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

Abstract

Electronic devices and methods are provided for disease prognosis using a neural network model and based on demographic information and anatomical images. An electronic device receives demographic information associated with a person. A patient associated with the anatomical region of the person is determined based on application of the first neural network model on the demographic information. A second neural network model is selected from a set of neural network models based on the determined patient. A second neural network model is applied on the received first set of images associated with the anatomical region of the person to determine a first disease severity corresponding to the determined patient. The second neural network model is different from the first neural network model. A display device associated with the electronic device is controlled to present information about the determined severity of the first disease and the determined patient.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS / INCORPORATED BY REFERENCE

[0002] This application claims priority to U.S. Patent Application No. 18 / 069,447 filed in the U.S. Patent Office on December 21, 2022. The entire contents of each of the above-referenced applications are incorporated herein by reference. Technical Field

[0003] Various embodiments of the present disclosure relate to disease prognosis. More specifically, various embodiments of the present disclosure relate to disease prognosis based on demographic information and anatomical images using a neural network model. Background Art

[0004] Advances in the field of disease prognosis have led to the development of non-contact and non-invasive diagnostic techniques. Typically, disease diagnosis can be performed based on collecting body fluid or blood samples from patients. The collected samples can be transported to a pathology laboratory and tested to diagnose the illness or disease associated with the patient. Since existing invasive techniques require a lot of time to collect samples, disease diagnosis can be a time-consuming process. In addition, sample collection and disease diagnosis can be performed manually, and therefore, disease diagnosis accuracy may be reduced due to human error. In addition, since invasive techniques require human contact, infectious diseases may be easily spread. Therefore, advanced disease prognosis techniques that eliminate physical contact, improve accuracy, and are time-efficient may be desirable.

[0005] Further limitations and disadvantages of conventional and prior approaches will become apparent to those skilled in the art through a comparison of the described systems with certain aspects of the present disclosure, as set forth in the remainder of this application and with reference to the accompanying figures. Summary of the invention

[0006] Electronic devices and methods are provided for disease prognosis based on demographic information and anatomical images using a neural network model, substantially as shown in and / or described in conjunction with at least one of the accompanying drawings, as more fully set forth in the claims.

[0007] These and other features and advantages of the present disclosure may be understood by reviewing the following detailed description of the disclosure and the accompanying drawings, in which like reference numerals refer to like parts throughout. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 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.

[0009] Figure 2 The present invention is a diagram showing an embodiment of the present invention. Figure 1 A block diagram of an exemplary electronic device.

[0010] Figure 3 is a diagram illustrating 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.

[0011] Figure 4 is a diagram illustrating an exemplary processing pipeline for determining patient progression according to an embodiment of the present disclosure.

[0012] Figure 5 is a diagram illustrating an exemplary processing pipeline for determining treatment recommendations according to an embodiment of the present disclosure.

[0013] Figure 6 is a flow chart illustrating an exemplary operation of disease prognosis based on demographic information and anatomical images using a neural network model according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0014] The implementation described below can be found in the disclosed electronic device and method for disease prognosis based on demographic information and anatomical images using a neural network model. An exemplary aspect of the electronic device may include a circuit that can be configured to receive demographic information associated with a person (such as but not limited to age, gender, nationality, region, race, family income, diet type, lifestyle type, work type, medical history, or vaccination information). The electronic device can be configured to determine a patient associated with an anatomical region of the person (such as but not limited to an eye region, a subcutaneous region, an epidermal region, a dermal region, a subcutaneous tissue region, a bone region, or a visceral region) based on the application of a first neural network model on the received demographic information. Examples of patients may include, but are not limited to, infectious diseases, defect diseases, genetic diseases, genetic diseases, non-genetic diseases, lifestyle-related diseases, hormonal diseases, or physiological diseases. The electronic device may also be configured to select a second neural network model from a set of neural network models based on the determined patient. The electronic device may be configured to receive a first set of images associated with an anatomical region of the person. The electronic device may be configured to apply the selected second neural network model on the received first set of images. The second neural network model may be different from the first neural network model. The electronic device may be configured to determine a first disease severity corresponding to a determined patient associated with an anatomical region of the person based on the application of the second neural network model to the received first set of images. Examples of the first disease severity may include, but are not limited to, a latent stage, a prodromal stage, an acute stage, or a recovery stage. In addition, the electronic device may be configured to control a display device associated with the electronic device to present information about the determined first disease severity and the determined patient.

