Systems, apparatuses, and methods for disease prediction

Abstract

A system for training a graph neural network (GNN) for disease prediction includes at least one memory configured to store instructions and at least one processor configured to execute the instructions to cause the system to obtain a plurality of first parameter values of parameters from individuals, determine a causal structure indicative of one or more causal relationships between the plurality of parameters based on the plurality of parameters, and train the at least one GNN with the one or more causal relationships to create a trained GNN, the trained GNN configured to output a disease prediction based on second parameter values, the second parameter values being parameter values of parameters from a patient.

Description

Atorney Docket No.: 32860U-004099-WO-PQA SYSTEMS, APPARATUSES, AND METHODS FOR DISEASE PREDICTIONCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application is a PCT International Application of Indian Application No.202511003155, filed on January 14, 2025, the entire contents of which are incorporated herein by reference.TECHNICAL FIELD

[0002] The present disclosure relates to systems, apparatuses, and / or methods for disease prediction.BACKGROUND

[0003] Health of an individual may be related to one or more parameters. The one or more parameters may be interconnected and may provide information about an individual's health.SUMMARY

[0004] At least one example embodiment relates to a system for disease prediction. The system may include at least one memory configured to store instructions and at least one processor configured to execute the instructions to cause the system to obtain a plurality of first parameter values of parameters from individuals, determine a causal structure indicative of one or more causal relationships between the plurality of parameters based on the plurality of parameters, and tram the GNN with the one or more causal relationships to create a trained GNN, the trained GNN configured to output a disease prediction based on second parameter values, the second parameter values being parameter values of parameters from a patient.Attorney Docket No.: 32860U-004099-WO-PQA

[0005] In at least one example embodiment, the determining the causal structure includes performing causal discovery between the plurality of parameters from the individuals based on the first parameter values.

[0006] In at least one example embodiment, the determining the causal structure may include determining a causal graph through domain knowledge using natural language processing.

[0007] In at least one example embodiment, the causal structure may be a directed acyclic graph.

[0008] In at least one example embodiment, the training the at least one GNN may include inputting the causal structure into the at least one GNN.

[0009] In at least one example embodiment, the plurality of parameters may include one or more of lab parameters, vitals, or demographic information for the individuals.

[0010] Also described herein is a system for disease prediction. The system may include at least one memory configured to store instructions and at least one processor configured to execute the instructions to cause the system to obtain a plurality of first parameter values of parameters of a patient, form a causal structure from the plurality of parameter values, the causal structure being based on a causal discovery indicative of one or more causal relationships between the parameters, and input the causal structure into a graph neural network (GNN) to obtain a disease prediction of the patient from the GNN.

[0011] In at least one example embodiment, the GNN may be trained based on the causal discovery.

[0012] In at least one example embodiment, the plurality of parameters may include one or more of lab parameters, vitals, or demographic information for the individual.

[0013] Also described herein is a method for training at least one graph neural network (GNN) for disease prediction. The method may include obtaining a plurality of first parameterAtorney Docket No.: 32860U-004099-WO-PQA values of parameters from individuals, determining a causal structure indicative of one or more causal relationships between the plurality of parameters based on the plurality of parameters, and training the GNN with the one or more causal relationships to create a trained GNN, the trained GNN configured to output a disease prediction based on second parameter values, the second parameter values being parameter values of parameters from a patient.

[0014] In at least one example embodiment, the determining the causal structure may include performing causal discovery' between the plurality of parameters from the individuals based on the first parameter values.

[0015] In at least one example embodiment, the determining the causal structure may include determining a causal graph through domain knowledge using natural language processing.

[0016] In at least one example embodiment, the causal structure may be a directed acyclic graph.

[0017] In at least one example embodiment, the training the at least one GNN may include inputting the causal structure into the at least one GNN.

[0018] In at least one example embodiment, the plurality’ of parameters may include one or more of lab parameters, vitals, or demographic information for the individuals.

[0019] Also described herein is a method for disease prediction. The method may include obtaining a plurality of first parameter values of parameters of a patient, forming a causal structure from the plurality of parameter values, the causal structure being based on a causal discovery indicative of one or more causal relationships between the parameters, and inputting the causal structure into a graph neural network (GNN) to obtain a disease prediction of the patient from the GNN.

[0020] In at least one example embodiment, the GNN may be trained based on the causal discovery’.Atorney Docket No.: 32860U-004099-WO-PQA

[0021] In at least one example embodiment, the plurality of parameters may include one or more of lab parameters, vitals, or demographic information for the individual.

[0022] Also described herein is a non-transi tory computer-readable storage medium storing computer-executable instruction that, when executed by at least one processor of a system, may cause the system to perform a method for training at least one graph neural network (GNN) for disease prediction. The method may include obtaining a plurality' of first parameter values of parameters from individuals, determining a causal structure indicative of one or more causal relationships between the plurality' of parameters based on the plurality' of parameters, and training the GNN with the one or more causal relationships to create a trained GNN, the trained GNN configured to output a disease prediction based on second parameter values, the second parameter values being parameter values of parameters from a patient.

[0023] In at least one example embodiment, the determining the causal structure may include performing causal discovery' between the plurality of parameters from the individuals based on the first parameter values.

[0024] In at least one example embodiment, the determining the causal structure may include determining a causal graph through domain knowledge using natural language processing.

[0025] In at least one example embodiment, the causal structure may be a directed acyclic graph.

[0026] In at least one example embodiment, the training the at least one GNN may include inputting the causal structure into the at least one GNN.

