A design specification for Critical Illness Digital Twins (CIDTs) to cure sepsis: responding to the National Academies of Sciences, Engineering and Medicine Report "Foundational Research Gaps and Future Directions for Digital Twins".

On December 15, 2023, The National Academies of Sciences, Engineering and Medicine (NASEM) released a report entitled: "Foundational Research Gaps and Future Directions for Digital Twins." The ostensible purpose of this report was to bring some structure to the burgeoning field of digital twins by providing a working definition and a series of research challenges that need to be addressed to allow this technology to fulfill its full potential. In the work presented herein we focus on five specific findings from the NASEM Report: 1) definition of a Digital Twin, 2) using "fit-for-purpose" guidance, 3) developing novel approaches to Verification, Validation and Uncertainty Quantification (VVUQ) of Digital Twins, 4) incorporating control as an explicit purpose for a Digital Twin and 5) using a Digital Twin to guide data collection and sensor development, and describe how these findings are addressed through the design specifications for a Critical Illness Digital Twin (CIDT) aimed at curing sepsis.

Toward mechanistic medical digital twins: some use cases in immunology.

A fundamental challenge for personalized medicine is to capture enough of the complexity of an individual patient to determine an optimal way to keep them healthy or restore their health. This will require personalized computational models of sufficient resolution and with enough mechanistic information to provide actionable information to the clinician. Such personalized models are increasingly referred to as medical digital twins. Digital twin technology for health applications is still in its infancy, and extensive research and development is required. This article focuses on several projects in different stages of development that can lead to specific-and practical-medical digital twins or digital twin modeling platforms. It emerged from a two-day forum on problems related to medical digital twins, particularly those involving an immune system component. Open access video recordings of the forum discussions are available.

Forum on immune digital twins: a meeting report.

Medical digital twins are computational models of human biology relevant to a given medical condition, which are tailored to an individual patient, thereby predicting the course of disease and individualized treatments, an important goal of personalized medicine. The immune system, which has a central role in many diseases, is highly heterogeneous between individuals, and thus poses a major challenge for this technology. In February 2023, an international group of experts convened for two days to discuss these challenges related to immune digital twins. The group consisted of clinicians, immunologists, biologists, and mathematical modelers, representative of the interdisciplinary nature of medical digital twin development. A video recording of the entire event is available. This paper presents a synopsis of the discussions, brief descriptions of ongoing digital twin projects at different stages of progress. It also proposes a 5-year action plan for further developing this technology. The main recommendations are to identify and pursue a small number of promising use cases, to develop stimulation-specific assays of immune function in a clinical setting, and to develop a database of existing computational immune models, as well as advanced modeling technology and infrastructure.

Examining B-cell dynamics and responsiveness in different inflammatory milieus using an agent-based model.

INTRODUCTION: B-cells are essential components of the immune system that neutralize infectious agents through the generation of antigen-specific antibodies and through the phagocytic functions of naïve and memory B-cells. However, the B-cell response can become compromised by a variety of conditions that alter the overall inflammatory milieu, be that due to substantial, acute insults as seen in sepsis, or due to those that produce low-level, smoldering background inflammation such as diabetes, obesity, or advanced age. This B-cell dysfunction, mediated by the inflammatory cytokines Interleukin-6 (IL-6) and Tumor Necrosis Factor-alpha (TNF-α), increases the susceptibility of late-stage sepsis patients to nosocomial infections and increases the incidence or severity of recurrent infections, such as SARS-CoV-2, in those with chronic conditions. We propose that modeling B-cell dynamics can aid the investigation of their responses to different levels and patterns of systemic inflammation. METHODS: The B-cell Immunity Agent-based Model (BCIABM) was developed by integrating knowledge regarding naïve B-cells, short-lived plasma cells, long-lived plasma cells, memory B-cells, and regulatory B-cells, along with their various differentiation pathways and cytokines/mediators. The BCIABM was calibrated to reflect physiologic behaviors in response to: 1) mild antigen stimuli expected to result in immune sensitization through the generation of effective immune memory, and 2) severe antigen challenges representing the acute substantial inflammation seen during sepsis, previously documented in studies on B-cell behavior in septic patients. Once calibrated, the BCIABM was used to simulate the B-cell response to repeat antigen stimuli during states of low, chronic background inflammation, implemented as low background levels of IL-6 and TNF-α often seen in patients with conditions such as diabetes, obesity, or advanced age. The levels of immune responsiveness were evaluated and validated by comparing to a Veteran's Administration (VA) patient cohort with COVID-19 infection known to have a higher incidence of such comorbidities. RESULTS: The BCIABM was successfully able to reproduce the expected appropriate development of immune memory to mild antigen exposure, as well as the immunoparalysis seen in septic patients. Simulation experiments then revealed significantly decreased B-cell responsiveness as levels of background chronic inflammation increased, reproducing the different COVID-19 infection data seen in a VA population. CONCLUSION: The BCIABM proved useful in dynamically representing known mechanisms of B-cell function and reproduced immune memory responses across a range of different antigen exposures and inflammatory statuses. These results elucidate previous studies demonstrating a similar negative correlation between the B-cell response and background inflammation by positing an established and conserved mechanism that explains B-cell dysfunction across a wide range of phenotypic presentations.

