System and method for predicting pulmonary complications following rib fractures

Abstract

Described herein are methods, systems, and computational environments for predicting clinical outcomes based on a regression model trained on data of patients having a rib fracture. Also described are methods, systems, and computational environments for generating the regression model for predicting clinical outcomes. One aspect of the present disclosure provides a method of determining a subject's risk of adverse response after a rib fracture, comprising, consisting of, or consisting essentially of applying a predictive algorithm to serum analysis data including one or more biomarkers.

Description

Attorney Docket No.: H193-0021PCT / HJF 690-24SYSTEM AND METHOD FOR PREDICTING PULMONARY COMPLICATIONS FOLLOWING RIB FRACTURESSTATEMENT REGARDING FEDERALLY SPONSORED RESEARCH OR DEVELOPMENT

[0001] This invention was made with government support under HU0001-23-2-0037 and HU0001-2- 12-0029 awarded by the Uniformed Services University of the Health Sciences. The government has certain rights in the invention.CROSS REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of U.S. Provisional Patent Application 63 / 686.336, filed on August 23, 2024, which is hereby incorporated by reference in its entirety.FIELD OF THE DISCLOSURE

[0003] Described herein are methods, systems, and computational environments for predicting clinical outcomes based on a regression model trained on data of patients having a rib fracture. Also described are methods, systems, and computational environments for generating the regression model for predicting clinical outcomes.BACKGROUND

[0004] Rib fractures are rising in the United States, with over 500,000 cases annually, and can lead to significant morbidity and mortality. Acute lung injury (ALI) occurs early following injury and is due to direct lung parenchymal damage and immune system dysregulation. Pneumonia is a later complication of the initial ALI and evolves over time during to persistence of immune dysregulation and hypoventilation due to pain. These complications are influenced by the dynamic interaction between the affected lung, the immune responses, and the rib fractures. Early classification of injury severity can improve patient outcomes.SUMMARY OF THE DISCLOSURE

[0005] This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identity' all key features or essential features of the claimed subject matter, nor is it intended to be used alone as an aid in determining the scope of the claimed subject matter.

[0006] One aspect of the present disclosure provides a method of determining a subject’s risk of adverse response after a rib fracture, comprising, consisting of, or consisting essentially of applying a predictive algorithm to serum analysis data including one or more biomarkers.Attorney Docket No.: H193-0021PCT / HJF 690-24

[0007] In some embodiments, the adverse response includes acute lung injury, acute kidney injury , and / or respiratory distress.

[0008] In some embodiments, the one or more biomarkers are selected from: eotaxin-3, IL-6, TNF- a. FGF basic, IFN-y. G-CSF. IL-8, IP-10 (CXCL10), MIG (CXCL 9), MCP-4, IL-2R.O, and IL-16.

[0009] Another aspect of the present disclosure provides a computer-based algorithm for determining the severity of a patient’s thoracic injury.

[0010] Another aspect of the present disclosure provides a computer-based system configured to determine and display the severity of a patient' s thoracic injury, comprising, consisting of, or consisting essentially of a predictive algorithm.

[0011] Another aspect of the present disclosure provides all that is described and illustrated herein.BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The detailed description is described with reference to tire accompanying figures. The figures are merely exemplary to illustrate certain features that may be used singularly or in combination with other features, and the present disclosure should not be limited to the embodiments shown.

[0013] FIGs. 1 A and IB illustrate associations of immune responses with complications.

[0014] FIGs. 2A and 2B illustrate associations of rib fractures (RFx) with complications may suggest energy transfer patterns.

[0015] FIGs. 3A-3D illustrate the dynamic phase change of immune responses.

[0016] FIGs. 4A and 4B illustrate how the dynamic interplay between RFx and immune responses can significantly impact clinical outcomes.

[0017] FIG. 5 A illustrates the identification of 34 cytokines after data quality check from 431 serum samples.

[0018] FIGs. 5B and 5C illustrate 12 biomarkers for predicting multiple complications, such as acute kidney injury (AKI), acute lung injury (ALI), and pneumonia.

[0019] FIGs. 6A-6G illustrate that clusters 1 and 2 of FIG. 5A differ in rib fractures and complications.

[0020] FIG. 7 illustrates prediction modeling for complications.

[0021] FIGs. 8A-8C illustrate predicting two binary outcomes AKI and ALL

[0022] FIGs. 9 A and 9B illustrate assessment of the F13 models for pneumonia prediction.

[0023] FIGs. 10A and 10B illustrate assessment for the final ALI models.

[0024] FIGs. 11 A and 1 IB illustrate assessment for the final AKI models.DETAILED DESCRIPTION

[0025] The following detailed description is presented to enable any person skilled in the art to make and use the subject of the application. For purposes of explanation, specific nomenclature is setAttorney Docket No.: H193-0021PCT / HJF 690-24 forth to provide a thorough understanding of the present disclosure. However, it will be apparent to one skilled in the art that these specific details are not required to practice the subject of the application. Descriptions of specific applications are provided only as representative examples. The present application is not intended to be limited to the embodiments shown but is to be accorded the widest possible scope consistent with the principles and features disclosed herein.

[0026] Technical and scientific terms used herein have the meanings commonly understood by one of ordinary skill in the art to which the present disclosure pertains, unless otherwise defined.

[0027] As used herein, the singular forms “a.” ‘‘an,” and “the” designate both the singular and the plural, unless expressly stated to designate the singular only.

[0028] As used herein the terms “marker” and “biomarkers” are used interchangeably to refer to a measurable substance from a biological sample. For example, these can comprise one or more protein data markers, one or more nucleic acid data markers, one or more metabolite data markers, or a combination thereof.

[0029] As used herein, the term “serum” refers to fluid that remains from blood plasma after fibrinogen, prothrombin, and other clotting factors have been removed or fluid from blood plasma without fibrinogen, prothrombin, and other clotting factors.

[0030] As used herein, the tenn “serum biomarker” refers to a biomarker derived, extracted, or otherwise obtained from the serum.

