Serum and predictive analytics for risk calculation in peripheral arterial disease

Abstract

Among the various aspects of the present disclosure is the provision of a systems and methods for peripheral arterial disease (PAD), predicting PAD patient prognosis, and selecting appropriate treatments for PAD patients based on patient clinical data using machine learning methods.

Description

[0001] SERUM AND PREDICTIVE ANALYTICS FOR RISK CALCULATION IN PERIPHERAL ARTERIAL DISEASE

[0002] CROSS-REFERENCE TO RELATED APPLICATIONS

[0003] This application claims priority to U.S Provisional Patent Application No. 63 / 693,695, filed September 11 , 2024, the entire contents of which are incorporated herein by reference.

[0004] STATEMENT REGARDING FEDERALLY SPONSORED RESEARCH OR DEVELOPMENT

[0005] This invention was made with government support under HL153262 awarded by the National Institutes of Health. The government has certain rights in the invention.

[0006] FIELD OF THE INVENTION

[0007] The present disclosure generally relates to systems and methods of diagnosing peripheral arterial disease (PAD), predicting PAD patient prognosis, and selecting appropriate treatments for PAD patients.

[0008] BACKGROUND OF THE INVENTION

[0009] Peripheral arterial disease (PAD) impacts >12 million people in the U.S., with more than 70% being asymptomatic, leading to disease progression and chronic limb-threatening ischemia (CLTI). This results in significant disability, higher mortality, and substantial healthcare costs. To address this, we propose developing and validating a transformative diagnostic platform integrating traditional lipid profiles, risk factors, novel serum biomarkers (including circulating Fatty Acid Synthase; cFAS), and advanced machine learning algorithms for early diagnosis and prediction of PAD progression.

[0010] Current PAD diagnostic methods, such as the ankle-brachial index (AB I) and CT / MRI, require specialized equipment and technical expertise. Invasive surgical therapy is often deferred in newly diagnosed PAD cases. A novel diagnostic and predictive platform that combines biomarkers and risk factors with machine learning can significantly accelerate the identification of PAD and determine those at risk of disease progression. The current disclosure aims to develop a comprehensive diagnostic platform that integrates traditional lipid profiles, the novel biomarker cFAS, and other clinical risk factors, analyzed through machine learning algorithms, to enhance early diagnosis and prediction of PAD progression. This approach addresses current methods' inadequacies, particularly for asymptomatic individuals with known risk factors such as hyperlipidemia and smoking. Preliminary data has demonstrated that cFAS correlates highly with PAD incidence and can identify asymptomatic and symptomatic PAD with high accuracy. As disclosed herein, machine learning models performed by our group support a 1 -month and 1-year predictive capability of electronic health records (EHR) variables to identify individuals with cardiovascular disease.

[0011] SUMMARY OF THE INVENTION

[0012] Among the various aspects of the present disclosure is the provision of systems and methods for classifying a PAD severity in a patient, predicting a prognosis for the patient for at least one time point, and recommending a treatment for the patient based on patient clinical data using machine learning methods.

[0013] In one aspect, a computer-implemented method to produce a classification of PAD severity in a patient is disclosed that includes receiving a patient clinical dataset comprising a plurality of patient clinical data obtained from the patient; and transforming the patient clinical dataset into the classification of patient PAD seventy with a first multivariate logistic regression model. In some aspects, the method further comprises displaying the classification of patient PAD severity to a practitioner. In some aspects, the method further comprises transforming the patient clinical dataset and the classification of patient PAD severity into a predicted prognosis of the patient at one or more timepoints with a second multivariate logistic regression model. In some aspects, the method further comprises displaying the predicted prognosis of the patient at one or more timepoints to the practitioner. In some aspects, the method further comprises identifying a recommended treatment for the patient based on the classification of patient PAD seventy, the predicted prognosis of the patient at one or more timepoints, and any combination thereof; and displaying, the recommended treatment for the patient to the practitioner. In some aspects, the patient’s clinical dataset comprises at least one of traditional lipid profiles (total cholesterol, LDL, triglycerides), and cardiovascular risk factors (smoking, diabetes, hypertension, age), and cFAS levels. In some aspects, the classification of patient PAD severity is selected from PAD not indicated, sub-clinical PAD, and advanced PAD. In some aspects, the predicted prognosis of the patient at one or more timepoints comprises a likelihood of advanced PAD onset, a likelihood of CLTI onset, a likelihood of response to risk factor modification, a likelihood of response to aggressive surgical intervention, a likelihood of end-stage clinical status, and any combination thereof. In some aspects, the predicted prognosis of the patient at one or more timepoints comprise predicted prognosis of the patient at a timepoint ranging from about 1 month to about 1 year after an initial classification of patient PAD seventy. In some aspects, the recommended treatment for the patient is selected from continued monitoring, risk factor modification, aggressive surgical intervention, palliative care, and any combination thereof.

[0014] In another aspect, a computer-implemented method for predicting PAD seventy in a patient is disclosed that includes receiving, at a user interface, a plurality of parameters associated with PAD of the patient, wherein the plurality of parameters associated with PAD of the patient comprise lipid profiles, cardiovascular risk factors, and cFAS levels; applying one or more inputs to a supervised machine learning model, the one or more inputs comprising the plurality of parameters associated with PAD of the patient, the model being previously trained using historical data, the historical data comprising PAD parameters associated with PAD and their corresponding patient response to PAD; receiving one or more outputs from the model, at least one of the one or more outputs including a predicted patient response to PAD; transmitting, for display on the user interface, the one or more outputs from the model; updating the historical data to include the plurality of parameters associated with PAD of the patient and the corresponding one or more outputs; and re-training the model using the updated historical data.

[0015] In another aspect, a system for predicting PAD severity in a patient is disclosed that provides at least one memory storing computer-executable instructions; and at least one processor in communication with the at least one memory, wherein the at least one processor is configured to execute the computer-executable instructions to: receive a plurality of parameters associated with PAD of the patient, wherein the plurality of parameters associated with PAD of the patient comprise lipid profiles, cardiovascular risk factors, and cFAS levels; apply one or more inputs to a supervised machine learning model, the one or more inputs comprising the plurality of parameters associated with PAD of the patient, the model being previously trained using historical data, the historical data comprising PAD parameters associated with PAD and their corresponding patient response to PAD; receive one or more outputs from the model, at least one of the one or more outputs including a predicted patient response to PAD; display, on a user interface, the one or more outputs from the model; update the historical data to include the plurality of parameters associated with PAD of the patient and the corresponding one or more outputs; and re-train the model using the updated historical data.

[0016] Other objects and features will be in part apparent and in part pointed out hereinafter.

[0017] DESCRIPTION OF THE DRAWINGS

[0018] Those of skill in the art will understand that the drawings, described below, are for illustrative purposes only. The drawings are not intended to limit the scope of the present teachings in any way.

