Healthcare-associated infections (HAIs) from multi-drug resistant organisms (MDROs) pose a significant challenge for healthcare systems. Patients can arrive at hospitals already infected ("importation") or acquire infections during their stay ("nosocomial infection"). Many cases, often asymptomatic, complicate rapid identification due to testing limitations and delays. Although recent advancements in mathematical modeling and machine learning have aimed to identify at-risk patients, these methods face challenges: transmission models often overlook valuable electronic health record (EHR) data, while machine learning approaches typically lack mechanistic insights into underlying processes. To address these issues, we propose NeurABM, a novel framework that integrates neural networks and agent-based models (ABM) to leverage the strengths of both methods. NeurABM simultaneously learns a neural network for patient-level importation predictions and an ABM for infection identification. Our findings show that NeurABM significantly outperforms existing methods, marking a breakthrough in accurately identifying importation cases and forecasting future nosocomial infections in clinical practice.

One of the most significant challenges in combating against the spread of infectious diseases was the difficulty in estimating the true magnitude of infections. Unreported infections could drive up disease spread, making it very hard to accurately estimate the infectivity of the pathogen, therewith hampering our ability to react effectively. Despite the use of surveillance-based methods such as serological studies, identifying the true magnitude is still challenging. This paper proposes an information theoretic approach for accurately estimating the number of total infections. Our approach is built on top of Ordinary Differential Equations (ODE) based models, which are commonly used in epidemiology and for estimating such infections. We show how we can help such models to better compute the number of total infections and identify the parametrization by which we need the fewest bits to describe the observed dynamics of reported infections. Our experiments on COVID-19 spread show that our approach leads to not only substantially better estimates of the number of total infections but also better forecasts of infections than standard model calibration based methods. We additionally show how our learned parametrization helps in modeling more accurate what-if scenarios with non-pharmaceutical interventions. Our approach provides a general method for improving epidemic modeling which is applicable broadly.

Decision-focused learning (DFL) has recently emerged as a powerful approach for predict-then-optimize problems by customizing a predictive model to a downstream optimization task. However, existing end-to-end DFL methods are hindered by three significant bottlenecks: model mismatch error, sample average approximation error, and gradient approximation error. Model mismatch error stems from the misalignment between the model's parameterized predictive distribution and the true probability distribution. Sample average approximation error arises when using finite samples to approximate the expected optimization objective. Gradient approximation error occurs as DFL relies on the KKT condition for exact gradient computation, while most methods approximate the gradient for backpropagation in non-convex objectives. In this paper, we present DF2 -- the first \textit{distribution-free} decision-focused learning method explicitly designed to address these three bottlenecks. Rather than depending on a task-specific forecaster that requires precise model assumptions, our method directly learns the expected optimization function during training. To efficiently learn the function in a data-driven manner, we devise an attention-based model architecture inspired by the distribution-based parameterization of the expected objective. Our method is, to the best of our knowledge, the first to address all three bottlenecks within a single model. We evaluate DF2 on a synthetic problem, a wind power bidding problem, and a non-convex vaccine distribution problem, demonstrating the effectiveness of DF2.

Objective: To evaluate the economic costs of reducing the University of Virginia Hospital's present "3-negative" policy, which continues methicillin-resistant Staphylococcus aureus (MRSA) contact precautions until patients receive 3 consecutive negative test results, to either 2 or 1 negative. Design: Cost-effective analysis. Settings: The University of Virginia Hospital. Patients: The study included data from 41,216 patients from 2015 to 2019. Methods: We developed a model for MRSA transmission in the University of Virginia Hospital, accounting for both environmental contamination and interactions between patients and providers, which were derived from electronic health record (EHR) data. The model was fit to MRSA incidence over the study period under the current 3-negative clearance policy. A counterfactual simulation was used to estimate outcomes and costs for 2- and 1-negative policies compared with the current 3-negative policy. Results: Our findings suggest that 2-negative and 1-negative policies would have led to 6 (95% CI, -30 to 44; P < .001) and 17 (95% CI, -23 to 59; -10.1% to 25.8%; P < .001) more MRSA cases, respectively, at the hospital over the study period. Overall, the 1-negative policy has statistically significantly lower costs ($628,452; 95% CI, $513,592-$752,148) annually (P < .001) in US dollars, inflation-adjusted for 2023) than the 2-negative policy ($687,946; 95% CI, $562,522-$812,662) and 3-negative ($702,823; 95% CI, $577,277-$846,605). Conclusions: A single negative MRSA nares PCR test may provide sufficient evidence to discontinue MRSA contact precautions, and it may be the most cost-effective option.