[0031] Examples of serum biomarkers may be, but are not limited to. basic fibroblast growth (FGF basic), epidermal growth factor (EGF), eotaxin-1 (CCL-11). eotaxin-3 (CCL-26). fms related receptor tyrosine kinase-1 (FLT-1), granulocyte-colony stimulating factor (G-CSF), granulocyte-monocyte colony stimulating factor (GMCSF), hepatocyte growth factor (HGF), interferon alpha-2A (IFNa2A). interferon gamma (IFN-y), interleukin- 10 (IL-10), interleukin- 12 / interleukin-23p40 (IL-12 / IL-23p40), interleukin- 15 (IL-15), interleukin- 16 (IL-16), interleukin- 17alpha (IL-17a), interleukin-1 receptor antagonist (IL-IRA), interleukin-22 (1-22), interleukin-2 receptor subunit alpha (IL-2Ra), interleukin- 3 (IL-3), interleukin-5 (IL-5), interleukin-6 (IL-6), interleukin-7 (IL-7), interleukin-8 (IL-8), interleukin-9 (IL-9), interferon gamma-inducing protein-10 (IP-10), monocyte chemoattractant protein- 1 (MCP-1), monocyte chemoattractant protein-4 (MCP-4), macrophage-derived chemokine (MDC), monokine induced by gamma interferon (MIG, CXCL9), macrophage inflammatory protein- lb (MIP- 1|3), placental growth factor (PLGF), thymus and activation regulated chemokine (TARC), angiopoicntin-1 receptor (TIE-2), tumor necrosis factor alpha (TNF-a), vascular endothelial growth factor (VEGF, VEGFA), vascular endothelial growth factor C (VEGFC), and / or vascular endothelial growth factor D (VEGFD).

[0032] In embodiments, the one or more serum biomarkers are selected from: eotaxin-3, IL-6, TNF-a, FGF basic, IFN-y, G-CSF, IL-8, IP-10 (CXCL10), MIG (CXCL 9), MCP-4, IL-2Ra, and IL- 16.Attorney Docket No.: H193-0021PCT / HJF 690-24

[0033] As used herein, the term “injury severity score” (ISS) refers to a medical score for assessing trauma severity. The ISS may correlate with mortality, morbidity, and hospitalization time after trauma.

[0034] “About” is used to provide flexibility to a numerical range endpoint by providing that a given value may be “slightly above” or “slightly below” the endpoint without affecting the desired result.

[0035] The use herein of the terms “including,” “comprising,” or “having,” and variations thereof, is meant to encompass the elements listed thereafter and equivalents thereof as well as additional elements. As used herein, “and / or” refers to and encompasses any and all possible combinations of one or more of the associated listed items, as well as the lack of combinations where interpreted in the alternative (“or”).

[0036] As used herein, the transitional phrase “consisting essentially of’ (and grammatical variants) is to be interpreted as encompassing the recited materials or steps “and those that do not materially affect the basic and novel characteristic(s)” of the claimed subject matter. As an example, materials or steps that do not affect the claimed subject matter include those materials or steps that do not affect the method of determining a subject’s risk of adverse response after a rib fracture or the method of predicting the probability of developing AKI, ALI, or pneumonia after a rib fracture. Thus, die term “consisting essentially of’ as used herein should not be interpreted as equivalent to “comprising.”

[0037] Moreover, the present disclosure also contemplates diat in some embodiments, any feature or combination of features set forth herein can be excluded or omitted. To illustrate, if the specification states that a complex comprises components A, B and C, it is specifically intended that any of A, B or C, or a combination thereof, can be omitted and disclaimed singularly or in any combination.

[0038] Recitation of ranges of values herein are merely intended to sen e as a shorthand method of referring individually to each separate value falling within the range, unless otherwise indicated herein, and each separate value is incorporated into the specification as if it were individually recited herein. For example, if a concentration range is stated as 1% to 50%, it is intended that values such as 2% to 40%, 10% to 30%. or 1% to 3%, etc., are expressly enumerated in this specification. These are only examples of what is specifically intended, and all possible combinations of numerical values between and including the lowest value and the highest value enumerated are to be considered to be expressly stated in this disclosure.

[0039] As used herein, the term ‘subject” and “patient” are used interchangeably herein and refer to both human and nonliuman animals. The term “nonhuman animals” of the disclosure includes all vertebrates, e.g. , mammals and non-mammals, such as nonliuman primates, sheep, dog, cat, horse, cow, chickens, amphibians, reptiles, and the like. In some embodiments, the subject comprises a human who is undergoing a risk assessment using a system and / or method as prescribed herein. As an example, the subject is a human having a rib fracture and is in need of assessment by the methods described herein.Attorney Docket No.: H193-0021PCT / HJF 690-24

[0040] Unless otherwise defined, all technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

[0041] One aspect of the present disclosure provides a prognostic platform, also referred to as a Clinical Decision Support Tool (CDST), for accurately assessing the severity of thoracic trauma injuries. The system and method described herein are particularly useful for fractures related to ribs 1, 2. 5, and 10. along with the clinical complications such as organ injury, including AK1 and / or AL1, with or without respiratory distress (RD) induced by pathology such as pneumonia. The disclosed platform uses machine learning techniques and data from the Meso Scale Discovery (MSD) serum biomarker dataset to provide a precise classification of patients into high- and low-severity classes, which can be denoted as H and L, respectively.

[0042] The platform is founded on the analysis of 431 serum biomarker samples, which were grouped into two major distinct clusters based on their clinical characteristics. Further details are described in the Examples herein below. Cluster 1 comprises patients with lower incidence of specified rib fractures and clinical complications (such as organ injury and / or RD), while Cluster 2 represents individuals with higher incidence of the rib fractures and clinical complications. These clusters exhibit significant differences in variables including age, ISS, and total hospital days, with higher median values for cluster 2 compared to cluster 1. Utilizing customized algorithms for feature selection, twelve biomarkers have been identified from the serum samples. These are eotaxin 3, IL-6, TNF-a, FGF basic, IFN-y, G-CSF, IL-8, IP-10 (CXCL10), MIG (CXCL 9), MCP-4, IL-2Ra, and IL-16. It is noted that these biomarkers consist of five proinflammatory (eotaxin-3, IL-6, TNF-a. FGF basic, IFN-y) and seven anti-inflammatory (G-CSF, IL-8. IP-10, MIG, MCP-4, IL-2Ra, IL-16) cytokines / chemokines, which are pivotal in understanding the immune response to thoracic trauma. It is further noted that substitutions of one or more of these biomarkers is within the scope of the disclosure.