[0019] FIG. 1 is a block diagram schematically illustrating a system in accordance with one aspect of the disclosure.

[0020] FIG. 2 is a block diagram schematically illustrating a computing device in accordance with one aspect of the disclosure.

[0021] FIG. 3 is a block diagram schematically illustrating a remote or user computing device in accordance with one aspect of the disclosure.

[0022] FIG. 4 is a block diagram schematically illustrating a server system in accordance with one aspect of the disclosure. FIG. 5 is a flowchart of study patients. Patients were selected for the study from an initial pool of 1 ,081 patients in our vascular biobank. A total of 734 patients were excluded for reasons including lack of serum samples (n=198), presence of other significant vascular disease (n=140), prior inclusion in other studies (n=100), unverified PAD status (n=152), advanced chronic kidney disease (CKD stage 4 / 5; n=54), history of alcohol abuse (n=35), repeat patients (n=28), anticoagulation use without PAD (n=10), smoking history without PAD (n=12), and cardiovascular disease without PAD (n=5). The final cohort included 347 patients, categorized as 34 without PAD, 164 with PAD, and 149 with CLTI.

[0023] FIG. 6 is a violin plot displaying serum cFAS levels across three patient groups: No PAD, PAD, and CLTI. The distribution and density of serum cFAS levels are shown for each group, with individual data points overlaid. The median and interquartile ranges are represented within the box plots embedded in each violin. Serum cFAS levels are markedly higher in the PAD and CLTI groups compared to the No PAD group, with the highest levels observed in patients with CLTI, indicating a potential correlation between cFAS levels and PAD severity.

[0024] FIG. 7 is a ROC curve illustrating the diagnostic performance of serum cFAS levels for distinguishing PAD from No PAD. The empirical ROC curve (solid line) shows sensitivity (True Positive Rate) versus 1 -specificity (False Positive Rate) for various cFAS thresholds. The optimal cutoff point, determined using the Youden Index, is marked at cFAS = 0.34 ng / mg, which maximizes sensitivity and specificity. The dashed line represents the chance line, indicating random classification performance. This optimal cutoff highlights the diagnostic potential of cFAS for PAD detection.

[0025] FIG. 8 is a ROC curve showing the diagnostic performance of serum cFAS levels for distinguishing CLTI from No PAD or PAD. The empirical ROC curve (solid line) plots sensitivity (True Positive Rate) versus 1 -specificity (False Positive Rate) across various cFAS thresholds. The optimal cutoff point, determined by the Youden Index, is indicated at cFAS = 0.49 ng / mg, maximizing sensitivity and specificity for CLTI detection. The dashed line represents the chance line, illustrating random classification. This cutoff underscores the potential of cFAS as a marker for advanced PAD stages such as CLTI.

[0026] DETAILED DESCRIPTION OF THE INVENTION

[0027] The present disclosure is directed to a systems and methods for diagnosing peripheral arterial disease (PAD), predicting PAD patient prognosis, and selecting appropriate treatments for PAD patients. The disclosed systems and methods include a diagnostic and predictive platform that combines biomarkers and risk factors with machine learning to significantly accelerate the identification of individuals with PAD and determine who is at risk of disease progression.

[0028] In various aspects, the disclosed systems and methods include a comprehensive diagnostic platform that integrates traditional lipid profiles, an additional biomarker cFAS, other clinical risk factors for analysis through machine learning algorithms. In some aspects, the disclosed systems and methods provide early diagnosis of PAD and a prediction of disease progression. In some aspects, the disclosed systems and methods provide for early identification of individuals who are more likely to benefit from aggressive risk factor modification and advanced surgical therapy.

[0029] As described in the Examples herein, cFAS correlates highly with PAD incidence and can identify individuals with advanced symptomatic PAD with high accuracy. Further, machine learning models in some aspects were demonstrated to support a 1 -month and 1-year predictive capability of electronic health records (EHR) variables to identify individuals with cardiovascular disease and the risk of disease progression.

[0030] Without being limited to any particular theory, combining cFAS with traditional lipid profiles and other cardiovascular risk factors, is thought to more accurately identify individuals with advanced PAD, and are further at risk for PAD progression. Endogenous cellular Fatty Acid Synthase (FAS) is an essential metabolic enzyme responsible for the de novo synthesis of SFAs. Serum circulating FAS (cFAS) is produced by the liver and released in a bound form to serum LDL particles. Notably, cFAS serum content does not correlate with serum LDL content or statin use. As previously demonstrated, conditional knockdown of Fasn in the liver or inhibition of cFAS with a molecular inhibitor prevents atherosclerotic plaque formation in adult Apoe-7- mice maintained on a high-fat diet (Meade et al. JVS-Vascular Science, 2023, 4, 100138; Meade et al., Arteriosclerosis, Thrombosis, and Vascular Biology, 2023, 43, Abstract 311 ). In human subjects, cFAS has been demonstrated as a serum biomarker for atherosclerotic disease severity in patients with PAD. In various aspects, the disclosed systems and methods provide for the ability to receive and integrate multiple data sources including, but not limited to, traditional lipid profiles (total cholesterol, LDL, triglycerides), and cardiovascular risk factors (smoking, diabetes, hypertension, age), and cFAS levels.

[0031] In various aspects, the disclosed systems and methods include a first multivariate logistic regression model configured to transform a patient’s clinical dataset from multiple data sources into a classification of PAD seventy in the patient. Non-limiting examples of suitable patient data from multiple data sources includes traditional lipid profiles (total cholesterol, LDL, HDL, triglycerides), risk factors (smoking, diabetes, hypertension, age, sex), and serum cFAS levels. Nonlimiting examples of classifications of PAD severity include PAD not indicated, sub- clinical PAD, and advanced PAD. In some aspects, the multivariate logistic regression models are trained using a retrospective dataset that includes a plurality of patient datasets and classifications of PAD seventy. In some aspects, the multivariate logistic regression and / or machine learning models are updated with historical data to include the plurality of parameters associated with PAD of the patient and the models may be re-trained using the updated historical data.

[0032] In various other aspects, the disclosed systems and methods include a second multivariate logistic regression model configured to produce a prediction of patient prognosis at one or more timepoints. Non-limiting examples of suitable timepoints at which patient prognosis includes a timepoint ranging from about 1 month to about 1 year or more after the patient’s current classification of PAD seventy. In some aspects, the prediction of patient prognosis comprises a likelihood of advanced PAD onset, a likelihood of CLTI onset, a likelihood of response to risk factor modification, a likelihood of response to aggressive surgical intervention, and a likelihood of end-stage clinical status.

[0033] In some aspects, the second multivariate logistic regression model transforms an expanded patient dataset that includes the patient dataset described above and additionally the patient’s classification of PAD seventy to produce the predicted prognoses. In some aspects, the patient’s classification of PAD seventy may be clinically measured and provided as part of the patient’s records. In other aspects, the patient’s classification of PAD seventy may be produced using the first multivariate logistic regression model as described above.

