Search

The ongoing SARS-Cov-2 pandemic had many drastic effects upon society beyond the illness and death it caused. Pandemic mitigation measures disrupted and altered behaviors related to social mobility, significantly increasing the time spent at home compared to the pre-pandemic period. Further, it was well documented that social anxiety and stress increased at a population level. Early in the pandemic there was speculation in the popular media that reporting of paranormal phenomena (e.g., UFOs, ghosts, etc.) increased due to factors associated with the pandemic. Past research on UFO/UAP reporting has theorized that increases are triggered by social factors, and so the pandemic provided a natural experiment to test these claims. To measure UFO reports we utilized two public databases of UFO reports for sightings in the United States, provided by the National UFO Reporting Center and the Mutual UFO Network. To estimate the impact of the pandemic we utilized two measures, one for social mobility and one for pandemic/disease severity. Google Community Mobility Reports provided a metric of social mobility for people who use Google Maps on their cellular telephone (i.e., amount of time spent at work compared to home), which we aggregated to a state level to estimate time spent at home. Second, we used new weekly SARS-CoV-2 cases and deaths, both absolute counts and per capita, which can be considered to be an indirect measure of anxiety and stress. We find that UFO reports did increase in 2020 compared to 2019 (p

The goal of this project was to utilize mechanistic simulation to demonstrate a methodology that could determine drug combination dose schedules and dose intensities that would be most effective in eliminating multidrug-resistant cancer cells in early-stage colon cancer. An agent-based model of cell dynamics in human colon crypts was calibrated using measurements of human biopsy specimens. Mutant cancer cells were simulated as cells that were resistant to each of two drugs when the drugs were used separately. The drugs, 5-flurouracil and sulindac, have different mechanisms of action. An artificial neural network was used to generate nearly 200,000 two-drug dose schedules. A high-performance computer simulated each dose schedule as a in silico clinical trial and evaluated each dose schedule for its efficiency to cure (eliminate) multidrug-resistant cancer cells and its toxicity to the host, as indicated by continued crypt function. Among the dose schedules that were generated, 2,430 dose schedules were found to cure all multidrug-resistant mutants in each of the 50 simulated trials and retained colon crypt function. One dose schedule was optimal; it eliminated multidrug-resistant cancer cells with the minimum toxicity and had a time schedule that would be practical for implementation in the clinic. These results demonstrate a procedure to identify which combination drug dose schedules could be most effective in eliminating drug-resistant cancer cells. This was accomplished using a calibrated agent–based model of a human tissue, and a high-performance computer simulation of clinical trials. Significance: The results of computer-simulated clinical trials suggest a practical dose schedule for two drugs, 5-fluorouracil and sulindac, that could eliminate multidrug resistant early-stage colon cancer cells with minimum toxicity to the host.

Skeletal muscle has a robust, inherent ability to regenerate in response to injury from acute to chronic. In severe trauma, however, complete regeneration is not possible, resulting in a permanent loss of skeletal muscle tissue referred to as volumetric muscle loss (VML). There are few consistently reliable therapeutic or surgical options to address VML. A major limitation in investigation of possible therapies is the absence of a well-characterized large animal model. In this study, we present results of a comprehensive transcriptomic, proteomic, and morphologic characterization of wound healing following VML in a novel canine model of VML which we compare to a nine-patient cohort of combat-associated VML. The canine model is translationally relevant as it provides both a regional (spatial) and temporal map of the wound healing processes that occur in human VML. Collectively, these data show the spatiotemporal transcriptomic, proteomic, and morphologic properties of canine VML healing as a framework and model system applicable to future studies investigating novel therapies for human VML. Impact Statement The spatiotemporal transcriptomic, proteomic, and morphologic properties of canine volumetric muscle loss (VML) healing is a translational framework and model system applicable to future studies investigating novel therapies for human VML.

The 2430 dose schedules that cured all doubly resistant mutants in 100% of 50 independent trials and allowed crypts to recover.

Long COVID is recognized as a significant consequence of SARS-COV2 infection. While the pathogenesis of Long COVID is still a subject of extensive investigation, there is considerable potential benefit in being able to predict which patients will develop Long COVID. We hypothesize that there would be distinct differences in the prediction of Long COVID based on the severity of the index infection, and use whether the index infection required hospitalization or not as a proxy for developing predictive models. We divide a large population of COVID patients drawn from the United States National Institutes of Health (NIH) National COVID Cohort Collaborative (N3C) Data Enclave Repository into two cohorts based on the severity of their initial COVID-19 illness and correspondingly trained two machine learning models: the Long COVID after Severe Disease Model (LCaSDM) and the Long COVID after Mild Disease Model (LCaMDM). The resulting models performed well on internal validation/testing, with a F1 score of 0.94 for the LCaSDM and 0.82 for the LCaMDM. There were distinct differences in the top 10 features used by each model, possibly reflecting the differences in type and amount of pathophysiological data between the hospitalized and non-hospitalized patients and/or reflecting different pathophysiological trajectories in the development of Long COVID. Of particular interest was the importance of Plant Hardiness Zone in the feature set for the LCaMDM, which may point to a role of climate and/or sunlight in the progression to Long COVID. Future work will involve a more detailed investigation of the potential role of climate and sunlight, as well as refinement of the predictive models as Long COVID becomes increasingly parsed into distinct clinical phenotypes.