[0027] In at least one example embodiment, the plurality of parameters may include one or more of lab parameters, vitals, or demographic information for the individuals.

[0028] Also described herein is a non-transitory computer-readable storage medium storing computer-executable instruction that, when executed by at least one processor of a system, mayAttorney Docket No.: 32860U-004099-WO-PQA cause the system to perform a method for disease prediction. The method may include obtaining a plurality of first parameter values of parameters of a patient, forming a causal structure from the plurality' of parameter values, the causal structure being based on a causal discovery indicative of one or more causal relationships between the parameters, and inputting the causal structure into a graph neural network (GNN) to obtain a disease prediction of the patient from the GNN.

[0029] In at least one example embodiment, the GNN may be trained based on the causal discovery'.

[0030] In at least one example embodiment, the plurality of parameters may include one or more of lab parameters, vitals, or demographic information for the individualBRIEF DESCRIPTION OF THE DRAWINGS

[0031] The various features and advantages of the non-limiting embodiments herein may become more apparent upon review of the detailed description in conjunction with the accompanying drawings. The accompanying drawings are merely provided for illustrative purposes and should not be interpreted to limit the scope of the claims. The accompanying drawings are not to be considered as drawn to scale unless explicitly noted. For purposes of clarity', various dimensions of the drawings may have been exaggerated.

[0032] FIG. 1 is a block diagram of a sy stem that may implement the various methods described herein according to at least one example embodiment.

[0033] FIG. 2 illustrates a method of training a graph neural network and deploy ing the graph neural network for disease prediction according to at least one example embodiment.

[0034] FIG. 3 illustrates a directed acyclic graph according to at least one example embodiment.Attorney Docket No.: 32860U-004099-WO-PQA

[0035] FIG. 4 illustrates a graph neural network according to at least one example embodiment.

[0036] FIG. 5 illustrates a flow chart of a method of training a graph neural network for disease prediction according to at least one example embodiment.

[0037] FIG. 6 illustrates a flow chart of a method of implementing the graph neural network of FIG. 5 according to at least one example embodiment.DETAILED DESCRIPTION OF EXAMPLE EMBODIMENTS

[0038] Independent of the grammatical term usage, individuals with male, female or other gender identities are included within the term.

[0039] Some detailed example embodiments are disclosed herein. However, specific structural and functional details disclosed herein are merely representative for purposes of describing some example embodiments. Example embodiments may, however, be embodied in many alternate forms and should not be construed as limited to only example embodiments set forth herein.

[0040] Accordingly, while example embodiments are capable of various modifications and alternative forms, example embodiments thereof are shown by way of example in the drawings and will herein be described in detail. It should be understood, however, that there is no intent to limit an example embodiment to the particular forms disclosed, but to the contrary, example embodiments are to cover all modifications, combinations, equivalents, and alternatives falling within the scope of an example embodiment. Like numbers refer to like elements throughout the description of the figures.

[0041] It should be understood that when an element or layer is referred to as being “on,” “connected to,” “coupled to,” or “covering” another element or layer, it may be directly on, connected to, coupled to, or covering the other element or layer or intervening elements orAtorney Docket No.: 32860U-004099-WO-POA layers may be present. In contrast, when an element is referred to as being "directly on,” “directly connected to,” or “directly coupled to” another element or layer, there are no intervening elements or layers present. Like numbers refer to like elements throughout the specification. As used herein, the term “and / or” includes any and all combinations of one or more of the associated listed items.

[0042] It should be understood that, although the terms first, second, third, etc. may be used herein to describe various elements, regions, layers and / or sections, these elements, regions, layers, and / or sections should not be limited by these terms. These terms are only used to distinguish one element, region, layer, or section from another region, layer, or section. Thus, a first element, region, layer, or section discussed below could be termed a second element, region, layer, or section without departing from the teachings of example embodiment.

[0043] The terminology used herein is for the purpose of describing various example embodiment only and is not intended to be limiting of example embodiment. As used herein, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “includes,” “including,” “comprises,” and / or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, and / or elements, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements and / or groups thereof.

[0044] When the words “about” and “substantially” are used in this specification in connection with a numerical value, it is intended that the associated numerical value include a tolerance of ±10% around the stated numerical value, unless otherwise explicitly defined. Moreover, when the terms “generally” or “substantially” are used in connection with geometric shapes, it is intended that precision of the geometric shape is not required but that latitude for the shape is within the scope of the disclosure. Furthermore, regardless of whether numericalAttorney Docket No.: 32860U-004099-WO-PQA values or shapes are modified as “about,” “generally,” or “substantially,” it will be understood that these values and shapes should be construed as including a manufacturing or operational tolerance (e.g., ±10%) around the stated numerical values or shapes.

[0045] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which example embodiment belong. It will be further understood that terms, including those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0046] FIG. 1 illustrates a system 100 that may implement the methods and algorithms described herein. For example, the system 100 may be used for causal discovery, generating a causal structure, and / or generating and / or implementing a disease prediction model. In at least one example embodiment, the system 100 includes at least one processor 102, at least one memory 104, and at least one communication interface 106. The at least one memory 104 may be configured to store instruct ons that may be executed by the at least one processor 102 to cause the system 100 to perform one or more functions.

[0047] As will be appreciated, depending on the implementation of the system 100, the system 100 may include additional components. However, it is not necessary that all of these generally conventional components be shown in order to disclose the illustrative example embodiment. For example purposes, the system 100 will be discussed with regard to the at least one processor 102. However, it should be understood that the system 100 may include one or more processors or other processing circuitry, such as one or more Application Specific Integrated Circuits (ASICs).