[0034] In various additional aspects, the prediction of patient prognosis may be used to provide a recommendation for a treatment for the patient. By way of nonlimiting example, if the first multivariate logistic regression model classifies the patient as having pre-clinical or early-stage PAD and the second multivariate logistic regression model produces a high likelihood of responding to risk factor modification, then risk factor modification may be recommended to the patient. By way of another non-limiting example, if the first multivariate logistic regression model classifies the patient as having pre-clinical or early-stage PAD and the second multivariate logistic regression model produces a high likelihood of responding to aggressive surgical intervention, then aggressive surgical intervention may be recommended to the patient. By way of another non-limiting example, if the first multivariate logistic regression model classifies the patient as having advanced PAD, CLTI, or end-stage clinical status and the second multivariate logistic regression model produces a high likelihood of not responding to risk factor modification or surgical intervention, then palliative care may be recommended to the patient.

[0035] In various aspects, the first and second multivariate logistic regression models may be trained using training sets that include a plurality of patients and associated data including, but not limited to a clinical dataset of each patient, a classification of PAD severity for each patient, and a prognosis for each patient.

[0036] Computing Systems and Devices

[0037] In various aspects, the first and second multivariate logistic regression models used in the disclosed systems and methods may be implemented using a computing system or computing device. FIG. 1 depicts a simplified block diagram of the system for implementing the computer-aided method described herein. As illustrated in FIG. 1 , the computing device 300 may be configured to implement at least a portion of the tasks associated with the disclosed methods described herein. The computer system 300 may include a computing device 302. In one aspect, the computing device 302 is part of a server system 304, which also includes a database server 306. The computing device 302 is in communication with a database 308 through the database server 306. The computing device 302 is communicably coupled to a user computing device 330 and a patient record system 334 through a network 350. The network 350 may be any network that allows local area or wide area communication between the devices. For example, the network 350 may allow communicative coupling to the Internet through at least one of many interfaces including, but not limited to, at least one of a network, such as the Internet, a local area network (LAN), a wide area network (WAN), an integrated services digital network (ISDN), a dial-up-connection, a digital subscriber line (DSL), a cellular phone connection, and a cable modem. The user computing device 330 may be any device capable of accessing the Internet including, but not limited to, a desktop computer, a laptop computer, a personal digital assistant (PDA), a cellular phone, a smartphone, a tablet, a phablet, wearable electronics, smartwatch, or other web-based connectable equipment or mobile devices. The patient record system 334 may be any computing system or device containing stored patient records used in the disclosed systems and methods as described above.

[0038] In other aspects, the computing device 302 is configured to perform a plurality of tasks associated with the disclosed computer-aided methods of diagnosing peripheral arterial disease (PAD), predicting PAD patient prognosis, and selecting appropriate treatments for PAD patients. In some aspects, the computing device 302, user computing device 330, and / or patient record system 334 may be operatively connected via a network 350.

[0039] FIG. 2 depicts a component configuration 400 of computing device 402, which includes database 410 along with other related computing components. In some aspects, computing device 402 is similar to computing device 302 (shown in FIG. 1 ). A user 404 may access components of computing device 402. In some aspects, database 410 is similar to database 308 (shown in FIG. 1 ).

[0040] In one aspect, database 410 includes patient data 412, ML data 418, and GUI data 420. Patient data 412 may include patient clinical data received from the patient record system 334 of FIG. 1 . Non-limiting examples of patient data 412 include various measurements of traditional lipid profiles (total cholesterol, LDL, triglycerides), cardiovascular risk factors (smoking, diabetes, hypertension, age), and cFAS levels. ML data 418 may include data used to define the architecture and constants of the first and / or second multivariate logistic regression models used to implement the disclosed systems and methods described herein. GUI data 420 includes data used to implement various activities associated with user interfaces with the disclosed systems and methods including, but not limited to, specifying and uploading a patient dataset, formatting and displaying results such as classification of PAD status or prognosis at one or more timepoints, recommendations for treatments, and any other suitable GUI data without limitation.

[0041] Computing device 402 also includes a number of components that perform specific tasks associated with the implementation of the disclosed systems and methods. In an example aspect, computing device 402 includes a data storage device 430, a PAD classification component 440, a PAD prognosis component 450, and a communication component 460. The PAD classification component 440 is configured to implement the production of a patient’s classification of PAD seventy using the first multivariate logistic regression model as described herein. The PAD prognosis component 450 is configured to predict the patient’s prognosis at one or more time points using the second multivariate logistic regression model as described herein. The data storage device 430 is configured to store data received or generated by computing device 402, such as any of the data stored in database 410, patient clinical data received from patient record system 334, or any other outputs of processes implemented by any component of computing device 402.

[0042] The communication component 460 is configured to enable communications between computing device 402 and other devices (e.g. user computing device 330 shown in FIG. 1 ) over a network, such as a network 350 (shown in FIG. 1 ), or a plurality of network connections using predefined network protocols such as TCP / IP (Transmission Control Protocol / lnternet Protocol).

[0043] FIG. 3 depicts a configuration of a remote or user computing device 502, such as user computing device 330 (shown in FIG. 1 ). Computing device 502 may include a processor 505 for executing instructions. In some aspects, executable instructions may be stored in a memory area 510. Processor 505 may include one or more processing units (e.g., in a multi-core configuration). Memory area 510 may be any device allowing information such as executable instructions and / or other data to be stored and retrieved. Memory area 510 may include one or more computer-readable media.

[0044] Computing device 502 may also include at least one media output component 515 for presenting information to a user 501. Media output component 515 may be any component capable of conveying information to user 501. In some aspects, media output component 515 may include an output adapter, such as a video adapter and / or an audio adapter. An output adapter may be operatively coupled to processor 505 and operatively coupleable to an output device such as a display device (e.g., a liquid crystal display (LCD), organic light-emitting diode (OLED) display, cathode ray tube (CRT), or “electronic ink” display) or an audio output device (e.g., a speaker or headphones). In some aspects, media output component 515 may be configured to present an interactive user interface (e.g., a web browser or client application) to user 501 .

[0045] In some aspects, computing device 502 may include an input device 520 for receiving input from user 501 . Input device 520 may include, for example, a keyboard, a pointing device, a mouse, a stylus, a touch-sensitive panel (e.g., a touchpad or a touch screen), a camera, a gyroscope, an accelerometer, a position detector, and / or an audio input device. A single component such as a touch screen may function as both an output device of media output component 515 and input device 520.