[0043] Building upon these findings, the present disclosure trained six predictive models using the identified twelve biomarkers in the initial or earliest patient assessment data (I-data), including random forest (F12-RF) and least absolute shrinkage and selection operator (F12-LASSO). Subsequently, these models were evaluated using the follow-up data (F-data) for prediction of the complications after rib fractures. Results indicated that the top models have acceptable discrimination for the complications (e.g., AKI, ALL and pneumonia), with area under the curve (AUC) of 0.784, 0.793, and 0.832, respectively. Post-training corrections were applied to enhance model performance. Platt-scaling was implemented to recalibrate the top models; that is. F12-RF models for organ injury (respectively ALI and AKI), and F12-LASSO model for RD (pathological pneumonia). Following this step, these models demonstrated adequate calibration while maintaining high discrimination The recalibrated F12-RF models exhibited an intercept of 0.001 and a slope of 1, with goodness-of-fit test p-values of 0.86 and 0.53, indicating their reliability in AKI and ALI prediction after rib fractures. Similarly , the recalibratedAttorney Docket No.: H193-0021PCT / HJF 690-24F12-LASS0 model displayed a favorable intercept of 0 and a slope of 1, reaffirming its reliability in pneumonia prediction.

[0044] Another aspect of the present disclosure provides a method of determining a risk of adverse complications (e.g., organ injury and / or RD) after a rib fracture. The method comprises applying a predictive algorithm to serum analysis data including biomarker levels assayed for at least one of the above-mentioned biomarkers; classifying a patient’s severity; and displaying a severity level to a user.

[0045] Another aspect of the present disclosure provides a system configured to rate the severity of a patient’s thoracic injury. The system comprises a computing platform, algorithm, and a display, where the algorithm is configured to determine a severity level of a patient’s thoracic injury.

[0046] The systems and methods described herein advantageously allow early identification of patients who are at risk of acute responses to lung injury. The disclosed CDST not only stratifies the risk of patients with rib fractures for medical therapy but also identifies those who would benefit from surgical intervention, specifically surgical stabilization of rib fractures. By incorporating individual patient data and biomarker levels of serum biomarker profiles, the disclosed platform facilitates personalized treatment strategies, ultimately improving patient outcomes and reducing unnecessary interventions.

[0047] Another aspect of the present disclosure provides all that is described and illustrated herein.

[0048] The systems described herein can be implemented in hardware, software, firmware, or combinations of hardware, software and / or firmware. In some examples, the systems described in this specification may be implemented using a non-transitory computer readable medium storing computer executable instructions that when executed by one or more processors of a computer cause the computer to perform operations. Computer readable media suitable for implementing the systems described in this specification include non-transitory computer-readable media, such as disk mcmon- devices, chip memory devices, programmable logic devices, random access memory (RAM), read only memory (ROM), optical read / write memory, cache memory, magnetic read / write mcmon . flash memory, and application-specific integrated circuits. In addition, a computer readable medium that implements a system described in this specification may be located on a single device or computing platform or may be distributed across multiple devices or computing platforms.

[0049] One skilled in the art will readily appreciate that the present disclosure is well adapted to carry out the objects and obtain the ends and advantages mentioned, as well as those inherent therein. The disclosures described herein are presently representative of preferred embodiments, are exemplary, and are not intended as limitations on the scope of the present disclosure. Changes therein and other uses will occur to those skilled in the art which are encompassed within the spirit of the present disclosure as defined by the scope of the claims.

[0050] No admission is made that any reference, including any non-patent or patent document cited in this specification, constitutes prior art. It will be understood that, unless otherwise stated,Attorney Docket No.: H193-0021PCT / HJF 690-24 reference to any document herein does not constitute an admission that any of these documents forms part of the common general knowledge in the art in the United States or in any other country. Any discussion of the references states what their authors assert, and the applicant reserves the right to challenge the accuracy and pertinence of any of the documents cited herein. All references cited herein are fully incorporated by reference, unless explicitly indicated otherwise. The present disclosure shall control in the event there are any disparities between any definitions and / or description found in the cited references.

[0051] The following Examples are provided by way of illustration and not by way of limitation.

[0052] Example 1

[0053] The data were collected from military and civilian patients with rib fractures. After quality checks and removal of variables with more than 30% missing values, 431 samples from 142 patients were used. The data includes 92 variables, such as rib fractures in ribs 1 to 12, various clinical complications (or outcomes) like organ injury, such as AKI. and ALI; respiratory distress pathology, such as pneumonia; and total hospital days (THD), demographics, and 34 serum cytokines measured on the Meso Scale Discovery (MSD) platform. For predictive modeling, the data was divided into I- data for model training and F-data for assessment. The I-data is the initial (within 72 hours after injury) or earliest assessment data available; the F-data is the follow-up data other than the I-data. The models were evaluated using multiple statistical metrics, such as discrimination using the area under the curve (AUC), sensitivity, and specificity, calibration intercept and slope, and the percentage of variance explained by a model (R2).

[0054] It was identified that the relationship between rib fractures and immune responses is bidirectional; that is, rib fractures can induce immune responses, and immune responses can impact the severity of rib fractures. Many cytokines, such as IL2ra, are common predictors for multiple post-rib fracture complications, such as ALI and pneumonia. In addition, cytokines are strongly associated with rib fractures in impacting the incidence of complications, contributing to their strong dynamic association. As time progresses post-rib fracture, the association of anti-inflammatory biomarkers with ALI and pneumonia strengthens compared to the association of proinflammatory biomarkers with ALI and pneumonia. Therefore, the dynamic interplay of rib fractures and immune responses significantly impacts the complications. This forms the basis for the next step to select cytokine biomarkers and develop prediction models for prediction of the complications following rib fractures.

[0055] The current rib fracture cohort had limited data from only 142 patients. Among the patients, the incidence rates were low for complications, such as 4.2% for pneumonia. 22% for AKI. and 28% for ALL Instead of feature selection for each complication, cluster analysis was conducted using the MSD cytokine data based on the 431 serum samples. Two distinct clusters of cytokines that were characterized by pro- and anti-inflammatory biomarkers, respectively, were identified. By contrasting these two clusters of cytokines, three clusters of samples were classified. The two major sample clustersAttorney Docket No.: H193-0021PCT / HJF 690-24 were focused on, as the third cluster had only two samples. Next, the sample clusters were associated with rib fractures and complications. It was found that cluster 2 has significantly higher percentages of fractures in ribs 1, 2, 5, and 10, respectively, and high incidence of multiple complications (such as multiple organ injuries, including AKI and ALI, and respiratory distress, caused by pathology such as pneumonia), compared to cluster 1. In addition, corresponding patients in cluster 2 were significantly older and had significantly higher ISS and longer hospital stay compared to the patients in cluster 1. Finally, the two sample clusters were treated as calculated outcomes for feature selection, leading to the successful identification of 12 biomarkers, using a combination of algorithms (including bootstrap resampling, random forest selection, and recursive feature elimination).

