An AI-driven system for detecting and predicting diabetic foot complications in early stages

Abstract

A system for detecting and predicting diabetic foot complications, consisting of: an input and storage module configured to capture foot images of a patient, capture data on the patient's medical history, and capture assessments of the patient's physiological symptoms, wherein the data is captured via a user interface that allows the user to interact with the system, and wherein the captured data is stored in a storage unit; a centralized processing module comprising an intelligent processor integrated with a memory and a graphics processing unit, wherein the intelligent processor of the centralized processing unit is configured to preprocess the data collected by the input and memory module, analyze the data, and make predictions based on the data, wherein the intelligent processor comprises: a preprocessing sub-module configured to enhance, normalize, and segment the foot images, annotate features in the foot images, detect certain foot abnormalities using a deep learning detection module, and convert the medical history data and physiological symptom assessments into a standardized format; and an analysis and prediction sub-module configured to generate a visual feature score based on a weighted analysis of detected foot abnormalities, to generate a patient history score based on a weighted analysis of medical history data, to generate a physiological symptom score based on a weighted analysis of physiological symptom ratings, and to calculate a comprehensive diabetic foot score by integrating the visual feature score, the patient history score, and the physiological symptom score; an output processing module operatively connected to the centralized processing module and comprising a visualization and recommendation sub-module configured to: classify the patient into a risk category based on the comprehensive diabetic foot score generated by the analysis and prediction sub-module; generate personalized recommendations based on the classified risk category; and provide the patient and Provide healthcare providers with a detailed report via the user interface; a communication interface configured to facilitate data transfer between different modules of the system; and a display operatively connected to the user interface and showing the input capture interface, the processing interface, and the generated detailed report display interface.

Description

FIELD OF THE INVENTION

[0001] The present disclosure relates to an AI-driven system for early detection and prediction of diabetic foot complications. More specifically, the present invention relates to an intelligent system for early detection and prediction of diabetic foot complications. The system is configured to predict diabetic foot complications by generating a diabetic foot score before the final amputation stage is reached. The system utilizes patient history, physiological symptoms, and visual changes to generate the final score that predicts the diabetic foot complication. BACKGROUND OF THE INVENTION

[0002] Diabetes mellitus (DM) is a widespread chronic metabolic disease affecting approximately 451 million people worldwide. India is the second most affected country after China, with 77 million cases. Among the serious complications of diabetes, diabetic foot complications (DFC) pose a significant challenge to healthcare systems and patients' quality of life.

[0003] DFC encompasses a range of conditions, including neuropathies, calluses, circulatory disorders, and foot ulcers resulting from ischemia, neuropathy, and vascular damage. These complications contribute significantly to morbidity and mortality, leading to infections, ulcers, and gangrene. The financial burden is significant: patients with diabetic foot spend approximately 32.3% of their total income on foot treatments, compared to 9.3% for diabetics without foot complications.

[0004] Early detection of diabetic foot complications is crucial. Studies suggest that up to 80% of diabetic foot ulcers (DFUs) could be prevented through timely intervention. While various technologies, such as thermography, have shown promise for early detection, they remain prohibitively expensive for comprehensive self-monitoring.

[0005] Recent advances in artificial intelligence have demonstrated high accuracy (sensitivity and specificity >0.9) for automated DFU detection in experimental settings. However, existing solutions often focus on single-factor analysis rather than considering the multiple aspects that clinicians consider during clinical assessment.

[0006] In light of the foregoing discussion, there is a need to address the problem of existing solutions for DFU detection. The present invention proposes an AI-driven system that mimics real-life medical diagnosis by integrating patient history, physiological symptoms, and visual assessment. By combining these critical factors, the invention creates a comprehensive and accessible solution for early detection and risk stratification of diabetic foot complications. This could reduce amputation rates and improve the quality of life of diabetics worldwide. Summary of the invention

[0007] The present disclosure relates to an AI-supported system for the early detection and prognosis of diabetic foot complications. The proposed AI-based system is configured to mimic real-life medical diagnosis. It utilizes computer vision techniques, patient history, and physiological symptoms from captured images to assess diabetic foot complications. The system is configured to detect diabetic foot complications early, assess risk tolerance, and proactively intervene. This enables early, accurate diagnosis of the diabetic foot. The system uses artificial intelligence to calculate a diabetic foot score, taking into account foot images, history data, and self-reported symptom ratings.The diabetic foot score helps classify risk levels and offers personalized remedies, preventative measures, self-care recommendations, and a warning for immediate medical intervention.

