arXiv subjects

Beckett Sterner

Publications and source records attributed to Beckett Sterner.

7 recordsLinked to original sources

arXiv2026

A Longitudinal Attribute-Conditioned Neural Network for Modeling Health-State Transition Probabilities in Temporally Irregular Data: The LANTERN Framework

Accurate estimation of long-term care transition probabilities is central to disability insurance pricing, reserving, and solvency assessment. Classical actuarial multi-state models commonly rely on Markov, semi-Markov, or proportional-hazard specifications, which provide a direct connection to cohort projection but may be restrictive for irregular longitudinal health data with nonlinear aging patterns and heterogeneous covariate histories. This paper develops a well-calibrated estimator of multi-state transition probabilities for irregular longitudinal health data. The model learns from individual health history, incorporates the time elapsed between observations, and conditions transition probabilities on demographic and socioeconomic attributes. It produces a valid probability distribution over the next observed health state, with four possible states: healthy, mild disability, severe disability, and death. Individual probabilities are aggregated by age group and origin state to form transition matrices compatible with actuarial cohort projection. Using longitudinal data from the Health and Retirement Study, we compare the proposed estimator with logistic regression, gradient-boosted trees, a recurrent neural network, and a last-state persistence benchmark. The evaluation considers probabilistic accuracy, endpoint discrimination and calibration for severe disability and death, risk concentration, and transition matrix error after aggregation. The proposed estimator improves severe disability discrimination relative to logistic regression and gradient-boosted tree benchmarks, maintains strong calibration, and yields the lowest transition matrix error among the evaluated models in the held-out test analysis. Results show that a structured machine learning estimator can support long-term care transition modeling when judged by calibration and projection fidelity, beyond discrimination.

cs.LG↗

arXiv2025

Forecasting Coccidioidomycosis (Valley Fever) in Arizona: A Graph Neural Network Approach

Coccidioidomycosis, commonly known as Valley Fever, remains a significant public health concern in endemic regions of the southwestern United States. This study develops the first graph neural network (GNN) model for forecasting Valley Fever incidence in Arizona. The model integrates surveillance case data with environmental predictors using graph structures, including soil conditions, atmospheric variables, agricultural indicators, and air quality metrics. Our approach explores correlation-based relationships among variables influencing disease transmission. The model captures critical delays in disease progression through lagged effects, enhancing its capacity to reflect complex temporal dependencies in disease ecology. Results demonstrate that the GNN architecture effectively models Valley Fever trends and provides insights into key environmental drivers of disease incidence. These findings can inform early warning systems and guide resource allocation for disease prevention efforts in high-risk areas.

cs.LG↗

arXiv2025

A Simple Approximate Bayesian Inference Neural Surrogate for Stochastic Petri Net Models

Stochastic Petri Nets (SPNs) are an increasingly popular tool of choice for modeling discrete-event dynamics in areas such as epidemiology and systems biology, yet their parameter estimation remains challenging in general and in particular when transition rates depend on external covariates and explicit likelihoods are unavailable. We introduce a neural-surrogate (neural-network-based approximation of the posterior distribution) framework that predicts the coefficients of known covariate-dependent rate functions directly from noisy, partially observed token trajectories. Our model employs a lightweight 1D Convolutional Residual Network trained end-to-end on Gillespie-simulated SPN realizations, learning to invert system dynamics under realistic conditions of event dropout. During inference, Monte Carlo dropout provides calibrated uncertainty bounds together with point estimates. On synthetic SPNs with $10\%$ missing events, our surrogate recovers rate-function coefficients with an $RMSE = 0.043$ and substantially runs faster than traditional Bayesian approaches. These results demonstrate that data-driven, likelihood-free surrogates can enable accurate, robust, and real-time parameter recovery in complex, partially observed discrete-event systems.

cs.LG↗

arXiv2025

The Basic Reproduction Number for Petri Net Models: A Next-Generation Matrix Approach

The basic reproduction number ($R_0$) is an epidemiological metric that represents the average number of new infections caused by a single infectious individual in a completely susceptible population. The methodology for calculating this metric is well-defined for numerous model types, including, most prominently, Ordinary Differential Equations (ODEs). The basic reproduction number is used in disease modeling to predict the potential of an outbreak and the transmissibility of a disease, as well as by governments to inform public health interventions and resource allocation for controlling the spread of diseases. A Petri Net (PN) is a directed bipartite graph where places, transitions, arcs, and the firing of the arcs determine the dynamic behavior of the system. Petri Net models have been an increasingly used tool within the epidemiology community. However, no generalized method for calculating $R_0$ directly from PN models has been established. Thus, in this paper, we establish a generalized computational framework for calculating $R_0$ directly from Petri Net models. We adapt the next-generation matrix method to be compatible with multiple Petri Net formalisms, including both deterministic Variable Arc Weight Petri Nets (VAPNs) and stochastic continuous-time Petri Nets (SPNs). We demonstrate the method's versatility on a range of complex epidemiological models, including those with multiple strains, asymptomatic states, and nonlinear dynamics. Crucially, we numerically validate our framework by demonstrating that the analytically derived $R_0$ values are in strong agreement with those estimated from simulation data, thereby confirming the method's accuracy and practical utility.

math.AT↗

arXiv2024

MPAT: Modular Petri Net Assembly Toolkit

We present a Python package called Modular Petri Net Assembly Toolkit (MPAT) that empowers users to easily create large-scale, modular Petri Nets for various spatial configurations, including extensive spatial grids or those derived from shape files, augmented with heterogeneous information layers. Petri Nets are powerful discrete event system modeling tools in computational biology and engineering. However, their utility for automated construction of large-scale spatial models has been limited by gaps in existing modeling software packages. MPAT addresses this gap by supporting the development of modular Petri Net models with flexible spatial geometries.

cs.MS↗

arXiv2024

A Numerical Comparison of Petri Net and Ordinary Differential Equation SIR Component Models

Petri Nets are an increasingly used modeling framework for the spread of disease across populations or within an individual. For example, the Susceptible-Infectious-Recovered (SIR) compartment model is foundational for population epidemiological modeling and has been implemented in several prior Petri Net studies. While the SIR model is typically expressed as Ordinary Differential Equations (ODEs), with continuous time and variables, Petri Nets operate as discrete event simulations with deterministic or stochastic timings. We present the first systematic study of the numerical convergence of two distinct Petri Net implementations of the SIRS compartment model relative to the standard ODE. In particular, we introduce a novel deterministic implementation of the SIRS model using dynamic transition weights in the GPenSIM package and stochastic Petri Net models using SPIKE. We show how rescaling and rounding procedures are critical for the numerical convergence of Petri Net SIR models relative to the ODEs, and we achieve a relative root mean squared error of less than 1% compared to ODE simulations for biologically relevant parameter ranges. Our findings confirm that both stochastic and deterministic discrete time Petri Nets are valid for modeling SIR-type dynamics with appropriate numerical procedures, laying the foundations for larger-scale use of Petri Net models.

q-bio.OT↗

arXiv2023

A Novel Dataset Towards Extracting Virus-Host Interactions

We describe a novel dataset for the automated recognition of named taxonomic and other entities relevant to the association of viruses with their hosts. We further describe some initial results using pre-trained models on the named-entity recognition (NER) task on this novel dataset. We propose that our dataset of manually annotated abstracts now offers a Gold Standard Corpus for training future NER models in the automated extraction of host-pathogen detection methods from scientific publications, and further explain how our work makes first steps towards predicting the important human health-related concept of viral spillover risk automatically from the scientific literature.

cs.CL↗