[0056] The 12 biomarkers were found to have acceptable predictive ability for multiple complications, such as AKI, ALI, and pneumonia, with AUC of 0.784. 0.793, and 0.832 from the best models, respectively. The models were then refined to include additional predictors. The number of displaced fractures on ribs 1-3 (Ribl-3) was identified as an additional predictor for ALI and pneumonia, but not for AKI. Conversely, age. gender, and ISS are additional predictors for AKI, but not for ALI and pneumonia. The final models by including the corresponding additional predictor(s) presented improved discrimination. For example, the pneumonia model (F13-LASSO) has AUC of 0.888. compared to the original F12-LASSO model with AUC of 0.832. These final models with posttraining correction had adequate calibration, while maintaining high discrimination, indicating significant clinical utility. Twelve cytokines were selected as model inputs for predictive modeling using machine learning, which include five proinflammatory and seven anti-inflammatory biomarkers. The results indicated that a random forest model (AUC = 0.904, sensitivity = 0.923, specificity = 0.819) is optimal for predicting the presence or absence of respiratory’ distress caused by pathology such as pneumonia. After a post-training step for model correction, the model maintained its accuracy while achieving adequate calibration (intercept = 0.001, slope = 1). A regression model was also developed for predicting continuous THD (R2= 0.55).

[0057] A regression model can be, for example, a linear model, wherein variables are modeled as being a linear function of time, based on an expectation that the values of the variables will fall along a Gaussian distribution (a “Gaussian prior’’). A regression model can alternatively be, for example, a nonlinear model such as a logarithmic model, an exponential model and the like, without limitation thereto. Regression models can be selected based on a prior of variables of the target time series, which shall not be limited to a Gaussian prior and can include, for example, binomial distributions. Bernoulli distributions, Laplacian distributions and the like, and thus a regression model can be, for example, a generalized linear model based on a given prior.

[0058] A cost function is optimized for an input of the regression model, wherein the cost function can include a regularization term. For example, regularization terms can be a Lasso (ft) re gidarization term, denoted by the operator || A Lasso regularization term generally includes a regularizationAttorney Docket No.: H193-0021PCT / HJF 690-24 parameter multiplied to control magnitude of the regularization term, which can be a hyperparameter / . set arbitrarily, or can be set according to results of experimentation based on desired strength of the effect of regularization.

[0059] According to example embodiments of the present disclosure, Lasso regularization terms generally yield sparse output wherein most coefficients are zero, reflecting a model which adheres to a Laplacian prior; based on a Laplacian distribution. Lasso regularization terms tend to push small values to zero. Due to the sparse property of Lasso regularization output, the regularization effect of each of the regularization terms upon the difference penalty is also sparse. This has been observed to achieve better results than non-sparse regularization terms.

[0060] According to example embodiments of the present disclosure, optimizing a cost function, without limitation as to the loss function and without limitation as to regularization parameters, generally describes executing a regularization filter on an input of the regression model.

[0061] A regression model can alternatively be a random forest model, wherein variables are modeled across an ensemble of decision trees which are each trained to predict a same input differently. An output of the ensemble is an average taken across each of tire decision trees of the ensemble.

[0062] Thus, according to example embodiments of the present disclosure, one or more processors of a computing system can perform steps to train a prediction model and predict a probability of developing at least one organ injury and / or at least one respiratory distress pathology.

[0063] A regression model can be stored on storage of any computing system as described herein, having one or more physical or virtual processor(s) capable of executing the regression model to compute tasks for particular functions.

[0064] Sample data can be any labeled dataset indicating whether data points therein are positive or negative for a particular result, such as developing clinical outcomes as described herein. For example, the dataset can be labeled to indicate that a particular data point is positive or negative for a particular result. Alternatively, the dataset can be labeled to indicate classes, clusters, fittings, or other characteristics of data points, such that the labels indicate that a particular data point does or does not belong to a particular class, cluster, fitting, and the like.

[0065] A loss function, or more generally an objective function, is any mathematical function having an output which can be optimized during the training of a regression model.

[0066] Training of the regression model can at least train on a first loss function to learn parameters of a linear or nonlinear model. Parameters are generally matrices which weigh inputs of a regression model by matrix arithmetic, and a regression model can include one or more parameters corresponding to each input of the regression model.

[0067] A parameter set of a regression model can be initialized having particular matrix values, which can be further updated during training epochs. A regression model can be trained on a loss function for multiple iterations, taking reference data of a set batch size per iteration. The regressionAttorney Docket No.: H193-0021PCT / HJF 690-24 model can be trained for a set number of epochs, an epoch referring to a period during which an entire dataset is computed by the regression model once; the parameter set is then updated based on computations performed during this period.

[0068] Twelve biomarkers were identified as model inputs through systematic studies on the relationship between rib fractures, immune responses, and clinical complications. These biomarkers can accurately predict pneumonia and THD following rib fractures. Identifying and modulating these biomarkers could provide a more precise approach to preventing or treating complications in both military and civilian settings.

[0069] Thus, a regression model according to example embodiments of the present disclosure can include a linear model, nonlinear model, or ensemble model trained on a dataset indicating incidence of organ injury and respiratory distress pathology, and other clinical outcomes among patients having a rib fracture.

[0070] Such a regression model can be executed by one or more processors of a computing system to receive input including biomarker levels assayed from serum biomarker samples of a subject having a rib fracture. According to example embodiments of the present disclosure, the biomarker levels assayed from serum biomarker samples include biomarker levels of at least one proinflammatory biomarker and biomarker levels of at least one anti-inflammatory biomarker. Examples of proinflammatory biomarkers include FGF basic. IL-6, IFN-y, TNF-a, and eotaxin-3. Examples of antiinflammatory biomarkers include G-CSF, IL-8, IP-10, MIG, MCP-4, IL-2Ra, and IL-16.

[0071] Biomarker levels assayed from serum biomarker samples can include biomarker levels of any or all of eotaxin-3, IL-6. TNF-a. FGF basic, IFN-y. G-CSF. IL-8, IP-10 (CXCL10), MIG (CXCL 9), MCP-4, IL-2Ra, and IL- 16.