[0015] Conventional disease prognosis techniques may require a person to go to a testing facility in person for diagnosis. In addition, existing techniques may require physical contact and / or insertion of medical / surgical instruments to collect samples. After the samples are collected, various pathological tests may be performed on the collected samples. The duration of performing the pathological test may depend on the type of test and the number of physiological parameters to be tested. In addition, since the pathological test may be performed by a human radiologist / pathologist, there may be a possibility of human error.

[0016] In contrast, the disclosed technology performed by an electronic device can utilize demographic information associated with a person and anatomical images for automatic disease prognosis. Based on the application of a first neural network model on demographic information, a patient associated with an anatomical region of the person can be determined. Based on the determined patient, a second neural network model can be selected from a set of neural network models. The second neural network model can be applied to a first set of images (such as captured images) associated with the anatomical region of the person to determine the severity of a first disease corresponding to the determined patient. The second neural network model can be different from the first neural network model. In addition, information about the determined first disease severity and the determined patient can be displayed to the person. The disclosed technology can use a first neural network model to automatically determine a patient that may infect a person, and can also determine the anatomical region of the patient based on demographic information associated with the person. Therefore, a first-level screening or filtering of common patients that a person may be susceptible to can be identified for further examination. Thereafter, after determining the patient and the anatomical region, 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 examination. The image of the anatomical region can be analyzed by a second neural network model to automatically determine the severity of the disease corresponding to the patient. Therefore, the process of disease prognosis can be automated based on the systematic identification of human patients and the subsequent image-based diagnosis corresponding to the severity of the patient's disease. The person may not need to go to a pathology test in person and wait for the test report. The disclosed technology can perform disease prognosis remotely and non-invasively, and can give accurate results in a short time, which may be crucial for the further treatment of the person.

[0017] Figure 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 1, showing a network environment 100. Network environment 100 may include an electronic device 102, a server 104, a database 106, and a communication network 108. Database 106 may include a set 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. Electronic device 102 may be communicatively coupled to server 104 and database 106 via communication network 108. Figure 1 Also shown in FIG. 1 is a person 112 that may be associated with or may operate the electronic device 102 .

[0018] Electronic device 102 may include suitable logic, circuitry, interfaces, and / or code that may be configured to determine a patient associated with person 112 and a first disease severity of the determined patient. Electronic device 102 may be configured to determine a patient associated with an anatomical region of person 112 based on the application of first neural network model 110A on demographic information associated with person 112. Electronic device 102 may also be configured to select second neural network model 110B from a set of neural network models based on the determined patient. In an embodiment, electronic device 102 may be configured to capture a first set of images of the anatomical region of person 112. In another embodiment, the first set of images may be pre-stored, and electronic device 102 may receive the first set of images from a memory or from an image capture device storing the first set of images. Electronic device 102 may be configured to apply the selected second neural network model 110B on the first set of images of the anatomical region. Electronic device 102 may be configured to determine a first disease severity corresponding to the patient associated with the determined anatomical region of person 112 based on the application of second neural network model 110B on the received first set of images. Furthermore, the electronic device 102 may be configured to control a display device associated with the electronic device 102 to present information regarding the determined first disease severity and the determined patient.

[0019] Examples of electronic device 102 may include medical devices, health-related machines / engines, computing devices, desktops, personal computers, laptops, computer workstations, tablet computing devices, smart phones, cellular phones, mobile phones, consumer electronics (CE) digital devices with displays, televisions (TVs), wearable displays, head-mounted displays, signs, digital mirrors (or smart mirrors), video walls (comprising two or more displays continuously spliced ​​or overlapped together to form one large screen), or edge devices connected to a user's home network or an organizational network.

[0020] 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 (e.g., an eye region, a subcutaneous region, an epidermal region, a dermal region, a subcutaneous tissue region, a bone region, or a visceral region, etc.) of the person 112. 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 via a web application, a cloud application, 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 a combination thereof.

[0021] In at least one embodiment, the server 104 can be implemented as multiple distributed cloud-based resources using several techniques well known to those of ordinary skill in the art. Those of ordinary skill in the art will appreciate that the scope of the present disclosure may not be limited to implementing the server 104 and the electronic device 102 as two separate entities. In some embodiments, the functionality of the server 104 may be fully or at least partially incorporated into the electronic device 102 without departing from the scope of the present disclosure.

[0022] Database 106 may include suitable logic, interfaces, and / or code that may be configured to store information associated with the first set of images, demographic information, and a set of neural network models that 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 as an alternative to) storing a 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) on database 106, the set of neural network models may also be stored in electronic device 102. Furthermore, the first set of images and demographic information may also be stored in electronic device 102.

[0023] The database 106 may be derived from data in a relational or non-relational database or a set of comma separated value (csv) files in a conventional or large data store. The database 106 may be stored or cached on a device such as the server 104 or the electronic device 102. The device storing the database 106 may be configured to receive a query for information associated with at least one of the first set of images, demographic information, or a set of neural network models. For example, the query may be received from the electronic device 102. Based on the received query, the database 106 may extract relevant information, and the device hosting the database 106 may transmit the extracted information to the electronic device 102.

[0024] In some embodiments, the database 106 may be hosted on multiple servers stored in the same or different locations. The operations of the database 106 may be performed using hardware including a processor, a microprocessor (e.g., to perform or control the implementation of one or more operations), a field programmable gate array (FPGA), or an application specific integrated circuit (ASIC). In some other cases, the database 106 may be implemented using software.

[0025] The communication network 108 may include a communication medium through which the electronic device 102 may 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 5G New Radio), a satellite network (such as a network of low-Earth satellites), a Wireless Fidelity (Wi-Fi) network, a personal area network (PAN), a local area network (LAN), or a metropolitan area network (MAN). Various devices in the network environment 100 may be configured to connect to the communication network 108 according to various wired and wireless communication protocols. Examples of such wired and wireless communication protocols may include, but are not limited to, Transmission Control Protocol and Internet Protocol (TCP / IP), User Datagram Protocol (UDP), Hypertext Transfer Protocol (HTTP), File Transfer Protocol (FTP), ZigBee, EDGE, IEEE 802.11, Light Fidelity (Li-Fi), 802.16, IEEE 802.11s, IEEE 802.11g, multi-hop communication, wireless access point (AP), device-to-device communication, cellular communication protocol, and at least one of a Bluetooth (BT) communication protocol.

[0026] Each of a set of neural network models (such as the first neural network model 110A, the second neural network model 110B, and the third neural network model 110C) can be a system of computing networks or artificial neurons arranged as nodes in multiple layers. The multiple layers of each neural network model may include an input layer, one or more hidden layers, and an output layer. Each of the multiple layers may include one or more nodes (or artificial neurons represented by circles, for example). The outputs of all nodes in the input layer may be coupled to at least one node in the hidden layer. Similarly, the input of each hidden layer may be coupled to the output of at least one node in other layers of the neural network model. The output of each hidden layer may be coupled to the input of at least one node in other layers of the neural network model. The nodes in the final layer may receive input from at least one hidden layer to output a result. The number of layers and the number of nodes in each layer may be determined according to hyperparameters of the neural network model. Such hyperparameters may be set before, during, or after training the neural network model on a training data set.

[0027] Each node of each of a set of neural network models can correspond to a mathematical function (e.g., a sigmoid function or a linear rectifier unit) with a set of parameters that are adjustable during training of the network. The set of parameters may include, for example, weight parameters and regularization parameters, etc. Each node can use a mathematical function to calculate an output based on one or more inputs from nodes in other layers (e.g., previous layers) of the neural network model. All or some of the nodes of the neural network model can correspond to the same or different same mathematical functions.