Heterogeneous agent-based models (HABMs) can simulate the dynamics of multiple types of entities and their interactions on contact networks. In recent years, they have gathered great interest and are widely applied in multiple fields, such as personalized recommendations, publication ranking, and epidemic modeling. Nevertheless, conventional HABMs on graphs can only capture pair-wise interactions between agents but fail to capture the more complex dynamics of group interactions (e.g., multiple people in the same location simultaneously), consequently leading to suboptimal performance. To address this, we propose using hypergraphs to capture such group interactions better and extend the current graph-based HABMs to hypergraphs. Specifically, we use MRSA (Methicillin-resistant Staphylococcus aureus, a kind of infectious disease acquired by patients during treatment at healthcare facilities) spread in the University of Virginia hospital as an example to showcase how we extend an existing graph-based HABM, Graph-HeterSIS, to a hypergraph-based HABM (H(2)ABM), Hypergraph-HeterSIS. We show how the hyper graphs can capture the structural dioerence between contacts before and during the first wave of COVID-19 outbreak in Virginia better than graphs. Our experiments show that H2ABM better captures the underlying group interactions and better fits and forecasts MRSA cases.

Time series data are ubiquitous across a wide range of real-world domains. While real-world time series analysis (TSA) requires human experts to integrate numerical series data with multimodal domain-specific knowledge, most existing TSA models rely solely on numerical data, overlooking the significance of information beyond numerical series. This oversight is due to the untapped potential of textual series data and the absence of a comprehensive, high-quality multimodal dataset. To overcome this obstacle, we introduce Time-MMD, the first multi-domain, multimodal time series dataset covering 9 primary data domains. Time-MMD ensures fine-grained modality alignment, eliminates data contamination, and provides high usability. Additionally, we develop MM-TSFlib, the first multimodal time-series forecasting (TSF) library, seamlessly pipelining multimodal TSF evaluations based on Time-MMD for in-depth analyses. Extensive experiments conducted on Time-MMD through MM-TSFlib demonstrate significant performance enhancements by extending unimodal TSF to multimodality, evidenced by over 15 and up to 40 and library revolutionize broader applications, impacts, research topics to advance TSA. The dataset and library are available at https://github.com/AdityaLab/Time-MMD and https://github.com/AdityaLab/MM-TSFlib.

Healthcare acquired infections (HAIs) (e.g., Methicillin-resistant Staphylococcus aureus infection) have complex transmission pathways, spreading not just via direct person-to-person contacts, but also via contaminated surfaces. Prior work in mathematical epidemiology has led to a class of models – which we call load sharing models – that provide a discrete-time, stochastic formalization of HAI-spread on temporal contact networks. The focus of this paper is the source detection problem for the load sharing model. The source detection problem has been studied extensively in SEIR type models, but this prior work does not apply to load sharing models. We show that a natural formulation of the source detection problem for the load sharing model is computationally hard, even to approximate. We then present two alternate formulations that are much more tractable. The tractability of our problems depends crucially on the submodularity of the expected number of infections as a function of the source set. Prior techniques for showing submodularity, such as the "live graph" technique are not applicable for the load sharing model and our key technical contribution is to use a more sophisticated "coupling" technique to show the submodularity result. We propose algorithms for our two problem formulations by extending existing algorithmic results from submodular optimization and combining these with an expectation propagation heuristic for the load sharing model that leads to orders-of-magnitude speedup. We present experimental results on temporal contact networks based on fine-grained EMR data from three different hospitals. Our results on synthetic outbreaks on these networks show that our algorithms outperform baselines by up to 5.97 times. Furthermore, case studies based on hospital outbreaks of Clostridioides difficile infection show that our algorithms identify clinically meaningful sources.