Machine learning (ML) and Artificial Intelligence (AI) approaches are increasingly applied to predicting the development of sepsis and multiple organ failure. While there has been success in demonstrating the clinical utility of such systems in terms of affecting various outcomes, there are fundamental challenges to the ML/AI approach in terms of improving the actual predictive performance and future robustness of such systems. Given that one of the primary proposed avenues for improving algorithmic performance is the addition of molecular/biomarker/genetic features to the data used to train these systems, the overall sparsity of such available data suggests the need to generate synthetic data to aid in training, as has been the case in numerous other ML/AI tasks, such as image recognition/generation and text analysis/generation. We propose the need to generate synthetic molecular/mediator time series data coincides with the advent of the concept of medical digital twins, specifically related to interpretations of medical digital twins that hew closely to the original description and use of industrial digital twins, which involve simulating multiple individual twins from a common computational model specification. Herein we present an example of generating synthetic time series data of a panel of pro- and anti-inflammatory cytokines using the Critical Illness Digital Twin (CIDT) regarding the development of post-traumatic acute respiratory distress syndrome.

BackgroundThe clinical characterization of the functional status of active wounds remains a considerable challenge that at present, requires excision of a tissue biopsy. In this pilot study, we use a convolutional Siamese neural network architecture to predict the functional state of a wound using digital photographs of wounds in a canine model of volumetric muscle loss (VML).Materials and MethodsImages of volumetric muscle loss injuries and tissue biopsies were obtained in a canine model of VML. Gene expression profiles for each image were obtained using RNAseq. These profiles were then converted to functional profiles using a manual review of validated gene ontology databases. A Siamese neural network was trained to regress functional profile expression values as a function of the data contained in an extracted image segment showing the surface of a small tissue biopsy. Network performance was assessed in a test set of images using Mean Absolute Percentage Error (MAPE).ResultsThe network was able to predict the functional expression of a range of functions based with a MAPE ranging from ∼5% to ∼50%, with functions that are most closely associated with the early-state of wound healing to be those best-predicted.ConclusionsThese initial results suggest promise for further research regarding this novel use of ML regression on medical images. The regression of functional profiles, as opposed to specific genes, both addresses the challenge of genetic redundancy and gives a deeper insight into the mechanistic configuration of a region of tissue in wounds. As this preliminary study focuses on the first 14 days of wound healing, future work will focus on extending the training data to include longer time periods which would result in additional functions, such as tissue remodeling, having a larger presence in the training data.

Background Though significant progress in disease elimination has been made over the past decades, trachoma is the leading infectious cause of blindness globally. Further efforts in trachoma elimination are paradoxically being limited by the relative rarity of the disease, which makes clinical training for monitoring surveys difficult. In this work, we evaluate the plausibility of an Artificial Intelligence model to augment or replace human image graders in the evaluation/diagnosis of trachomatous inflammation—follicular (TF). Methods We utilized a dataset consisting of 2300 images with a 5% positivity rate for TF. We developed classifiers by implementing two state-of-the-art Convolutional Neural Network architectures, ResNet101 and VGG16, and applying a suite of data augmentation/oversampling techniques to the positive images. We then augmented our data set with additional images from independent research groups and evaluated performance. Results Models performed well in minimizing the number of false negatives, given the constraint of the low numbers of images in which TF was present. The best performing models achieved a sensitivity of 95% and positive predictive value of 50–70% while reducing the number images requiring skilled grading by 66–75%. Basic oversampling and data augmentation techniques were most successful at improving model performance, while techniques that are grounded in clinical experience, such as highlighting follicles, were less successful. Discussion The developed models perform well and significantly reduce the burden on graders by minimizing the number of false negative identifications. Further improvements in model skill will benefit from data sets with more TF as well as a range in image quality and image capture techniques used. While these models approach/meet the community-accepted standard for skilled field graders (i.e., Cohen’s Kappa >0.7), they are insufficient to be deployed independently/clinically at this time; rather, they can be utilized to significantly reduce the burden on skilled image graders.

BACKGROUND As trachoma is eliminated, skilled field graders become less adept at correctly identifying active disease (trachomatous inflammation—follicular [TF]). Deciding if trachoma has been eliminated from a district or if treatment strategies need to be continued or reinstated is of critical public health importance. Telemedicine solutions require both connectivity, which can be poor in the resource-limited regions of the world in which trachoma occurs, and accurate grading of the images. OBJECTIVE Our purpose was to develop and validate a cloud-based “virtual reading center” (VRC) model using crowdsourcing for image interpretation. METHODS The Amazon Mechanical Turk (AMT) platform was used to recruit lay graders to interpret 2299 gradable images from a prior field trial of a smartphone-based camera system. Each image received 7 grades for US $0.05 per grade in this VRC. The resultant data set was divided into training and test sets to internally validate the VRC. In the training set, crowdsourcing scores were summed, and the optimal raw score cutoff was chosen to optimize kappa agreement and the resulting prevalence of TF. The best method was then applied to the test set, and the sensitivity, specificity, kappa, and TF prevalence were calculated. RESULTS In this trial, over 16,000 grades were rendered in just over 60 minutes for US $1098 including AMT fees. After choosing an AMT raw score cut point to optimize kappa near the World Health Organization (WHO)–endorsed level of 0.7 (with a simulated 40% prevalence TF), crowdsourcing was 95% sensitive and 87% specific for TF in the training set with a kappa of 0.797. All 196 crowdsourced-positive images received a skilled overread to mimic a tiered reading center and specificity improved to 99%, while sensitivity remained above 78%. Kappa for the entire sample improved from 0.162 to 0.685 with overreads, and the skilled grader burden was reduced by over 80%. This tiered VRC model was then applied to the test set and produced a sensitivity of 99% and a specificity of 76% with a kappa of 0.775 in the entire set. The prevalence estimated by the VRC was 2.70% (95% CI 1.84%-3.80%) compared to the ground truth prevalence of 2.87% (95% CI 1.98%-4.01%). CONCLUSIONS A VRC model using crowdsourcing as a first pass with skilled grading of positive images was able to identify TF rapidly and accurately in a low prevalence setting. The findings from this study support further validation of a VRC and crowdsourcing for image grading and estimation of trachoma prevalence from field-acquired images, although further prospective field testing is required to determine if diagnostic characteristics are acceptable in real-world surveys with a low prevalence of the disease.