[0028] In the training of the 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 of a given input (from the training data set) matches the correct result of the loss function based on the neural network model. The above process can be repeated for the same or different inputs until the minimum value of the loss function can be achieved and the training error can be minimized. Several training methods are known in the art, such as gradient descent, stochastic gradient descent, batch gradient descent, gradient boosting, and meta-heuristics.

[0029] The neural network model may include electronic data that may be implemented as a software component of an application executable on electronic device 102, for example. The neural network model may rely on a library, an external script, or other logic / instructions executed 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 person 112 to determine a patient associated with an anatomical region of person 112. In addition, a second neural network model 110B may be applied to a first set of images associated with an anatomical region of person 112 to determine a first disease severity corresponding to a determined patient associated with the anatomical region of person 112. In addition, a third neural network model 110C may be applied to the determined patient and the determined progression of the determined patient to generate a treatment recommendation. Examples of generated treatment suggestions may include, but are not limited to, medication suggestions, dosage suggestions, therapy suggestions, dietary suggestions, physical exercise suggestions, breathing exercise suggestions, sleep suggestions, activity suggestions, meditation / yoga suggestions, walking / jogging / running suggestions, bicycling suggestions, swimming suggestions, training suggestions, music suggestions, or entertainment suggestions. Additionally, or alternatively, a set of neural network models may be implemented using hardware including a processor, a microprocessor (e.g., to execute or control the implementation of one or more operations), a field programmable gate array (FPGA), or an application specific integrated circuit (ASIC). Alternatively, in some embodiments, a set of neural network models may be implemented using a combination of hardware and software.

[0030] In an embodiment, the first neural network model 110A may be trained based on at least one of demographic information, patient information, and anatomical region information associated with a plurality of different persons, but is not limited to. In an embodiment, the second neural network model 110B may be trained based on at least one of a set of images of anatomical regions of a plurality of different persons, but is not limited to, and is further trained based on a predefined set of disease severities corresponding to a determined patient, and the set of images may be captured within a predefined time span. For example, the predefined set of disease severities may include, but is not limited to, a latent stage, a prodromal stage, an acute stage, or a recovery stage. In another embodiment, the second neural network model 110B may be trained based on at least one of a set of images of an anatomical region of the same person, but is not limited to, and is further trained based on a predefined set of disease severities corresponding to a determined patient, and the set of images may be captured within a predefined time span. The third neural network model 110C may be trained based on at least one of demographic information, patient information, disease progression information, disease severity information, or treatment plan information associated with a plurality of different persons.

[0031] Examples of a set of neural network models may 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-CNNs, fast R-CNNs, faster R-CNNs, artificial neural networks (ANNs), (You Only Look Once) YOLO networks, RNNs based on long short-term memory (LSTM) networks, CNN+ANNs, LSTM+ANNs, RNNs based on gated recurrent units (GRUs), fully connected neural networks, RNNs based on connectionist temporal classification (CTC), deep Bayesian neural networks, generative adversarial networks (GANs), and / or combinations of these networks. In some embodiments, a learning engine for a set of neural network models may include numerical computing techniques using data flow graphs. In some embodiments, each neural network model may be based on a hybrid architecture of multiple deep neural networks (DNNs).

[0032] In operation, the electronic device 102 may be triggered or receive user input to perform a disease prognosis for a specific person or a specific anatomical region of a person. The electronic device 102 may be configured to receive demographic information associated with the person 112. For example, the demographic information associated with the person 112 may be received by the electronic device 102 as user input from the person 112. The demographic information may include, but is not limited to, age, gender, nationality, region, race, household income, diet type, lifestyle, job type, medical history, or vaccination information. Demographic information may include, but is not limited to, at least one of age, gender (such as male, female, etc.), nationality (such as United States, Spain, Germany, India, etc.), region (such as hilly, tropical, plains, etc.), race (such as Aboriginal, African American or Black, Asian, European American or White, Native American, Native Hawaiian or Pacific Islander, etc.), household income (i.e., the total income earned by all members of the household in a 12-month period), diet type (such as vegetarian, non-vegetarian, vegan, ketogenic, etc.), lifestyle type (such as rural, urban, beach mountain, etc.), job type (agriculture, business, employee, etc.), medical history (such as information about allergies, diseases, surgeries, immunizations, and physical examination and test results, etc.), or vaccination information (rotavirus vaccine, nasal flu vaccine, shingles vaccine, chickenpox vaccine, etc.). For example, in Figure 3 The receipt of demographic information is further described in.