[0046] Computing device 502 may also include a communication interface 525, which may be communicatively coupleable to a remote device. Communication interface 525 may include, for example, a wired or wireless network adapter or a wireless data transceiver for use with a mobile phone network (e.g., Global System for Mobile communications (GSM), 3G, 4G or Bluetooth) or other mobile data network (e.g., Worldwide Interoperability for Microwave Access (WIMAX)).

[0047] Stored in memory area 510 are, for example, computer-readable instructions for providing a user interface to user 501 via media output component 515 and, optionally, receiving and processing input from input device 520. A user interface may include, among other possibilities, a web browser and client application. Web browsers enable users 501 to display and interact with media and other information typically embedded on a web page or a website from a web server. A client application allows users 501 to interact with a server application associated with, for example, a vendor or business.

[0048] FIG. 4 illustrates an example configuration of a server system 602. Server system 602 may include, but is not limited to, database server 306 and computing device 302 (both shown in FIG. 1 ). In some aspects, server system 602 is similar to server system 304 (shown in FIG. 1 ). Server system 602 may include a processor 605 for executing instructions. Instructions may be stored in a memory area 625, for example. Processor 605 may include one or more processing units (e.g., in a multi-core configuration).

[0049] Processor 605 may be operatively coupled to a communication interface 615 such that server system 602 may be capable of communicating with a remote device such as user computing device 330 (shown in FIG. 1 ) or another server system 602. For example, communication interface 615 may receive requests from a user computing device 330 via a network 350 (shown in FIG. 1 ).

[0050] Processor 605 may also be operatively coupled to a storage device 625. Storage device 625 may be any computer-operated hardware suitable for storing and / or retrieving data. In some aspects, storage device 625 may be integrated into server system 602. For example, server system 602 may include one or more hard disk drives as storage device 625. In other aspects, storage device 625 may be external to server system 602 and may be accessed by a plurality of server systems 602. For example, storage device 625 may include multiple storage units such as hard disks or solid-state disks in a redundant array of inexpensive disks (RAID) configuration. Storage device 625 may include a storage area network (SAN) and / or a network attached storage (NAS) system.

[0051] In some aspects, processor 605 may be operatively coupled to storage device 625 via a storage interface 620. Storage interface 620 may be any component capable of providing processor 605 with access to storage device 625. Storage interface 620 may include, for example, an Advanced Technology Attachment (ATA) adapter, a Serial ATA (SATA) adapter, a Small Computer System Interface (SCSI) adapter, a RAID controller, a SAN adapter, a network adapter, and / or any component providing processor 605 with access to storage device 625.

[0052] Memory areas 510 (shown in FIG. 3) and 610 may include, but are not limited to, random access memory (RAM) such as dynamic RAM (DRAM) or static RAM (SRAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), and non-volatile RAM (NVRAM). The above memory types are examples only and are thus not limiting as to the types of memory usable for the storage of a computer program.

[0053] The computer systems and computer-aided methods discussed herein may include additional, less, or alternate actions and / or functionalities, including those discussed elsewhere herein. The computer systems may include or be implemented via computer-executable instructions stored on non-transitory computer-readable media. The methods may be implemented via one or more local or remote processors, transceivers, servers, and / or sensors (such as processors, transceivers, servers, and / or sensors mounted on vehicle or mobile devices, or associated with smart infrastructure or remote servers), and / or via computer-executable instructions stored on non-transitory computer-readable media or medium.

[0054] The methods and algorithms of the disclosure may be enclosed in a controller or processor. Furthermore, methods and algorithms of the present disclosure, can be embodied as a computer-implemented method or methods for performing such computer-implemented method or methods, and can also be embodied in the form of a tangible or non-transitory computer-readable storage medium containing a computer program or other machine-readable instructions (herein “computer program”), wherein when the computer program is loaded into a computer or other processor (herein “computer”) and / or is executed by the computer, the computer becomes an apparatus for practicing the method or methods. Storage media for containing such computer programs include, for example, floppy disks and diskettes, compact disk (CD)-ROMs (whether or not writeable), DVD digital disks, RAM and ROM memories, computer hard drives and backup drives, external hard drives, “thumb” drives, and any other storage medium readable by a computer. The method or methods can also be embodied in the form of a computer program, for example, whether stored in a storage medium or transmitted over a transmission medium such as electrical conductors, fiber optics or other light conductors, or by electromagnetic radiation, wherein when the computer program is loaded into a computer and / or is executed by the computer, the computer becomes an apparatus for practicing the method or methods. The method or methods may be implemented on a general-purpose microprocessor or on a digital processor specifically configured to practice the process or processes. When a general-purpose microprocessor is employed, the computer program code configures the circuitry of the microprocessor to create specific logic circuit arrangements. Storage medium readable by a computer includes medium being readable by a computer per se or by another machine that reads the computer instructions for providing those instructions to a computer for controlling its operation. Such machines may include, for example, machines for reading the storage media mentioned above.

[0055] In some aspects, a computing device is configured to implement machine learning, such that the computing device “learns” to analyze, organize, and / or process data without being explicitly programmed. Machine learning may be implemented through machine learning (ML) methods and algorithms. In one aspect, a machine learning (ML) module is configured to implement ML methods and algorithms. In some aspects, ML methods and algorithms are applied to data inputs and generate machine learning (ML) outputs. Data inputs may include but are not limited to images or frames of a video, object characteristics, and object categorizations. Data inputs may further include sensor data, image data, video data, telematics data, authentication data, authorization data, security data, mobile device data, geolocation information, transaction data, personal identification data, financial data, usage data, weather pattern data, “big data” sets, and / or user preference data. ML outputs may include but are not limited to: a tracked shape output, categorization of an object, categorization of a region within a medical image (segmentation), categorization of a type of motion, a diagnosis based on the motion of an object, motion analysis of an object, and trained model parameters ML outputs may further include: speech recognition, image or video recognition, medical diagnoses, statistical or financial models, autonomous vehicle decisionmaking models, robotics behavior modeling, fraud detection analysis, user recommendations and personalization, game Al, skill acquisition, targeted marketing, big data visualization, weather forecasting, and / or information extracted about a computer device, a user, a home, a vehicle, or a party of a transaction. In some aspects, data inputs may include certain ML outputs.

[0056] Although the disclosed systems and methods are described herein in terms of analysis of patient clinical data using multivariate logistic regression models, with suitable modifications, the disclosed systems and methods may be implemented using any suitable machine learning method and / or algorithm without limitation. In some aspects, at least one of a plurality of ML methods and algorithms may be applied, which may include but are not limited to: genetic algorithms, linear or logistic regressions, instance-based algorithms, regularization algorithms, decision trees, Bayesian networks, cluster analysis, association rule learning, artificial neural networks, deep learning, dimensionality reduction, and support vector machines. In various aspects, the implemented ML methods and algorithms are directed toward at least one of a plurality of categorizations of machine learning, such as supervised learning, unsupervised learning, adversarial learning, and reinforcement learning.