[0008] One objective of the present disclosure is to provide an AI-driven system for the early detection and prediction of diabetic foot complications. The system includes an input and storage module for acquiring a patient's foot images, collecting patient medical history data, and collecting the patient's physiological symptom assessments. Data acquisition is performed via a user interface that allows the user to interact with the system, and the acquired data is stored in a storage unit. A central processing module with an intelligent processor, integrated with a memory and a graphics processing unit, preprocesses the data acquired by the input and storage module, analyzes it, and makes predictions based on it.The intelligent processor includes: a preprocessing submodule for enhancing, normalizing, and segmenting the foot images; annotating features in the foot images; detecting specific foot abnormalities using a deep learning detection module; and structuring the medical history data and physiological symptom scores into a standardized format. An analysis and prediction submodule for generating a visual feature score based on a weighted analysis of the detected foot abnormalities; generating a patient history score based on a weighted analysis of the medical history data; generating a physiological symptom score based on a weighted analysis of the physiological symptom scores; and calculating a comprehensive diabetic foot score by integrating the visual feature score, the patient history score, and the physiological symptom score.The system further comprises: an output processing module operatively connected to the centralized processing module and comprising a visualization and recommendation sub-module configured to: classify the patient into a risk category based on the comprehensive diabetic foot score generated by the analysis and prediction sub-module; generate personalized recommendations based on the classified risk category; and provide a detailed report to the patient and the healthcare provider via the user interface; a communication interface configured to facilitate data transfer between different modules of the system; and a display operatively connected to the user interface and displaying the input capture interface, the processing interface, and the interface for displaying the generated detailed report.

[0009] One objective of the present disclosure is to provide an AI-driven system that can detect and predict complications of the diabetic foot at an early stage.

[0010] Another objective of the present disclosure is to develop an AI-driven architecture that integrates visual assessment, patient history, and physiological symptoms for the early detection of diabetic foot complications.

[0011] Another objective of this disclosure is to create a risk stratification system that generates a comprehensive Diabetic Foot Score to classify patients according to their likelihood of developing serious foot complications.

[0012] Another objective of this disclosure is to provide personalized recommendations and intervention strategies based on risk classification to prevent the progression of serious complications such as amputation.

[0013] Another objective of this disclosure is to bridge the gap between patients and timely diagnosis by creating an accessible tool that reflects clinical diagnostic processes.

[0014] To further clarify the advantages and features of the present disclosure, the invention will be explained in more detail with reference to specific embodiments illustrated in the accompanying drawings. These drawings illustrate only typical embodiments of the invention and are therefore not to be considered as limiting its scope. The invention will be described and explained in more detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE CHARACTERS

[0015] These and other features, aspects, and advantages of the present disclosure will become better understood when the following detailed description is read with reference to the accompanying drawings, in which like characters represent like parts throughout. Fig. 1 shows a block diagram of an AI-driven system for detecting and predicting early-stage diabetic foot complications according to an embodiment of the present disclosure; and Fig. 2 shows a diagram illustrating the architecture of the proposed AI-driven system for detecting diabetic foot complications according to an embodiment of the present disclosure.

[0016] Those skilled in the art will also appreciate that the elements in the drawings are shown for convenience and are not necessarily to scale. For example, the flowcharts illustrate the method by key steps to enhance understanding of aspects of the present disclosure. Furthermore, with respect to device construction, one or more components of the device may be represented in the drawings by conventional symbols. The drawings may show only the specific details relevant to understanding embodiments of the present disclosure in order not to clutter the drawings with details that would be readily apparent to those skilled in the art from the present description. DETAILED DESCRIPTION:

[0017] To facilitate an understanding of the principles of the invention, reference will now be made to the embodiment illustrated in the drawings and a clear description thereof. However, the scope of the invention is not limited thereby. Changes and further modifications to the illustrated system, as well as further applications of the principles of the invention, are possible, as would normally occur to one skilled in the art to which the invention pertains.

[0018] It will be understood by those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the invention and are not intended to be limiting thereof.

[0019] References in this specification to "one aspect," "another aspect," or similar language mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Therefore, the language "in one embodiment," "in another embodiment," and similar language throughout this specification may or may not refer to the same embodiment.