[0072] The regression model can include respective sets of parameters corresponding to any or all of these biomarker levels assayed from serum biomarker samples, such that one or more parameters assign weight to a biomarker level which is input into the regression model.

[0073] The regression model can further include respective sets of parameters corresponding to other sets of inputs, such that one or more parameters assign weight to these respective inputs, including an age, a gender, and an ISS of a subject having a fracture, as well as a count of rib fractures of a subject having a rib fracture, which can further include a count of rib fractures at ribs 1 and 2; a count of rib fractures at ribs 3 to 6; and a count of rib fractures at ribs 7 to 10.

[0074] Moreover, inputs can include multiple sets of the same input for different times, and parameters of the regression model can weigh inputs differently depending on time. For example, parameters of the regression model can assign greater weight to biomarker levels assayed for proinflammatory markers within 72 hours of the subject suffering a rib fracture than: biomarker levels assayed for the same proinflammatory markers 72 hours or later after the subject suffers the rib fracture, and biomarker levels assayed for anti-inflammatory markers within 72 hours of the subject sufferingAttorney Docket No.: H193-0021PCT / HJF 690-24 the rib fracture. Moreover, parameters of the regression model can assign greater weight to biomarker levels assayed for anti-inflammatory markers 72 hours or later after the subject suffers a rib fracture than: biomarker levels assayed for the same anti-inflammatory markers within 72 hours of the subject suffering the rib fracture, and biomarker levels assayed for proinflammatory markers 72 hours or later after the subject suffers the rib fracture.

[0075] Example 2

[0076] Rib fractures (RFx) are associated with multiple complications (e.g. sepsis and pneumonia) that contribute significantly to morbidity and mortality. This Example indicates that such complications result from a dynamic interplay between RFx and the immune system. This system was named the “RFx-immune responses-complication” triad (or RIC). Specifically, three immune response patterns were identified in this Example based on RFx locations. Insights into the RIC system offered guidance to systematically identify biomarkers for prediction of the complications.

[0077] The rib fracture cohort included 142 patients with RFx. Consenting adults with one or more rib fractures confirmed by chest X-ray or CT scan were included. Pregnant women and patients who were at risk with multiple blood draws were excluded. Initial data was collected with 72 hours. Seventyseven clinical measurements including RFx by location, complications and demographics were identified. Four hundred and thirty one serum samples were assay ed with 23 cytokines and chemokines on the Meso Scale Discovery (MSD) platform. Patient characteristics are shown in Table 1 below.Attorney Docket No.: H193-0021PCT / HJF 690-24

[0078] To explore the dynamic interplay between RFx and immune responses, each patient’s data was split into two non-overlapping subsets: initial and follow-up assessment data (I- and F-data. respectively). The RIC was investigated using path modeling. Immune responses were measured by the 1st principal component (PC) of the cytokines and chemokines.

[0079] FIGs. 1 A and IB illustrate associations of immune responses with complications. FIG. 1 A illustrates unadjusted correlation, while FIG. IB illustrates partial correlation with adjustment for RFx by location, age, gender, and ISS. Red color indicates stronger association than green.

[0080] FIGs. 2A and 2B illustrate associations of RFx with complications may suggest energy’ transfer patterns. FIG. 2A illustrates an unadjusted correlation, and FIG. 2B illustrates a partial correlation with adjustment for immune responses, age, gender, and ISS. Green and red colors indicate positive and negative associations, respectively.

[0081] FIGs. 3A-3D illustrate the dynamic phase change of immune responses. Two clusters of cytokines and chemokines were previously identified in the RFx cohort, of which major proteins in cluster 1 and 2 are associated with proinflammation (3A) and anti-inflammation (3B), respectively. Comparing the I and F-data (3C and 3D) indicated dynamic phase change of immune responses. The X-axis in FIG. 3C, from left to right, is: IL-2. IL-9, IL-22. IL-17a. TNF-a. IL-13, IFN-g, IL-15. IL-7, IL-2Ra. HGF. TIE-2, IL-IRA, MCP-1, IL-6, MIG, VEGFD, MDC. eotaxin-3. FGF basic, PLGF. MIP- la, IL-8, IL-6. GCSF, IL-3, VEGF. IL-12 / lL-23p40. MCP-4. M1P-1 , FLT-1. TARC, VEGFC. and 1P- 10. The X-axis in FIG. 3D. from left to right, is: IL-1, IL-9, IL-13, IL-5, IFN-g. IL-17a, TNF-a, IL-22. IL-15, MIP-la, IL-8, FGF basic, eotaxin-3, IL-7, PLGF, IL-IRA, MDC, VEGFD, HGF. IL-2Ra, TIE- 2, GCSF, IL-3. IL-12 / IL-23p40. FLT-1. MCP-4. MIP-1 [3, TARC, VEGF. VEGFC, MCP1, IL- 16, IP- 10, and MIG.

[0082] FIGs. 4A and 4B illustrate how the dynamic interplay between RFx and immune responses can significantly impact clinical outcomes. As shown in FIG. 4A, the association of RFx with pneumonia becomes less strong as time goes on after RFx, when anti-inflammatory biomarkers are dominant over proinflammatory biomarkers. As shown in FIG. 4B, the association of anti-inflammatory biomarkers with pneumonia becomes much stronger as time proceeds after RFx, compared to the proinflammatory' biomarker-pneumonia association.

[0083] Biomarker levels of 12 biomarkers and cofactors were input into a regression model to predict outcomes, and “F12’‘ models as described herein include these 12 biomarker levels as inputs. FIG. 5 A illustrates the identification of 34 cytokines after data quality check from 431 serum samples.Attorney Docket No.: H193-0021PCT / HJF 690-24As shown in FIG. 5 A, two major sample clusters were identified (indicated by “1” and “2”). The 3rd cluster (indicated by “3”) contains only 2 samples. Based on the RIC, F12 (plus other variables) were identified that can accurately predict multiple complications, such as AKI, ALI, and pneumonia (FIGs. 5B and 5C). FIGs. 6A-6G illustrate that the tw o clusters differ in rib fractures and complications.

[0084] Table 2 below summarizes regression model metrics associated with various complications, such as AKI, ALI, and pneumonia. The F13 model includes the inputs of the F12 model, in addition to the total number of fractures in rib 1-3 (RBF1-3). The F15 model includes the inputs of the F12 model, in addition to age, gender, and ISS.