We introduce EINNs, a framework crafted for epidemic forecasting that builds upon the theoretical grounds provided by mechanistic models as well as the data-driven expressibility afforded by AI models, and their capabilities to ingest heterogeneous information. Although neural forecasting models have been successful in multiple tasks, predictions well-correlated with epidemic trends and long-term predictions remain open challenges. Epidemiological ODE models contain mechanisms that can guide us in these two tasks; however, they have limited capability of ingesting data sources and modeling composite signals. Thus, we propose to leverage work in physics-informed neural networks to learn latent epidemic dynamics and transfer relevant knowledge to another neural network which ingests multiple data sources and has more appropriate inductive bias. In contrast with previous work, we do not assume the observability of complete dynamics and do not need to numerically solve the ODE equations during training. Our thorough experiments on all US states and HHS regions for COVID-19 and influenza forecasting showcase the clear benefits of our approach in both short-term and long-term forecasting as well as in learning the mechanistic dynamics over other non-trivial alternatives.

Healthcare-associated infections (HAIs) are a major problem in hospital infection control. Although HAIs can be suppressed using contact precautions, such precautions are expensive, and we can only apply them to a small fraction of patients (i.e., a limited budget). In this work, we focus on two clinical problems arising from the limited budget: (a) choosing the best patients to be placed under precaution given a limited budget to minimize the spread (the isolation problem), and (b) choosing the best patients to release when limited budget requires some of the patients to be cleared from precaution (the clearance problem). A critical challenge in addressing them is that HAIs have multiple transmission pathways such that locations can also accumulate ‘load’ and spread the disease. One of the most common practices when placing patients under contact precautions is the regular clearance of pathogen loads. However, standard propagation models like independent cascade (IC)/susceptible-infectious-susceptible (SIS) cannot capture such mechanisms directly. Hence to account for this challenge, using non-linear system theory, we develop a novel spectral characterization of a recently proposed pathogen load based model, 2-Mode-SIS model, on people/location networks to capture spread dynamics of HAIs. We formulate the two clinical problems using this spectral characterization and develop effective and efficient algorithms for them. Our experiments show that our methods outperform several natural structural and clinical approaches on real-world hospital testbeds and pick meaningful solutions.

Diffusion-based graph generative models have recently obtained promising results for graph generation. However, existing diffusion-based graph generative models are mostly one-shot generative models that apply Gaussian diffusion in the dequantized adjacency matrix space. Such a strategy can suffer from difficulty in model training, slow sampling speed, and incapability of incorporating constraints. We propose an \emph{autoregressive diffusion} model for graph generation. Unlike existing methods, we define a node-absorbing diffusion process that operates directly in the discrete graph space. For forward diffusion, we design a \emph{diffusion ordering network}, which learns a data-dependent node absorbing ordering from graph topology. For reverse generation, we design a \emph{denoising network} that uses the reverse node ordering to efficiently reconstruct the graph by predicting the node type of the new node and its edges with previously denoised nodes at a time. Based on the permutation invariance of graph, we show that the two networks can be jointly trained by optimizing a simple lower bound of data likelihood. Our experiments on six diverse generic graph datasets and two molecule datasets show that our model achieves better or comparable generation performance with previous state-of-the-art, and meanwhile enjoys fast generation speed.

Short-term probabilistic forecasts of the trajectory of the COVID-19 pandemic in the United States have served as a visible and important communication channel between the scientific modeling community and both the general public and decision-makers. Forecasting models provide specific, quantitative, and evaluable predictions that inform short-term decisions such as healthcare staffing needs, school closures, and allocation of medical supplies. Starting in April 2020, the US COVID-19 Forecast Hub ( https://covid19forecasthub.org/ ) collected, disseminated, and synthesized tens of millions of specific predictions from more than 90 different academic, industry, and independent research groups. A multimodel ensemble forecast that combined predictions from dozens of groups every week provided the most consistently accurate probabilistic forecasts of incident deaths due to COVID-19 at the state and national level from April 2020 through October 2021. The performance of 27 individual models that submitted complete forecasts of COVID-19 deaths consistently throughout this year showed high variability in forecast skill across time, geospatial units, and forecast horizons. Two-thirds of the models evaluated showed better accuracy than a naïve baseline model. Forecast accuracy degraded as models made predictions further into the future, with probabilistic error at a 20-wk horizon three to five times larger than when predicting at a 1-wk horizon. This project underscores the role that collaboration and active coordination between governmental public-health agencies, academic modeling teams, and industry partners can play in developing modern modeling capabilities to support local, state, and federal response to outbreaks.