[0048] The at least one processor 102 may include, but is not limited to, a central processing unit (CPU), an arithmetic logic unit (ALU), a graphics processing unit (GPU), an applicationAttorney Docket No.: 32860U-004099-WO-PQA processor (AP), a digital signal processor (DSP), a microcomputer, a field programmable gate array (FPGA), and programmable logic unit, application-specific integrated circuit (ASIC), a neural network processing unit (NPU), an Electronic Control Unit (ECU), a quantum computer, and the like. In some example embodiments, the processing circuitry7may include a non-transitory computer readable storage medium or device (e.g., memory ), for example a solid state drive (SSD), storing a program of instructions, and a processor (e.g., CPU) configured to execute the program of instructions to implement the functionality and / or methods performed by some or all of the systems according to any of the example embodiments.

[0049] The at least one memory7104 may be a computer readable storage medium that generally includes a random access memory7(RAM), read only memory7(ROM), and / or a permanent mass storage device, such as a disk drive. The at least one may also store an operating system and any other routines / modules / applications for providing the functionalities of the system 100 to be executed by the at least one processor 102. These software components may also be loaded from a separate computer readable storage medium into the at least one using a drive mechanism (not shown). Such separate computer readable storage medium may include a disc, tape, DVD / CD-ROM drive, memory card, or other like computer readable storage medium (not shown). In some example embodiments, software components may be loaded into the at least one memory 104 via one of the at least one communication interface 106, rather than via a computer readable storage medium.

[0050] The at least one processor 102 or other processing circuitry may be configured to carry out instructions of a computer program by performing the arithmetical, logical, and input / output operations of the system. Instructions may be provided to the at least one processor 102 by the at least one memory 104.

[0051] The at least one communication interface 106 may be wired and may include components that interface the at least one processor 102 with the other input / outputAttorney Docket No.: 32860U-004099-WO-POA components. As will be understood, the at least one communication interface 106 and programs stored in the at least one memory 104 to set forth the special purpose functionalities of the system 100 will vary depending on the implementation of the system 100.

[0052] The at least one communication interface 106 may also include one or more user input devices (e.g., a keyboard, a keypad, a mouse, or the like) and user output devices (e.g., a display, a speaker, or the like).

[0053] As disclosed herein, the term "storage medium," "computer readable storage medium" or "non-transitory computer readable storage medium” may represent one or more devices for storing data, including read only memory (ROM), random access memory' (RAM), magnetic RAM, core memory, magnetic disk storage mediums, optical storage mediums, flash memory devices and / or other tangible machine-readable mediums for storing information. The term "computer-readable medium" may include, but is not limited to, portable or fixed storage devices, optical storage devices, and various other mediums capable of storing, containing or carrying instruction(s) and / or data.

[0054] Furthermore, example embodiments may be implemented by hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof. When implemented in software, firmware, middleware or microcode, the program code or code segments to perform the necessary tasks may be stored in a machine or computer readable medium such as a computer readable storage medium. When implemented in software, a processor or processors will perform the necessary tasks. For example, as mentioned above, according to one or more example embodiments, at least one memory may include or store a computer program or computer program code, and the at least one memory and the computer program code may be configured to. with at least one processor, execute a method for noise cancellation to perform the necessary tasks. Additionally, the processor, memory and example algorithms, encoded as computer program code, serve as means forAtorney Docket No.: 32860U-004099-WO-PQA providing or causing performance of operations discussed herein. At least one other example embodiment may include a computer program including program segments or instructions that, when executed by at least one processor of a system, cause the system to perform a method for noise cancellation.

[0055] A code segment of a computer program may represent a procedure, function, subprogram, program, routine, subroutine, module, software package, class, or any combination of instructions, data structures or program statements. A code segment may be coupled to another code segment or a hardware circuit by passing and / or receiving information, data, arguments, parameters or memory contents. Information, arguments, parameters, data, etc. may be passed, forwarded, or transmitted via any suitable technique including memory sharing, message passing, token passing, network transmission, etc.

[0056] The systems and methods described herein provide improved disease prediction methods. In particular, current machine learning and deep learning algorithms lack generalizability and explainability which poses challenges in clinical settings. The systems and methods described herein utilize causal machine learning, focused on cause-and-effect relationships to provide improved disease prediction models. As described herein, linear causal relationships may be defined among clinical parameters using causal discovery with a linear non-Gaussian acyclic model. These linear causal relationships may be used to define a causal structure that may be used to train a simplicial graph neural network which may capture nonlinear relationships between the clinical parameters. The systems and methods described herein have been tested and validated with different population datasets which illustrates generalizability and explainability for early sepsis prediction as a case study.