Characterizing the Crosstalk Between Programmed Cell Death Pathways in Cytokine Storm With an Agent-Based Model.

Background: There is increasing recognition of extensive crosstalk between programmed cell death pathways (PCDPs), such as apoptosis, pyroptosis, and necroptosis, resulting in a highly redundant system responsive to a breadth of potential pathogens. However, because pyroptosis and necroptosis propagate inflammation, these redundancies also present challenges for therapeutic control of dysregulated hyperinflammation seen in cytokine storm (CS) generated organ dysfunction. Hypothesis: We hypothesize that the conversion of existing knowledge regarding apoptosis, pyroptosis, and necroptosis into a computational model can enhance our understanding of the crosstalk between PCDPs via simulation experiments of microbe interactions and experimental interventions. Materials and Methods: Literature regarding apoptosis, pyroptosis, and necroptosis was reviewed and transposed into an agent-based model, the programmed cell death agent-based model (PCDABM). Computational experiments were performed to simulate the activation of various PCDPs as seen by differing microbes, specifically: influenza A virus (IAV), enteropathic Escherichia coli (EPEC), and Salmonella enterica (SE). The potential protective value of PCDP crosstalk was evaluated by silencing either pyroptosis, necroptosis, or both. Computational experiments were also performed simulating the effect of potential therapies blocking tumor necrosis factor (TNF) and interleukin (IL)-1. Results: The PCDABM was implemented in the agent-based modeling toolkit NetLogo. Computational experiments of infection with IAV, EPEC, and SE reproduced cross-activation of PCDPs with effective microbial clearance. Simulations of anti-TNF and anti-IL-1 did not reduce the aggregated amount of inflammation-generated system damage, the surrogate for CS-generated tissue damage. Conclusions: Redundancies have evolved in host PCDPs to maintain protection against a wide range of pathogens. However, these redundancies also challenge attempts at dampening the pathogenic hyperinflammatory state of CS using therapeutic immunomodulation. Integrative simulation models such as the PCDABM can aid in identifying potentially targetable inflection points to mitigate CS while maintaining effective host defense.

Children are small adults (when properly normalized): Transferrable/generalizable sepsis prediction.

Background: Though governed by the same underlying biology, the differential physiology of children causes the temporal evolution from health to a septic/diseased state to follow trajectories that are distinct from adult cases. As pediatric sepsis data sets are less readily available than for adult sepsis, we aim to leverage this shared underlying biology by normalizing pediatric physiological data such that it would be directly comparable to adult data, and then develop machine-learning (ML) based classifiers to predict the onset of sepsis in the pediatric population. We then externally validated the classifiers in an independent adult dataset. Methods: Vital signs and laboratory observables were obtained from the Pediatric Intensive Care (PIC) database. These data elements were normalized for age and placed on a continuous scale, termed the Continuous Age-Normalized SOFA (CAN-SOFA) score. The XGBoost algorithm was used to classify pediatric patients that are septic. We tested the trained model using adult data from the MIMIC-IV database. Results: On the pediatric population, the sepsis classifier has an accuracy of 0.84 and an F1-Score of 0.867. On the adult population, the sepsis classifier has an accuracy of 0.80 and an F1-score of 0.88; when tested on the adult population, the model showed similar performance degradation ("data drift") as in the pediatric population. Conclusions: In this work, we demonstrate that, using a straightforward age-normalization method, EHR's can be generalizable compared (at least in the context of sepsis) between the pediatric and adult populations.