[0020] The terms "comprises," "comprising," or other variations thereof are intended to cover non-exclusive inclusion, such that a process or method comprising a list of steps may include not only those steps, but also additional steps not expressly listed or inherent in that process or method. Likewise, the statement "comprises" for one or more devices, subsystems, elements, structures, or components does not exclude, without further limitation, the existence of other devices, subsystems, elements, structures, components, or additional devices, subsystems, elements, structures, or components.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the invention pertains. The systems, methods, and examples provided herein are for illustrative purposes only and should not be considered limiting.

[0022] Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0023] The functional units described in this specification are referred to as devices. A device may be implemented in programmable hardware devices such as processors, digital signal processors, central processing units, field-programmable gate arrays, programmable array logic systems, programmable logic devices, cloud processing systems, or the like. The devices may also be implemented in software for execution by various types of processors. An identified device may contain executable code and may consist, for example, of one or more physical or logical blocks of computer instructions, which may be organized, for example, as an object, procedure, function, or other construct.However, the executable file of an identified device does not have to be physically stored in the same location, but may consist of different instructions stored in different locations which, logically linked, form the device and fulfill its purpose.

[0024] The executable code of a device or module may consist of one or more instructions and may even be distributed across multiple code segments, different applications, and multiple storage devices. Similarly, operational data may be identified and represented within the device and presented in any form and data structure. The operational data may be captured as a single data set or distributed across different storage devices and may be present, at least in part, as electronic signals in a system or network.

[0025] References in this specification to "a selected embodiment," "an embodiment," or "an embodiment" mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the disclosed subject matter. Therefore, the phrases "a selected embodiment," "in an embodiment," or "in an embodiment" in various places in this specification do not necessarily refer to the same embodiment.

[0026] Furthermore, the described features, structures, or characteristics may be combined in any manner in one or more embodiments. The following description contains numerous specific details in order to provide a thorough understanding of embodiments of the disclosed subject matter. However, those skilled in the art will recognize that the disclosed subject matter may be practiced without one or more of the specific details, or with different methods, components, materials, etc. In other instances, well-known structures, materials, or operations are not shown or described in detail in order not to obscure aspects of the disclosed subject matter.

[0027] According to the exemplary embodiments, the disclosed computer programs or modules may be executed in a variety of ways, for example, as an application in the memory of a device or as a hosted application on a server that communicates with the device application or browser using various standard protocols such as TCP / IP, HTTP, XML, SOAP, REST, JSON, and other suitable protocols. The disclosed computer programs may be written in exemplary programming languages that execute from the memory of the device or from a hosted server, such as BASIC, COBOL, C, C++, Java, Pascal, or scripting languages such as JavaScript, Python, Ruby, PHP, Perl, or other suitable programming languages.

[0028] Some of the disclosed embodiments involve or otherwise involve the transmission of data over a network, for example, the delivery of various inputs or files over the network. The network may include, for example, the Internet, wide area networks (WANs), local area networks (LANs), analog or digital wired and wireless telephone networks (e.g., PSTN, Integrated Services Digital Network (ISDN), cellular networks, and Digital Subscriber Line (xDSL)), radio, television, cable, satellite, and / or other transmission or tunneling mechanisms for transmitting data. The network may include multiple networks or subnetworks, each including, for example, a wired or wireless data path. The network may include a circuit-switched voice network, a packet-switched data network, or another network for transmitting electronic communications.For example, the network may include Internet Protocol (IP) or Asynchronous Transfer Mode (ATM) networks supporting voice, such as VoIP, Voice over ATM, or other comparable protocols for voice data communication. In one implementation, the network includes a cellular network configured for the exchange of text or SMS messages.

[0029] Examples of the network include a Personal Area Network (PAN), a Storage Area Network (SAN), a Home Area Network (HAN), a Campus Area Network (CAN), a Local Area Network (LAN), a Wide Area Network (WAN), a Metropolitan Area Network (MAN), a Virtual Private Network (VPN), an Enterprise Private Network (EPN), the Internet, a Global Area Network (GAN), etc.

[0030] Fig. 1 shows a block diagram of an AI-driven system for detecting and predicting early-stage diabetic foot complications according to an embodiment of the present disclosure.