[0057] FIG. 2 illustrates a method for disease prediction in accordance with at least one example embodiment. In at least one example embodiment, the method may begin at S202 where parameters and values of the parameters are obtained from individuals. The parametersAttorney Docket No.: 32860U-004099-WO-POA and the values of the parameters may be obtained from lab data related to one or more organs of each individual, vitals of each individual, and demographic information of each individual. In at least one example embodiment, the parameters may include routine lab parameters such as one or more of: lactate, alanine aminotransferase (“ALT’"), partial thromboplastin time (“PTT”), international normalized ratio (“INR”), globulin, monocyte count, hematocrit, magnesium, pH, sodium, urea nitrogen, triglycerides, creatinine, bilirubin total, cholesterol total, aspartate aminotransferase (“AST”), mean corpuscular hemoglobin concentration (“MCHC”), percent eosinophils, phosphate, C-reactive protein, prothrombin time (“PT”), neutrophil count, basophil count, glucose, D-dimer, albumin, percent neutrophils, percent lymphocytes, calcium total, chloride, % hemoglobin Ale, high density lipoprotein (“HDL”), red blood cell (“RBC”) count, red blood cell distribution width (“RDW”), white blood cell (“WBC”) count, troponin T, mean corpuscular hemoglobin (“MCH”), percent monocytes, eosinophil count, alkaline phosphatase (“ALP”), fibrinogen functional, hemoglobin, low density lipoprotein (“LDL”), mean corpuscular volume (“MCV”), percent basophils, lymphocyte count, platelet count, protein total, potassium, and bicarbonate. The parameters may also include vitals such as diastolic blood pressure (“DBP”), systolic blood pressure (“SBP”), oxygen (O2) saturation, respiratory rate, heart rate, and temperature as well as demographic parameters such as age and gender. The parameters are not limited herein. In at least one example embodiment, the parameters may be obtained from data sources that are publicly accessible. For example, the parameters may be obtained from a MIMIC-IV dataset and / or aZigong Fourth People’s Hospital dataset in at least one example embodiment.

[0058] After the parameters are obtained, at S204 causal discovery may be performed which may output a causal structure 205. In at least one example embodiment, a causal graph may be determined by causal discovery or through domain knowledge using natural language processing. Natural language processing models may be used by mining text from researchAtorney Docket No.: 32860U-004099-WO-PQA articles, for example, to determine relationships between data. Techniques such as named entity recognition (“NER”) and dependency parsing may be used to identify causal relationships. These relationships may be used to build a structure such as a causal graph. Natural language processing models may also create knowledge graphs that may be configured to synthesize causal pathways from large scale textual data.

[0059] In at least one example embodiment, causal discovery' may be performed using a Linear Non-Gaussian Acyclic Model (“LiNGAM”). Although embodiments herein are described with reference to causal discovery performed using LiNGAM, other causal discovery algorithms may be used. For example, one or more of Peter-Clark (“PC”), Fast Causal Inference (“FCI”), Greedy Equivalence Search (“GES”), or Max-Min Hill Climbing (“MMHC”) may be used to perform causal discovery. Causal discover}' may establish a cause and effect relationship between one or more variables. In particular, inputting the obtained parameters into the LiNGAM may output a causal structure such as a directed acyclic graph. The LiNGAM may perform causal discovery by leveraging an assumption that the input data generated by a linear structure with non-Gaussian noise. The model may use statistical techniques like Independent Component Analysis (ICA) to identify underlying independent sources driving the observed data. By examining the non-Gaussianity of the residuals after modeling linear dependencies, LiNGAM can infer the causal directionality between variables, uncovering the acyclic structure of the input data. This method may distinguish causal relationships from mere correlations.

[0060] The directed acyclic graph may include one or more nodes connected via one or more edges. The one or more nodes may represent the parameters obtained at S202. When a first node is connected to a second node via an edge, the edge represents a causal influence between the nodes. Thus, one of the first node or the second node may impact the other of the first node or the second node. This may indicate a cause-and-effect relationship betweenAtorney Docket No.: 32860U-004099-WO-PQA connected nodes of the directed acyclic graph. Each node may be connected to as many nodes as are determined to be in a cause-and-effect relationship with that node.

[0061] At S206, the causal graph, such as the directed acyclic graph, is input into a Graph Neural Network (GNN) to train the GNN for disease prediction. In at least one example embodiment, the GNN may be a disease prediction model. The GNN may include multiple layers. Each layer may incorporate activation functions to introduce non-linearity. The GNN may be trained using a message-passing mechanism, where each node (representing a clinical parameter) is configured to aggregate information from neighboring nodes to update its own representation. These updated representations are then passed to the nodes in the next layer. During classification, the final node representations, after multiple layers of message passing, are used as input to a classification head (often a fully connected layer) that produces an output. The GNN may be trained iteratively by optimizing a loss function that compares the predicted classification with the ground truth, allowing the GNN to adjust its parameters and improve its predictions over time. In particular, the causal structure 205 with values of the parameters for patients from the data obtained at S202 may be input with the ground truth for each patient or individual into the GNN. In at least one example embodiment, data for each patient may be input into the GNN individually and independently from additional data for other patients from the healthy individual and the diseased individual data sets. The ground truth for each patient may include a disease status for one or more organs of the individual. For example, if the patient has a disease or condition, the ground truth may be indicated as a ’T” while if the patient does not have a disease or condition, the ground truth may be indicated as a ‘’0”. In at least one example embodiment, when a causal structure / graph is fed into the GNN for classification, the GNN may guide the information flow across the connections / edges that encode causal relationships, ensuring that only relevant relationships are used in the prediction process.Attorney Docket No.: 32860U-004099-WO-PQA

[0062] In at least one example embodiment, the GNN may be at least one simplicial GNN which may be configured to generalize operations and concepts of GNNs to simplicial concepts. The GNN may be configured to leam non-linear relationships between parameters by aggregating information from neighboring nodes of the directed acyclic graph. Thus, the GNN may utilize the directed acyclic graph to inform its learning process. For example, using a causal structure such as a directed acyclic graph in its learning process may allow the GNN to account for confounding variables and ignore spurious relationships that occur without a causal basis. The GNN may use the edges of the directed acyclic graph to understand and propagate information through the directed acyclic graph which may capture both linear and non-linear relationships between the parameters. Linear relationships may be determined directly from edges connecting two nodes. Non-linear relationships in a directed acyclic graph may be captured through transformations applied across layers during message passing in the GNN. The layers may include learnable weights and non-linear activation functions which may enable the GNN to combine and propagate information from connected nodes which may reflect complex dependencies beyond direct edges. The GNN may also be configured to extract features from the directed acyclic graph for classification.