Management of acute cholecystitis in patients on anti-thrombotic therapy: A single center experience.

Background: Acute cholecystitis in patients on anti-thrombotic therapy (ATT) presents a clinical dilemma at the intersection between conflicting guidelines, specifically between timing of early operative management (OM) versus time-to-reversal of certain ATT agents. With growing recognition that nonoperative management (NOM) is associated with considerable morbidity, and evidence in the literature that early OM in patients on ATT is safe, we reviewed our own practice to examine how we addressed these conflicting guidelines. Materials and methods: We performed a retrospective review of patients with acute cholecystitis between December 2017 and March 2022. Patients were classified as ATT or non-ATT; ATT patients were subdivided into anticoagulation (AC) and antiplatelet (AP) groups. Rates of OM were compared. Results: 502 patients with acute cholecystitis were identified, 464 non-ATT and 38 ATT. 30 ATT patients were on AC, 7 on AP, and 1 on both. Non-ATT patients were significantly more likely to receive OM at index presentation compared to those on ATT: 89.9 % vs 63.2 % (p < 0.05). Subgroup analysis of the ATT group showed AP patients were significantly less likely to receive OM compared to those on AC, 12.5 % vs 77 % (p < 0.05). Conclusions: At our institution, patients on ATT were significantly less likely to undergo OM for acute cholecystitis compared with non-ATT patients. Those on AC received OM significantly more than patients on AP. Further study is needed to better define the management of this growing population so that acute cholecystitis guidelines might address this issue in the future.

Artificial Intelligence Optical Biopsy for Evaluating the Functional State of Wounds.

INTRODUCTION: The clinical characterization of the functional status of active wounds in terms of their driving cellular and molecular biology remains a considerable challenge that currently requires excision via a tissue biopsy. In this pilot study, we use convolutional Siamese neural network (SNN) architecture to predict the functional state of a wound using digital photographs of wounds in a canine model of volumetric muscle loss (VML). METHODS: Digital images of VML injuries and tissue biopsies were obtained in a standardized fashion from an established canine model of VML. Gene expression profiles for each biopsy site were obtained using RNA sequencing. These profiles were converted to functional profiles by a manual review of validated gene ontology databases in which we determined a hierarchical representation of gene functions based on functional specificity. An SNN was trained to regress functional profile expression values, informed by an image segment showing the surface of a small tissue biopsy. RESULTS: The SNN was able to predict the functional expression of a range of functions based with error ranging from ∼5% to ∼30%, with functions that are most closely associated with the early state of wound healing to be those best-predicted. CONCLUSIONS: These initial results suggest promise for further research regarding this novel use of machine learning 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.

Current patterns of trauma center proliferation have not led to proportionate improvements in access to care or mortality after injury: An ecologic study.