[0057] A control sample or a reference sample as described herein can be a sample from a healthy subject. A reference value can be used in place of a control or reference sample, which was previously obtained from a healthy subject or a group of healthy subjects. A control sample or a reference sample can also be a sample with a known amount of a detectable compound or a spiked sample.

[0058] Compositions and methods described herein utilizing molecular biology protocols can be according to a variety of standard techniques known to the art (see e.g., Sambrook and Russel (2006) Condensed Protocols from Molecular Cloning: A Laboratory Manual, Cold Spring Harbor Laboratory Press, ISBN-10: 0879697717; Ausubel et al. (2002) Short Protocols in Molecular Biology, 5th ed., Current Protocols, ISBN-10: 0471250929; Sambrook and Russel (2001 ) Molecular Cloning: A Laboratory Manual, 3d ed., Cold Spring Harbor Laboratory Press, ISBN-10: 0879695773; Elhai, J. and Wolk, C. P. 1988. Methods in Enzymology 167, 747-754; Studier (2005) Protein Expr Purif. 41 (1 ), 207-234; Gellissen, ed. (2005) Production of Recombinant Proteins: Novel Microbial and Eukaryotic Expression Systems, Wiley-VCH, ISBN-10: 3527310363; Baneyx (2004) Protein Expression Technologies, Taylor & Francis, ISBN-10: 0954523253).

[0059] Definitions and methods described herein are provided to better define the present disclosure and to guide those of ordinary skill in the art in the practice of the present disclosure. Unless otherwise noted, terms are to be understood according to conventional usage by those of ordinary skill in the relevant art.

[0060] In some embodiments, numbers expressing quantities of ingredients, properties such as molecular weight, reaction conditions, and so forth, used to describe and claim certain embodiments of the present disclosure are to be understood as being modified in some instances by the term “about.” In some embodiments, the term “about” is used to indicate that a value includes the standard deviation of the mean for the device or method being employed to determine the value. In some embodiments, the numerical parameters set forth in the written description and attached claims are approximations that can vary depending upon the desired properties sought to be obtained by a particular embodiment. In some embodiments, the numerical parameters should be construed in light of the number of reported significant digits and by applying ordinary rounding techniques. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of some embodiments of the present disclosure are approximations, the numerical values set forth in the specific examples are reported as precisely as practicable. The numerical values presented in some embodiments of the present disclosure may contain certain errors necessarily resulting from the standard deviation found in their respective testing measurements. The recitation of ranges of values herein is merely intended to serve as a shorthand method of referring individually to each separate value falling within the range. Unless otherwise indicated herein, each individual value is incorporated into the specification as if it were individually recited herein. The recitation of discrete values is understood to include ranges between each value.

[0061] In some embodiments, the terms “a” and “an” and “the” and similar references used in the context of describing a particular embodiment (especially in the context of certain of the following claims) can be construed to cover both the singular and the plural, unless specifically noted otherwise. In some embodiments, the term “or” as used herein, including the claims, is used to mean “and / or” unless explicitly indicated to refer to alternatives only or the alternatives are mutually exclusive.

[0062] The terms “comprise,” “have” and “include” are open-ended linking verbs. Any forms or tenses of one or more of these verbs, such as “comprises,” “comprising,” “has,” “having,” “includes” and “including,” are also open-ended. For example, any method that “comprises,” “has” or “includes” one or more steps is not limited to possessing only those one or more steps and can also cover other unlisted steps. Similarly, any composition or device that “comprises,” “has” or “includes” one or more features is not limited to possessing only those one or more features and can cover other unlisted features.

[0063] All methods described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The use of any and all examples, or exemplary language (e.g., “such as”) provided with respect to certain embodiments herein is intended merely to better illuminate the present disclosure and does not pose a limitation on the scope of the present disclosure otherwise claimed. No language in the specification should be construed as indicating any non-claimed element essential to the practice of the present disclosure.

[0064] Groupings of alternative elements or embodiments of the present disclosure disclosed herein are not to be construed as limitations. Each group member can be referred to and claimed individually or in any combination with other members of the group or other elements found herein. One or more members of a group can be included in, or deleted from, a group for reasons of convenience or patentability. When any such inclusion or deletion occurs, the specification is herein deemed to contain the group as modified thus fulfilling the written description of all Markush groups used in the appended claims.

[0065] All publications, patents, patent applications, and other references cited in this application are incorporated herein by reference in their entirety for all purposes to the same extent as if each individual publication, patent, patent application or other reference was specifically and individually indicated to be incorporated by reference in its entirety for all purposes. Citation of a reference herein shall not be construed as an admission that such is prior art to the present disclosure.

[0066] Having described the present disclosure in detail, it will be apparent that modifications, variations, and equivalent embodiments are possible without departing the scope of the present disclosure defined in the appended claims. Furthermore, it should be appreciated that all examples in the present disclosure are provided as non-limiting examples.

[0067] EXAMPLES

[0068] The following non-limiting examples are provided to further illustrate the present disclosure. It should be appreciated by those of skill in the art that the techniques disclosed in the examples that follow represent approaches the inventors have found function well in the practice of the present disclosure, and thus can be considered to constitute examples of modes for its practice. However, those of skill in the art should, in light of the present disclosure, appreciate that many changes can be made in the specific embodiments that are disclosed and still obtain a like or similar result without departing from the spirit and scope of the present disclosure.

[0069] EXAMPLE 1 - SERUM CFAS CONTENT CORRELATES WITH INCIDENCE OF PERIPHERAL ARTERIAL DISEASE

[0070] To characterize cFAS as a clinical biomarker for classifying PAD and CLTI seventy and predicting patient prognosis, the following experiments were conducted. Patients with / without PAD and CLTI were retrospectively reviewed. Total serum cFAS content was evaluated using ELISA and normalized to total protein. Patient demographics and PAD incidence were collected via chart review. Serum cFAS and demographics were compared, and regression analysis was used to determine the correlation between cFAS and PAD incidence, and the impact of co-morbidities on cFAS content. Results indicate optimal cutoffs for cFAS in distinguishing between individuals with and without PAD or CLTI. This study demonstrates that cFAS is an independent serum-based diagnostic biomarker for PAD, can distinguish between patients with PAD versus CLTI, and may predict disease severity. METHODS