[0063] In at least one example embodiment, the GNN may be trained for disease prediction with clinical parameters in a graph format as inputs with disease diagnoses as ground truths that may be used as labels or outputs.

[0064] In at least one example embodiment, graph adversarial attacks may be performed to illustrate explainability of the GNN. For example, a graph structure of the GNN may be altered to determine the most important simplices of the GNN. If altering a particular simplex leads to a significant change in predictions made by the GNN, then the simplex is deemed important for the decision.Atorney Docket No.: 32860U-004099-WO-PQA

[0065] In at least one example embodiment, performance of the GNN may be scored based on one or more of accuracy, sensitivity, positive predictive value (“PPV”), negative predictive value (“NPV”), area under the receiver operating characteristic (“AUROC”), and area under the precision-recall curve (“AUPRC”).

[0066] For example, external validation of the GNN on two data sets returned the following performance values: Data set 1: accuracy: 83.32%, sensitivity: 80.09%, specificity: 84.50%, PPV: 83.46%, NPV: 81.29%, AUROC: 90.45%, and AUPRC: 87.67%; and Data set 2: accuracy: 82.16%, sensitivity: 80.47%, specificity: 83.76%, PPV: 82.51%, NPV: 81.84%, AUROC: 90.33%, and AUPRC: 87.16%. In at least one example embodiment, the two data sets may be from different public sources and may include data with individuals of different ethnicity, geography, health systems, hospital settings, and severity levels of infection. The similarity- of the performance metrics across both data sets illustrates the generalizability of the GNN. Thus, the GNN is robust to different types of data and may be used for disease prediction and / or detection independent of ethnicity, geography, health systems, hospital settings, and severity levels of infection.

[0067] In at least one example embodiment, a training process for the GNN may include the steps S202 to S206. Upon completion of the training process, the GNN may be deployed to output multi-organ health scores for input patient data. The multi-organ health scores may be referred to herein as multi-organ health status.

[0068] After the GNN is trained, parameters 207 and values of the parameters 207 from an individual may be obtained. The parameters 207 may include one or more of the parameters described above at step S202 while the values of the parameters 207 may be individual to the patient. The values of the parameters 207 may be input into the causal structure 205 determined from the causal discovery performed at S204.Attorney Docket No.: 32860U-004099-WO-PQA

[0069] The causal structure 205 including the values of the parameters 207 may then be input into the trained GNN. The trained GNN may be configured to output a disease prediction 209 for the patient. The disease prediction may be determined from the parameters 207, the values of the parameters 207, and the causal structure 205.

[0070] FIG. 3 is a causal structure 300 obtained using LiNGAM as described above. The causal structure 300 is an example embodiment of the causal structure 205 described above in FIG. 2. The causal structure 300 may be a directed acyclic graph. The causal structure 300 includes a plurality of nodes 302 and edges 304. Each of the plurality of nodes 302 may be coupled to one or more nodes 302 via the edges 304. Each node of the plurality of nodes 302 may represent a parameter. Example parameters include hemoglobin, temperature, respiratory rate, gender, Basophils percentage, Eosinophils percentage, white blood cell count, and heartrate. The parameters are not limited herein and may include any of the parameters listed above with respect to FIG. 2. Each of the edges 304 may include an associated number. The number may represent a causal influence or direct effect of one node of the plurality of nodes 302 on a connected node of the plurality of nodes 302. In at least one example embodiment, the numbers indicative of the causal influence between nodes may be determined by analyzing a non-Gaussian nature of the data to identify a directionality of the causal relationships. The causal structure 300 may define cause-and-effect relationships between the nodes which may enable a GNN to determine relationships between parameters which may be used to determine a disease prediction.

[0071] In at least one example embodiment, the directionality of the edges, shown by arrows in FIG. 3 and the associated numbers for the edges may be omitted when the causal structure 300 is input into the GNN. The GNN may only receive the plurality of nodes 302 and the edges 304. Further, then patient data such as the parameters 207 is input into the causal structure 300, each node of the plurality of nodes 302 that includes a corresponding patient parameter of theAtorney Docket No.: 32860U-004099-WO-PQA parameters 207 may be replaced by the patient data for that parameter. The causal structure 300 with the patient data may then be input into the GNN to determine the multi-organ health scores 209 for the patient.

[0072] FIG. 4 is an GNN 400 according to at least one example embodiment. The GNN may include one or more layers. The one or more layers 402 may be interconnected and may be configured to receive an input and output a final health score. The one or more layers may include hidden layers and may be one or more of linear layers, convolutional layers, or additional GNN layers for multiple tasks specific to one or more organs. The GNN may receive an input 404 which may be fed into a first layer of the one or more layers 402. The GNN may include one or more nodes 406 that may be connected by one or more edges 408. The one or more edges 408 may be configured to connect the one or more nodes 406 within the one or more layer 402 of the GNN. The GNN may be configured to generate an output 410. The output 410 may be a disease prediction as described herein.