[0031] Referring to Fig. 1, the AI-driven system (100) for detecting and predicting diabetic foot complications comprises: an input and storage module (102) configured to capture foot images of a patient, capture data on the patient's medical history, and capture assessments of the patient's physiological symptoms, wherein the data is captured via a user interface (102a) that allows the user to interact with the system (100), and wherein the captured data is stored in a storage unit (102b);and a central processing module (104) comprising an intelligent processor (104a) integrated with a memory and a graphics processing unit, wherein the intelligent processor of the central processing unit (104) is configured to pre-process the data acquired by the input and storage module (102), analyze the data, and make predictions based thereon, wherein the intelligent processor (104a) comprises: a pre-processing sub-module (106) configured to: enhance, normalize, and segment the foot images; annotate features in the foot images; detect specific foot abnormalities using a deep learning detection module (106a); structure the medical history data and physiological symptom assessments into a standardized format;and an analysis and prognosis sub-module (108) configured to: generate a visual feature score based on a weighted analysis of the detected foot abnormalities; generate a patient history score based on a weighted analysis of the medical history data; generate a physiological symptom score based on a weighted analysis of the physiological symptom scores; and calculate a comprehensive diabetic foot score by integrating the visual feature score, the patient history score, and the physiological symptom score. The AI-driven system (100) further comprises: an output processing module (110) operatively connected to the central processing module (104) and comprising a visualization and recommendation sub-module (110a) configured to: classify the patient into a risk category based on the comprehensive diabetic foot score generated by the analysis and prognosis sub-module (108);generate personalized recommendations based on the classified risk category; and provide a detailed report to the patient and healthcare providers via the user interface (102a); a communication interface (112) configured to facilitate data transfer between various modules of the system (100); and a display (114) operatively connected to the user interface (102a) and displaying the input capture interface, the processing interface, and the interface for displaying the generated detailed report.;

[0032] In one embodiment, the foot abnormalities detected by the deep learning detection module (106a) include at least one of the following: ulcers, calluses, nail bed changes, discoloration, swelling, and circulatory disorders.

[0033] In one embodiment, the deep learning detection module (106a) comprises a You Only Look Once (YOLO) neural network architecture configured to output bounding boxes and confidence scores for detected foot anomalies.

[0034] In one embodiment, the medical history data includes at least one of the following: previous ulcers, previous amputations, delayed wound healing, chronic pain, peripheral neuropathy, and duration of diabetes.

[0035] In one embodiment, the physiological symptom ratings include numerical self-ratings of at least one of the following symptoms: numbness, pain, tingling, redness, and swelling.

[0036] In one embodiment, the analysis and prediction sub-module (108) further comprises a machine learning module configured to correlate the physiological symptom scores with disease progression patterns.

[0037] In one embodiment, the risk category is classified as one of the following: low risk, medium risk, or high risk, and wherein: the visualization and recommendation sub-module (110a) is configured to provide self-care guidelines for patients classified as low risk; the visualization and recommendation sub-module (110a) is configured to suggest lifestyle changes to patients classified as medium risk; and the visualization and recommendation sub-module (110a) is configured to automatically connect patients classified as high risk to healthcare providers via a communication interface.

[0038] In one embodiment, the storage unit (102b) comprises a big data repository configured to store historical foot images, medical history data, and physiological symptom assessments, to track changes in the comprehensive diabetic foot score over time, and to provide comparative analysis between current and previous assessments, wherein the storage unit (102b) is connected to the centralized processing module (104).

[0039] In one embodiment, the visualization and recommendation sub-module (110a) is further configured to highlight detected anomalies on the foot images, provide an explanation of the factors contributing to the comprehensive diabetic foot score, and generate a structured report including the visual feature score, the patient history score, and the physiological symptom score with their respective contributions to the comprehensive diabetic foot score, wherein the report is transmitted to healthcare providers via the communication interface (112).

[0040] In one embodiment, the input and storage module (102), the centralized processing module (104), the output processing module (110), and the communication interface (112) may be implemented in programmable hardware devices such as processors, digital signal processors, central processing units, field-programmable gate arrays, programmable array logic, programmable logic devices, cloud processing systems, or the like.