[0071] Patient Cohort

[0072] A retrospective review of individuals who participated in the vascular biobank over a 9-year period (2014-2023) was conducted. Participants were categorized as healthy controls without PAD, individuals with PAD, or individuals with CLTI, based on the ABI and Rutherford score (Conte et al., Eur J Vase Endovac Surg, 2019, 58(1 S), S1-S109 e33; Rutherford et al., J Vase Surg, 1997, 26(3), 517-538). Control participants were screened by detailed clinical history and bilateral ABI measurement. Only individuals with ABI > 0.90 in both limbs and Rutherford class 0 were included. Patients were excluded if they had been included in prior published studies or had a history of stage 4 or 5 chronic kidney disease (CKD), alcohol abuse, or advanced liver disease (Fig. 5). Demographic data collected included age at the time of serum sampling, sex, body mass index (BMI), race / ethnicity, and smoking status (prior / current). Medical history, medication use, and laboratory values were obtained from clinical chart reviews. To calculate the Framingham Risk Score (FRS) (Ankle et al., JAMA, 2008, 300(2), 197-208), available patient demographics were entered into the 2018 Prevention Guidelines CV Risk Calculator (Arnett et al., Circulation, 2019, 140(11 ), e563- e595; Calculator PGTCR, 2018 Prevention Guidelines Tool CV Risk Calculator, static.heart.org / riskcalc / app / index.html). Patient values outside the calculator’s parameters were rounded to the nearest valid value (e.g., age <40 was rounded up to 40, and triglyceride (TG) <130 was rounded up to 130) (Hirsch et al., JAMA, 2001 , 286(11 ), 1317-1324).

[0073] Blood Collection and Processing

[0074] Intravenous whole blood samples were collected from consenting individuals who were fasting for at least 6 hours prior to a planned elective surgery. As previously described, whole blood samples were collected in red-topped and green-topped vacutainer tubes, and immediately processed in the laboratory with centrifugation to isolate serum and plasma components (Meade et al., JVS Vase Sci, 2023, 4, 100181 ). Serum and plasma were then aliquoted into 100 pL fractions and stored at -80°C for future analytical use. Serum and Plasma Analysis

[0075] As previously described, serum aliquots were used to measure cFAS with a commercially available ELISA (Aviva Systems Biology, San Diego, CA) (De Silva et al., Atherosclerosis, 2019, 287, 38-45; Tay et al., Sci Rep, 2021 , 11 (1 ), 19272; Meade et al., Communications Biology, 2025, 8, 262). To account for variations in the duration of fasting prior to surgery, total protein levels were determined via Bradford assay and used to normalize serum cFAS concentrations. Plasma samples were analyzed at the Washington University Diabetes Research Center (DRC) Core Laboratory for Clinical Studies (CLCS) for measurement of total cholesterol (TC), TG, direct high-density lipoprotein (HDL), and LDL.

[0076] Statistical Analysis

[0077] Receiver-operating characteristic (ROC) analysis is a statistical tool used to assess the diagnostic performance of a biomarker by calculating the area under the curve (AUC), which represents the measure of the ability of the test to correctly classify individuals as having or not having a disease. ROC analyses were conducted to determine the optimal cutoff points for circulating cFAS levels in distinguishing between different groups of patients: those who are normal, those with PAD, and those with CLTI. Multivariable regressions were built to measure the independent effect of cFAS threshold on patient group classifications. Candidate variables with univariable p<0.15 entered stepwise logistic regression optimizing AIC (Akaike Information Criterion) / BIC (Bayesian Information Criterion). Models with best AIC and BIC were selected. Chi-square test or Fisher's exact test was utilized for categorical variables. Continuous variables were analyzed with two- sided t-test if normally distributed and Mann-Whitney U test if non-Gaussian. Categorical variables are represented as a number (percentage). All statistical analyses were performed using the R software (version 4.3.1 ).

[0078] RESULTS

[0079] Differences between Study Groups

[0080] Of the 1081 patients reviewed in the vascular biobank, a total of 347 patients met the inclusion criteria (Fig 5). Of these, 34 (9.8%) were healthy controls with no PAD, 164 (47.3%) had PAD, and 149 (42.9%) had CLTI (Fig 6). Mean cFAS values were 0.21 ±0.28, 0.56 ±0.70, and 0.61 ±0.70 pg / mg in controls, PAD, and CLTI, respectively (p<0.01 ). cFAS correlated inversely with ABI (p=-0.22, p<0.001 ) and directly with Rutherford score (p=0.18, p<0.001 ). The normal group had a significantly younger mean age of 26.2 years (±5.4) compared to the PAD group at 64.8 years (±10.2) and the CLTI group at 63.4 years (±10.6) (p<0.001 ). The BMI was numerically higher in the PAD group (28.6 ±5.9) and CLTI group (27.4 ±6.5) compared to the No PAD group (26.7 ±5.8, p=0.120). Gender distribution revealed a higher proportion of males in the PAD (64.6%) and CLTI (67.8%) groups compared to the No PAD group (41 .2%, p=0.016). Most notably, cFAS levels were significantly elevated in the PAD group (560 pg / mg ± 680) and the CLTI group (610 pg / mg ± 740) compared to the No PAD group (210 pg / mg ± 280, p=0.007; Fig 6, Tables 1-2).

[0081] Subgroup analyses demonstrated no significant effect of statin therapy (p=0.860), daily aspirin (p=0.412), insulin therapy (p=0.226), coronary artery disease history (p=0.483), or asymptomatic carotid stenosis (p=0.569) on serum cFAS. Adjusted models including these covariates yielded an unchanged cFAS- PAD odds ratio. cFAS did not differ between patients with asymptomatic carotid stenosis and those without (p=0.569), suggesting that lower-extremity PAD seventy is the primary determinant of cFAS elevation in this cohort. Other notable findings observed between groups includes differences in total cholesterol (No PAD 163.4 ± 38.5 vs PAD 148.0 ± 45.2 vs CLTI 138.9 ± 42.3, p=0.008), triglycerides (No PAD 87.1 ± 41 .7 vs PAD 151 .2 ± 99.3 vs CLTI 148.9 ± 97.1 , p=0.001 ), LDL (No PAD 99.3 ± 32.2 vs PAD 82.1 ± 35.9 vs CLTI 77.4 ± 34.6, p=0.005), HDL (No PAD 48.9 ± 11 .1 vs PAD 41 .4 ± 13.5 vs CLTI 38.4 ± 13.4, p<0.001 ), and Framingham Risk Score (No PAD 1 % ± 1 % vs PAD 25% ± 16% vs CLTI 21 % ± 13%, p<0.001 ). cFAS Differences between Study Groups

[0082] ROC analysis identified two critical cutoff points for serum cFAS levels. A serum cFAS level of >340 pg / mg was determined to be the optimal threshold for differentiating individuals without PAD from those with either PAD or CLTI. At this threshold, the ROC curve demonstrated a good AUC, with a true positive rate (TPR) of 52.4% and a false positive rate (FPR) of 20.06% for PAD or CLTI (Fig. 7). For distinguishing CLTI specifically, a higher cFAS cutoff of >490 pg / mg was found to be optimal, yielding a TPR of 49.0% and an FPR of 35.9% (Fig. 8).