[0073] FIG. 5 is a flow chart of a method 500 for training a GNN for disease prediction. The method 500 may begin at S502 where parameters and values of the parameters are obtained. The parameters and the values of the parameters may be obtained from one or more data sources that may be publicly accessible. The parameters and the values of the parameters may be the parameters and the values of the parameters obtained at S202 described above.

[0074] At step S504, causal discovery may be performed. As described above, causal discovery may be performed by a model or algorithm that takes the parameters and the values of the parameters as inputs and outputs causal relationships of the parameters. For example, as described above, causal discovery may be performed using LiNGAM which may output a causal structure such as a directed acyclic graph. The directed acyclic graph may include one or more nodes connected via one or more edges.Atorney Docket No.: 32860U-004099-WO-PQA

[0075] At step S506, at least one GNN is trained with the causal relationships determined from the causal discovery. The at least one GNN may be trained as described above with reference to FIG. 2 such that the GNN is configured to output a disease prediction when the GNN is deployed after is it trained.

[0076] FIG. 6 illustrates a method 600 for utilizing a trained GNN to predict a disease for a patient in accordance with at least one example embodiment. In at least one example embodiment, the method 600 may begin at S602 where parameters are obtained from an individual, the parameters may be patient parameters such as the parameters 207 and the values of the parameters 207 for a patient.

[0077] At step S604, the values of the parameters 207 are input into a causal structure such as the causal structure 205 determined during training of the GNN.

[0078] At S606, the GNN is used to generate a disease prediction. In at least one example embodiment, the disease prediction may be determined for a particular patient after the GNN is trained. The input may include the causal structure determined at S604. Thus, the GNN may be configured to receive the input data of the patient in the form of the causal structure 205 and determine a disease prediction such as the disease prediction 209 for that individual.

[0079] Thus, the GNN may be configured to receive the input data of the patient in the form of a causal graph and determine a disease that may occur for the patient based on the causal graph that was used to train the GNN. For example, if particular parameters that are included in the input of the patient have been determined by the GNN to lead to a particular disease, then the GNN may output the particular disease as a disease prediction for the patient.

[0080] The methods described herein may be implemented by the system 100 described with respect to FIG. 1 in at least one example embodiment. Additionally, in at least one example embodiment, a means for processing may be configured to perform the methods described herein.Attorney Docket No.: 32860U-004099-WO-POA

[0081] The above-described systems and methods provide improved systems and methods for disease prediction. The GNN described herein may be applicable in a variety of healthcare applications as it may be able to identify effective combinations of routine parameters or integrate routine parameters with biomarkers for enhanced risk prediction of various diseases. Further, the systems and methods described herein may provide generalizable GNN that may be configured to be implemented for data from individuals of different ethnicity, geography, health systems, hospital settings, and severity levels of infection. The GNN may be robust to different types of data and may be used for disease prediction and / or detection independent of ethnicity, geography, health systems, hospital settings, and severity levels of infection which may provide improved systems and methods for disease prediction.

[0082] The GNN’s predictive capabilities are further enhanced by its ability to recommend unmeasured but informative tests based on individual risk profiles. For example, individuals with a higher risk of cardiac events may be advised to undergo biomarker tests such as NT-proBNP or hsTroponin, offering a deeper understanding of their cardiovascular health and aiding in precise intervention planning. By providing both prediction and personalized recommendations, the GNN empowers healthcare professionals to intervene early, improve outcomes, and optimize resource use in both preventive and critical care environments.

[0083] Appendix A, incorporated by reference in Indian Provisional Application No.202511003155, filed on January 14, 2025, is incorporated herein by reference in its entirety.

[0084] Example embodiments have been disclosed herein, it should be understood that other variations may be possible. Such variations are not to be regarded as a departure from the spirit and scope of the present disclosure, and all such modifications as would be obvious to one skilled in the art are intended to be included within the scope of the following claims.NON-LIMITING ILLUSTRATIVE EMBODIMENTSAtorney Docket No.: 32860U-004099-WO-PQA

[0085] The following is a list of non-limiting illustrative embodiments disclosed herein:

[0086] Illustrative embodiment 1 includes a system for training a graph neural network (GNN) for disease prediction, the system comprises: at least one memory7configured to store instructions; and at least one processor configured to execute the instructions to cause the system to obtain a plurality7of first parameter values of parameters from healthy individuals and diseased individuals, determine a causal structure indicative of one or more causal relationships between the plurality7of parameters based on the plurality7of parameters, and train the GNN with the one or more causal relationships to create a trained GNN, the trained GNN configured to output a disease prediction based on second parameter values, the second parameter values being parameter values of parameters from a patient.

[0087] Illustrative embodiment 2 includes the system of illustrative embodiment 1, wherein the determining the causal structure includes performing causal discovery between the plurality of parameters from the individuals based on the first parameter values.

[0088] Illustrative embodiment 3 includes the system of any one of illustrative embodiments 1 and 2, wherein the determining the causal structure includes determining a causal graph through domain knowledge using natural language processing.

[0089] Illustrative embodiment 4 includes the system of any one of illustrative embodiments 1, 2, and 3, wherein the causal structure is a directed acyclic graph.

[0090] Illustrative embodiment 5 includes the system of any one of illustrative embodiments 1, 2, 3, and 4, wherein the training the at least one GNN includes inputting the causal structure into the at least one GNN.