[0041] The present invention relates to an advanced AI-based system for the early detection of diabetic foot complications by generating a diabetic foot score. The system operates with four interconnected modules that work harmoniously to provide precise risk assessment and personalized recommendations. The system collects three main data types: patient foot images, a comprehensive medical history of diabetes and foot complications, and self-reported physiological symptom assessments such as numbness, pain, and circulatory disorders. After data acquisition, the system processes the foot images using optimization, normalization, and segmentation techniques to improve analysis accuracy. A deep learning detection model identifies specific foot abnormalities such as ulcers, calluses, nail bed changes, and circulatory disorders and generates bounding boxes and confidence scores for each detected feature.At the same time, the system structures the patient's medical history and symptom assessments into standardized formats suitable for analytical processing. The system then performs a comprehensive analysis and generates three different scores. The visual features score evaluates detected abnormalities in foot images and weights various visual indicators according to clinical significance. The patient history score considers a weighted analysis of factors such as previous ulcers, amputations, and wound healing patterns. The physiological symptoms score quantifies and weights self-reported sensations and visible changes. These three scores are integrated using a proprietary algorithm to calculate a comprehensive diabetic foot score that reflects the patient's overall risk. Based on this, the system assigns patients to risk categories and creates personalized recommendations.Low-risk patients receive self-care guidelines, medium-risk patients receive lifestyle modification suggestions, and high-risk patients are automatically connected to healthcare professionals who can intervene immediately. The system also generates detailed reports highlighting detected abnormalities, explaining the factors contributing to the diabetic foot score, and providing healthcare professionals with structured insights for informed clinical decision-making.

[0042] Fig. 2 shows a diagram illustrating the architecture of the proposed AI-driven system for detecting diabetic foot complications according to an embodiment of the present disclosure.

[0043] The proposed AI-driven diabetic foot complication detection system is configured to predict the diabetic foot by generating a diabetic foot score before reaching the final amputation stage. The system utilizes data such as medical history, physiological symptoms, and visual changes (via images) to generate a final diabetic foot score.

[0044] As in Fig.As shown in Figure 2, the AI-powered system is designed to simulate real-life medical diagnoses by combining computer vision, patient history, and physiological symptoms to assess complications of the diabetic foot. The system enables early detection, risk stratification, and proactive intervention, thus bridging the gap between patients and an early, accurate diagnosis. The system incorporates foot images, history data, and self-reported symptom assessments to generate a Diabetic Foot Score (y). This score helps classify risk levels and provides personalized remedies, preventative measures, self-treatment recommendations, and an alert for immediate medical intervention. The system consists of four core modules, described below: The acquisition and storage module is configured to capture three critical data items essential for assessing diabetic foot complications and store them in a big data repository for real-time processing. These data include: Foot images (y1 - Visual features): Patients capture foot images that are analyzed for visible abnormalities. Medical history (y2 - Patient history): Information on previous complications such as ulcers, amputations, or delayed wound healing. Physiological assessments (y3 - Sensory and circulatory symptoms): Patients report sensory symptoms (numbness, pain, tingling) and circulatory changes (redness, swelling).

[0045] The preprocessing module is configured to ensure reliable analysis. The preprocessing module is configured to perform image processing by enhancing, normalizing, and segmenting the images to improve detection accuracy; annotating the features in the acquired foot data images, with each feature surrounded by a bounding box with the corresponding label; detecting features using a deep learning model (YOLO(y1), where the features include key foot features such as ulcers, calluses, nail bed changes, and circulatory disorders). The deep learning model outputs bounding boxes and confidence values confirming the presence and severity of these features in the new input test images.and performing data structuring for y2 and y3, where the medical history (y2) is categorically structured according to the principle of 'yes' or 'no' and self-reported symptoms are available in structured numerical formats for analysis to assess severity.;

[0046] The analysis and prediction module is configured to simulate a clinical diagnosis in real time by correlating multiple factors, generating a comprehensive risk score. The diabetic foot complications (visual features) image score (y1) automates the visual inspection process that physicians typically perform to assess foot conditions such as ulcers, discoloration, and swelling. By analyzing images for these features, the system assigns weighted scores based on severity. The formula for calculating this score is y1 = x1.w1 + x2.w2 + x3.w3 + x4.w4 + x5.w5 **, where x1, x2,..., x5 represent visual abnormalities (skin changes, pressure changes, alignment problems, etc.) and w1, w2,..., w5 are their respective risk weights. The patient history (clinical background) score (y2) represents the diagnostic weighting of the patient history by physicians.To do this, it analyzes historical data such as previous ulcers or amputations (indicating a high risk of recurrence), delayed wound healing (indicating circulatory disorders), and chronic pain or calf pain (possibly a sign of peripheral neuropathy). Each historical factor is weighted and contributes to an overall score that influences the final diagnosis. The physiological symptom score (sensory and circulatory factors) (y3) considers patient-reported symptoms such as pain, numbness, or tingling. Patients provide numerical self-assessments on a scale, and the system calculates a severity score. Machine learning models further correlate these symptoms with disease progression, thus improving the accuracy of the diagnosis.