[0083] Univariable analysis comparing individuals without PAD to those with PAD or CLTI indicated that a cFAS level of >340 pg / mg was associated with significantly higher odds of having PAD or CLTI, with an odds ratio (OR) of 0.13 (95% Cl: 0.07 to 0.19, p<0.001 ). This finding suggests that elevated cFAS levels strongly correlate with the presence of PAD or CLTI. In a multivariable model adjusted for factors including age, diabetes status, HDL cholesterol, renal insufficiency, and statin and aspirin use, the association remained significant with an OR of 0.05 (95% Cl: 0.01 to 0.09, p=0.015), reinforcing the independent relationship between elevated cFAS levels and PAD or CLTI.

[0084] In comparisons of individuals with no PAD or PAD, versus those with CLTI, the univariable model showed that a cFAS level of >490 pg / mg was associated with an odds ratio (OR) of 0.14 (95% Cl: 0.03 to 0.24, p=0.013). This suggested that individuals with cFAS levels above this threshold are more likely to have CLTI than those without CLTI. In the multivariable model, adjusting for relevant factors, the adjusted OR was 0.10 (95% Cl: -0.00 to 0.21 , p=0.055), indicating a trend towards significance and suggesting that elevated cFAS levels may also independently correlate with CLTI.

[0085] DISCUSSION

[0086] This study evaluated whether serum cFAS could serve as a biomarker for PAD across varying levels of disease seventy. The association between cFAS levels and PAD incidence was investigated adjusting for confounding factors such as age, sex, and comorbidities such as diabetes and smoking. ROC analysis revealed that serum cFAS levels were significantly associated with the presence of PAD and CLTI, highlighting its potential utility as a diagnostic marker. In this cohort of 347 tested patients, cFAS could identify PAD or CLTI (cutoff >340 pg / mg) with 52.4% sensitivity and 79.9% specificity. For identifying CLTI alone, a higher cutoff (>490 pg / mg) demonstrated a sensitivity of 49% and specificity of 64.1%. Serum cFAS at ~340 pg / mg may flag high-risk or equivocal-ABI patients for definitive evaluation. Among PAD patients, levels >490 pg / mg may identify those at highest risk of progression to CLTI, informing surveillance frequency and early intervention.

[0087] Recent studies support the association between serum cFAS levels and peripheral arterial disease beyond the coronary arteries (De Silva et al., Atherosclerosis, 2019, 287, 38-45; Tay et al., Sci Rep, 2021 , 11 (1 ), 19272; Meade et al., Communications Biology, 2025, 8, 262). For instance, elevated serum cFAS has been observed in patients with carotid artery stenosis, particularly those with concomitant diabetes (De Silva et al., Atherosclerosis, 2019, 287, 38-45). Immunoprecipitation studies have demonstrated that the 275 kDa cFAS protein associates with Apolipoprotein B (ApoB), the primary apolipoprotein in LDL particles (De Silva et al., Atherosclerosis, 2019, 287, 38-45). Conditional knockdown of the Fasn gene in the liver significantly reduces serum cFAS levels, as seen in Fasnfl / flApoe~~ mice, which also show reduced atherosclerotic plaque formation when maintained on a high-fat diet (Meade et al., Communications Biology, 2025, 8, 262). In humans, elevated serum cFAS has been linked with higher FAS and saturated fatty acid content in the peripheral arteries, contributing to macrophage foam cell formation and atherosclerosis progression (Tay et al., Sci Rep, 2021 , 11 (1 ), 19272; Meade et al., Communications Biology, 2025, 8, 262). These findings suggest that serum cFAS may serve as an indicator of atherosclerotic disease severity. In this current study it is further demonstrated that cFAS levels are elevated in patients with confirmed PAD and reach the highest levels in those with CLTI.

[0088] This study deliberately excluded serum samples from patients included in previous publications to provide a new and independent assessment of cFAS as a marker for PAD (De Silva et al., Atherosclerosis, 2019, 287, 38-45; Tay et al., Sci Rep, 2021 , 11 (1 ), 19272). In the current multivariable model, cFAS maintained its association with PAD and CLTI independent of other traditional vascular disease risk factors, building on earlier pilot studies and suggesting that cFAS may predict PAD disease risk better than LDL or ABI alone (Tay et al., Sci Rep, 2021 , 11 (1 ), 19272). Other studies have proposed that markers of fatty acid synthesis, such as saturated fatty acids, actively contribute to atherosclerotic disease progression beyond simple LDL risk stratification (Wei et al., Nature, 2016, 539(7628), 294- 298; Bogan et al., Cells, 2024, 13(8); Rocha et al., Atherosclerosis, 2016, 244, 211-215). Although the association between cFAS and PAD severity did not reach statistical significance at the higher threshold for CLTI, the observed trend suggests that cFAS could be valuable for identifying advanced disease stages in larger studies. This aligns with evidence indicating that CLTI encompasses a spectrum of end-stage PAD complications, including rest pain, non-healing wounds, tissue necrosis, and gangrene (Gerhard-Herman et al., Circulation, 2017, 135(12), e726-e779; Conte et al., Eur J Vase Endovasc Surg, 2019, 58(1 S), SI- 8109 e33). Due to the limitations of the sample size, the CLTI cases were not stratified beyond Rutherford Class and did not base the assessments on anatomical disease seventy or differentiate between atherosclerotic or thrombotic occlusions. Future studies should address the capacity of cFAS to provide a more nuanced diagnostic signal in patients with varying CLTI seventies due to atherosclerosis.

[0089] The 2019 ASCVD guidelines reinforced LDL as a primary marker for cardiovascular risk assessment, largely based on studies showing reduced cardiovascular events in patients with lower LDL levels or those on statin therapy (Arnett et al., Circulation, 2019, 140(11 ), e563-e595). Initially developed by the American College of Cardiology (ACC) and American Heart Association (AHA) in 2013 (Stone et al., J Am Coll Cardiol, 2014, 63(25 Pt B), 2889-2934), these guidelines have since expanded to include a broader range of vasculopathies, including PAD and its complications. In the absence of a PAD-specific biomarker, LDL and AB I are frequently used as surrogate indicators of disease risk (Khan et al., Curr Cardio Rev, 2008, 4(2), 101-106; Ankle et al., JAMA, 2008, 300(2), 197- 208; Niazi et al., Catheter Cardiovasc Interv, 2006, 68(5), 788-792). However, large-scale studies consistently show significant underdiagnosis of PAD, particularly among asymptomatic individuals and those with atypical symptoms (Hirsch et al., JAMA, 2001 , 286(11 ), 1317-1324; Ohman et al., Am Heart J, 2006, 151 (4), 786, e1-10). For example, both the REACH Registry and the PARTNERS study reported that conventional screening measures failed to identify PAD in approximately 25% to 50% of cases (Hirsch et al., JAMA, 2001 , 286(11 ), 1317- 1324; Ohman et al., Am Heart J, 2006, 151 (4), 786, e1 -10), underscoring the need for more reliable diagnostic modalities in current clinical practice.