There has been a great deal of interest in the concept, development and implementation of medical digital twins. This interest has led to wide ranging perceptions of what constitutes a medical digital twin. This Perspectives article will provide 1) a description of fundamental features of industrial digital twins, the source of the digital twin concept, 2) aspects of biology that challenge the implementation of medical digital twins, 3) a schematic program of how a specific medical digital twin project could be defined, and 4) an example description within that schematic program for a specific type of medical digital twin intended for drug discovery, testing and repurposing, the Drug Development Digital Twin (DDDT).

Background As trachoma is eliminated, skilled field graders become less adept at correctly identifying active disease (trachomatous inflammation—follicular [TF]). Deciding if trachoma has been eliminated from a district or if treatment strategies need to be continued or reinstated is of critical public health importance. Telemedicine solutions require both connectivity, which can be poor in the resource-limited regions of the world in which trachoma occurs, and accurate grading of the images. Objective Our purpose was to develop and validate a cloud-based “virtual reading center” (VRC) model using crowdsourcing for image interpretation. Methods The Amazon Mechanical Turk (AMT) platform was used to recruit lay graders to interpret 2299 gradable images from a prior field trial of a smartphone-based camera system. Each image received 7 grades for US $0.05 per grade in this VRC. The resultant data set was divided into training and test sets to internally validate the VRC. In the training set, crowdsourcing scores were summed, and the optimal raw score cutoff was chosen to optimize kappa agreement and the resulting prevalence of TF. The best method was then applied to the test set, and the sensitivity, specificity, kappa, and TF prevalence were calculated. Results In this trial, over 16,000 grades were rendered in just over 60 minutes for US $1098 including AMT fees. After choosing an AMT raw score cut point to optimize kappa near the World Health Organization (WHO)–endorsed level of 0.7 (with a simulated 40% prevalence TF), crowdsourcing was 95% sensitive and 87% specific for TF in the training set with a kappa of 0.797. All 196 crowdsourced-positive images received a skilled overread to mimic a tiered reading center and specificity improved to 99%, while sensitivity remained above 78%. Kappa for the entire sample improved from 0.162 to 0.685 with overreads, and the skilled grader burden was reduced by over 80%. This tiered VRC model was then applied to the test set and produced a sensitivity of 99% and a specificity of 76% with a kappa of 0.775 in the entire set. The prevalence estimated by the VRC was 2.70% (95% CI 1.84%-3.80%) compared to the ground truth prevalence of 2.87% (95% CI 1.98%-4.01%). Conclusions A VRC model using crowdsourcing as a first pass with skilled grading of positive images was able to identify TF rapidly and accurately in a low prevalence setting. The findings from this study support further validation of a VRC and crowdsourcing for image grading and estimation of trachoma prevalence from field-acquired images, although further prospective field testing is required to determine if diagnostic characteristics are acceptable in real-world surveys with a low prevalence of the disease.

PURPOSE Adjuvant chemotherapy is used after surgery for stages II and III colorectal cancer to reduce recurrence. Nevertheless, recurrence may occur years later with the emergence of initially undetected minimal residual disease (MRD). Attempts to reduce recurrence by increasing the dose intensity and increasing the time of adjuvant therapy have been limited by the adverse effects of the recommended cytotoxic agents. The goals of this study were to suggest an alternative to the recommended cytotoxic agents and to determine optimal adjuvant therapy dose schedules that would reduce the percentage of recurrence at 5 years while retaining colon crypt function. METHODS A total of 84,400 dose schedules with different duration, interval between doses, and intensity of treatment were simulated with a high-performance computer. Simulated treatments used the drug sulindac, which had previously been used in primary prevention. With appropriate dose schedules, it can induce apoptosis at the crypt lumen surface while retaining crypt function. We used a computer model of cell dynamics in colon crypts that had been calibrated with measurements of human biopsy specimens. Proliferating mutant cells were assumed to emerge from MRD within crypts. Simulated outcomes included the recurrence percentage at 5 years and the retention of crypt function. RESULTS Optimal dose schedules were determined for adjuvant treatment of MRD that reduced the percentage of recurrence at 5 years of stages I, II, and III colon cancer to zero. CONCLUSION A new adjuvant therapy for colon cancer based upon optimum dose schedules of intermittent apoptotic treatment may prevent the recurrence of colon cancer from MRD and avoid the adverse effects of cytotoxic treatments.