[0033] The electronic device 102 may also be configured to apply the first neural network model 110A on the received demographic information. A set of neural network models may be stored on the database 106. Based on the application of the first neural network model 110A, the electronic device 102 may determine a patient associated with the anatomical region of the person 112. For example, the patient may include, but is not limited to, infectious diseases (such as influenza, measles, HIV, strep throat, and COVID-19), deficiency diseases (such as scurvy, rickets, beriberi, 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, atherosclerosis, stroke, respiratory diseases, obesity, and type 2 diabetes), hormonal diseases (such as acromegaly and cystic fibrosis), or physiological diseases (such as asthma, glaucoma, and diabetes). The anatomical region of the person 112 may include, but is not limited to, an eye region, a subcutaneous region, an epidermal region, a dermal region, a subcutaneous tissue region, a bone region, or a visceral region. Figure 3 Identification of patients based on demographic information is further described in.

[0034] The electronic device 102 may also receive a first set of images associated with an anatomical region of the person 112. In an example, the first set of images may be received from the database 106. In another example, the first set of images may be captured by an image capture device associated with the electronic device 102 and may be received from the image capture device. In another example, the first set of images may be pre-stored on the electronic device 102 in a memory device of the electronic device 102 (such as a memory device). Figure 2 In this case, the first set of images may be retrieved from a memory device of electronic device 102. Electronic device 102 may be configured to select second neural network model 110B from a set of neural network models. The selection of second neural network model 110B may be based on the determined patient. The selected second neural network model 110B may be applied to the first set of images. Based on the application of second neural network model 110B, electronic device 102 may determine a first disease severity corresponding to the determined patient associated with the anatomical region of person 112.

[0035] In an example, the severity of the disease may correspond to, but is not limited to, at least one of a latent stage, a prodromal stage, an acute stage, or a recovery stage. For example, the latent stage may be the time period required for the development of an infection after a person is exposed to a pathogenic organism (such as a bacterium, a virus, or a fungus). The latent stage ends when the initial signs or symptoms of the disease appear in the person. The prodromal stage may correspond to the time period after the latent stage and before the onset of characteristic symptoms of the infection. In the prodromal stage, the infection may be transmitted to other people who have physical contact with the infected person. In the prodromal stage, the source of infection may continue to replicate, which may trigger an immune response in the infected person, and thereby reduce the symptoms to mild and non-specific. The acute stage of the patient may correspond to the active replication or proliferation stage of the pathogen, wherein the number of pathogens in the human body may grow exponentially in a short period of time. In the acute stage, symptoms may appear in the affected organs and the whole body of the infected person due to the strong response of the immune system. The recovery stage may correspond to the recovery stage of the patient, at which stage the symptoms may disappear, and the body of the infected person may return to normal.

[0036] In an embodiment, the second neural network model 110B may be, but is not limited to, trained based on at least one of a set of images of anatomical regions of a plurality of different persons, and further trained based on a predefined set of disease severity levels corresponding to the determined patient. A set of images of a plurality of different persons may be captured within a predefined time span. In another embodiment, the second neural network model 110B may be, but is not limited to, trained based on at least one of a set of images of anatomical regions of the same person, and further trained based on a predefined set of disease severity levels corresponding to the determined patient, and a set of images of the same person may be captured within a predefined time span. For example, Figure 3 Determination of disease severity is further described in .

[0037] In an embodiment, electronic device 102 may be configured to control a display device associated with electronic device 102 to present information about the determined disease severity and the determined patient. Based on the presented information, person 112 or a medical practitioner associated with person 112 may decide on a treatment plan for person 112.