[0085] FIGs. 7 and 8A-8C demonstrate prediction modeling for complications, and Table 3 below summarizes statistical analysis measures corresponding to the data of FIG. 7. As shown in FIGs. 8A- 8C, two binary outcomes were predicted: AKI and ALI.

[0086] FIGs. 9A and 9B illustrate assessment of the F13 models for pneumonia prediction. Table4 below summarizes regression model metrics corresponding to the data of FIGs. 9A and 9B.Attorney Docket No.: H193-0021PCT / HJF 690-24

[0087] FIGs. 10A and 10B illustrate assessment for the final ALI models. Table 5 below summarizes regression model metrics corresponding to the data of FIGs. 10A and 10B.

[0088] FIGs. 11A and 11B illustrate assessment for the final AKI models. Table 6 below summarizes regression model metrics corresponding to the data of FIGs. 11 A and 1 IB.

[0089] The disclosed findings revealed that RFx. immune responses (1ME). and clinical complications form an interconnected system (the RIC triad). This system is governed by trauma- induced immune responses, energy transfer patterns, and their temporal evolution. The dynamic interplay between RFx and IME significantly impacts the development and timing of complications, such as ALI, AKI, and pneumonia, which forms the basis for selecting cytokine biomarkers and developing prediction models. The classification of rib fracture sites into three distinct groups, based on their associations with complications, indicates that the location and impact energy of fractures play a key role in shaping immune responses and clinical trajectories. These grouped patterns appear to reflect underlying differences in energy transfer and immune activation. Leveraging the serum MSD data, 12 biomarkers capable of predicting pneumonia and THD with acceptable accuracy were identified. Interestingly, feature selection for individual complications revealed that RBF1-3 is a crucial predictor for ALI and pneumonia, but not for AKI. Conversely, variables such as age, gender, and ISS are significant predictors for AKI, but not for ALI. Regarding pneumonia, the F13-LASSO model achieves highest discrimination (AUC = 0.9) and adequate calibration. Modulating these biomarkers provides a more promising approach to preventing or treating complications in both military and civilian healthcare settings.Attorney Docket No.: H193-0021PCT / HJF 690-24

[0090] While one or more examples of the techniques described herein have been described, various alterations, additions, permutations, and equivalents thereof are included within the scope of the techniques described herein.

[0091] In the description of examples, reference is made to the accompanying drawings that fonn a part hereof, which show by way of illustration specific examples of the claimed subject matter. It is to be understood that other examples may be used and that changes or alterations, such as structural changes, may be made. Such examples, changes or alterations are not necessarily departures from the scope with respect to the intended claimed subject matter. While the steps herein may be presented in a certain order, in some cases the ordering may be changed so that certain inputs are provided at different times or in a different order without changing the function of the systems and methods described. The disclosed procedures could also be executed in different orders. Additionally, various computations that are herein need not be performed in the order disclosed, and other examples using alternative orderings of the computations could be readily implemented. In addition to being reordered, the computations could also be decomposed into sub-computations with the same results.

[0092] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described. Rather, die specific features and acts are disclosed as example forms of implementing the claims.

[0093] The components described herein represent instructions that may be stored in any type of computer-readable medium (also referred to as a computer-readable storage medium or computer- readable storage medium) and may be implemented in software and / or hardware. All of the methods and processes described above may be embodied in, and fully automated via, software code modules and / or computer-executable instructions executed by one or more computers or processors, hardware, or some combination thereof. Some or all of the methods may alternatively be embodied in specialized computer hardware. A computer-readable medium may be. for example, but not limited to. an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. In embodiments, the memories 112. 128, and 312 of FIGS. 1 and 3 respectively may be computer-readable mediums.Attorney Docket No.: H193-0021PCT / HJF 690-24

[0094] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing. Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object-oriented programming language such as Java, Smalltalk, C++, or the like, and conventional procedural programming languages, such as the “C” programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer, and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0095] Conditional language such as, among others, “may,” “could,” “may” or “might,” unless specifically stated otherwise, are understood within the context to present that certain examples include, while other examples do not include, certain features, elements and / or steps. Thus, such conditional language is not generally intended to imply that certain features, elements, and / or steps are in any way required for one or more examples or that one or more examples necessarily include logic for deciding, with or without user input or prompting, whether certain features, elements and / or steps are included or are to be performed in any particular example.

[0096] Conjunctive language such as the phrase “at least one of X, Y or Z,” unless specifically stated otherwise, is to be understood to present that an item, term, etc. may be either X, Y, or Z, or any combination thereof, including multiples of each element. Unless explicitly described as singular, “a” means singular and plural.

[0097] Any routine descriptions, elements, or blocks in the flow diagrams described herein and / or depicted in the attached figures should be understood as potentially representing modules, segments, or portions of code that include one or more computer-executable instructions for implementing specific logical functions or elements in the routine. Alternate implementations are included within the scope of the examples described herein in which elements or functions may be deleted, or executed out of order from that shown or discussed, including substantially synchronously, in reverse order, with additional operations, or omitting operations, depending on the functionality involved as would be understood by those skilled in the art.

[0098] Aspects of the present disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer programAttorney Docket No.: H193-0021PCT / HJF 690-24 instructions may be provided to a processor of a general-purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0099] These computer program instructions may also be stored in a computer readable medium that can direct a computer, other programmable data processing apparatus, or other devices to function in a particular manner, such that the instructions stored in the computer readable medium produce an article of manufacture including instructions which implement die function / act specified in the flowchart and / or block diagram block or blocks. The computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus, or other devices to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0100] The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustration, and combinations of blocks in the block diagrams and / or flowchart illustration, can be implemented by special purpose hardware-based systems that perfonn the specified functions or acts, or combinations of special purpose hardware and computer instructions.

[0101] Although the figures show a specific order of method steps, the order of the steps may differ from what is depicted. Also, two or more steps may be performed concurrently or with partial concurrence. Such variation will depend on the software and hardware systems chosen and on the designer's choice. All such variations are within the scope of the disclosure. Likewise, software implementations could be accomplished with standard programming techniques with rule-based logic and other logic to accomplish the various connection steps, processing steps, comparison steps, and decision steps.