BackgroundDespite a great deal of interest in the application of artificial intelligence (AI) to sepsis/critical illness, most current approaches are limited in their potential impact: prediction models do not (and cannot) address the lack of effective therapeutics and current approaches to enhancing the treatment of sepsis focus on optimizing the application of existing interventions, and thus cannot address the development of new treatment options/modalities. The inability to test new therapeutic applications was highlighted by the generally unsatisfactory results from drug repurposing efforts in COVID-19.HypothesisAddressing this challenge requires the application of simulation-based, model-free deep reinforcement learning (DRL) in a fashion akin to training the game-playing AIs. We have previously demonstrated the potential of this method in the context of bacterial sepsis in which the microbial infection is responsive to antibiotic therapy. The current work addresses the control problem of multi-modal, adaptive immunomodulation in the circumstance where there is no effective anti-pathogen therapy (e.g., in a novel viral pandemic or in the face of resistant microbes).MethodsThis is a proof-of-concept study that determines the controllability of sepsis without the ability to pharmacologically suppress the pathogen. We use as a surrogate system a previously validated agent-based model, the Innate Immune Response Agent-based Model (IIRABM), for control discovery using DRL. The DRL algorithm ‘trains’ an AI on simulations of infection where both the control and observation spaces are limited to operating upon the defined immune mediators included in the IIRABM (a total of 11). Policies were learned using the Deep Deterministic Policy Gradient approach, with the objective function being a return to baseline system health.ResultsDRL trained an AI policy that improved system mortality from 85% to 10.4%. Control actions affected every one of the 11 targetable cytokines and could be divided into those with static/unchanging controls and those with variable/adaptive controls. Adaptive controls primarily targeted 3 different aspects of the immune response: 2nd order pro-inflammation governing TH1/TH2 balance, primary anti-inflammation, and inflammatory cell proliferation.DiscussionThe current treatment of sepsis is hampered by limitations in therapeutic options able to affect the biology of sepsis. This is heightened in circumstances where no effective antimicrobials exist, as was the case for COVID-19. Current AI methods are intrinsically unable to address this problem; doing so requires training AIs in contexts that fully represent the counterfactual space of potential treatments. The synthetic data needed for this task is only possible through the use of high-resolution, mechanism-based simulations. Finally, being able to treat sepsis will require a reorientation as to the sensing and actuating requirements needed to develop these simulations and bring them to the bedside.

Introduction: Disease states are being characterized at finer and finer levels of resolution via biomarker or gene expression profiles, while at the same time. Machine learning (ML) is increasingly used to analyze and potentially classify or predict the behavior of biological systems based on such characterization. As ML applications are extremely data-intensive, given the relative sparsity of biomedical data sets ML training of artificial neural networks (ANNs) often require the use of synthetic training data. Agent-based models (ABMs) that incorporate known biological mechanisms and their associated stochastic properties are a potential means of generating synthetic data. Herein we present an example of ML used to train an artificial neural network (ANN) as a surrogate system used to predict the time evolution of an ABM focusing on the clinical condition of sepsis.Methods: The disease trajectories for clinical sepsis, in terms of temporal cytokine and phenotypic dynamics, can be interpreted as a random dynamical system. The Innate Immune Response Agent-based Model (IIRABM) is a well-established model that utilizes known cellular and molecular rules to simulate disease trajectories corresponding to clinical sepsis. We have utilized two distinct neural network architectures, Long Short-Term Memory and Multi-Layer Perceptron, to take a time sequence of five measurements of eleven IIRABM simulated serum cytokine concentrations as input and to return both the future cytokine trajectories as well as an aggregate metric representing the patient’s state of health.Results: The ANNs predicted model trajectories with the expected amount of error, due to stochasticity in the simulation, and recognizing that the mapping from a specific cytokine profile to a state-of-health is not unique. The Multi-Layer Perceptron neural network, generated predictions with a more accurate forecasted trajectory cone.Discussion: This work serves as a proof-of-concept for the use of ANNs to predict disease progression in sepsis as represented by an ABM. The findings demonstrate that multicellular systems with intrinsic stochasticity can be approximated with an ANN, but that forecasting a specific trajectory of the system requires sequential updating of the system state to provide a rolling forecast horizon.

Volumetric soft tissue and muscle wounds can arise from trauma or necrotizing soft tissue infection. Quantifying the size of these wounds can be challenging, as they often have irregular borders and contours and invariably involve skin loss. 3-dimensional Computed Tomography (3dCT) has been used to characterize the volume of numerous tissue structures, but these use cases invariably involve structures for which clear anatomic borders exist. This is not the case for volumetric soft tissue or muscle wounds, where the volume of the wound being assessed, which is actually a void representing the absence of tissue, does not contain an explicit border at the superficial surface. We present a method that allows quantification of the void size of volumetric muscle wounds using CT scans processed with the software package 3D Slicer. This quantification allows us to chart the progression of healing in such wounds with sequential scans. The development of a means to quantify wound size and healing rate is a necessary capability in order to assess the efficacy of potential therapeutic interventions aimed at enhancing healing of such wounds.

Despite nearly 50 years of research there currently remains no mediator-directed therapy approved for the treatment of sepsis. The failure to effectively translate the copious mechanistic knowledge regarding systemic inflammation to effective therapies is a dramatic example of the translational dilemma. Dynamic computational modeling has been proposed as a vital means of integrating community-wide knowledge into an investigatory framework that allows the application of engineering-like principles to the problem of sepsis. Agent-based modeling is a computational modeling method that has been used to address some of the fundamental issues facing the sepsis research community. This chapter will introduce the rationale to augment traditional research practices with agent-based modeling, describe the basic steps in the construction and use of agent-based models, and provide examples of how the use of agent-based modeling can provide an investigatory pathway to solving the challenge of sepsis.