[0047] The Diabetic Foot Score (y) is derived from three subscores: y = f(y1, y2, y3), where f is a function that weights visual, historical, and physiological factors to determine overall risk. In the visualization and recommendation module, patients receive a detailed report explaining their Diabetic Foot Score and highlighting any abnormalities. Risk-based recommendations include self-care guidelines for low-risk patients, lifestyle modifications for moderate-risk patients, and automatic connection to a physician for further evaluation in high-risk cases. Physicians receive structured insights, including an image-based assessment of severity (y1), impact of history (y2), and symptom correlation (y3).

[0048] The present invention provides an AI-powered system for detecting diabetic foot complications. The system utilizes data collected from the patient and analyzes it to calculate a diabetic foot score. The system closely resembles the diagnostic approach used by physicians in clinical practice. It uses deep learning models to detect and quantify these visual features (y1) from captured foot images and assign risk scores based on severity. To assess the risk of recurrence, taking into account previous complications such as ulcers, amputations, or delayed wound healing, the system systematically analyzes historical data (y2) to identify patterns that may indicate an increased likelihood of diabetic foot complications.Additionally, the system captures self-reported physiological assessments (y3) to inquire about sensory and circulatory symptoms—such as numbness, pain, tingling, or swelling—to assess nerve damage and vascular health. These assessments are then correlated with potential risks for diabetic feet. Finally, the system integrates all these factors to provide a holistic diagnosis and recommend treatment. The system combines y1, y2, and y3 into a comprehensive risk score (y), providing actionable insights and self-management recommendations and connecting high-risk patients directly with healthcare professionals when needed.By mimicking this structured clinical assessment process, the AI-driven system ensures early detection, proactive intervention, and seamless doctor-patient connectivity, bridging the gap between traditional in-person examinations and modern remote healthcare solutions. By integrating computer vision, AI-driven analytics, and clinical decision-making principles, this system enhances early detection, remote monitoring, and preventive intervention for diabetic foot complications.

[0049] The present invention is a comprehensive AI-based system for detecting diabetic foot complications. The system predicts diabetic foot complications early by integrating patient medical history, physiological symptoms, and visual foot assessments. The system leverages data from multiple sources to generate a diabetic foot score, enabling timely interventions and preventive measures. The proposed system consists of four main modules: data ingestion and storage in the cloud, image preprocessing and cleaning, score analysis and calculation, and prognosis, visualizations, and recommendations. The system not only considers various parameters such as medical history, current symptoms, and visual features, but also analyzes them separately, organizes and structures them, and finally combines them into a score that indicates risk.

[0050] The drawings and the foregoing description illustrate examples of embodiments. Those skilled in the art will recognize that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be separated into multiple functional elements. Elements of one embodiment may be added to another embodiment. For example, the order of the processes described herein may be changed and is not limited to the manner described herein. Furthermore, the actions of a flowchart need not be performed in the order shown; nor do all actions need to be performed. Also, actions that are not dependent on other actions may be performed in parallel with the other actions. The scope of the embodiments is in no way limited by these specific examples.Numerous variations, whether explicitly stated in the specification or not, such as differences in structure, dimensions, and use of materials, are possible. The scope of the embodiments is at least as broad as indicated in the following claims.

