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.

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.

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.

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.

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.

Wearables and Deep Learning Classify Fall Risk From Gait in Multiple Sclerosis.

Falls are a significant problem for persons with multiple sclerosis (PwMS). Yet fall prevention interventions are not often prescribed until after a fall has been reported to a healthcare provider. While still nascent, objective fall risk assessments could help in prescribing preventative interventions. To this end, retrospective fall status classification commonly serves as an intermediate step in developing prospective fall risk assessments. Previous research has identified measures of gait biomechanics that differ between PwMS who have fallen and those who have not, but these biomechanical indices have not yet been leveraged to detect PwMS who have fallen. Moreover, they require the use of laboratory-based measurement technologies, which prevent clinical deployment. Here we demonstrate that a bidirectional long short-term (BiLSTM) memory deep neural network was able to identify PwMS who have recently fallen with good performance (AUC of 0.88) based on accelerometer data recorded from two wearable sensors during a one-minute walking task. These results provide substantial improvements over machine learning models trained on spatiotemporal gait parameters (21% improvement in AUC), statistical features from the wearable sensor data (16%), and patient-reported (19%) and neurologist-administered (24%) measures in this sample. The success and simplicity (two wearable sensors, only one-minute of walking) of this approach indicates the promise of inexpensive wearable sensors for capturing fall risk in PwMS.

Metrics extracted from a single wearable sensor during sit-stand transitions relate to mobility impairment and fall risk in people with multiple sclerosis.

BACKGROUND: Approximately half of the 2.3 million people with multiple sclerosis (PwMS) will fall in any three-month period. Currently clinicians rely on self-report measures or simple functional assessments, administered at discrete time points, to assess fall risk. Wearable inertial sensors are a promising technology for increasing the sensitivity of clinical assessments to accurately predict fall risk, but current accelerometer-based approaches are limited. RESEARCH QUESTION: Will metrics derived from wearable accelerometers during a 30-second chair stand test (30CST) correlate with clinical measures of disease severity, balance confidence and fatigue in PwMS, and can these metrics be used to accurately discriminate fallers from non-fallers? METHODS: Thirty-eight PwMS (21 fallers) completed self-report outcome measures then performed the 30CST while triaxial acceleration data were collected from inertial sensors adhered to the thigh and chest. Accelerometer metrics were derived for the sit-to-stand and stand-to-sit transitions and relationships with clinical metrics were assessed. Finally, the metrics were used to develop a logistic regression model to classify fall status. RESULTS: Accelerometer-derived metrics were significantly associated with multiple clinical metrics that capture disease severity, balance confidence and fatigue. Performance of a logistic regression for classifying fall status was enhanced by including accelerometer features (accuracy 74%, AUC 0.78) compared to the standard of care (accuracy 68%, AUC 0.74) or patient reported outcomes (accuracy 71%, AUC 0.75). SIGNIFICANCE: Accelerometer derived metrics were associated with clinically relevant measures of disease severity, fatigue and balance confidence during a balance challenging task. Inertial sensors could feasibly be utilized to enhance the accuracy of functional assessments to identify fall risk in PwMS. Simplicity of these accelerometer-based metrics could facilitate deployment for community-based monitoring.