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.

Background The clinical characterization of the biological status of complex wounds remains a considerable challenge. Digital photography provides a non–invasive means of obtaining wound information and is currently employed to assess wounds qualitatively. Advances in machine learning (ML) image processing provide a means of identifying “hidden” features in pictures. This pilot study trains a convolutional neural network (CNN) to predict gene expression based on digital photographs of wounds in a canine model of volumetric muscle loss (VML). Materials and Methods Images of volumetric muscle loss injuries and tissue biopsies were obtained in a canine model of VML. A CNN was trained to regress gene expression values as a function of the extracted image segment (color and spatial distribution). Performance of the CNN was assessed in a held-back test set of images using Mean Absolute Percentage Error (MAPE). Results The CNN was able to predict the gene expression of certain genes based on digital images, with a MAPE ranging from ∼10% to ∼30%, indicating the presence and identification of distinct, and identifiable patterns in gene expression throughout the wound. Conclusions These initial results suggest promise for further research regarding this novel use of ML regression on medical images. Specifically, the use of CNNs to determine the mechanistic biological state of a VML wound could aid both the design of future mechanistic interventions and the design of trials to test those therapies. Future work will expand the CNN training and/or test set, with potential expansion to predicting functional gene modules.

Despite nearly 50 years of research there currently remains no mediator-directed therapy approved for the treatment of sepsis. The failure to effectively translate the copious mechanistic knowledge regarding systemic inflammation to effective therapies is a dramatic example of the translational dilemma. Dynamic computational modeling has been proposed as a vital means of integrating community-wide knowledge into an investigatory framework that allows the application of engineering-like principles to the problem of sepsis. Agent-based modeling is a computational modeling method that has been used to address some of the fundamental issues facing the sepsis research community. This chapter will introduce the rationale to augment traditional research practices with agent-based modeling, describe the basic steps in the construction and use of agent-based models, and provide examples of how the use of agent-based modeling can provide an investigatory pathway to solving the challenge of sepsis.

The inflammatory response is a dynamic, complex process that involves multiple interacting cell types and molecular mediators. Proinflammatory, feed-forward processes allow for proper ramp-up of inflammation but can also drive a maladaptive, overly exuberant response that harms tissues. Antiinflammatory, negative feedback processes keep these feed-forward aspects of inflammation in check and often stimulate healing, but when produced inappropriately can either impair healing or, at the other extreme, drive excessive scaring and fibrosis. Biomaterials are used to repair injured tissues but may be suboptimal or even harmful if they exacerbate the inflammatory response in those tissues. In this chapter, we describe how computational approaches to modeling inflammation in silico—including some studies involving biomaterials—have helped us decipher some of the complexity of inflammation, suggesting applications of computational modeling to optimize the preclinical and clinical use of biomaterials.

Gut inflammation plays a crucial role in a host of disease processes, most notably in inflammatory bowel disease (IBD) and gut derived sepsis. The gut is also the primary interface between an individual’s microbiome and the host, where appropriate equipoise of mucosal inflammatory potential is a critical goal. The architecture and histological structure of the gut mucosa remains a primary means of diagnosing different gastrointestinal diseases, and as such, computational representations with a translational goal should be able to replicate, at least to some degree, the alterations of gut mucosal architecture resulting from different pathophysiological processes. Given that gut inflammation forms the common pathway by which a host of different disease processes can manifest, we propose that a translationally useful computational representation of gut inflammation should be able to generate these different disease processes through different perturbations on a common, underlying model (as is the case in the real world). To that end we have developed the Spatially Explicit General-purpose Model of Enteric Tissue (SEGMEnT) as a common, unifying platform with which to examine how different perturbations and disorders can lead to a range of recognized pathophysiologic phenotypes. We have additionally expanded SEGMEnT to a high-performance computing (HPC) version that gives the capability to simulate billions of cells and achieve anatomic-scale representation.

The fundamental challenge posed by the “translational dilemma” is the ability to translate the results of basic science research into effective therapeutics. This chapter takes the perspective that the goal of medicine is treatment of disease, and that such treatment can be cast as a control problem. More specifically, the general concept of “personalized” and “precision” medicine should be approached as a control discovery task, for which there are existing tools and methods that rely on the development and use of mathematical and computational models. As opposed to the common usages of “precision” and “personalized” medicine, we specifically identify four axioms that define “precision medicine” and serve as criteria to be met in the control discovery process: (1) personalization; (2) precision; (3) treatment; and (4) inclusiveness, as related to determining appropriate interventions to treat complex diseases. Mechanistic mathematical and computational models, with their roots in optimization and control theory, play a critical role in discovering modalities of control. Though success relies heavily on sufficiently detailed mechanistic models for which development, calibration, and evaluation are formidable tasks, we assert that this approach provides the only foreseeable way forward for successfully achieving personalized, precision medicine.

