normal breast duct epithelial dynamics may provide vital insight into the cascading systems failure that leads to breast cancer. To this end, extensive information on the baseline behavior of normal mammary epithelium and breast cancer oncogenesis was integrated into a computational model termed the Ductal Epithelium Agent-Based Model (DEABM). The DEABM is composed of computational agents that behave according to rules established from published cellular and molecular mechanisms concerning breast duct epithelial dynamics and oncogenesis. The DEABM implements DNA damage and repair, cell division, genetic inheritance and simulates the local tissue environment with hormone excretion and receptor signaling. Unrepaired DNA damage impacts the integrity of the genome within individual cells, including a set of eight representative oncogenes and tumor suppressors previously implicated in breast cancer, with subsequent consequences on successive generations of cells. The DEABM reproduced cellular population dynamics seen during the menstrual cycle and pregnancy, and demonstrated the oncogenic effect of known genetic factors associated with breast cancer, namely TP53 and Myc, in simulations spanning ?40 years of simulated time. Simulations comparing normal to BRCA1-mutant breast tissue demonstrated rates of invasive cancer development similar to published epidemiologic data with respect to both cumulative incidence over time and estrogen-receptor status. Investigation of the modeling of ER?-positive (ER+) tumorigenesis led to a novel hypothesis implicating the transcription factor and tumor suppressor RUNX3. These data suggest that the DEABM can serve as a potentially valuable framework to augment the traditional investigatory workflow for future hypothesis generation and testing of the mechanisms of breast cancer oncogenesis.

Project description:OBJECTIVES:We tested the hypothesis that a C-reactive protein and ferritin-based systemic inflammation contingency table can track mortality risk in pediatric severe sepsis. DESIGN:Prospective cohort study. SETTING:Tertiary PICU. PATIENTS:Children with 100 separate admission episodes of severe sepsis were enrolled. INTERVENTIONS:Blood samples were attained on day 2 of sepsis and bi-weekly for biomarker batch analysis. A 2?×?2 contingency table using C-reactive protein and ferritin thresholds was developed. MEASUREMENTS AND MAIN RESULTS:A C-reactive protein of 4.08?mg/dL and a ferritin of 1,980?ng/mL were found to be optimal cutoffs for outcome prediction at first sampling (n = 100) using the Youden index. PICU mortality was increased in the "high-risk" C-reactive protein greater than or equal to 4.08?mg/dL and ferritin greater than or equal to 1,980?ng/mL category (6/13 [46.15%]) compared with the "intermediate-risk" C-reactive protein greater than or equal to 4.08?mg/dL and ferritin less than 1,980?ng/mL or C-reactive protein less than 4.08?mg/dL and ferritin greater than or equal to 1,980?ng/mL categories (2/43 [4.65%]), and the "low-risk" C-reactive protein less than 4.08?mg/dL and ferritin less than 1,980?ng/mL category (0/44 [0%]) (odds ratio, 36.43 [95% CI, 6.16-215.21]). The high-risk category was also associated with the development of immunoparalysis (odds ratio, 4.47 [95% CI, 1.34-14.96]) and macrophage activation syndrome (odds ratio, 24.20 [95% CI, 5.50-106.54]). Sixty-three children underwent sequential blood sampling; those who were initially in the low-risk category (n = 24) and those who subsequently migrated (n = 19) to the low-risk category all survived, whereas those who remained in the "at-risk" categories had increased mortality (7/20 [35%]; p < 0.05). CONCLUSIONS:A C-reactive protein- and ferritin-based contingency table effectively assessed mortality risk. Reduction in systemic inflammation below a combined threshold C-reactive protein of 4.08?mg/dL and ferritin of 1,980?ng/mL appeared to be a desired response in children with severe sepsis.

Dataset Information

Examining the controllability of sepsis using genetic algorithms on an agent-based model of systemic inflammation.

Publications

Examining the controllability of sepsis using genetic algorithms on an agent-based model of systemic inflammation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure