Disease prognosis based on demographic information and anatomical images using neural network models

Abstract

An electronic device and method for disease prognosis based on demographic information and anatomical images using a neural network model are provided. The electronic device receives demographic information associated with a person. A disease associated with an anatomical region of the person is determined based on applying a first neural network model to the demographic information. A second neural network model is selected from a set of neural network models based on the determined disease. The second neural network model is applied to a received first set of images associated with the anatomical region of the person to determine a first disease severity corresponding to the determined disease. The second neural network model is different from the first neural network model. A display device associated with the electronic device is controlled to render information related to the determined first disease severity and the determined disease.

Description

[Technical Field]

[0001] Cross-reference to related applications / incorporation by reference This application claims the benefit of priority to U.S. Patent Application No. 18 / 069,447, filed with the United States Patent and Trademark Office on December 21, 2022, which is incorporated herein by reference in its entirety.

[0002] Various embodiments of the present disclosure relate to disease prognosis, particularly to disease prognosis based on demographic information and anatomical images using neural network models. [Background technology]

[0003] Advances in the field of disease prognosis have led to the development of non-contact and non-invasive diagnostic methods. Disease diagnosis can typically be performed based on the collection of bodily fluid or blood samples from a patient. The collected samples can then be transported to a pathology laboratory and tested to diagnose the patient's associated illness or disease. Existing invasive techniques require significant time for sample collection, making disease diagnosis a lengthy process. Furthermore, sample collection and disease diagnosis are sometimes performed manually, leading to human error and potentially reducing the accuracy of disease diagnosis. Furthermore, invasive techniques require human contact, potentially facilitating the spread of infectious diseases. Therefore, a time-efficient, advanced disease prognosis method that eliminates physical contact and improves accuracy is desirable. Summary of the Invention

[0004] Further limitations and disadvantages of conventional approaches will become apparent to those skilled in the art upon comparing the described system with certain aspects of the present disclosure illustrated in the remainder of this application and with reference to the drawings.

[0005] Provided are electronic devices and methods for disease prognosis based on demographic information and anatomical images using neural network models substantially as shown and / or described in connection with at least one of the figures and more fully set forth in the claims.

[0006] These and other features and advantages of the present disclosure will become apparent from a consideration of the following detailed description of the disclosure when taken in conjunction with the accompanying drawings, in which like reference characters refer to like elements throughout. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a block diagram illustrating an exemplary environment for disease prognosis based on demographic information and anatomical images using a neural network model, according to an embodiment of the present disclosure. [Figure 2] FIG. 2 is a block diagram illustrating the example electronic device of FIG. 1 in accordance with an embodiment of the present disclosure. [Figure 3] FIG. 1 illustrates an exemplary processing pipeline for disease prognosis based on demographic information and anatomical images using a neural network model, according to an embodiment of the present disclosure. [Figure 4] FIG. 1 illustrates an exemplary processing pipeline for determining disease progression, according to an embodiment of the present disclosure. [Figure 5] FIG. 1 illustrates an exemplary processing pipeline for determining treatment recommendations, according to an embodiment of the present disclosure. [Figure 6] 1 is a flowchart illustrating exemplary operations for disease prognosis based on demographic information and anatomical images using a neural network model, according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0008] The disclosed electronic device and method for disease prognosis based on demographic information and anatomical images using a neural network model may find implementation as described below. An exemplary embodiment of the electronic device may include circuitry configurable to receive demographic information associated with a person (such as, but not limited to, age, sex, nationality, region, ethnicity, household income, diet type, lifestyle type, work type, medical history, or vaccination information). The electronic device may be configured to determine a disease associated with an anatomical region of the person (such as, but not limited to, an ocular region, a subcutaneous region, an epidermal region, a dermal region, a subcutaneous region, a bone region, or a visceral region) based on applying a first neural network model to the received demographic information. Examples of diseases may include, but are not limited to, an infectious disease, a deficiency disease, a genetic disease, a genetic disease, a non-genetic disease, a lifestyle-related disease, a hormonal disease, or a physiological disease. The electronic device may be further configured to select a second neural network model from a set of neural network models based on the determined disease. The electronic device can be configured to receive a first set of images associated with an anatomical region of the person. The electronic device can be configured to apply a selected second neural network model to the received first set of images. The second neural network model can be different from the first neural network model. The electronic device can be configured to determine a first disease severity corresponding to a determined disease associated with the anatomical region of the person based on applying the second neural network model to the received first set of images. Examples of the first disease severity can include, but are not limited to, an incubation period, a prodromal period, an acute period, or a recovery period. Further, the electronic device can be configured to control a display device associated with the electronic device to render information related to the determined first disease severity and the determined disease.

[0009] Traditional disease prognostic diagnostic methods require a person to be physically present at a testing facility for diagnosis. Additionally, existing methods require physical contact and / or insertion of medical / surgical instruments for sample collection. Once a sample is collected, various pathological tests can be performed on the collected sample. The time to perform a pathological test can depend on the type of test and the number of physiological parameters to be tested. Furthermore, because pathological tests are performed by human radiologists / pathologists, human error may exist.

[0010] In contrast, the method performed by the disclosed electronic device can utilize demographic information and anatomical images associated with a person for automated disease prognosis. A disease associated with an anatomical region of the person can be determined based on applying a first neural network model to the demographic information. A second neural network model can be selected from a set of neural network models based on the determined disease. The second neural network model can be applied to a first set of images (such as captured images) associated with the person's anatomical region to determine a first disease severity corresponding to the determined disease. The second neural network model can be different from the first neural network model. Furthermore, information about the determined first disease severity and the determined disease can be displayed to the person. The disclosed technology can automatically determine diseases that may affect the person using the first neural network model, and can also determine the anatomical region of the disease based on demographic information associated with the person. Thus, a first level of screening or filtering of common diseases to which the person is susceptible can be identified for further investigation. Thereafter, once the disease and anatomical region have been determined, the person can be prompted to capture an image of the anatomical region for further investigation or to upload a previously captured image of the anatomical region. A second neural network model can analyze the image of the anatomical region to automatically determine the disease severity corresponding to the disease. Thus, the process of disease prognosis can be automated based on the systematic identification of the person's disease and the image-based diagnosis of the disease severity corresponding to the disease. The person does not need to physically go to a pathology laboratory and wait for the test report. The disclosed method can perform disease prognosis noninvasively and remotely, and can provide accurate results in a short time, which can be important for the person's further treatment.

[0011] FIG. 1 is a block diagram illustrating an exemplary environment for disease prognosis based on demographic information and anatomical images using a neural network model, according to an embodiment of the present disclosure. FIG. 1 illustrates a network environment 100. The network environment 100 may include an electronic device 102, a server 104, a database 106, and a communication network 108. The database 106 may include a series of neural network models, such as a first neural network model 110A, a second neural network model 110B, and a third neural network model 110C. The electronic device 102 may be communicatively coupled to the server 104 and the database 106 via the communication network 108. Also illustrated in FIG. 1 is a person 112 that may be associated with or operate the electronic device 102.

[0012] The electronic device 102 may include suitable logic, circuitry, interfaces, and / or code that may be configured to determine a disease associated with the person 112 and determine a first disease severity for the determined disease. The electronic device 102 may be configured to determine a disease associated with an anatomical region of the person 112 based on applying a first neural network model 110A to demographic information associated with the person 112. The electronic device 102 may be further configured to select a second neural network model 110B from a set of neural network models based on the determined disease. In one embodiment, the electronic device 102 may be configured to capture a first set of images of an anatomical region of the person 112. In another embodiment, the first set of images may be pre-stored, and the electronic device 102 may receive the first set of images from a memory or image capture device that stores the first set of images. The electronic device 102 may be configured to apply the selected second neural network model 110B to the first set of images of the anatomical region. The electronic device 102 can be configured to determine a first disease severity corresponding to the determined disease associated with the anatomical region of the person 112 based on applying the second neural network model 110B to the received first set of images. Further, the electronic device 102 can be configured to control a display device associated with the electronic device 102 to render the determined first disease severity and information related to the determined disease.

[0013] Examples of electronic devices 102 may include medical devices, health-related machines / engines, computing devices, desktops, personal computers, laptops, computer workstations, tablet computing devices, smartphones, cellular phones, mobile phones, consumer electronics (CE) digital devices with displays, televisions (TVs), wearable displays, head-mounted displays, signage, digital mirrors (or smart mirrors), video walls (consisting of two or more displays tiled or stacked consecutively on top of each other to form one large screen), or edge devices connected to a user's home network or an organization's network.

[0014] The server 104 may include suitable logic, circuitry, interfaces, and / or code that may be configured to receive demographic information associated with the person 112 and a first set of images associated with an anatomical region of the person 112 (e.g., an eye region, a subcutaneous region, an epidermal region, a dermal region, a subcutaneous region, a bone region, or a visceral region, etc.). The server 104 may provide the demographic information associated with the person 112 and the first set of images associated with the anatomical region of the person 112 to the electronic device 102. The server 104 may perform operations through web applications, cloud applications, HTTP requests, repository operations, file transfers, etc. Example implementations of the server 104 may include, but are not limited to, a database server, a file server, a web server, an application server, a mainframe server, a cloud computing server, or combinations thereof.

[0015] In at least one embodiment, server 104 may be implemented as multiple distributed cloud-based resources using techniques known to those skilled in the art. Those skilled in the art will appreciate that the scope of the present disclosure may not be limited to the implementation of server 104 and electronic device 102 as two separate entities. In some embodiments, the functionality of server 104 may be incorporated, in whole or at least in part, into electronic device 102 without departing from the scope of the present disclosure.

[0016] Database 106 may include suitable logic, interfaces, and / or code that may be configured to store information related to a first set of images, demographic information, and a set of neural network models, which may include first neural network model 110A, second neural network model 110B, and third neural network model 110C. In an embodiment, in addition to (or instead of) storing the set of neural network models (one or more of first neural network model 110A, second neural network model 110B, and third neural network model 110C) in database 106, the set of neural network models may also be stored on electronic device 102. Additionally, the first set of images and demographic information may also be stored on electronic device 102.

[0017] The database 106 can be derived from data from a relational or non-relational database, or from a set of comma-separated values ​​(csv) files in traditional storage or big data storage. The database 106 can be stored or cached on a device, such as the server 104 or the electronic device 102. The device storing the database 106 can be configured to receive a query for information related to at least one of the first set of images, demographic information, or a set of neural network models. For example, the query can be received from the electronic device 102. The database 106 can extract the relevant information based on the received query, and the device hosting the database 106 can send the extracted information to the electronic device 102.

[0018] In some embodiments, database 106 may be hosted on multiple servers stored in the same or different locations. The operations of database 106 may be performed using hardware, including a processor, a microprocessor (e.g., that performs or controls the execution of one or more operations), a field programmable gate array (FPGA), or an application specific integrated circuit (ASIC). In some other cases, database 106 may be implemented using software.

[0019] The communication network 108 may include a communication medium that enables the electronic device 102 to be communicatively coupled to the server 104 and the database 106. Examples of the communication network 108 may include, but are not limited to, the Internet, a cloud network, a cellular or wireless mobile network (such as Long Term Evolution and Fifth Generation (5G) New Radio (NR)), a satellite network (such as a network of low-earth orbit satellites), a Wireless Fidelity (Wi-Fi) network, a personal area network (PAN), a local area network (LAN), or a metropolitan area network (MAN). The various devices in the network environment 100 may be configured to connect to the communication network 108 according to a variety of wired and wireless communication protocols. Examples of such wired and wireless communication protocols include, but are not limited to, at least one of Transmission Control Protocol and Internet Protocol (TCP / IP), User Datagram Protocol (UDP), Hypertext Transfer Protocol (HTTP), File Transfer Protocol (FTP), ZigBee, EDGE, IEEE802.11, Light Fidelity (Li-Fi), 802.16, IEEE802.11s, IEEE802.11g, multi-hop communication, wireless access point (AP), device-to-device communication, cellular communication protocols, and Bluetooth (BT) communication protocols.

[0020] Each of the series of neural network models (e.g., first neural network model 110A, second neural network model 110B, and third neural network model 110C) can be a system of computational networks or artificial neurons arranged as nodes in multiple layers. The multiple layers of each neural network model can include an input layer, one or more hidden layers, and an output layer. Each of the multiple layers can include one or more nodes (or artificial neurons, represented, for example, by circles). The output of every node in the input layer can be connected to at least one node in the hidden layer(s). Similarly, the input of each hidden layer can be connected to the output of at least one node in a layer of the neural network model. The output of each hidden layer can be connected to the input of at least one node in another layer of the neural network model. The node(s) in the final layer can receive inputs from at least one hidden layer and output a result. The number of layers and the number of nodes in each layer can be determined from hyperparameters of the neural network model. Such hyperparameters can be set before, during, or after training the neural network model on a training dataset.

[0021] Each node in each of the series of neural network models can correspond to a mathematical function (e.g., a sigmoid function or a rectified linear unit) having a set of parameters that can be adjusted during training of the network. The set of parameters can include, for example, weight parameters and regularization parameters. Each node can calculate an output using the mathematical function based on one or more inputs from nodes in other layer(s) (e.g., previous layer(s)) of the neural network model. All or some of the nodes in a neural network model can correspond to the same or different mathematical functions.

[0022] In training a neural network model, one or more parameters of each node of the neural network model can be updated based on whether the output of the final layer for a given input (from the training dataset) matches the correct result based on the loss function of the neural network model. The above process can be repeated for the same or different inputs until a minimum of the loss function is achieved, thereby minimizing the training error. Several training methods are known in the art, such as gradient descent, stochastic gradient descent, batch gradient descent, gradient boosting, and metaheuristic methods.

[0023] A neural network model may include electronic data that may be implemented, for example, as a software component of an application executable on the electronic device 102. A neural network model may rely on libraries, external scripts, or other logic / instructions for execution by a processing device, such as a circuit. A set of neural network models may include code and routines configured to enable a computing device, such as a circuit, to perform one or more operations. For example, a first neural network model 110A may be applied to demographic information associated with the person 112 to determine a disease associated with an anatomical region of the person 112. Further, a second neural network model 110B may be applied to a first set of images associated with the anatomical region of the person 112 to determine a first disease severity corresponding to the determined disease associated with the anatomical region of the person 112. A third neural network model 110C may also be applied to the determined disease and the determined progression of the determined disease to generate a treatment recommendation. Examples of generated treatment recommendations may include, but are not limited to, medication recommendations, medication recommendations, treatment recommendations, dietary recommendations, physical exercise recommendations, breathing exercise recommendations, sleep recommendations, activity recommendations, meditation / yoga recommendations, walking / jogging / running recommendations, cycling recommendations, swimming recommendations, workout recommendations, music recommendations, or recreational recommendations. Additionally or alternatively, the series of neural network models may be implemented using hardware, including a processor, a microprocessor (e.g., that performs or controls one or more operations), a field programmable gate array (FPGA), or an application specific integrated circuit (ASIC). Alternatively, in some embodiments, the series of neural network models may be implemented using a combination of hardware and software.

[0024] In one embodiment, the first neural network model 110A can be trained based on at least one of, but not limited to, demographic information, disease information, and anatomical region information associated with a plurality of different individuals. In one embodiment, the second neural network model 110B can be trained based on at least one of, but not limited to, image sets of anatomical regions of a plurality of different individuals, and further based on a predetermined range of disease severity levels corresponding to the determined disease and a set of images that can be captured over a predetermined period of time. For example, the predetermined range of disease severity levels can include, but is not limited to, the incubation period, prodromal period, acute period, or recovery period. In another embodiment, the second neural network model 110B can be trained based on at least one of, but not limited to, image sets of anatomical regions of the same individual, and a predetermined range of disease severity levels corresponding to the determined disease and a set of images that can be captured over a predetermined period of time. The third neural network model 110C can be trained based on at least one of, but not limited to, demographic information, disease information, disease progression information, disease severity information, or treatment plan information associated with a plurality of different individuals.

[0025] Examples of the set of neural network models include, but are not limited to, deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), CNN-recurrent neural networks (CNN-RNNs), R-CNN, Fast R-CNN, Faster R-CNN, artificial neural networks (ANNs), (You Only Look Once) YOLO networks, long-short-term memory (LSTM) network-based RNNs, CNN+ANNs, LSTM+ANNs, gated recurrent unit (GRU)-based RNNs, fully connected neural networks, connectionist temporal classification (CTC)-based RNNs, deep Bayesian neural networks, generative adversarial networks (GANs), and / or combinations of these networks. In some embodiments, the learning engine of the set of neural network models can include a numerical computation method using a data flow graph. In some embodiments, each neural network model can be based on a hybrid architecture of multiple deep neural networks (DNNs).

[0026] Upon operation, the electronic device 102 can be triggered to, or receive user input to, perform a disease prognosis for a particular person or a particular anatomical region of the person. The electronic device 102 can be configured to receive demographic information related to the person 112. For example, the electronic device 102 can receive demographic information related to the person 112 as user input from the person 112. The demographic information can include, but is not limited to, age, gender, nationality, region, ethnicity, household income, diet type, lifestyle type, work type, medical history, or vaccination information. Demographic information may include, but is not limited to, age, gender (e.g., male, female, transgender), nationality (e.g., American, Hispanic, German, Indian), region (e.g., hill country, tropical, plains), ethnicity (e.g., Aboriginal, African American or Black, Asian, European American or Caucasian, Native American, Native Hawaiian or Pacific Islander), household income (i.e., total income received by all members of the household over a 12-month period), diet type (e.g., vegetarian, non-vegetarian, vegan, ketogenic), lifestyle type (e.g., rural, urban, seaside, mountain), type of work (e.g., farmer, business, employee), medical history (e.g., allergies, illnesses, surgeries, vaccinations, medical exam and test results), or vaccination information (e.g., rotavirus vaccine, nasal influenza vaccine, shingles vaccine, chickenpox vaccine). Receipt of demographic information is further described, for example, with reference to FIG. 3.

[0027] The electronic device 102 may be further configured to apply a first neural network model 110A to the received demographic information. The set of neural network models may be stored in the database 106. The electronic device 102 may determine a disease associated with an anatomical region of the person 112 based on the application of the first neural network model 110A. For example, diseases can include, but are not limited to, infectious diseases (such as influenza, measles, HIV, streptococcus, and COVID-19), deficiencies (such as scurvy, rickets, Beiberi's disease, and hypocalcemia), genetic diseases (such as cystic fibrosis, hemophilia, and sickle cell anemia), genetic diseases (such as Down syndrome, trisomy 21, fragile X syndrome, Klinefelter syndrome, and triple X syndrome), non-genetic diseases (such as heart disease, stroke, cancer, and diabetes), lifestyle-related diseases (such as heart disease, arteriosclerosis, stroke, respiratory disease, obesity, and type 2 diabetes), hormonal diseases (such as acromegaly and cystic fibrosis), or physiological diseases (such as asthma, glaucoma, and diabetes). Anatomical regions of the person 112 can include, but are not limited to, an ocular region, a subcutaneous region, an epidermal region, a dermal region, a subcutaneous region, a bone region, or a visceral region. Note that determining diseases based on demographic information is further described, for example, with reference to FIG. 3.

[0028] The electronic device 102 can further receive a first image set related to an anatomical region of the person 112. In one example, the first image set can be received from the database 106. In another example, an image capture device associated with the electronic device 102 can capture the first image set, and the first image set can be received from the image capture device. In another example, the first image set can be pre-stored in a memory device (such as memory 204 in FIG. 2 ) of the electronic device 102. In such a case, the first image set can be retrieved from the memory device of the electronic device 102. The electronic device 102 can be configured to select a second neural network model 110B from the set of neural network models. The selection of the second neural network model 110B can be based on the determined disease. The selected second neural network model 110B can be applied to the first image set. The electronic device 102 may determine a first disease severity corresponding to the determined disease associated with the anatomical region of the person 112 based on application of the second neural network model 110B.

[0029] In some instances, the severity of the disease can correspond to at least one of, but not limited to, a latent phase, a prodromal phase, an acute phase, or a recovery phase. For example, the latent phase is the period from when a person is exposed to a pathogenic organism (e.g., a bacterium, virus, fungus, etc.) until the onset of infection. The latent period can end when a person shows early signs or symptoms of disease. The prodromal phase can correspond to the period after the latent period and before the onset of characteristic symptoms of infection. During the prodromal period, transmission of infection to other people in physical contact with the infected person can occur. During the prodromal period, the infectious agent continues to replicate and elicits an immune response in the infected person, which can limit symptoms to mild and nonspecific symptoms. The acute phase of the disease can correspond to the active replication or multiplication stage of the pathogen, and the number of pathogens in the human body can increase exponentially in a short period of time. During the acute phase, a strong immune system response can cause significant disease in the infected person's affected organs and systemic symptoms. The recovery phase can correspond to the recovery period of the disease, during which symptoms subside and the infected person's body can return to normal.

[0030] In one embodiment, the second neural network model 110B can be further trained based on at least one of, but not limited to, a set of images of anatomical regions of a plurality of different persons and a predetermined set of disease severities corresponding to the determined disease. The set of images of a plurality of different persons can be captured over a predetermined period of time. In another embodiment, the second neural network model 110B can be trained based on at least one of, but not limited to, a set of images of anatomical regions of the same person, a predetermined set of disease severities corresponding to the determined disease, and a set of images of the same person that can be captured over a predetermined period of time. Determining disease severity is further described, for example, in FIG. 3.

[0031] In some embodiments, electronic device 102 can be configured to control a display device associated with electronic device 102 to render information related to the determined disease severity and the determined disease. Person 112, or a physician associated with person 112, can determine a treatment plan for person 112 based on the rendered information.

[0032] FIG. 2 is a block diagram illustrating the example electronic device of FIG. 1 in accordance with an embodiment of the present disclosure. The description of FIG. 2 is provided with reference to the elements of FIG. 1. FIG. 2 illustrates a block diagram 200 of the electronic device 102. The electronic device 102 may include a circuit 202. The electronic device 102 may further include a memory 204, an input / output (I / O) device 206, and a network interface 210. The I / O device 206 may include a display device 208 that may be utilized to render information related to the determined disease severity and the determined disease. The circuit 202 may be communicatively coupled to the memory 204, the I / O device 206, and the network interface 210. The circuit 202 may be configured to communicate with the server 104.

[0033] The circuit 202 may include suitable logic, circuits, and interfaces that may be configured to execute program instructions associated with different operations performed by the electronic device 102. For example, the circuit 202 may be configured to determine a disease associated with an anatomical region of the person 112 based on applying a first neural network model 110A to the received demographic information. The circuit 202 may be further configured to select a second neural network model 110B from a set of neural network models based on the determined disease. The circuit 202 may be configured to receive a first set of images associated with an anatomical region of the person 112. The circuit 202 may be configured to apply the selected second neural network model 110B to the received first set of images. The second neural network model 110B may be different from the first neural network model 110A. The circuit 202 may be configured to determine a first disease severity corresponding to the determined disease associated with the anatomical region of the person based on applying the second neural network model 110B to the received first set of images. Additionally, the circuitry 202 can be configured to control a display device 208 associated with the electronic device 102 to render information related to the determined first disease severity and the determined disease. The circuitry 202 can include one or more specialized processing units, which can be implemented as independent processors. In some embodiments, the one or more specialized processing units can be implemented as an integrated processor or a group of processors that collectively perform the functions of the one or more specialized processing units. The circuitry 202 can be implemented based on multiple processor technologies known in the art. Example implementations of the circuitry 202 can be an X86-based processor, a graphics processing unit (GPU), a reduced instruction set computing (RISC) processor, an application-specific integrated circuit (ASIC) processor, a complex instruction set computing (CISC) processor, a microcontroller, a central processing unit (CPU), and / or other control circuitry.

[0034] The memory 204 may include suitable logic, circuitry, and / or interfaces that may be configured to store instructions executable by the circuit 202. The instructions stored in the memory 204 may be configured to be executed by the circuit 202 to perform the operations of the electronic device 102 (and / or the circuit 202). The memory 204 may further be configured to store an operating system and associated applications. The memory 204 may include a series of neural network models, such as a first neural network model 110A, a second neural network model 110B, and a third neural network model 110C. According to certain embodiments, the memory 204 may be configured to store disease-related information, a first image set, and demographic information. Example implementations of the memory 204 may include, but are not limited to, random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), a hard disk drive (HDD), a solid-state drive (SSD), a CPU cache, and / or a secure digital (SD) card.

[0035] The I / O device 206 may include suitable logic, circuitry, interfaces, and / or code that may be configured to receive user input. The I / O device 206 may further be configured to provide output in response to the user input. For example, the I / O device 206 may receive user input indicating demographic information associated with the person 112 for determining a disease of the person 112. The I / O device 206 may further receive a user selection of a file set corresponding to a first set of images for determining disease severity. The I / O device 206 may render the determined disease and determined disease severity associated with the person 112. The I / O device 206 may include various input and output devices that may be configured to communicate with the circuit 202. Examples of input devices may include, but are not limited to, a touch screen, a keyboard, a mouse, a joystick, and / or a microphone. Examples of output devices may include, but are not limited to, a display device 208 and / or a speaker.

[0036] The display device 208 may include suitable logic, circuitry, interfaces, and / or code that may be configured to render information related to the determined disease severity and the determined disease on a display screen of the display device 208. According to some embodiments, the display device 208 may include a touch screen for receiving user input. The display device 208 may be implemented through a number of known technologies, such as, but not limited to, a liquid crystal display (LCD) display, a light emitting diode (LED) display, a plasma display, or organic LED (OLED) display technology, and / or other display technologies. According to some embodiments, the display device 208 may refer to a display screen of a smart glasses device, a 3D display, a see-through display, a projection display, an electrochromic display, and / or a transparent display.

[0037] The network interface 210 may include suitable logic, circuitry, interfaces, and / or code that may be configured to establish communications between the electronic device 102 and the server 104 over the communications network 108. The network interface 210 may be implemented using various known technologies to support wired or wireless communications between the electronic device 102 and the communications network 108. The network interface 210 may include, but is not limited to, an antenna, a radio frequency (RF) transceiver, one or more amplifiers, a tuner, one or more oscillators, a digital signal processor, a coder-decoder (CODEC) chipset, a subscriber identity module (SIM) card, and / or a local buffer.

[0038] The network interface 210 can communicate via wireless communication with networks such as the Internet, an intranet, and / or wireless networks such as a cellular telephone network, a wireless local area network (LAN), and / or a metropolitan area network (MAN). The wireless communication can use any of a number of communication standards, protocols, and technologies, such as Global System for Mobile Communications (GSM), Enhanced Data GSM Environment (EDGE), Wideband Code Division Multiple Access (W-CDMA), Long Term Evolution (LTE), Fifth Generation (5G) New Radio (NR), Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Bluetooth, Wireless Fidelity (WiFi) (e.g., IEEE 802.11a, IEEE 802.11b, IEEE 802.11g, and / or IEEE 802.11n), Voice over Internet Protocol (VoIP), Light Fidelity (Li-Fi), Wi-MAX, protocols for email, instant messaging, and / or short message service (SMS). The operation of circuit 202 is described in detail, for example, in FIGS.

[0039] Figure 3 illustrates an exemplary processing pipeline for disease prognosis based on demographic information and anatomical images using a neural network model, according to an embodiment of the present disclosure. The description of Figure 3 is provided with reference to elements of Figures 1 and 2. Figure 3 illustrates a processing pipeline 300 for disease prognosis based on demographic information and anatomical images using a neural network model. The processing pipeline 300 illustrates a series of operations that may begin at 302 and end at 314. The series of operations may be performed by the circuit 202 of the electronic device 102.

[0040] At 302, a demographic information reception operation may be performed. In the demographic information reception operation, the circuit 202 may be configured to receive demographic information associated with the person 112. The demographic information associated with the person may be received as user input from the person 112 via the I / O device 206 of the electronic device 102. In another embodiment, the demographic information may be stored in the database 106. The circuit 202 may send a query for the demographic information to the database 106. The database 106 may extract the demographic information based on the received query and send the extracted demographic information to the electronic device 102. The demographic information may include information associated with the person 112 that the circuit 202 may use to determine a disease associated with the anatomical region 308B of the person 112. Demographic information may include, but is not limited to, at least one of age, gender (e.g., male, female, or other gender), nationality (e.g., American, Hispanic, German, Indian), region (e.g., hill country, tropical, plains, cold), ethnicity (e.g., Aboriginal, African American, Black, Asian, European American, Caucasian, Native American, Native Hawaiian, Pacific Islander). Demographic information may further include, but is not limited to, household income (i.e., total income received by all members of the household in a 12-month period), diet type (e.g., vegetarian, non-vegetarian, vegan, ketogenic), or lifestyle type (e.g., rural, urban, seaside, mountain). Demographic information may further include, but is not limited to, type of job (e.g., farming, business, employee), medical history (e.g., information about allergies, illnesses, surgeries, vaccinations, health checkup and test results), or vaccination information (e.g., rotavirus vaccine, nasal influenza vaccine, shingles vaccine, chickenpox vaccine, Covid-19 vaccine).

[0041] At 304, a first neural network model application operation may be performed. In the first neural network model application operation, the circuit 202 may be configured to retrieve the first neural network model 110A from a memory that may store the first neural network model 110A. If the first neural network model 110A is stored in the database 106, the first neural network model 110A may be retrieved from the database 106 and stored in the memory 204. In another scenario, the first neural network model 110A may be pre-stored in the memory 204. In such a case, the circuit 202 may retrieve the first neural network model 110A from the memory 204. The first neural network model 110A may be trained based on at least one of, but not limited to, demographic information, disease information, and anatomical region information associated with a plurality of different individuals. For example, the first neural network model 110A can be trained based on various factors, such as demographic information (e.g., ethnicity, nationality), disease information, and / or anatomical region information, associated with a plurality of different persons, such that applying the first neural network model 110A to the demographic information of the person 112 can facilitate determining a disease associated with the person 112. The circuit 202 can be configured to apply the first neural network model 110A to the demographic information of the person 112. To apply the first neural network model 110A to the demographic information associated with the person 112, various parameters of the demographic information (e.g., age, gender, region, ethnicity, diet type, work type, and medical history) can be provided as inputs to the first neural network model 110A.

[0042] At 306, an ailment determination operation may be performed. In the ailment determination operation, the circuit 202 may be configured to determine an ailment associated with the anatomical region 308B of the person 112. The circuit 202 may determine the ailment associated with the person 112 based on applying the first neural network model 110A to the received demographic information associated with the anatomical region 308B of the person 112. For example, the disease may include, but is not limited to, an infectious disease (such as influenza, measles, HIV, streptococcus, and COVID-19), a deficiency (such as scurvy, rickets, Beiberi's disease, and hypocalcemia), a genetic disease (such as cystic fibrosis, hemophilia, and sickle cell anemia), a genetic disease (such as Down syndrome, trisomy 21, fragile X syndrome, Klinefelter syndrome, and triple X syndrome), a non-genetic disease (such as heart disease, stroke, cancer, or diabetes), a lifestyle-related disease (such as heart disease, arteriosclerosis, stroke, respiratory disease, obesity, or type 2 diabetes), a hormonal disease (such as acromegaly or cystic fibrosis), or a physiological disease (such as asthma, glaucoma, or diabetes). An anatomical region of the person 112 may include, but is not limited to, an ocular region, a subcutaneous region, an epidermal region, a dermal region, a subcutaneous region, a bone region, or a visceral region.

[0043] In one embodiment, the first neural network model 110A can be trained based on factors such as demographic information (e.g., ethnicity, nationality), disease information, and / or anatomical region information associated with a number of different individuals. Example records of a training dataset associated with the first neural network model 110A are described in connection with Table 1 below. TIFF2026501208000002.tif67155 Table 1: Exemplary training data set for the first neural network model 110A

[0044] Referring to Table 1, for example, the training dataset may include a first record of an American woman between 50 and 65 years old who is obese, non-vegetarian, retired, and has a history of type 2 diabetes. According to the first record, the person may have diabetic retinopathy, which may affect their eyes. Further, the training dataset may include a second record of an Asian man between 30 and 35 years old who is an athlete, vegetarian, has a sedentary desk job, and has a history of skin allergies. According to the second record, the person may have acne, which may affect their facial skin. Furthermore, the training dataset may include a third record of a European woman between 40 and 50 years old who is overweight, vegetarian, has a sedentary desk job, and has a history of vitamin deficiency. According to the third record, the person may have calcium deficiency, which may affect their bones. It should be noted that the data presented in Table 1 should be viewed solely as experimental data and should not be construed as limiting the present disclosure.

[0045] In one example, the demographic information of person 112 may indicate that person 112 is a 55-year-old Latino woman who is obese and likely has diabetes. Referring to Table 1, circuit 202 may determine that an individual feature of person 112's demographic information may have the highest similarity with a first record in the training dataset based on applying first neural network model 110A to the demographic information of person 112. Thus, first neural network model 110A may classify person 112's disease as "diabetic retinopathy" and the person's 112's anatomical region as the person's 112's eye.

[0046] At 308, a first set of images reception operation can be performed. In the first image set reception operation, the circuit 202 can be configured to receive a first set of images (e.g., images 308A) associated with an anatomical region 308B of the person 112. For example, as shown in FIG. 3 , the anatomical region 308B can correspond to the eyes of the person 112. The first set of images (e.g., images 308A) can include, but are not limited to, digital images, analog images, two-dimensional images, three-dimensional images, infrared images, X-ray images, ultrasound images, etc. In one embodiment, the first set of images (e.g., images 308A) can be one or more images associated with the entire anatomical region 308B. In another embodiment, the first set of images (e.g., images 308A) can be one or more images associated with a portion of the anatomical region 308B. For example, the anatomical region 308B can be captured in a first image set (e.g., images 308A) as all or part of the anatomical region 308B associated with the person 112. In one embodiment, the first image set (e.g., images 308A) can be received from the database 106. In another embodiment, an image capture device associated with the electronic device 102 captures the first image set (e.g., images 308A) and the first image set (e.g., images 308A) can be received from the image capture device. In another scenario, the first image set (e.g., images 308A) can be pre-stored in the memory 204 of the electronic device 102. In such a case, the first image set (e.g., images 308A) can be retrieved from the memory 204. The circuit 202 can be configured to select the second neural network model 110B from the set of neural network models. The selection of the second neural network model 110B can be based on the determined disease. For example, the memory 204 and / or the database 106 may store a series of neural network models, each associated with a particular disease.

[0047] At 310, a second neural network model application operation can be performed. In the second neural network model application operation, the circuit 202 can be configured to apply the second neural network model 110B to the received first set of images. The selection of the second neural network model 110B from the set of neural network models can be based on the determined disease. Information about the determined disease can be stored in the database 106 or can be stored locally in the memory 204 of the electronic device 102. Upon selecting the second neural network model 110B, the circuit 202 can apply the selected second neural network model 110B to the received first set of images related to the anatomical region 308B of the person 112.

[0048] In one embodiment, the second neural network model 110B can be trained based on a set of images of anatomical regions 308B of a plurality of different individuals. The image sets can be captured over a predetermined time period. The second neural network model 110B can be further trained based on a predetermined range of disease severity (e.g., latent, prodromal, acute, or convalescent, etc.) corresponding to the determined disease. Example records of a training dataset associated with the second neural network model 110B are described in connection with Table 2 below. TIFF2026501208000003.tif52155 Table 2: Exemplary training data set for the second neural network model 110B

[0049] Referring to Table 2, for example, the second neural network model 110B can be associated with an eye disease such as diabetic retinopathy. The training dataset can include a first record including "Image-1" of "Person-1," where "Image-1" can correspond to an eye image captured when "Person-1" is suffering from stage 1 of the disease (i.e., diabetic retinopathy). Similarly, the training dataset can include a second record including "Image-2" of "Person-1," where "Image-2" can correspond to an eye image captured when "Person-1" is suffering from stage 2 of the disease (i.e., diabetic retinopathy). Furthermore, the training dataset can include other records, such as a third record including "Image-3" of "Person-2," where "Image-3" can correspond to an eye image captured when "Person-2" is suffering from stage 2 of the disease (i.e., diabetic retinopathy). Note that the data shown in Table 2 can be considered merely as experimental data and should not be construed as limiting the present disclosure.

[0050] In another embodiment, a second neural network model 110B can be trained based on a set of images of the same person's anatomical region 308B, and further based on a predetermined range of disease severity levels corresponding to the determined disease. The set of images of a particular person can be captured over a predetermined period of time. Example records of a training dataset associated with the second neural network model 110B are described in connection with Table 3 below. TIFF2026501208000004.tif52155 Table 3: Another exemplary training data set for the second neural network model 110B

[0051] Referring to Table 3, for example, the second neural network model 110B can be associated with an eye disease such as diabetic retinopathy. The training dataset can include images of the eyes of the same person, such as "Person-1." For example, the training dataset can include "Image-1," which corresponds to Stage 1 of the disease (i.e., diabetic retinopathy). Similarly, the training dataset can include multiple images corresponding to Stage 2 of the disease. Examples of such images can include "Image-2," "Image-3," and "Image-4." Furthermore, the training dataset can include "Image-5," which corresponds to Stage 3 of the disease, and can also include "Image-6" and "Image-7," which correspond to Stage 4 of the disease. Note that the data shown in Table 3 can be considered merely as experimental data and should not be construed as limiting the present disclosure.

[0052] At 312, a first disease severity determination operation may be performed. In the first disease severity determination operation, the circuit 202 may be configured to determine a first disease severity corresponding to a determined disease associated with the anatomical region 308B of the person 112. The first disease severity determination for the determined disease may be based on application of the second neural network model 110B. For example, the circuit 202 may receive a first set of images associated with the anatomical region 308B of the person 112 based on a determination of a disease (e.g., an infection, a defect, etc.) associated with the anatomical region (e.g., an eye, a skin, etc.) of the person 112. Further, the circuit 202 may be configured to apply the second neural network model 110B to the received first set of images to determine a first disease severity corresponding to the determined disease associated with the anatomical region 308B of the person 112.

[0053] In one example, the received first set of images (e.g., image 308A) can be provided to the second neural network model 110B. The second neural network model 110B can be, for example, a convolutional neural network model or a deep learning model. The second neural network model 110B can convert each of the received first set of images into image features associated with the corresponding image. For example, these features can include edges, lines, predetermined shapes, brightness, hue, saturation, and contours. The second neural network model 110B can include predetermined weights and biases for nodes in various layers and hyperparameters for the second neural network model 110B based on training of the second neural network model 110B. The circuit 202 can apply the predetermined weights, biases, and hyperparameters to the converted features of each of the received set of images to determine a prediction score associated with each of a set of predetermined disease severities. The circuit 202 can compare the determined prediction score to a predetermined threshold to determine a disease stage associated with the person 112. For example, the circuitry 202 may determine that the person 112 has stage 1 diabetic retinopathy based on a received set of images (eg, image 308A).

[0054] An operation to display disease severity and ailment can be performed at 314. In the disease severity and ailment display operation, the circuitry 202 can be configured to control the display device 208 to render information related to the determined disease severity and the determined ailment. For example, the circuitry 202 can display the disease severity and the determined ailment on the display device 208 via a user interface.

[0055] Traditional disease prognostic diagnostic methods require a person to be physically present at a testing facility for diagnosis. Additionally, existing methods require physical contact and / or insertion of medical / surgical instruments for sample collection. Once a sample is collected, various pathological tests can be performed on the collected sample. The time to perform a pathological test can depend on the type of test and the number of physiological parameters to be tested. Furthermore, because pathological tests are performed by radiologists / pathologists, human error may exist.

[0056] In contrast, the electronic device 102 can utilize demographic information and anatomical images associated with a person for automated disease prognosis. A disease associated with an anatomical region of the person can be automatically determined based on application of the first neural network model 110A to the demographic information. A second neural network model 110B (i.e., a model different from the first neural network model 110A) can be selected from a set of neural network models based on the determined disease. The second neural network model 110B can be applied to a first image set (e.g., image 308A) associated with the person's anatomical region 308B to determine a first disease severity corresponding to the determined disease. The determined first disease severity and information related to the determined disease can be displayed to the person. The electronic device 102 can also use the first neural network model 110A to automatically determine a disease that may affect the person and determine the anatomical region of the disease based on demographic information associated with the person. Thus, a first level of screening or filtering of common diseases to which the person is susceptible can be identified for further investigation. After the disease and anatomical region are determined, the person can be prompted to capture an image of the anatomical region or upload a previously captured image of the anatomical region for further investigation. The second neural network model 110B can analyze the image of the anatomical region to automatically determine the disease severity corresponding to the disease. Thus, the process of disease prognosis can be automated based on the systematic identification of the person's disease and the image-based diagnosis of the disease severity corresponding to the disease. The person does not need to physically go to a pathology examination and wait for the examination report. The electronic device 102 can perform disease prognosis noninvasively and remotely, providing accurate results in a short time, which can be important for the person's further treatment.

[0057] Figure 4 illustrates an exemplary processing pipeline for determining disease progression, according to an embodiment of the present disclosure. The description of Figure 4 is provided with reference to elements of Figures 1, 2, and 3. Figure 4 illustrates a processing pipeline 400 for determining disease progression. The processing pipeline 400 illustrates a series of operations that may begin at 402 and end at 410. The series of operations may be performed by the circuitry 202 of the electronic device 102.

[0058] At 402, a first disease severity determination operation may be performed. In the first disease severity determination, the circuit 202 may be configured to determine a first disease severity corresponding to a determined disease associated with the anatomical region 308B of the person 112. The circuit 202 may be configured to receive demographic information associated with the person 112. The disease associated with the anatomical region 308B of the person may be determined based on applying the first neural network model 110A to the demographic information. A second neural network model 110B may be selected from a set of neural network models based on the determined disease. The second neural network model 110B may be applied to a received first set of images associated with the anatomical region 308B of the person to determine a first disease severity corresponding to the determined disease. The received first set of images may correspond to (or be captured at) a first time instance. The determination of the first disease severity is further described, for example, in FIG. 3 (310 and 312).

[0059] At 404, a second disease severity determination operation can be performed. In the second disease severity determination, the circuit 202 can be configured to determine a second disease severity corresponding to a determined disease associated with the anatomical region 308B of the person 112. The circuit 202 can be configured to receive demographic information associated with the person 112. A disease associated with the anatomical region 308B of the person 112 can be determined based on applying the first neural network model 110A to the demographic information. A second neural network model 110B can be selected from the set of neural network models based on the determined disease. The second neural network model 110B can be applied to a received second set of images associated with the anatomical region 308B of the person 112 to determine a second disease severity corresponding to the determined disease. The received second set of images can correspond to a second time instance that is after the first time instance. The second disease severity determination can be similar to the first disease severity determination, for example, as further described in FIG. 3 (310 and 312).

[0060] At 406, a disease severity comparison operation can be performed. In the disease severity comparison operation, the circuit 202 can be configured to compare the determined first disease severity with the determined second disease severity. As described, the first disease severity corresponds to a first set of images captured at a first time instance, and the second disease severity corresponds to a second set of images captured at a second time instance. The circuit 202 can compare the first disease severity with the second disease severity to determine the progression of the disease from the first time instance to the second time instance. For example, a person 112 who may be infected with a disease can desire to know the progression of the disease from the first time instance (when the disease was first detected) to the second time instance (a later time). Based on the determination of the disease progression, it can be determined whether the person 112 is in recovery and has been cured of the disease, or whether the disease has worsened.

[0061] At 408, an ailment progression determination operation can be performed. In the disease progression determination, the circuit 202 can be configured to determine the progression of a disease associated with the person 112 based on a comparison between a first disease severity (at a first time instance) and a second disease severity (at a second time instance). One skilled in the art will understand that the comparison between the first disease severity and the second disease severity facilitates monitoring or analyzing disease progression, since the first disease severity is determined based on a first set of images at a first instance and the second disease severity is determined based on a second set of images at a second instance, with the second time instance being later than the first time instance. For example, for a determined disease of the person 112, it may be necessary to monitor disease progression in order to effectively treat the determined disease. In some scenarios, the process of determining disease progression and monitoring disease treatment can be repeated until the determined disease is completely cured.

[0062] At 410, an ailment progression display operation can be performed. In the ailment progression display operation, the circuitry 202 can be configured to control the display device 208 to render information regarding the determined progression of the determined disease. The person 112 can use the information regarding the determined progression of the person's 112 determined disease to have a follow-up consultation with a medical practitioner or to adapt a treatment plan for the disease based on a previous consultation with a medical practitioner.

[0063] Figure 5 illustrates an exemplary processing pipeline for determining a treatment recommendation, according to an embodiment of the present disclosure. The description of Figure 5 is provided with reference to elements of Figures 1, 2, 3, and 4. Figure 5 illustrates a processing pipeline 500 for determining a treatment recommendation. The processing pipeline 500 illustrates a series of operations starting at 502 and ending at 508. The series of operations may be performed by the circuitry 202 of the electronic device 102.

[0064] At 502, an ailment and progression determination operation can be performed. In the ailment and progression determination operation, the circuit 202 can be configured to determine a determined disease progression based on a comparison of a determined first disease severity at a first time instance and a determined second disease severity at a second time instance. The ailment and progression determination operation is further described, for example, in FIG. 4 (406 and 408).

[0065] At 504, a third neural network model application operation can be performed. In the third neural network model application operation, the circuit 202 can be configured to apply a third neural network model 110C to the determined disease and the determined progression of the determined disease. The third neural network model 110C can be trained based on demographic information, disease information, disease progression information, disease severity information, or treatment plan information associated with a plurality of different persons. For example, the third neural network model 110C can be trained using data related to demographic information (e.g., age, sex, nationality, region, ethnicity, household income), disease information (e.g., infection, deficiency, genetic disease), disease progression information (e.g., cured or worsening), disease severity information (e.g., incubation period, prodromal period, acute period, recovery period), or treatment plan information (e.g., medication recommendation, dosage recommendation, treatment recommendation) associated with a plurality of different persons.

[0066] At 506, a therapeutic recommendation generation operation can be performed. In the therapeutic recommendation generation operation, the circuitry can be configured to generate a therapeutic recommendation based on application of the third neural network model 110C. The therapeutic recommendation can include, but is not limited to, a drug recommendation, a medication recommendation, a treatment recommendation, a diet recommendation, a physical exercise recommendation, a breathing exercise recommendation, a sleep recommendation, an activity recommendation, a meditation / yoga recommendation, a walking / jogging / running recommendation, a cycling recommendation, a swimming recommendation, a workout recommendation, a music recommendation, or a recreation recommendation. Once trained, the third neural network model 110C can generate a therapeutic recommendation based on applying the third neural network model 110C to the determined disease and the determined progression of the determined disease.

[0067] For example, the person 112 may have a disease such as diabetic retinopathy, and the disease may be cured (i.e., the disease progresses) from stage 3 (a first time instance) to stage 4 (a second time instance). The circuit 202 may generate a treatment recommendation, such as a certain dose of a particular insulin medication, a diabetic diet, or particular eye drops to treat the diabetic retinopathy, based on applying the third neural network model 110C to information about the disease (i.e., diabetic retinopathy) and the progression of the disease (from stage 3 to stage 4).

[0068] At 508, a therapeutic recommendation display operation can be performed. In the therapeutic recommendation display operation, the circuitry 202 can be configured to control the display device 208 to display information regarding the determined therapeutic recommendation. The person 112 can use the information regarding the determined therapeutic recommendation to adapt their treatment plan for the disease and, if necessary, follow up with a medical practitioner.

[0069] 6 is a flowchart illustrating exemplary operations for disease prognosis based on demographic information and anatomical images using a neural network model, according to an embodiment of the present disclosure. FIG. 6 illustrates a flowchart 600. The description of flowchart 600 will be provided with reference to elements in FIGS. 1, 2, 3, 4, and 5. Flowchart 600 may include operations 602-618 and may be performed in electronic device 102 or circuit 202. The method illustrated in flowchart 600 may begin at 602 and proceed to 604.

[0070] At 604, demographic information associated with the person 112 may be received. The demographic information associated with the person 112 may be received as user input from the person 112 via the I / O device 206 of the electronic device 102. In another embodiment, the demographic information may be stored in the database 106. The circuit 202 may send a query for the demographic information to the database 106. The database 106 may extract the demographic information based on the received query and send the extracted demographic information to the electronic device 102. The demographic information may include information associated with the person 112 that the circuit 202 may use to determine a disease associated with the anatomical region 308B of the person 112. Receiving the demographic information is further described, for example, in FIG. 3 (302).

[0071] At 606, a first neural network model can be applied to the received demographic information. The circuit 202 can be configured to apply the first neural network model 110A to the demographic information of the person 112. To apply the first neural network model 110A to the demographic information associated with the person 112, various parameters of the demographic information (e.g., age, gender, region, ethnicity, diet type, work type, and medical history) can be provided as inputs to the first neural network model 110A. Applying the first neural network model 110A to the demographic information of the person 112 can facilitate determining a disease associated with the person 112. The application of the first neural network model 110A is further described, for example, in FIG. 3 (304).

[0072] At 608, a disease associated with the anatomical region of the person 112 can be determined based on applying the first neural network model 110A to the received demographic information. The circuit 202 can be configured to determine a disease associated with the anatomical region 308B based on applying the first neural network model 110A. Disease determination is further described, for example, in FIG. 3 (306).

[0073] At 610, a second neural network model 110B can be selected from the set of neural network models based on the determined disease. The circuit 202 can be configured to select the second neural network model 110B from the set of neural network models based on the determined disease. The selection of the second neural network model 110B is further described, for example, in FIG. 3 (308 and 310).

[0074] At 612, a first set of images associated with an anatomical region of the person 112 can be received. In an embodiment, the circuit 202 can be configured to receive a first set of images associated with the anatomical region 308B of the person 112. The first set of images can include, but are not limited to, digital images, analog images, two-dimensional images, three-dimensional images, infrared images, x-ray images, ultrasound images, etc. Receiving the first set of images is further described, for example, in FIG. 3 (308).

[0075] At 614, a selected second neural network model 110B, different from the first neural network model 110A, may be applied to the received first set of images. In an embodiment, the circuit 202 may be configured to apply the second neural network model 110B to the received first set of images. The second neural network model 110B may be different from the first neural network model 110A. Application of the second neural network to determine disease severity is further described, for example, in FIG. 3 (310).

[0076] At 616, a first disease severity (e.g., latent, prodromal, acute, or convalescent) corresponding to the determined disease associated with the anatomical region 308B of the person 112 can be determined based on applying the second neural network model 110B to the received first set of images. The circuit 202 can be configured to determine the first disease severity corresponding to the determined disease associated with the anatomical region 308B of the person 112 based on applying the second neural network model 110B to the received first set of images. Application of the second neural network model 110B to determine the determined disease severity is further described, for example, in FIG. 3 (312).

[0077] At 618, a display device associated with the electronic device 102 can be controlled to render information related to the determined disease severity and the determined disease. The circuitry 202 can be configured to control the display device 208 to render information related to the determined disease severity and the determined disease. Control can proceed to an end.

[0078] Although flowchart 600 is depicted as discrete operations such as 604, 606, 608, 610, 612, 614, 616, and 618, the disclosure is not so limited. Thus, in some embodiments, such discrete operations may be further divided into additional operations, combined into fewer operations, or eliminated depending on the particular implementation without departing from the essence of the disclosed embodiments.

[0079] Various embodiments of the present disclosure may provide a non-transitory computer-readable medium and / or storage medium having stored thereon computer-executable instructions executable by a machine and / or computer to operate an electronic device (e.g., electronic device 102 of FIG. 1 ). Such instructions may cause electronic device 102 to perform operations that may include receiving demographic information associated with a person (e.g., person 112). The operations may further include applying a first neural network model (e.g., first neural network model 110A) to the received demographic information. The operations may further include determining a disease associated with an anatomical region (e.g., anatomical region 308B) of person 112 based on applying first neural network model 110A to the received demographic information. The operations may further include selecting a second neural network model (e.g., second neural network model 110B) from the set of neural network models based on the determined disease. The operations may further include receiving a first set of images associated with anatomical region 308B of person 112. The operations may further include applying the selected second neural network model 110B to the received first set of images, where the second neural network model 110B can be different from the first neural network model 110A. The operations may further include determining a first disease severity corresponding to the determined disease associated with the anatomical region 308B of the person 112 based on applying the second neural network model 110B to the received first set of images. The operations may further include controlling a display device (e.g., display device 208) associated with the electronic device 102 to render information related to the determined disease severity and the determined disease.

[0080] An exemplary embodiment of the present disclosure may provide an electronic device (such as electronic device 102 of FIG. 1 ) including a circuit (such as circuit 202). The circuit 202 may be configured to receive demographic information associated with a person (e.g., person 112). The circuit 202 may be further configured to apply a first neural network model (e.g., first neural network model 110A) to the received demographic information. The circuit 202 may be further configured to determine a disease associated with an anatomical region (e.g., anatomical region 308B) of the person 112 based on applying the first neural network model 110A to the received demographic information. The circuit 202 may be further configured to select a second neural network model (e.g., second neural network model 110B) from a set of neural network models based on the determined disease. The circuit 202 may be further configured to receive a first set of images associated with anatomical region 308B of the person 112. The circuit 202 may be further configured to apply the selected second neural network model 110B to the received first set of images, where the second neural network model 110B may be different from the first neural network model 110A. The circuit 202 may be further configured to determine a first disease severity corresponding to the determined disease associated with the anatomical region 308B of the person 112 based on applying the second neural network model 110B to the received first set of images. The circuit 202 may be further configured to control a display device (e.g., display device 208) associated with the electronic device 102 to render information related to the determined disease severity and the determined disease.

[0081] In some embodiments, the anatomical region may include at least one of an ocular region, a subcutaneous region, an epidermal region, a dermal region, a subcutaneous region, a bone region, or a visceral region. Further, the demographic information associated with the person may include at least one of age, sex, nationality, region, ethnicity, household income, diet type, lifestyle type, occupation type, medical history, or vaccination information. Further, the disease may include at least one of an infectious disease, a deficiency disease, a genetic disease, a genetic disease, a non-genetic disease, a lifestyle-related disease, a hormonal disease, or a physiological disease.

[0082] In one embodiment, the first neural network model 110A can be trained based on at least one of demographic information, disease information, and anatomical region information associated with a plurality of different individuals.

[0083] In one embodiment, the circuit 202 can be further configured to receive a second set of images associated with the anatomical region 308B of the person 112. The received first set of images can correspond to a first time instance, and the received second set of images can correspond to a second time instance. The second time instance can be after the first time instance. The circuit 202 can be further configured to apply the selected second neural network model 110B to the received second set of images. The circuit 202 can be further configured to determine a second disease severity corresponding to the determined disease associated with the anatomical region of the person based on applying the second neural network model 110B to the received second set of images.

[0084] In one embodiment, the second neural network model 110B can be trained based on a set of images of anatomical regions 308B of a plurality of different individuals, and further based on a predetermined range of disease severity levels corresponding to the determined disease. The image sets can be captured over a predetermined period of time.

[0085] In one embodiment, a second neural network model 110B can be trained based on a set of images of the same person's anatomical region 308B, and further based on a predetermined range of disease severity levels corresponding to the determined disease. The image set can be captured over a predetermined period of time.

[0086] In certain embodiments, each of the determined first disease severity and the determined second disease severity can correspond to at least one of an incubation period, a prodromal period, an acute period, or a recovery period.

[0087] In an embodiment, the circuit 202 can be further configured to compare the determined first disease severity with the determined second disease severity. The circuit 202 can be further configured to determine a progression of the determined disease based on the comparison of the determined first disease severity with the determined second disease severity. The circuit 202 can be further configured to control a display device 208 associated with the electronic device to render information regarding the determined progression of the determined disease.

[0088] In an embodiment, circuit 202 can be further configured to apply a third neural network model (e.g., third neural network model 110C) to the determined disease and the determined progression of the determined disease. Circuit 202 can be further configured to generate a treatment recommendation based on applying third neural network model 110C to the determined disease and the determined progression. Circuit 202 can be further configured to control a display device 208 associated with electronic device 102 to render information regarding the determined progression of the determined disease.

[0089] In one embodiment, the treatment recommendation may correspond to at least one of a drug recommendation, a medication recommendation, a therapy recommendation, a diet recommendation, a physical exercise recommendation, a breathing exercise recommendation, a sleep recommendation, an activity recommendation, a meditation / yoga recommendation, a walking / jogging / running recommendation, a cycling recommendation, a swimming recommendation, a workout recommendation, a music recommendation, or a recreation recommendation.

[0090] In one embodiment, the third neural network model 110C can be trained based on demographic information, disease information, disease progression information, disease severity information, or treatment plan information associated with a plurality of different individuals.

[0091] The present disclosure can be implemented in hardware or a combination of hardware and software. The present disclosure can be implemented in a centralized manner in at least one computer system, or in a distributed manner where different elements can be distributed across several interconnected computer systems. Any computer system or other device adapted to perform the methods described herein can be suitable. The combination of hardware and software can be a general-purpose computer system that includes a computer program that, when loaded and executed, can control the computer system to perform the methods described herein. The present disclosure can be implemented in hardware, including portions of integrated circuits that also perform other functions.

[0092] The present disclosure may also be embodied in a computer program product, which includes all features that enable the implementation of the methods described herein and which is capable of executing these methods when loaded into a computer system. A computer program in this context means any expression, in any language, code or notation, of a set of instructions intended to cause a system having information processing capabilities to perform a particular function, either directly, or after a) conversion into another language, code or notation, or b) reproduction in a different content form, or both.

[0093] While the present disclosure has been described with reference to several embodiments, those skilled in the art will recognize that various modifications may be made and equivalents may be substituted without departing from the scope of the disclosure. Additionally, many modifications may be made to adapt a particular situation or material to the teachings of the disclosure without departing from the scope of the disclosure. Therefore, it is not intended that the disclosure be limited to the particular embodiments disclosed, but rather, it is intended to include all embodiments falling within the scope of the appended claims. [Explanation of symbols]

[0094] 300 Processing Pipeline 302 Demographic Information Reception 304 First neural network model application 306 Disease Determination 308 Received first image set 308A Images 308B Anatomical Region 310 Second neural network model application 312 First Disease Severity Determination 314 Disease Severity and Disease Labeling

Claims

1. 1. An electronic device comprising: receive demographic information relating to a person; applying a first neural network model to the received demographic information; determining a disease associated with the anatomical region of the person based on applying the first neural network model to the received demographic information; selecting a second neural network model from the set of neural network models based on the determined disease; receiving a first set of images relating to the anatomical region of the person; applying the selected second neural network model, different from the first neural network model, to the received first set of images; determining a first disease severity corresponding to the determined disease associated with the anatomical region of the person based on applying the second neural network model to the received first set of images; controlling a display device associated with the electronic device to render information about the determined first disease severity and the determined disease; An electronic device comprising a circuit configured to:

2. The anatomical region comprises at least one of an ocular region, a subcutaneous region, an epidermal region, a dermal region, a subcutaneous region, a bone region, or a visceral region; The electronic device of claim 1 .

3. the demographic information associated with the person includes at least one of age, sex, nationality, region, ethnicity, household income, diet type, lifestyle type, occupation type, medical history, or vaccination information; The electronic device of claim 1 .

4. The disease includes at least one of an infectious disease, a deficiency disease, a genetic disease, a non-genetic disease, a lifestyle-related disease, a hormonal disease, or a physiological disease; The electronic device of claim 1 .

5. the first neural network model is trained based on at least one of demographic information, disease information, and anatomical region information associated with a plurality of different individuals; The electronic device of claim 1 .

6. The circuit comprises: receiving a second set of images relating to the anatomical region of the person, wherein: the received first set of images corresponds to a first time instance, and the received second set of images corresponds to a second time instance; the second time instance is after the first time instance; applying the selected second neural network model to the received second set of images; determining a second disease severity corresponding to the determined disease associated with the anatomical region of the person based on applying the second neural network model to the received second set of images. The electronic device of claim 1 , configured to:

7. the second neural network model is trained based on a set of images of a plurality of different human anatomical regions, and further trained based on a predetermined range of disease severity corresponding to the determined disease; the set of images is captured over a predetermined period of time; 7. The electronic device of claim 6.

8. the second neural network model is trained based on a set of images of the same anatomical region of the person, and further trained based on a predetermined range of disease severity corresponding to the determined disease; the set of images is captured over a predetermined period of time; 7. The electronic device of claim 6.

9. each of the determined first disease severity and the determined second disease severity corresponds to at least one of an incubation period, a prodromal period, an acute period, or a recovery period; 7. The electronic device of claim 6.

10. The circuit comprises: comparing the determined first disease severity with the determined second disease severity; determining a progression of the determined disease based on the comparison of the determined first disease severity and the determined second disease severity; controlling the display device associated with the electronic device to render information regarding the determined progression of the determined disease. The electronic device according to claim 6 , configured to:

11. The circuit comprises: applying a third neural network model to the determined disease and the determined progression of the determined disease; generating a treatment recommendation based on applying the third neural network model to the determined disease and the determined progression; controlling the display device associated with the electronic device to render information related to the generated treatment recommendation; The electronic device according to claim 10, configured to:

12. the treatment recommendation corresponds to at least one of a medication recommendation, a dosing recommendation, a treatment recommendation, a dietary recommendation, a physical exercise recommendation, a breathing exercise recommendation, a sleep recommendation, an activity recommendation, a meditation / yoga recommendation, a walking / jogging / running recommendation, a cycling recommendation, a swimming recommendation, a workout recommendation, a music recommendation, or a recreation recommendation; 12. The electronic device of claim 11.

13. the third neural network model is trained based on demographic information, disease information, disease progression information, disease severity information, or treatment plan information associated with a plurality of different individuals; 12. The electronic device of claim 11.

14. In an electronic device, receiving demographic information relating to the person; applying a first neural network model to the received demographic information; determining a disease associated with the anatomical region of the person based on applying the first neural network model to the received demographic information; and selecting a second neural network model from a set of neural network models based on the determined disease; receiving a first set of images associated with the anatomical region of the person; applying the selected second neural network model to the received first set of images, the second neural network model being different from the first neural network model; determining a first disease severity corresponding to the determined disease associated with the anatomical region of the person based on applying the second neural network model to the received first set of images; controlling a display device associated with the electronic device to render information about the determined disease severity and the determined disease; A method comprising:

15. the first neural network model is trained based on at least one of demographic information, disease information, and anatomical region information associated with a plurality of different individuals; 15. The method of claim 14.

16. receiving a second set of images related to the anatomical region of the person; the received first set of images corresponds to a first time instance, and the received second set of images corresponds to a second time instance; the second time instance is after the first time instance; And, applying the selected second neural network model to the received second set of images; determining a second disease severity corresponding to the determined disease associated with the anatomical region of the person based on applying the second neural network model to the received second set of images; 15. The method of claim 14, further comprising:

17. the second neural network model is trained based on a set of images of a plurality of different human anatomical regions, and further trained based on a predetermined range of disease severity corresponding to the determined disease; the set of images is captured over a predetermined period of time; 17. The method of claim 16.

18. applying a third neural network model to the determined disease and the determined progression of the determined disease; generating a treatment recommendation based on applying the third neural network model to the determined disease and the determined progression; controlling the display device associated with the electronic device to render information regarding the determined progression of the determined disease; 15. The method of claim 14, further comprising:

19. the third neural network model is trained based on demographic information, disease information, disease progression information, disease severity information, or treatment plan information associated with a plurality of different individuals; 15. The method of claim 14.

20. A non-transitory computer-readable medium having stored thereon computer-executable instructions that, when executed by an electronic device, receiving demographic information relating to the person; applying a first neural network model to the received demographic information; determining a disease associated with the anatomical region of the person based on applying the first neural network model to the received demographic information; and selecting a second neural network model from a set of neural network models based on the determined disease; receiving a first set of images associated with the anatomical region of the person; applying the selected second neural network model to the received first set of images, the second neural network model being different from the first neural network model; determining a first disease severity corresponding to the determined disease associated with the anatomical region of the person based on applying the second neural network model to the received first set of images; controlling a display device associated with the electronic device to render information about the determined disease severity and the determined disease; 10. A non-transitory computer-readable medium for causing the electronic device to perform operations including:

Images