The 2019 novel coronavirus, SARS-CoV-2, is a pathogen of critical significance to international public health. Knowledge of the interplay between molecular-scale virus-receptor interactions, single-cell viral replication, intracellular-scale viral transport, and emergent tissue-scale viral propagation is limited. Moreover, little is known about immune system-virus-tissue interactions and how these can result in low-level (asymptomatic) infections in some cases and acute respiratory distress syndrome (ARDS) in others, particularly with respect to presentation in different age groups or pre-existing inflammatory risk factors. Given the nonlinear interactions within and among each of these processes, multiscale simulation models can shed light on the emergent dynamics that lead to divergent outcomes, identify actionable “choke points” for pharmacologic interventions, screen potential therapies, and identify potential biomarkers that differentiate patient outcomes. Given the complexity of the problem and the acute need for an actionable model to guide therapy discovery and optimization, we introduce and iteratively refine a prototype of a multiscale model of SARS-CoV-2 dynamics in lung tissue. The first prototype model was built and shared internationally as open source code and an online interactive model in under 12 hours, and community domain expertise is driving regular refinements. In a sustained community effort, this consortium is integrating data and expertise across virology, immunology, mathematical biology, quantitative systems physiology, cloud and high performance computing, and other domains to accelerate our response to this critical threat to international health. More broadly, this effort is creating a reusable, modular framework for studying viral replication and immune response in tissues, which can also potentially be adapted to related problems in immunology and immunotherapy.

IntroductionAgent-based modeling frequently used modeling method for multi-scale mechanistic modeling. However, the same properties that make agent-based models (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 free parameters often present in these models. We have proposed that various machine learning approaches (such as genetic algorithms (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.MethodsThis 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.ResultsThe 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 towards 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.ConclusionWe present an HPC-enabled evolutionary computing approach to calibrate a complex ABM to clinical data while preserving biological heterogeneity. The integration of machine learning, HPC, and multi-scale mechanistic modeling provides a pathway forward to effectively represent the heterogeneity of clinical populations and their data.Author SummaryIn this work, we utilize genetic algorithms (GA) to operate on the internal rule set of a computational of the human immune response to injury, the Innate Immune Response Agent-Based Model (IIRABM), such that it is iteratively refined to generate cytokine time series that closely match what is seen in a clinical cohort of burn patients. At the termination of the GA, there exists an ensemble of candidate model rule-sets/parameterizations which are validated by the experimental data

Viral respiratory infections, such as influenza, result in over 1 million deaths worldwide each year. To date, there are few therapeutic interventions able to affect the course of the disease once acquired, a deficit with stark consequences that were readily evident in the current COVID-19 pandemic. We present the Cellular Immune Agent Based Model (CIABM) as a flexible framework for modeling acute viral infection and cellular immune memory development. The mechanism/rule-based nature of the CIABM allows for interrogation of the complex dynamics of the human immune system during various types of viral infections. The CIABM is an extension of a prior agent-based model of the innate immune response, incorporating additional cellular types and mediators involved in the response to viral infection. The CIABM simulates the dynamics of viral respiratory infection in terms of epithelial invasion, immune cellular population changes and cytokine measurements. Validation of the CIABM involved effectively replicating in vivo measurements of circulating mediator levels from a clinical cohort of influenza patients. The general purpose nature of the CIABM allows for both the representation of various types of known viral infections and facilitates the exploration of hypothetical, novel viral pathogens.

There is increasing interest in the use of mechanism-based multi-scale computational models (such as agent-based models) to generate simulated clinical populations in order to discover and evaluate potential diagnostic and therapeutic modalities. A necessary precondition of this use is the ability to parameterize these highly complex models in an appropriate clinical context, which itself is often a complex environment. The description of the environment in which a biomedical simulation operates (model context) and parameterization of internal model rules (model content) requires the optimization of a large number of free-parameters; given the wide range of variable combinations, along with the intractability of ab initio modeling techniques which could be used to constrain these combinations, an astronomical number of simulations would be required to achieve this goal. In this work, we utilize a nested active-learning workflow to efficiently parameterize and contextualize an agent-based model (ABM) of systemic inflammation used to examine sepsis. Methods Billions of microbial sepsis patients were simulated using a previously validated ABM of acute systemic inflammation, the Innate Immune Response Agent-Based Model (IIRABM). Contextual parameter space was examined using the following parameters: cardio-respiratory-metabolic resilience; two properties of microbial virulence, invasiveness and toxigenesis; and degree of contamination from the environment. The model’s internal parameterization, which represents gene expression and associated cellular behaviors, was explored through the augmentation or inhibition of signaling pathways for 12 signaling mediators associated with inflammation and wound healing. We have implemented a nested active learning approach in which the clinically relevant model environment space for a given internal model parameterization is mapped using a small Artificial Neural Network (ANN). The outer AL level workflow is a larger ANN which uses a novel approach to active learning, Double Monte-Carlo Dropout Uncertainty (DMCDU), to efficiently regress the volume and centroid location of the CR space given by a single internal parameterization. Results A brute-force exploration of the IIRABM’s content and context would require approximately 3*10 12 simulations, and the result would be a coarse representation of a continuous space. We have reduced the number of simulations required to efficiently map the clinically relevant parameter space of this model by approximately 99%. Additionally, we have shown that more complex models with a larger number of variables may expect further improvements in efficiency.

Critical illness, a constellation of interrelated inflammatory and physiological derangements occurring subsequent to severe infection or injury, affects a large number of individuals in both developed and developing countries. The prototypical complex system embodied in critical illness has largely defied therapy beyond supportive care. We have focused on the utility of data-driven and mechanistic computational modelling to help address the complexity of critical illness and provide pathways towards discovering potential therapeutic options and combinations. Herein, we review recent progress in this field, with a focus on both animal and computational models of critical illness. We suggest that therapy for critical illness can be posed as a model-based dynamic control problem, and discuss novel theoretical and experimental approaches involving biohybrid devices aimed at reprogramming inflammation dynamically. Together, these advances offer the potential for Model-based Precision Medicine for critical illness.

