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.

Continual learning has emerged as a powerful approach to address the challenges of non-stationary environments, allowing machine learning models to adapt to new data while retaining the previously acquired knowledge. In time-sensitive healthcare applications, where entities such as physicians, hospital rooms, and medications exhibit continuous changes over time, continual learning holds great promise, yet its application remains relatively unexplored. This paper aims to bridge this gap by proposing a novel framework, i.e., Continually-Adaptive Representation Learning, designed to adapt representations in response to changing data distributions in evolving healthcare applications. Specifically, the proposed approach develops a continual learning strategy wherein the context information (e.g., interactions) of healthcare entities is exploited to continually identify and retrain the representations of those entities whose context evolved over time. Moreover, different from existing approaches, the proposed approach leverages the valuable patient information present in clinical notes to generate accurate and robust healthcare embeddings. Notably, the proposed continually-adaptive representations are have practical benefits in low-resource clinical settings where it is difficult to training machine learning models from scratch to accommodate the newly available data streams. Experimental evaluations on real-world healthcare datasets demonstrate the effectiveness of our approach in time-sensitive healthcare applications such as Clostridioides difficile (C.diff) Infection (CDI) incidence prediction task and medical intensive care unit transfer prediction task.

As hospitals move towards automating and integrating their computing systems, more fine-grained hospital operations data are becoming available. These data include hospital architectural drawings, logs of interactions between patients and healthcare professionals, prescription data, procedures data, and data on patient admission, discharge, and transfers. This has opened up many fascinating avenues for healthcare-related prediction tasks for improving patient care. However, in order to leverage off-the-shelf machine learning software for these tasks, one needs to learn structured representations of entities involved from heterogeneous, dynamic data streams. Here, we propose DECENT, an auto-encoding heterogeneous co-evolving dynamic neural network, for learning heterogeneous dynamic embeddings of patients, doctors, rooms, and medications from diverse data streams. These embeddings capture similarities among doctors, rooms, patients, and medications based on static attributes and dynamic interactions. DECENT enables several applications in healthcare prediction, such as predicting mortality risk and case severity of patients, adverse events (e.g., transfer back into an intensive care unit), and future healthcare-associated infections. The results of using the learned patient embeddings in predictive modeling show that DECENT has a gain of up to 48.1% on the mortality risk prediction task, 12.6% on the case severity prediction task, 6.4% on the medical intensive care unit transfer task, and 3.8% on the Clostridioides difficile (C.diff) Infection (CDI) prediction task over the state-of-the-art baselines. In addition, case studies on the learned doctor, medication, and room embeddings show that our approach learns meaningful and interpretable embeddings.

This paper studies the problem of detecting asymptomatic cases in a temporal contact network in which multiple outbreaks have occurred. For many infections, asymptomatic cases present a major obstacle to obtaining a precise understanding of infection-spread. We show that the key to detecting asymptomatic cases well, is taking into account both individual risk as well as the likelihood of disease-flow along edges. Most related research has ignored the interplay between these dual aspects influencing disease-spread. We take both aspects into account by formulating the asymptomatic case detection problem as a Directed Prize-Collecting Steiner Tree (DIRECTED PCST) problem. We present an approximation-preserving reduction from this problem to the Directed Steiner Tree problem and use this reduction to obtain scalable algorithms for the DIRECTED PCST problem. Using these algorithms, we solve instances with more than 1.5M edges obtained from both synthetic and actual fine-grained hospital data. On synthetic data, we demonstrate that our detection methods significantly outperform various baselines (with a gain of $3.6 \times$). As an application of our methods, we use a measure of exposure to detected asymptomatic Clostridioides difficile (C. diff) infection (CDI) cases as an additional feature for the important task of predicting symptomatic CDI cases. In this application, our method outperforms all baselines, including those that don’t use asymptomatic CDI cases as a feature and those that use other methods for detecting asymptomatic CDI cases. We also demonstrate that the solutions returned by our approach are clinically meaningful by presenting a case study.

This paper describes a data-driven simulation study that explores the relative impact of several low-cost and practical non-pharmaceutical interventions on the spread of COVID-19 in an outpatient hospital dialysis unit. The interventions considered include: (i) voluntary self-isolation of healthcare personnel (HCPs) with symptoms; (ii) a program of active syndromic surveillance and compulsory isolation of HCPs; (iii) the use of masks or respirators by patients and HCPs; (iv) improved social distancing among HCPs; (v) increased physical separation of dialysis stations; and (vi) patient isolation combined with preemptive isolation of exposed HCPs. Our simulations show that under conditions that existed prior to the COVID-19 outbreak, extremely high rates of COVID-19 infection can result in a dialysis unit. In simulations under worst-case modeling assumptions, a combination of relatively inexpensive interventions such as requiring surgical masks for everyone, encouraging social distancing between healthcare professionals (HCPs), slightly increasing the physical distance between dialysis stations, and-once the first symptomatic patient is detected-isolating that patient, replacing the HCP having had the most exposure to that patient, and relatively short-term use of N95 respirators by other HCPs can lead to a substantial reduction in both the attack rate and the likelihood of any spread beyond patient zero. For example, in a scenario with R0 = 3.0, 60% presymptomatic viral shedding, and a dialysis patient being the infection source, the attack rate falls from 87.8% at baseline to 34.6% with this intervention bundle. Furthermore, the likelihood of having no additional infections increases from 6.2% at baseline to 32.4% with this intervention bundle.

This paper presents a high-fidelity agent-based simulation of the spread of methicillin-resistant Staphylococcus aureus (MRSA), a serious hospital acquired infection, within the dialysis unit at the University of Iowa Hospitals and Clinics (UIHC). The simulation is based on ten days of fine-grained healthcare worker (HCW) movement and interaction data collected from a sensor mote instrumentation of the dialysis unit by our research group in the fall of 2013. The simulation layers a detailed model of MRSA pathogen transfer, die-off, shedding, and infection on top of agent interactions obtained from data. The specific question this paper focuses on is whether there are simple, inexpensive architectural or process changes one can make in the dialysis unit to reduce the spread of MRSA? We evaluate two architectural changes of the nurses' station: (i) splitting the central nurses' station into two smaller distinct nurses' stations, and (ii) doubling the surface area of the nursing station. The first architectural change is modeled as a graph partitioning problem on a HCW contact network obtained from our HCW movement data. Somewhat counter-intuitively, our results suggest that the first architectural modification and the resulting reduction in HCW-HCW contacts has little to no effect on the spread of MRSA and may in fact lead to an increase in MRSA infection counts in some cases. In contrast, the second modification leads to a substantial reduction - between 12% and 22% for simulations with different parameters - in the number of patients infected by MRSA. These results suggest that the dynamics of an environmentally mediated infection such as MRSA may be quite different from that of infections whose spread is not substantially affected by the environment (e.g., respiratory infections or influenza).