Decision-focused learning (DFL) was recently proposed for stochastic optimization problems that involve unknown parameters. By integrating predictive modeling with an implicitly differentiable optimization layer, DFL has shown superior performance to the standard two-stage predict-then-optimize pipeline. However, most existing DFL methods are only applicable to convex problems or a subset of nonconvex problems that can be easily relaxed to convex ones. Further, they can be inefficient in training due to the requirement of solving and differentiating through the optimization problem in every training iteration. We propose SO-EBM, a general and efficient DFL method for stochastic optimization using energy-based models. Instead of relying on KKT conditions to induce an implicit optimization layer, SO-EBM explicitly parameterizes the original optimization problem using a differentiable optimization layer based on energy functions. To better approximate the optimization landscape, we propose a coupled training objective that uses a maximum likelihood loss to capture the optimum location and a distribution-based regularizer to capture the overall energy landscape. Finally, we propose an efficient training procedure for SO-EBM with a self-normalized importance sampler based on a Gaussian mixture proposal. We evaluate SO-EBM in three applications: power scheduling, COVID-19 resource allocation, and non-convex adversarial security game, demonstrating the effectiveness and efficiency of SO-EBM.

The efficient detection of outbreaks and other cascading phenomena is a fundamental problem in a number of domains, including disease spread, social networks, and infrastructure networks. In such settings, monitoring and testing a small group of pre-selected nodes from the susceptible population (i.e., a sensor set) is often the preferred testing regime. We study the problem of selecting a sensor set that minimizes the delay in detection---we refer to this as the MinDelSS problem. Prior methods for minimizing the detection time rely on greedy algorithms using submodularity. We show that this approach can sometimes lead to a worse approximation for minimizing the detection time than desired. We also show that MinDelSS is hard to approximate within an O(n^(1-1/g))-factor for any constant g greater than or equal to 2 for a graph with n nodes. This instead motivates seeking a bicriteria approximations. We present the algorithm RoundSensor, which gives a rigorous worst case O(log(n))-factor for the detection time, while violating the budget by a factor of O(log^2(n)). Our algorithm is based on the sample average approximation technique from stochastic optimization, combined with linear programming and rounding. We evaluate our algorithm on several networks, including hospital contact networks, which validates its effectiveness in real settings.

How do we forecast an emerging pandemic in real time in a purely data-driven manner? How to leverage rich heterogeneous data based on various signals such as mobility, testing, and/or disease exposure for forecasting? How to handle noisy data and generate uncertainties in the forecast? In this paper, we present D eep C ovid , an operational deep learning frame-work designed for real-time COVID-19 forecasting. D eep -C ovid works well with sparse data and can handle noisy heterogeneous data signals by propagating the uncertainty from the data in a principled manner resulting in meaningful uncertainties in the forecast. The deployed framework also consists of modules for both real-time and retrospective exploratory analysis to enable interpretation of the forecasts. Results from real-time predictions (featured on the CDC website and FiveThirtyEight.com) since April 2020 indicates that our approach is competitive among the methods in the COVID-19 Forecast Hub, especially for short-term predictions.

Estimating the true extent of the outbreak was one of the major challenges in combating COVID-19 outbreak early on. Our inability in doing so, allowed unreported/undetected in- fections to drive up disease spread in numerous regions in the US and worldwide. Accurately identifying the true magnitude of infections still remains a major challenge, despite the use of surveillance-based methods such as serological studies, due to their costs and biases. In this paper, we propose an information theoretic approach to accurately estimate the unreported infections. Our approach, built on top of an existing ordinary differential equations based epi- demiological model, aims to deduce an optimal parameterization of the epidemiological model and the true extent of the outbreak which "best describes" the observed reported infections. Our experiments show that the parameterization learned by our framework leads to a better estimation of unreported infections as well as more accurate forecasts of the reported infec- tions compared to the baseline parameterization. We also demonstrate that our framework can be leveraged to simulate what-if scenarios with non-pharmaceutical interventions. Our results also support earlier findings that a large majority of COVID-19 infections were unreported and non-pharmaceutical interventions indeed helped in mitigating the COVID-19 outbreak.