Our objective was to determine if consuming table grapes reduces adiposity and its metabolic consequences and alters gut microbiota in mice fed a high fat (HF), butter-rich diet. C57BL/6J mice were fed a low fat (LF) diet or HF diet with 3% or 5% grapes for 11 weeks. Total body and inguinal fat were moderately, but significantly reduced in mice fed both levels of grapes compared to their controls. Mice fed 5% grapes had lower liver weights and triglyceride levels, and decreased expression of glycerol-3-phosphate acyltransferase (Gpat1) compared to the 5% controls. Mice fed 3% grapes had lower hepatic mRNA levels of peroxisome proliferator-activated receptor gamma 2, sterol-CoA desaturase 1, fatty-acid binding protein 4, and Gpat1 compared to the 3% controls. Although grape feeding had only a minor impact on markers of inflammation or lipogenesis in adipose tissue or intestine, 3% grapes decreased the intestinal abundance of sulfidogenic Desulfobacter spp., and the Bilophila wadsworthia-specific dissimilatory sulfite reductase gene (dsrA-Bw), and tended to increase the abundance of the beneficial bacterium Akkermansia muciniphila compared to controls. Additionally, Bifidobacterium, Lactobacillus, Allobaculum, and several other genera correlated negatively with adiposity. Allobaculum in particular was increased in the LF and 3% grapes groups compared to the HF-fed controls. Notably, grape feeding attenuated the HF-induced impairment in epithelial localization of the intestinal tight junction protein zonula occludens. Collectively, these data indicate that some of the adverse health consequences of consuming a HF diet rich in saturated fat can be attenuated by table grape consumption.

Cancer chemotherapy dose schedules are conventionally applied intermittently, with dose duration of the order of hours, intervals between doses of days or weeks, and cycles repeated for weeks. The large number of possible combinations of values of duration, interval, and lethality has been an impediment to empirically determine the optimal set of treatment conditions. The purpose of this project was to determine the set of parameters for duration, interval, and lethality that would be most effective for treating early colon cancer. An agent-based computer model that simulated cell proliferation kinetics in normal human colon crypts was calibrated with measurements of human biopsy specimens. Mutant cells were simulated as proliferating and forming an adenoma, or dying if treated with cytotoxic chemotherapy. Using a high performance computer, a total of 28,800 different parameter sets of duration, interval, and lethality were simulated. The effect of each parameter set on the stability of colon crypts, the time to cure a crypt of mutant cells, and the accumulated dose was determined. Of the 28,800 parameter sets, 434 parameter sets were effective in curing the crypts of mutant cells before they could form an adenoma and allowed the crypt normal cell dynamics to recover to pretreatment levels. A group of 14 similar parameter sets produced a minimal time to cure mutant cells. A different group of 9 similar parameter sets produced the least accumulated dose. These parameter sets may be considered as candidate dose schedules to guide clinical trials for early colon cancer.

A large and growing body of research implicates aberrant immune response and compositional shifts of the intestinal microbiota in the pathogenesis of many intestinal disorders. The molecular and physical interaction between the host and the microbiota, known as the host-microbiota interactome, is one of the key drivers in the pathophysiology of many of these disorders. This host-microbiota interactome is a set of dynamic and complex processes, and needs to be treated as a distinct entity and subject for study. Disentangling this complex web of interactions will require novel approaches, using a combination of data-driven bioinformatics with knowledge-driven computational modeling. This review describes the computational approaches for investigating the host-microbiota interactome, with emphasis on the human intestinal tract and innate immunity, and highlights open challenges and existing gaps in the computation methodology for advancing our knowledge about this important facet of human health.

BackgroundCancer is a complex, multiscale dynamical system, with interactions between tumor cells and non-cancerous host systems. Therapies act on this combined cancer-host system, sometimes with unexpected results. Systematic investigation of mechanistic computational models can augment traditional laboratory and clinical studies, helping identify the factors driving a treatment’s success or failure. However, given the uncertainties regarding the underlying biology, these multiscale computational models can take many potential forms, in addition to encompassing high-dimensional parameter spaces. Therefore, the exploration of these models is computationally challenging. We propose that integrating two existing technologies—one to aid the construction of multiscale agent-based models, the other developed to enhance model exploration and optimization—can provide a computational means for high-throughput hypothesis testing, and eventually, optimization.ResultsIn this paper, we introduce a high throughput computing (HTC) framework that integrates a mechanistic 3-D multicellular simulator (PhysiCell) with an extreme-scale model exploration platform (EMEWS) to investigate high-dimensional parameter spaces. We show early results in applying PhysiCell-EMEWS to 3-D cancer immunotherapy and show insights on therapeutic failure. We describe a generalized PhysiCell-EMEWS workflow for high-throughput cancer hypothesis testing, where hundreds or thousands of mechanistic simulations are compared against data-driven error metrics to perform hypothesis optimization.ConclusionsWhile key notational and computational challenges remain, mechanistic agent-based models and high-throughput model exploration environments can be combined to systematically and rapidly explore key problems in cancer. These high-throughput computational experiments can improve our understanding of the underlying biology, drive future experiments, and ultimately inform clinical practice.

