Simulating exposure-related behaviors using agent-based models embedded with needs-based artificial intelligence

Brandon, Namdi; Dionisio, Kathie L.; Isaacs, Kristin; Tornero‐Velez, Rogelio; Kapraun, Dustin F.; Setzer, R. Woodrow; Price, Paul S.

doi:10.1038/s41370-018-0052-y

Cited by 30 publications

(32 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sensing of information (global, from the environment, and social, i.e., from other agents), exchanging information (i.e., interactions between agents), and processing of information (i.e., decision making) are critical. Machine learning (ML) techniques can support these three elements and offer a more realistic way to adjust agents' behavior in ABM [23][24][25][26]. As more data become available in the analysis of the spread of disease, supporting ABM with data-driven approaches becomes a prominent research direction.…”

Section: Introductionmentioning

confidence: 99%

Risk perception and behavioral change during epidemics: Comparing models of individual and collective learning

et al. 2020

View full text Add to dashboard Cite

Modern societies are exposed to a myriad of risks ranging from disease to natural hazards and technological disruptions. Exploring how the awareness of risk spreads and how it triggers a diffusion of coping strategies is prominent in the research agenda of various domains. It requires a deep understanding of how individuals perceive risks and communicate about the effectiveness of protective measures, highlighting learning and social interaction as the core mechanisms driving such processes. Methodological approaches that range from purely physics-based diffusion models to data-driven environmental methods rely on agentbased modeling to accommodate context-dependent learning and social interactions in a diffusion process. Mixing agent-based modeling with data-driven machine learning has become popularity. However, little attention has been paid to the role of intelligent learning in risk appraisal and protective decisions, whether used in an individual or a collective process. The differences between collective learning and individual learning have not been sufficiently explored in diffusion modeling in general and in agent-based models of socioenvironmental systems in particular. To address this research gap, we explored the implications of intelligent learning on the gradient from individual to collective learning, using an agent-based model enhanced by machine learning. Our simulation experiments showed that individual intelligent judgement about risks and the selection of coping strategies by groups with majority votes were outperformed by leader-based groups and even individuals deciding alone. Social interactions appeared essential for both individual learning and group learning. The choice of how to represent social learning in an agent-based model could be driven by existing cultural and social norms prevalent in a modeled society.

show abstract

Section: Introductionmentioning

confidence: 99%

Risk perception and behavioral change during epidemics: Comparing models of individual and collective learning

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The middle term u i (x Ai ) is a Gaussian process with various forms of correlation structure available, capable of mimicking large classes of functions, which has the flexibility to capture more local behaviour of f i (x), and v i (x) is an uncorrelated nugget that represents the effect of the remaining inactive input variables, and/or any stochasticity exhibited by the model. We perform an initial space filling set of n = 125 runs D = (f (x (1) ), f (x (2) ), . .…”

Section: Calibration Via Bayes Linear Emulation and History Matchingmentioning

confidence: 99%

JUNE: open-source individual-based epidemiology simulation

Bullock

Cuesta-Lázaro

Quera-Bofarull

et al. 2020

Preprint

View full text Add to dashboard Cite

We introduce JUNE, an open-source framework for the detailed simulation of epidemics on the basis of social interactions in a virtual population constructed from geographically granular census data, reflecting age, sex, ethnicity, and socio-economic indicators. Interactions between individuals are modelled in groups of various sizes and properties, such as households, schools and workplaces, and other social activities using social mixing matrices. JUNE provides a suite of flexible parameterisations that describe infectious diseases, how they are transmitted and affect contaminated individuals. In this paper we apply JUNE to the specific case of modelling the spread of COVID-19 in England. We discuss the quality of initial model outputs which reproduce reported hospital admission and mortality statistics at national and regional levels as well as by age strata.

show abstract

“…In order to represent population exposure starting from individual data, probabilistic modeling techniques such as Maximum Likelihood Estimation (for variables that fall exclusively on normal distributions), Monte Carlo analysis, or Bayesian modeling were introduced (Harper 2004;Zidek et al 2005;Mutshinda et al 2008;Bogen et al 2009). Further to probabilistic modeling, stochastic agent-based models (Brandon et al 2018) refine further exposure estimates on the individual and population level by encompassing behavioral dynamics and exposure and risk determinants related to sociodemographic characteristics such as socio-economic status, age, gender or educational level. By properly describing these societal dynamics and following the evolution of the virtual agents, a more representative description of behavioral aspects of exposure can be obtained.…”

Section: Exposure Modelsmentioning

confidence: 99%

Critical assessment and integration of separate lines of evidence for risk assessment of chemical mixtures

et al. 2019

View full text Add to dashboard Cite

Humans are exposed to multiple chemicals on a daily basis instead of to just a single chemical, yet the majority of existing toxicity data comes from single-chemical exposure. Multiple factors must be considered such as the route, concentration, duration, and the timing of exposure when determining toxicity to the organism. The need for adequate model systems (in vivo, in vitro, in silico and mathematical) is paramount for better understanding of chemical mixture toxicity. Currently, shortcomings plague each model system as investigators struggle to find the appropriate balance of rigor, reproducibility and appropriateness in mixture toxicity studies. Significant questions exist when comparing single-to mixture-chemical toxicity concerning additivity, synergism, potentiation, or antagonism. Dose/concentration relevance is a major consideration and should be subthreshold for better accuracy in toxicity assessment. Previous work was limited by the technology and methodology of the time, but recent advances have resulted in significant progress in the study of mixture toxicology. Novel technologies have added insight to data obtained from in vivo studies for predictive toxicity testing. These include new in vitro models: omics-related tools, organs-on-a-chip and 3D cell culture, and in silico methods. Taken together, all these modern methodologies improve the understanding of the multiple toxicity pathways associated with adverse outcomes (e.g., adverse outcome pathways), thus allowing investigators to better predict risks linked to exposure to chemical mixtures. As technology and knowledge advance, our ability to harness and integrate separate streams of evidence regarding outcomes associated with chemical mixture exposure improves. As many national and international organizations are currently stressing, studies on chemical mixture toxicity are of primary importance.

show abstract

Simulating exposure-related behaviors using agent-based models embedded with needs-based artificial intelligence

Cited by 30 publications

References 16 publications

Risk perception and behavioral change during epidemics: Comparing models of individual and collective learning

Risk perception and behavioral change during epidemics: Comparing models of individual and collective learning

JUNE: open-source individual-based epidemiology simulation

Critical assessment and integration of separate lines of evidence for risk assessment of chemical mixtures

Contact Info

Product

Resources

About