[0102] As will be understood by one of ordinary skill in the art. each embodiment disclosed herein can comprise, consist essentially of, or consist of its particular stated element, step, ingredient, orAttorney Docket No.: H193-0021PCT / HJF 690-24 component. Thus, the terms “include” or “including” should be interpreted to recite: “comprise, consist of, or consist essentially of.” The transition term “comprise” or “comprises” means includes, but is not limited to, and allows for the inclusion of unspecified elements, steps, ingredients, or components, even in major amounts. The transitional phrase “consisting of excludes any element, step, ingredient, or component not specified. The transition phrase “consisting essentially of limits the scope of the embodiment to the specified elements, steps, ingredients, or components and to those that do not materially affect the embodiment.EXAMPLE EMBODIMENTS1: A method, comprising: training, by one or more processors of a computing system, a regression model on a dataset comprising at least one organ injury and / or at least one respiratory distress pathology among patients having a rib fracture: and predicting, by the one or more processors of the computing system, a probability of developing at least one organ injury and / or at least one respiratory distress pathology by inputting a plurality of biomarker levels into the trained regression model; wherein the plurality of biomarker levels are assayed from a serum sample of a subject having a rib fracture.2: The method of embodiment 1. wherein the plurality of biomarker levels comprises biomarker levels of one or more proinflammatory biomarkers and / or anti-inflammatory biomarkers.3: The method of embodiment 1 or 2, wherein the plurality of biomarker levels comprises biomarker levels of one or more proinflammatory biomarkers selected from eotaxin-3, IL-6, TNF-a, FGF-basic, and IFN-y.4: The method of embodiment 1 or 2, wherein the plurality of biomarker levels comprises biomarker levels of one or more anti-inflammatory biomarkers selected from G-CSF, IL-8, IP- 10, MIG, MCP-4, IL-2Ra, and IL-16.5: The method of any one of embodiments 1 to 4, wherein the regression model is selected from: a least absolute shrinkage and selection operator (“Lasso”) regression model and a random forest model.6: The method of any one of embodiments 1 to 4, wherein the regression model comprises a Lasso regression model, and a probability of developing a respiratory distress pathology is predicted by inputting the plurality of biomarker levels into the trained regression model.7: The method of any one of embodiments 1 to 4, wherein the regression model comprises a random forest model, and a probability of developing an organ injury is predicted by inputting the plurality of biomarker levels into the trained regression model.8: The method of any one of embodiments 1 to 7, wherein predicting the probability of developing at least one organ injury and / or at least one respiratory distress pathology further comprises inputting a count of rib fractures of the subject having a rib fracture into the trained regression model.9: The method of embodiment 8. wherein the count of rib fractures comprises a count of rib fractures at ribs 1 and 2; a count of rib fractures at ribs 3 to 6; or a count of rib fractures at ribs 7 to 10.Attorney Docket No.: H193-0021PCT / HJF 690-2410: The method of embodiment 8, wherein the count of rib fractures comprises a count of rib fractures at ribs 1 to 3, and a probability of developing at least one organ in jury other than acute kidney injury and / or a probability of developing at least one respiratory distress pathology is predicted by inputting the plurality of biomarker levels and the count of rib fractures into the trained regression model.11: The method of any one of embodiments 1 to 7. wherein predicting the probability' of developing at least one organ injury and / or at least one respiratory distress pathology further comprises inputting an age, a gender, and an injury severity score (“ I SS”) of the subject having a rib fracture into the trained regression model.12: The method of embodiment 11, wherein a probability of developing at least one organ injury other than acute lung injury is predicted by inputting the plurality of biomarker levels and the count of rib fractures into the trained regression model.13: The method of any one of embodiments 1 to 12. wherein the plurality of biomarker levels comprises a plurality' of proinflammatory biomarkers, and the plurality of biomarker levels are assayed within 72 hours of the subject suffering the rib fracture.14: The method of any one of embodiments 1 to 13, wherein the plurality of biomarker levels comprises a plurality' of anti-inflammatory biomarkers, and the plurality of biomarker levels are assayed 72 hours or later after the subject suffers the rib fracture.15: The method of any' one of embodiments 1 to 12, wherein the plurality of biomarker levels comprises a plurality of proinflammatory biomarkers and a plurality of anti-inflammatory' biomarkers, and the plurality of biomarker levels comprises a first plurality' of biomarker levels assayed within 72 hours of the subject suffering the rib fracture and a second plurality of biomarker levels assayed 72 hours or later after the subject suffers the rib fracture.16: The method of claim one of embodiments 1 to 12, wherein parameters of the regression model assign greater weight to biomarkcr levels of one or more proinflammatory' markers assayed within 72 hours of the subject suffering a rib fracture than: biomarker levels assayed for the one or more proinflammatory' markers assayed 72 hours or later after the subject suffers the rib fracture, and biomarker levels assayed for one or more anti-inflammatory' markers assayed within 72 hours of the subject suffering the rib fracture.17: The method of claim one of embodiments 1 to 12, wherein parameters of the regression model assign greater weight to biomarker levels of one or more anti-inflammatory' markers assayed 72 hours or later after the subject suffers a rib fracture than: biomarker levels of the one or more antiinflammatory markers assayed within 72 hours of the subject suffering the rib fracture, and biomarker levels of proinflammatory markers assayed 72 hours or later after the subject suffers the rib fracture.18: The method of any one of embodiments 1 to 17, wherein the at least one organ injury comprises acute kidney injury (“AKI”) and acute lung injury (‘’ALI”).Attorney Docket No.: H193-0021PCT / HJF 690-2419: The method of any one of embodiments 1 to 17, wherein the at least one respiratory distress pathology comprises pneumonia.20: A computing system, comprising: one or more processors, and a computer-readable storage medium communicatively coupled to the one or more processors, the computer-readable storage medium storing computer-readable instructions executable by the one or more processors that, when executed by the one or more processors, perform associated operations comprising the method according to any one of embodiments 1 to 19.21 : A non-transitory computer-readable storage medium, wherein the computer-readable storage medium stores a bitstream associated with a video sequence that is executable by one or more processors of an apparatus to cause the apparatus to initiate a method comprising the method according to any one of embodiments 1 to 19.22: A system for predicting at least one organ injury and / or at least one respiratory distress pathology of a subject comprising: one or more processors; an input component; an output component; and one or more computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to perform operations comprising: training, by one or more processors of a computing system, a regression model on a dataset comprising at least one organ injury and / or at least one respiratory distress pathology among patients having a rib fracture; and predicting, by the one or more processors of the computing system, a probability of developing at least one organ injury' and / or at least one respiratory distress pathology by inputting a plurality of biomarker levels into the trained regression model; wherein the plurality’ of biomarker levels is assayed from a serum sample of a subject having a rib fracture.