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.Author summarySepsis, characterized by 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 this work, we utilize a computational model of the human immune response to infectious injury to offer an explanation as to why previously attempted treatment strategies are inadequate and why the current approach to drug/therapy-development is inadequate. We then use evolutionary computation algorithms to explore drug-intervention space using this same computational model. This allows us to characterize the scale and scope of interventions needed to successfully control sepsis, as well as the types of data needed to derive these interventions. We demonstrate that multi-point and time-dependent varying controls are necessary and able to control the cytokine network dynamics of the immune system.

Objectives: Sepsis affects nearly 1 million people in the United States per year, has a mortality rate of 28–50m% and requires more than $20 billion a year in hospital costs. Over a quarter century of research has not yielded a single reliable diagnostic test or a directed therapeutic agent for sepsis. Central to this insufficiency is the fact that sepsis remains a clinical/physiological diagnosis representing a multitude of molecularly heterogeneous pathological trajectories. Advances in computational capabilities offered by High Performance Computing (HPC) platforms call for an evolution in the investigation of sepsis to attempt to define the boundaries of traditional research (bench, clinical and computational) through the use of computational proxy models. We present a novel investigatory and analytical approach, derived from how HPC resources and simulation are used in the physical sciences, to identify the epistemic boundary conditions of the study of clinical sepsis via the use of a proxy agent-based model of systemic inflammation. Design: Current predictive models for sepsis use correlative methods are limited by patient heterogeneity and data sparseness. We address this issue by using an HPC version of a system-level validated agent-based model of sepsis, the Innate Immune Response ABM (IIRBM), as a proxy system in order to identify boundary conditions for the possible behavioral space for sepsis. We then apply advanced analysis derived from the study of Random Dynamical Systems (RDS) to identify novel means for characterizing system behavior and providing insight into the tractability of traditional investigatory methods. Results: The behavior space of the IIRABM was examined by simulating over 70 million sepsis patients for up to 90 days for the following parameters: cardio-respiratory-metabolic resilience; microbial invasiveness; microbial toxigenesis; and degree of nosocomial exposure. In addition to using established methods for describing parameter space, we developed two novel methods for characterizing the behavior of a RDS: Probabilistic Basins of Attraction (PBoA) and Stochastic Trajectory Analysis (STA). Computationally generated behavioral landscapes demonstrated attractor structures around stochastic regions of behavior that could be described in a complementary fashion through use of PBoA and STA. The stochasticity of the boundaries of the attractors highlights the challenge for correlative attempts to characterize and classify clinical sepsis. Conclusions: HPC simulations of models like the IIRABM can be used to generate approximations of the behavior space of sepsis to both establish “boundaries of futility” with respect to existing investigatory approaches and apply system engineering principles to investigate the general dynamic properties of sepsis to provide a pathway for developing control strategies. The issues that bedevil the study and treatment of sepsis, namely clinical data sparseness and inadequate experimental sampling of system behavior space, are fundamental to nearly all biomedical research, manifesting in the “Crisis of Reproducibility” at all levels. HPC-augmented simulation-based research offers an investigatory strategy more consistent with that seen in the physical sciences (which combine experiment, theory and simulation), and an opportunity to utilize the leading advances in HPC, namely deep machine learning and evolutionary computing, to form the basis of an iterative scientific process to meet the full promise of Precision Medicine (right drug, right patient, right time).

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., Author summary Sepsis, characterized by 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 this work, we utilize a computational model of the human immune response to infectious injury to offer an explanation as to why previously attempted treatment strategies are inadequate and why the current approach to drug/therapy-development is inadequate. We then use evolutionary computation algorithms to explore drug-intervention space using this same computational model as a surrogate system for human sepsis to identify the scale and scope of interventions to successfully control sepsis, as well as the types of data needed to derive these interventions. We demonstrate that multi-point and time-dependent varying controls are necessary and able to control the cytokine network dynamics of the immune system.

The objective of this study was to determine if consuming an extractable or non-extractable fraction of table grapes reduced the metabolic consequences of consuming a high-fat, American-type diet. Male C57BL/6J mice were fed a low fat (LF) diet, a high fat (HF) diet, or a HF diet containing whole table grape powder (5% w/w), an extractable, polyphenol-rich (HF-EP) fraction, a non-extractable, polyphenol-poor (HF-NEP) fraction, or equal combinations of both fractions (HF-EP+NEP) from grape powder for 16 weeks. Mice fed the HF-EP and HF-EP+NEP diets had lower percentages of body fat and amounts of white adipose tissue (WAT) and improved glucose tolerance compared to the HF-fed controls. Mice fed the HF-EP+NEP diet had lower liver weights and triglyceride (TG) levels compared to the HF-fed controls. Mice fed the HF-EP+NEP diets had higher hepatic mRNA levels of hormone sensitive lipase and adipose TG lipase, and decreased expression of c-reactive protein compared to the HF-fed controls. In epididymal (visceral) WAT, the expression levels of several inflammatory genes were lower in mice fed the HF-EP and HF-EP+NEP diets compared to the HF-fed controls. Mice fed the HF diets had increased myeloperoxidase activity and impaired localization of the tight junction protein zonula occludens-1 in ileal mucosa compared to the HF-EP and HF-NEP diets. Several of these treatment effects were associated with alterations in gut bacterial community structure. Collectively, these data demonstrate that the polyphenol-rich, EP fraction from table grapes attenuated many of the adverse health consequences associated with consuming a HF diet.