[0051] Advantages, further advantages, and solutions to problems have been described above with reference to specific embodiments. However, the advantages, benefits, solutions to problems, and any components that may result in or enhance an advantage, benefit, or solution are not to be construed as critical, required, or essential features or components of any or all of the claims. REFERENCES 100 AI-driven system for detecting and predicting diabetic foot complications. 102 Input and memory module 102a User interface 102b storage unit 104 Central Processing Unit 104a Intelligent Processor 106 Preprocessing submodule 106a deep learning detection module 108 Submodule Analytics and Prediction 110 Output processing module 110a Visualization and Recommendation Submodule 112 Communication interface 114 Advertisement 202 pressure changes 202a Skin changes 202b Alignment changes 202c Nail bed changes 202d Circulation problems 202e Skin changes 204 tingling 204a Redness 204b Pain 204c Deafness 204d Swelling 206 Diabetic Foot Compilations Image Evaluation (Y1) 208 Physiological Symptoms (Y3) 210 Diabetic Foot Score (J) 212 Patient's Medical History (J2) 214 Diabetes 216 History of a Delayed Healing Wound D 218 History of calf pain 220 History of Leg Amputation 222 History of Toe Amputation 224 History of a Foot Ulcer

Claims

[1] A system for detecting and predicting diabetic foot complications, consisting of: an input and storage module configured to capture foot images of a patient, capture data on the patient's medical history, and capture assessments of the patient's physiological symptoms, wherein the data is captured via a user interface that allows the user to interact with the system, and wherein the captured data is stored in a storage unit; a centralized processing module comprising an intelligent processor integrated with a memory and a graphics processing unit, wherein the intelligent processor of the centralized processing unit is configured to preprocess the data collected by the input and memory module, analyze the data, and make predictions based on the data, wherein the intelligent processor comprises: a preprocessing sub-module configured to enhance, normalize, and segment the foot images, annotate features in the foot images, detect certain foot abnormalities using a deep learning detection module, and convert the medical history data and physiological symptom assessments into a standardized format; and an analysis and prediction sub-module configured to generate a visual feature score based on a weighted analysis of detected foot abnormalities, to generate a patient history score based on a weighted analysis of medical history data, to generate a physiological symptom score based on a weighted analysis of physiological symptom ratings, and to calculate a comprehensive diabetic foot score by integrating the visual feature score, the patient history score, and the physiological symptom score; an output processing module operatively connected to the centralized processing module and comprising a visualization and recommendation sub-module configured to: classify the patient into a risk category based on the comprehensive diabetic foot score generated by the analysis and prediction sub-module; generate personalized recommendations based on the classified risk category; and provide the patient and Provide healthcare providers with a detailed report via the user interface; a communication interface configured to facilitate data transfer between different modules of the system; and a display operatively connected to the user interface and showing the input capture interface, the processing interface, and the generated detailed report display interface. [2] The system of claim 1, wherein the foot abnormalities detected by the deep learning detection module include at least one of the following: ulcers, calluses, nail bed changes, discoloration, swelling, and circulatory disorders. [3] The system of claim 1, wherein the deep learning detection module comprises a You Only Look Once (YOLO) neural network architecture configured to output bounding boxes and confidence scores for detected foot anomalies. [4] The system of claim 1, wherein the medical history data includes at least one of the following: previous ulcers, previous amputations, delayed wound healing, chronic pain, peripheral neuropathy, and duration of diabetes. [5] The system of claim 1, wherein the physiological symptom ratings comprise numerical self-ratings of at least one of the following symptoms: numbness, pain, tingling, redness, and swelling. [6] The system of claim 1, wherein the analysis and prediction sub-module further comprises a machine learning module configured to correlate the physiological symptom scores with disease progression patterns. [7] The system of claim 1, wherein the risk category is classified as one of the following: low risk, medium risk, or high risk, and wherein: the visualization and recommendation sub-module is configured to provide self-care guidelines for patients classified as low risk; the visualization and recommendation sub-module is configured to suggest lifestyle changes to patients classified as medium risk; and the visualization and recommendation sub-module is configured to automatically connect patients classified as high risk to healthcare providers via a communication interface. [8] The system of claim 1, wherein the storage unit comprises a big data repository configured to store historical foot images, medical history data, and physiological symptom assessments, track changes in the comprehensive diabetic foot score over time, and provide comparative analysis between current and past assessments, the storage unit being connected to the centralized processing module. [9] The system of claim 1, wherein the visualization and recommendation sub-module is further configured to highlight detected abnormalities on the foot images; provide an explanation of the factors contributing to the comprehensive diabetic foot score; and generate a structured report including the visual features score, the patient history score, and the physiological symptoms score with their respective contributions to the comprehensive diabetic foot score, the report being communicated to healthcare providers via the communication interface.

Images