BACKGROUND: Timely access to high-level (I/II) trauma centers (HLTCs) is essential to minimize mortality after injury. Over the last 15 years, there has been a proliferation of HLTC nationally. The current study evaluates the impact of additional HLTC on population access and injury mortality. METHODS: A geocoded list of HLTC, with year designated, was obtained from the American Trauma Society, and 60-minute travel time polygons were created using OpenStreetMap data. Census block group population centroids, county population centroids, and American Communities Survey data from 2005 and 2020 were integrated. Age-adjusted nonoverdose injury mortality was obtained from CDC Wide-ranging Online Data for Epidemiologic Research and the Robert Wood Johnson Foundation. Geographically weighted regression models were used to identify independent predictors of HLTC access and injury mortality. RESULTS: Over the 15-year (2005-2020) study period, the number of HLTC increased by 31.0% (445 to 583), while population access to HLTC increased by 6.9% (77.5-84.4%). Despite this increase, access was unchanged in 83.1% of counties, with a median change in access of 0.0% (interquartile range, 0.0-1.1%). Population-level age-adjusted injury mortality rates increased by 5.39 per 100,000 population during this time (60.72 to 66.11 per 100,000). Geographically weighted regression controlling for population demography and health indicators found higher median income and higher population density to be positively associated with majority (≥50%) HLTC population coverage and negatively associated with county-level nonoverdose mortality. CONCLUSION: Over the past 15 years, the number of HLTC increased 31%, while population access to HLTC increased only 6.9%. High-level (I/II) trauma center designation is likely driven by factors other than population need. To optimize efficiency and decrease potential oversupply, the designation process should include population level metrics. Geographic information system methodology can be an effective tool to assess optimal placement. LEVEL OF EVIDENCE: Prognostic and Epidemiological; Level IV.

Prediction of Long COVID Based on Severity of Initial COVID-19 Infection: Differences in predictive feature sets between hospitalized versus non-hospitalized index infections.

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.

Preparing for the next pandemic: Simulation-based deep reinforcement learning to discover and test multimodal control of systemic inflammation using repurposed immunomodulatory agents.

Background: Preparation to address the critical gap in a future pandemic between non-pharmacological measures and the deployment of new drugs/vaccines requires addressing two factors: 1) finding virus/pathogen-agnostic pathophysiological targets to mitigate disease severity and 2) finding a more rational approach to repurposing existing drugs. It is increasingly recognized that acute viral disease severity is heavily driven by the immune response to the infection ("cytokine storm" or "cytokine release syndrome"). There exist numerous clinically available biologics that suppress various pro-inflammatory cytokines/mediators, but it is extremely difficult to identify clinically effective treatment regimens with these agents. We propose that this is a complex control problem that resists standard methods of developing treatment regimens and accomplishing this goal requires the application of simulation-based, model-free deep reinforcement learning (DRL) in a fashion akin to training successful game-playing artificial intelligences (AIs). This proof-of-concept study determines if simulated sepsis (e.g. infection-driven cytokine storm) can be controlled in the absence of effective antimicrobial agents by targeting cytokines for which FDA-approved biologics currently exist. Methods: We use a previously validated agent-based model, the Innate Immune Response Agent-based Model (IIRABM), for control discovery using DRL. DRL training used a Deep Deterministic Policy Gradient (DDPG) approach with a clinically plausible control interval of 6 hours with manipulation of six cytokines for which there are existing drugs: Tumor Necrosis Factor (TNF), Interleukin-1 (IL-1), Interleukin-4 (IL-4), Interleukin-8 (IL-8), Interleukin-12 (IL-12) and Interferon-γ(IFNg). Results: DRL trained an AI policy that could improve outcomes from a baseline Recovered Rate of 61% to one with a Recovered Rate of 90% over ~21 days simulated time. This DRL policy was then tested on four different parameterizations not seen in training representing a range of host and microbe characteristics, demonstrating a range of improvement in Recovered Rate by +33% to +56. Discussion: The current proof-of-concept study demonstrates that significant disease severity mitigation can potentially be accomplished with existing anti-mediator drugs, but only through a multi-modal, adaptive treatment policy requiring implementation with an AI. While the actual clinical implementation of this approach is a projection for the future, the current goal of this work is to inspire the development of a research ecosystem that marries what is needed to improve the simulation models with the development of the sensing/assay technologies to collect the data needed to iteratively refine those models.

Drug Development Digital Twins for Drug Discovery, Testing and Repurposing: A Schema for Requirements and Development.

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).

Transcriptomic, Proteomic, and Morphologic Characterization of Healing in Volumetric Muscle Loss.

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.

Frequency and Predictors of Trauma Transfer Futility to a Rural Level I Trauma Center.