[0103] While the example embodiments described above are described with respect to one particular implementation, it should be understood that, in the context of this document, the content of die example embodiments can also be implemented via a method, device, system, computer-readable medium, and / or another implementation. Additionally, any of example embodiments 1-21 may be implemented alone or in combination with any other one or more of die example embodiments 1-21.

Claims

Attorney Docket No.: H193-0021PCT / HJF 690-24CLAIMSWHAT IS CLAIMED IS:

1. A method, comprising : training, by one or more processors of a computing system, a regression model on a dataset comprising at least one organ injury and / or at least one respiratory distress pathology among patients having a rib fracture; and predicting, by the one or more processors of the computing system, a probability of developing at least one organ injury and / or at least one respiratory distress pathology by inputting a plurality of biomarker levels into the trained regression model; wherein the plurality of biomarker levels is assayed from a serum sample of a subject having a rib fracture.

2. The method of claim 1, wherein the plurality’ of biomarker levels comprises biomarker levels of one or more proinflammatory biomarkers and / or anti-inflammatory biomarkers.

3. The method of claim 1, wherein the plurality of biomarker levels comprises biomarker levels of one or more proinflammatory biomarkers selected from eotaxin-3, IL-6. TNF-a, FGF-basic, and IFN-y.

4. The method of claim 1, wherein the plurality of biomarker levels comprises biomarker levels of one or more anti-inflammatory biomarkers selected from G-CSF, IL-8, IP-10, MIG, MCP-4, IL-2Ra. and IL- 16.

5. The method of claim 1, wherein the regression model is selected from: a least absolute shrinkage and selection operator (“Lasso”) regression model and a random forest model.

6. The method of claim 1, wherein the regression model comprises a Lasso regression model, and a probability of developing a respiratory distress pathology is predicted by inputting the plurality’ of biomarker levels into the trained regression model.

7. The method of claim 1 , wherein the regression model comprises a random forest model, and a probability of developing an organ injury is predicted by inputting the plurality of biomarker levels into the trained regression model.

8. The method of claim 1. wherein predicting the probability of developing at least one organ injury’ and / or at least one respiratory distress pathology further comprises inputting a count of rib fractures of the subject having a rib fracture into the trained regression model.Attorney Docket No.: H193-0021PCT / HJF 690-249. The method of claim 8, wherein the count of rib fractures comprises a count of rib fractures at ribs 1 and 2; a count of rib fractures at ribs 3 to 6; or a count of rib fractures at ribs 7 to 10.

10. The method of claim 8, wherein the count of rib fractures comprises a count of rib fractures at ribs 1 to 3, and a probability of developing at least one organ injury other than acute kidney injury and / or a probability of developing at least one respiratory distress pathology is predicted by inputting the plurality of biomarker levels and the count of rib fractures into the trained regression model.

11. The method of claim 1, wherein predicting the probability of developing at least one organ injury and / or at least one respiratory distress pathology further comprises inputting an age, a gender, and an injury severity score fTSS”) of the subject having a rib fracture into the trained regression model.

12. The method of claim 11, wherein a probability' of developing at least one organ injury other than acute lung injury is predicted by inputting the plurality of biomarker levels and the count of rib fractures into the trained regression model.

13. The method of claim 1, wherein the plurality' of biomarker levels comprises a plurality of proinflammatory biomarkers, and the plurality of biomarker levels are assayed within 72 horns of the subject suffering the rib fracture.

14. The method of claim 1, wherein the plurality of biomarker levels comprises a plurality of anti-inflammatory biomarkers, and the plurality of biomarker levels are assay ed 72 hours or later after the subject suffers the rib fracture.

15. The method of claim 1, wherein the plurality of biomarker levels comprises a plurality of proinflammatory biomarkers and a plurality of anti-inflammatory biomarkers, and the plurality of biomarker levels comprises a first plurality of biomarker levels assayed within 72 hours of the subject suffering the rib fracture and a second plurality of biomarker levels assayed 72 hours or later after the subject suffers the rib fracture.

16. The method of claim 1, wherein parameters of the regression model assign greater weight to biomarker levels of one or more proinflammatory markers assayed within 72 hours of the subject suffering a rib fracture than: biomarker levels assayed for the one or more proinflammatory markers assayed 72 horns or later after the subject suffers the rib fracture, and biomarker levels assayedAttorney Docket No.: H193-0021PCT / HJF 690-24 for one or more anti-inflammatory markers assayed within 72 hours of the subject suffering the rib fracture.

17. The method of claim 1, wherein parameters of the regression model assign greater weight to biomarker levels of one or more anti-inflammatory markers assayed 72 hours or later after the subject suffers a rib fracture than: biomarker levels of the one or more anti-inflammatory markers assayed within 72 horns of the subject suffering the rib fracture, and biomarker levels of proinflammatory markers assayed 72 hours or later after the subject suffers the rib fracture.

18. The method of claim 1, wherein the at least one organ injury comprises acute kidney injury (“AKI”) and acute lung injury (“ALI”).

19. The method of claim 1, wherein the at least one respiratory distress pathology comprises pneumonia.

20. A computing system, comprising: one or more processors, and a computer-readable storage medium communicatively coupled to the one or more processors, the computer-readable storage medium storing computer-readable instructions executable by the one or more processors that, when executed by the one or more processors, perform associated operations comprising the method according to any one of claims 1 to 19.

21. A non-transitory computer-readable storage medium, wherein the computer-readable storage medium stores a bitstream associated with a video sequence that is executable by one or more processors of an apparatus to cause the apparatus to initiate a method comprising the method according to any one of claims 1 to 19.

22. A system for predicting at least one organ injury and / or at least one respiratory distress pathology of a subject comprising: one or more processors; an input component; an output component; and one or more computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to perform operations comprising: training, by one or more processors of a computing system, a regression model on a dataset comprising at least one organ injury and / or at least one respiratory distress pathology among patients having a rib fracture; andAttorney Docket No.: H193-0021PCT / HJF 690-24 predicting, by the one or more processors of the computing system, a probability of developing at least one organ injury and / or at least one respiratory distress pathology by inputting a plurality of biomarker levels into the trained regression model; wherein the plurality of biomarker levels is assayed from a serum sample of a subject having a rib fracture.

Images