[0090] Our study showed that LDL did not correlate with the presence of PAD or CLTI. In fact, total cholesterol and LDL levels were generally lower among patients with PAD and CLTI compared to those without PAD, likely due to the use of cholesterol-lowering medications such as statins. Current AHA / ACC guidelines recommend LDL as an indicator for atherosclerosis and a trigger for statin therapy, alongside ABI for PAD screening (Arnett et al., Circulation, 2019, 140(11 ), e563- e595). However, large-scale randomized controlled trials demonstrating LDL as a predictor for PAD are limited, and some studies suggest that LDL may not be a strong determinant of cardiovascular risk in specific populations, such as women (Arnett et al., Circulation, 2019, 140(11 ), e563-e595; Erqou et al., JAMA, 2009, 302(4), 412-423; Kamstrup et al., JAMA, 2009, 301 (22), 2331-2339; Tsimikas et al., N Engl J Med, 2020, 383(3), 244-255). This study found that cFAS was equally diagnostic in men and women, with sex not significantly influencing cFAS levels.

[0091] All participants in this study underwent an ABI test as the gold standard for diagnosing PAD and CLTI. The ACC / AHA guidelines reference (Feigelson et al., Am J Epidemiol, 1994, 140(6), 526-534) which rigorously assessed ABI for PAD screening, noting an ABI <0.8 had a 39% sensitivity and 70% specificity for detecting PAD. Other studies have similarly shown variability in ABI sensitivity, depending on whether the ABI is high or low, and affected by operator expertise (Khan et al., Curr Cardio Rev, 2008, 4(2), 101-106; Ankle et al., JAMA, 2008, 300(2), 197-208; Niazi et al., Catheter Cardiovasc Interv, 2006, 68(5), 788-792; Schroder et al., J Vase Surg, 2006, 44(3), 531 -536). Due to these limitations, the USPSTF does not currently endorse ABI testing for PAD screening, and the ABI is not reimbursed by CMS for asymptomatic patients (www.uspreventiveservicestaskforce.org). In contrast, a serum biomarker like cFAS, which has comparable sensitivity and specificity and requires only a small volume blood sample, could be accessible to primary care providers and has the potential identify patients with PAD.

Claims

ClaimsWhat is claimed is:1 . A computer-implemented method to produce a classification of peripheral arterial disease (PAD) seventy in a patient, the method comprising: a. receiving, at a computing device, a patient clinical dataset comprising a plurality of patient clinical data obtained from the patient; and b. transforming, using the computing device, the patient clinical dataset into the classification of patient PAD severity with a first multivariate logistic regression model.

2. The method of claim 1 , further comprising displaying, using the computing device, the classification of patient PAD seventy to a practitioner.

3. The method of any preceding claim, further comprising transforming, using the computing device, the patient clinical dataset and the classification of patient PAD severity into a predicted prognosis of the patient at one or more timepoints with a second multivariate logistic regression model.

4. The method of any preceding claim, further comprising displaying, using the computing device, the predicted prognosis of the patient at one or more timepoints to the practitioner.

5. The method of any preceding claim, further comprising a. identifying, using the computing device, a recommended treatment for the patient based on the classification of patient PAD seventy, the predicted prognosis of the patient at one or more timepoints, and any combination thereof; and b. displaying, using the computing device, the recommended treatment for the patient to the practitioner.

6. The method of any preceding claim, wherein the patient’s clinical dataset comprises at least one of traditional lipid profiles (total cholesterol, LDL,triglycerides), and cardiovascular risk factors (smoking, diabetes, hypertension, age), and cFAS levels.

7. The method of any preceding claim, wherein the classification of patient PAD seventy is selected from PAD not indicated, sub-clinical PAD, and advanced PAD.

8. The method of any preceding claim, wherein the predicted prognosis of the patient at one or more timepoints comprise a likelihood of advanced PAD onset, a likelihood of CLTI onset, a likelihood of response to risk factor modification, a likelihood of response to aggressive surgical intervention, a likelihood of end-stage clinical status, and any combination thereof.

9. The method of any preceding claim, wherein the predicted prognosis of the patient at one or more timepoints comprises predicted prognosis of the patient at a timepoint ranging from about 1 month to about 1 year after an initial classification of patient PAD seventy.

10. The method of any preceding claim, wherein the recommended treatment for the patient is selected from continued monitoring, risk factor modification, aggressive surgical intervention, palliative care, and any combination thereof.11 .A computer-implemented method for predicting peripheral arterial disease (PAD) severity in a patient, the method comprising: a. receiving, at a user interface, a plurality of parameters associated with PAD of the patient, wherein the plurality of parameters associated with PAD of the patient comprise lipid profiles, cardiovascular risk factors, and cFAS levels; b. applying one or more inputs to a supervised machine learning model, the one or more inputs comprising the plurality of parameters associated with PAD of the patient, the model being previously trained using historical data, the historical data comprising PAD parameters associated with PAD and their corresponding patient response to PAD;c. receiving one or more outputs from the model, at least one of the one or more outputs including a predicted patient response to PAD; d. transmitting, for display on the user interface, the one or more outputs from the model; e. updating the historical data to include the plurality of parameters associated with PAD of the patient and the corresponding one or more outputs; and f. re-training the model using the updated historical data.

12. The method of claim 11 , wherein the lipid profiles are selected from the group consisting of total cholesterol, LDL, triglycerides, or any combination thereof.

13. The method of claim 11 , wherein the cardiovascular risk factors are selected from the group consisting of smoking, diabetes, hypertension, age, and any combination thereof.

14. A system for predicting peripheral arterial disease (PAD) severity in a patient, the system comprising: at least one memory storing computer-executable instructions; and at least one processor in communication with the at least one memory, wherein the at least one processor is configured to execute the computer-executable instructions to: a. receive a plurality of parameters associated with PAD of the patient, wherein the plurality of parameters associated with PAD of the patient comprise lipid profiles, cardiovascular risk factors, and cFAS levels; b. apply one or more inputs to a supervised machine learning model, the one or more inputs comprising the plurality of parameters associated with PAD of the patient, the model being previously trained using historical data, the historical data comprising PAD parameters associated with PAD and their corresponding patient response to PAD;c. receive one or more outputs from the model, at least one of the one or more outputs including a predicted patient response to PAD; d. display, on a user interface, the one or more outputs from the model; update the historical data to include the plurality of parameters associated with PAD of the patient and the corresponding one or more outputs; and re-train the model using the updated historical data.

15. The system of claim 14, wherein the lipid profiles are selected from the group consisting of total cholesterol, LDL, triglycerides, or any combination thereof.

16. The system of claim 14, wherein the cardiovascular risk factors are selected from the group consisting of smoking, diabetes, hypertension, age, and any combination thereof.

Images