[0091] Illustrative embodiment 6 includes the system of any one of illustrative embodiments 1, 2. 3, 4, and 5. wherein the plurality of parameters include one or more of lab parameters, vitals, or demographic information for the individuals.Attorney Docket No.: 32860U-004099-WO-PQA

[0092] Illustrative embodiment 7 includes a system for disease prediction, the system comprises: at least one memory configured to store instructions; and at least one processor configured to execute the instructions to cause the system to obtain a plurality of first parameter values of parameters of a patient, form a causal structure from the plurality of parameter values, the causal structure being based on a causal discovery' indicative of one or more causal relationships between the parameters, and input the causal structure into a graph neural network (GNN) to obtain a disease prediction of the patient from the GNN.

[0093] Illustrative embodiment 8 includes the system of illustrative embodiment 7, wherein the GNN is trained based on the causal discovery'.

[0094] Illustrative embodiment 9 includes the system of any one of illustrative embodiments 7 and 8, wherein the plurality of parameters include one or more of lab parameters, vitals, or demographic information for the individual.

[0095] Illustrative embodiment 10 includes a method for training at least one graph neural network (GNN) for disease prediction, the method comprising: obtaining a plurality of first parameter values of parameters from individuals, determining a causal structure indicative of one or more causal relationships between the plurality of parameters based on the plurality of parameters, and training the GNN with the one or more causal relationships to create a trained GNN, the trained GNN configured to output a disease prediction based on second parameter values, the second parameter values being parameter values of parameters from a patient.

[0096] Illustrative embodiment 11 includes the method of illustrative embodiment 10, wherein the determining the causal structure includes performing causal discovery between the plurality of parameters from the individuals based on the first parameter values.

[0097] Illustrative embodiment 12 includes the method of any one of illustrative embodiments 10 and 11. wherein the determining the causal structure includes determining a causal graph through domain knowledge using natural language processing.Attorney Docket No.: 32860U-004099-WO-PQA

[0098] Illustrative embodiment 13 includes the method of any one of illustrative embodiments 10, 11, and 12, wherein the causal structure is a directed acyclic graph.

[0099] Illustrative embodiment 14 includes the method of any one of illustrative embodiments 10, 11, 12, and 13, wherein the training the at least one GNN includes inputting the causal structure into the at least one GNN.

[0100] Illustrative embodiment 15 includes the method of any one of illustrative embodiments 10, 11, 12, 13, and 14, wherein the plurality of parameters include one or more of lab parameters, vitals, or demographic information for the individuals.

[0101] Illustrative embodiment 16 includes a method for disease prediction, the method comprises: obtaining a plurality of first parameter values of parameters of a patient, forming a causal structure from the plurality of parameter values, the causal structure being based on a causal discovery indicative of one or more causal relationships between the parameters, and inputting the causal structure into a graph neural network (GNN) to obtain a disease prediction of the patient from the GNN.

[0102] Illustrative embodiment 17 includes the method of illustrative embodiment 16, wherein the GNN is trained based on the causal discovery.

[0103] Illustrative embodiment 18 includes the method of any one of illustrative embodiments 16 and 17, wherein the plurality of parameters include one or more of lab parameters, vitals, or demographic information for the individual.

[0104] Illustrative embodiment 19 includes a non-transitory computer-readable storage medium storing computer-executable instruction that, when executed by at least one processor of a system, cause the system to perform a method for training at least one graph neural network (GNN) for disease prediction, the method including obtaining a plurality of first parameter values of parameters from individuals, determining a causal structure indicative of one or more causal relationships between the plurality of parameters based on the plurality of parameters,Attorney Docket No.: 32860U-004099-WO-PQA and training the GNN with the one or more causal relationships to create a trained GNN, the trained GNN configured to output a disease prediction based on second parameter values, the second parameter values being parameter values of parameters from a patient.

[0105] Illustrative embodiment 20 includes the non-transitory computer-readable storage medium of illustrative embodiment 19, wherein the determining the causal structure includes performing causal discovery7between the plurality’ of parameters from the individuals based on the first parameter values.

[0106] Illustrative embodiment 21 includes the non-transitory7computer-readable storage medium of any one of illustrative embodiments 19 and 20, wherein the determining the causal structure includes determining a causal graph through domain knowledge using natural language processing.

[0107] Illustrative embodiment 22 includes the non-transitory computer-readable storage medium of any7one of illustrative embodiments 19, 20, and 21, wherein the causal structure is a directed acyclic graph.

[0108] Illustrative embodiment 23 includes the non-transitory computer-readable storage medium of any one of illustrative embodiments 19, 20, 21, and 22, wherein the training the at least one GNN includes inputting the causal structure into the at least one GNN.

[0109] Illustrative embodiment 24 includes the non-transitory computer-readable storage medium of any one of illustrative embodiments 19, 20, 21, 22, and 23, wherein the plurality of parameters include one or more of lab parameters, vitals, or demographic information for the individuals.

[0110] Illustrative embodiment 25 includes a non-transitory computer-readable storage medium storing computer-executable instruction that, when executed by at least one processor of a system, cause the system to perform a method for disease prediction, the method including obtaining a plurality of first parameter values of parameters of a patient, forming a causalAtorney Docket No.: 32860U-004099-WO-PQA structure from the plurality' of parameter values, the causal structure being based on a causal discovery indicative of one or more causal relationships between the parameters, and inputting the causal structure into a graph neural network (GNN) to obtain a disease prediction of the patient from the GNN.[OHl] Illustrative embodiment 26 includes the non-transitory computer-readable storage medium of illustrative embodiment 25, wherein the GNN is trained based on the causal discovery' .