INTRODUCTION: Transfer of trauma patients whose injuries are deemed unsurvivable, often results in early death or transition to comfort care and could be considered misuse of health care resources. This is particularly true where tertiary care resources are limited. Identifying riskfactors for and predicting futile transfers could reduce this impact and help to optimize triage and management. METHODS: A retrospective study of interfacility trauma transfers to a single rural Level I rauma center from 2014 to 2019. Futility was defined as death, hospice, or declaration of comfort measures within 48 h of transfer without procedural or radiographic intervention at the accepting center. Multiple logistic regressions identified independent predictors of futile transfers. The predictive power of Mechanism,Glasgow coma scale, Age, and Arterial pressure (MGAP), an injury severity score based on Mechanism, Glasgow coma scale, Age, and systolic blood Pressure, were evaluated. RESULTS: Of the 3368 trauma transfers, 37 (1.1%) met criteria as futile. Futile transfers occurred among patients who were significantly older with falls as the most common mechanism. Age, Glasgow coma scale, systolic blood Pressure and Injury Severity Score were significant (P < 0.05) independent predictors of futile transfer. MGAP had a high predictive power area under the receiver operating characteristic (AUROC 0.864, 95% confidence interval 0.803-0.925) for futility. CONCLUSIONS: A small proportion (1.1%) of transfers to a rural Level I trauma center met criteria for futility. Predictive tools, such as MGAP scoring, can provide objective criteria for evaluation of transfer necessity and prompt care pathways that involve pre-transfer communications, telemedicine, and/or patient centered goals of care discussions. Such tools could be used in conjunction with a more granular assessment regarding potential operational barriers to reduce futile transfers and to enhance optimization of resource utilization in low-resource service areas.

Preparing for the next COVID: Deep Reinforcement Learning trained Artificial Intelligence discovery of multi-modal immunomodulatory control of systemic inflammation in the absence of effective anti-microbials.

Background: Despite 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. Hypothesis: Addressing 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). Methods: This 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. Results: DRL 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. Discussion: The 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.

Optical Biopsy Using a Neural Network to Predict Gene Expression From Photos of Wounds.

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.

Defining Risk and Risk Factors for Unplanned ICU Admission of Trauma Patients.

BACKGROUND: Unplanned ICU admissions (up-ICUad) are associated with poor outcomes. It is difficult to identify who is at risk for up-ICUad in trauma patients. This study aimed to identify injury patterns and comorbidities associated with up-ICUad and develop a predictive tool for who is at risk. METHODS: A retrospective study compared trauma patients admitted to the floor who experienced an up-ICUad to similar patients without an up-ICUad. Univariate analysis and multivariate logistic regression identified independent risk factors associated with up-ICUad. Based on those factors, a Risk Score (RS) was created and compared between the two groups. RESULTS: 2.15% of the 7206 patients experienced an up-ICUad. The up-ICUad group was older, experienced longer length of stay, and had higher mortality. Age, congestive heart failure, COPD, peptic ulcer disease, mild liver disease, CKD, and significant injuries to the thorax, spine, and lower extremities were independently associated with up-ICUad. A RS equation was created and was used for each patient. CONCLUSIONS: Trauma patients are at increased risk for up-ICUad based on specific factors. These factors can be used to calculate a RS to determine who is at greatest risk for an up-ICUad which may be helpful for preventing up-ICUad.

The Use of Artificial Neural Networks to Forecast the Behavior of Agent-Based Models of Pathophysiology: An Example Utilizing an Agent-Based Model of Sepsis.

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.

Nested active learning for efficient model contextualization and parameterization: pathway to generating simulated populations using multi-scale computational models.

There is increasing interest in the use of mechanism-based multi-scale computational models (such as agent-based models (ABMs)) to generate simulated clinical populations in order to discover and evaluate potential diagnostic and therapeutic modalities. 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. In this work, we utilize a nested active learning (AL) workflow to efficiently parameterize and contextualize an ABM of systemic inflammation used to examine sepsis. Contextual parameter space was examined using four parameters external to the model's rule set. 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 AL approach in which the clinically relevant (CR) 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 that uses AL to efficiently regress the volume and centroid location of the CR space given by a single internal parameterization. We have reduced the number of simulations required to efficiently map the CR parameter space of this model by approximately 99%. In addition, we have shown that more complex models with a larger number of variables may expect further improvements in efficiency.