[0112] Illustrative embodiment 27 includes the non-transitory' computer-readable storage medium of any one of illustrative embodiments 25 and 26, yvherein the plurality' of parameters include one or more of lab parameters, vitals, or demographic information for the individual.

Claims

Attorney Docket No.: 32860U-004099-WO-PQAWE CLAIM:

1. A system for training a graph neural network (GNN) for disease prediction, the system comprising:at least one memory configured to store instructions; andat least one processor configured to execute the instructions to cause the system to obtain a plurality of first parameter values of parameters from individuals, determine a causal structure indicative of one or more causal relationships between the plurality of parameters based on the plurality of parameters, and train the GNN with the one or more causal relationships to create a trained GNN, the trained GNN configured to output a disease prediction based on second parameter values, the second parameter values being parameter values of parameters from a patient.

2. The system of claim 1, wherein the determining the causal structure includes performing causal discovery between the plurality of parameters from the individuals based on the first parameter values.

3. The system of claim 1, wherein the determining the causal structure includes determining a causal graph through domain knowledge using natural language processing.

4. The system of claim 1, wherein the causal structure is a directed acyclic graph.

5. The system of claim 1, wherein the training the at least one GNN includes inputting the causal structure into the at least one GNN.

6. The system of claim 1, wherein the plurality of parameters include one or more of lab parameters, vitals, or demographic information for the individuals.

7. A system for disease prediction, the system comprising:at least one memory configured to store instructions; andat least one processor configured to execute the instructions to cause the system to obtain a plurality of first parameter values of parameters of a patient,Atorney Docket No.: 32860U-004099-WO-PQAform a causal structure from the plurality of parameter values, the causal structure being based on a causal discovery indicative of one or more causal relationships between the parameters, andinput the causal structure into a graph neural network (GNN) to obtain a disease prediction of the patient from the GNN.

8. The system of clam 7, wherein the GNN is trained based on the causal discovery.

9. The system of claim 7, wherein the plurality of parameters include one or more of lab parameters, vitals, or demographic information for the individual.

10. A method for training at least one graph neural network (GNN) for disease prediction, the method comprising:obtaining a plurality7of first parameter values of parameters from individuals; determining a causal structure indicative of one or more causal relationships between the plurality of parameters based on the plurality of parameters; andtraining the GNN with the one or more causal relationships to create a trained GNN, the trained GNN configured to output a disease prediction based on second parameter values, the second parameter values being parameter values of parameters from a patient.

11. The method of claim 10, wherein the determining the causal structure includes performing causal discovery7between the plurality7of parameters from the individuals based on the first parameter values.

12. The method of claim 10, wherein the determining the causal structure includes determining a causal graph through domain knowledge using natural language processing.

13. The method of claim 10, wherein the causal structure is a directed acyclic graph.

14. The method of claim 10, wherein the training the at least one GNN includes inputting the causal structure into the at least one GNN.

15. The method of claim 10, wherein the plurality of parameters include one or more of lab parameters, vitals, or demographic information for the individuals.Attorney Docket No.: 32860U-004099-WO-PQA16. A method for disease prediction, the method comprising:obtaining a plurality of first parameter values of parameters of a patient, forming a causal structure from the plurality of parameter values, the causal structure being based on a causal discovery indicative of one or more causal relationships between the parameters, andinputting the causal structure into a graph neural network (GNN) to obtain a disease prediction of the patient from the GNN.

17. The method of clam 16, wherein the GNN is trained based on the causal discovery.

18. The method of claim 16, wherein the plurality of parameters include one or more of lab parameters, vitals, or demographic information for the individual.

19. A non-transitory computer-readable storage medium storing computer-executable instruction that, when executed by at least one processor of a system, cause the system to perform a method for training at least one graph neural network (GNN) for disease prediction, the method including:obtaining a plurality of first parameter values of parameters from individuals: determining a causal structure indicative of one or more causal relationships between the plurality of parameters based on the plurality of parameters; andtraining the GNN with the one or more causal relationships to create a trained GNN, the trained GNN configured to output a disease prediction based on second parameter values, the second parameter values being parameter values of parameters from a patient.

20. The non-transitory computer-readable storage medium of claim 19, wherein the determining the causal structure includes performing causal discovery’ between the plurality of parameters from the individuals based on the first parameter values.

21. The non-transitory computer-readable storage medium of claim 19, wherein the determining the causal structure includes determining a causal graph through domain knowledge using natural language processing.Attorney Docket No.: 32860U-004099-WO-PQA22. The non-transitory computer-readable storage medium of claim 19, wherein the causal structure is a directed acyclic graph.

23. The non-transitory computer-readable storage medium of claim 19, wherein the training the at least one GNN includes inputting the causal structure into the at least one GNN.

24. The non-transitory computer-readable storage medium of claim 19, wherein the plurality of parameters include one or more of lab parameters, vitals, or demographic information for the individuals.

25. A non-transitory computer-readable storage medium storing computer-executable instruction that, when executed by at least one processor of a system, cause the system to perform a method for disease prediction, the method including:obtaining a plurality of first parameter values of parameters of a patient, forming a causal structure from the plurality of parameter values, the causal structure being based on a causal discovery indicative of one or more causal relationships between the parameters, andinputting the causal structure into a graph neural network (GNN) to obtain a disease prediction of the patient from the GNN.

26. The non-transitory computer-readable storage medium of claim 25, wherein the GNN is trained based on the causal discovery.

27. The non-transitory computer-readable storage medium of claim 25, wherein the plurality of parameters include one or more of lab parameters, vitals, or demographic information for the individual.

Images