[0038] Figure 2 The present invention is a diagram showing an embodiment of the present invention. Figure 1 A block diagram of an exemplary electronic device of Figure 1 Explanation of the elements in Figure 2 . Reference Figure 2 , a block diagram 200 of an electronic device 102 is shown. The electronic device 102 may include circuitry 202. The electronic device 102 may also include memory 204, input / output (I / O) devices 206, and a network interface 210. The I / O devices 206 may include a display device 208 that may be used to present information about the determined disease severity and the determined patient. The circuitry 202 may be communicatively coupled to the memory 204, the I / O devices 206, and the network interface 210. The circuitry 202 may be configured to communicate with the server 104.

[0039] The circuit 202 may include suitable logic, circuitry, and interfaces that may be configured to execute program instructions associated with different operations to be performed by the electronic device 102. For example, the circuit 202 may be configured to determine a patient associated with the anatomical region of the person 112 based on the application of the first neural network model 110A on the received demographic information. The circuit 202 may also be configured to select a second neural network model 110B from a set of neural network models based on the determined patient. The circuit 202 may be configured to receive a first set of images associated with the anatomical region of the person 112. The circuit 202 may be configured to apply the selected second neural network model 110B on 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 patient associated with the anatomical region of the person based on the application of the second neural network model 110B on the received first set of images. In addition, the circuit 202 may be configured to control a display device 208 associated with the electronic device 102 to present information about the determined first disease severity and the determined patient. Circuit 202 may include one or more special processing units that may be implemented as separate processors. In an embodiment, one or more special processing units may be implemented as an integrated processor or a cluster of processors that collectively perform the functions of one or more special processing units. Circuit 202 may be implemented based on a variety of processor technologies known in the art. Examples of implementations of circuit 202 may be based on 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 circuits.

[0040] 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 operation of the electronic device 102 (and / or the circuit 202). The memory 204 may also be configured to store an operating system and associated applications. The memory 204 may include a set 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 an embodiment, the memory 204 may be configured to store information associated with a patient, a first set of images, demographic information. Examples of implementations of the memory 204 may include, but are not limited to, a random access memory (RAM), a read-only memory (ROM), an 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.

[0041] I / O device 206 may include suitable logic, circuits, interfaces and / or codes that may be configured to receive user input. I / O device 206 may also be configured to provide output in response to user input. For example, I / O device 206 may receive user input indicating demographic information associated with people 112 for determining the patient of people 112. I / O device 206 may also receive user selection of a group of files corresponding to the first group of images for determining the severity of the disease. I / O device 206 may present the determined patient and the determined severity of the disease associated with people 112. I / O device 206 may include various input and output devices that may be configured to communicate with circuit 202. Examples of input devices may include, but are not limited to, touch screens, keyboards, mice, joysticks and / or microphones. Examples of output devices may include, but are not limited to, display devices 208 and / or speakers.

[0042] The display device 208 may include suitable logic, circuitry, interfaces, and / or code that may be configured to present information about the determined severity of the disease and the determined patient on a display screen of the display device 208. According to an embodiment, the display device 208 may include a touch screen to receive user input. The display device 208 may be implemented by several known technologies such as, but not limited to, a liquid crystal display (LCD) display, a light emitting diode (LED) display, a plasma display, and / or an organic LED (OLED) display technology and / or other display technologies. According to an embodiment, the display device 208 may refer to a display screen of a smart glasses device, a 3D display, a perspective display, a projection-based display, an electrochromic display, and / or a transparent display.

[0043] The network interface 210 may include suitable logic, circuitry, interfaces, and / or code that may be configured to establish communication between the electronic device 102 and the server 104 via the communication network 108. The network interface 210 may be implemented using various known technologies that support wired or wireless communication between the electronic device 102 and the communication 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 codec (CODEC) chipset, a subscriber identity module (SIM) card, and / or a local buffer.

[0044] The network interface 210 can communicate with a network such as the Internet, an intranet, and / or a wireless network such as a cellular telephone network, a wireless local area network (LAN), and / or a metropolitan area network (MAN) via wireless communication. The wireless communication can use any of a variety 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 (Wi-Fi) (such as 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, email protocols, instant messaging, and / or short message service (SMS). For example, in Figure 3 , Figure 4 , Figure 5 and Figure 6 The operation of circuit 202 is described in detail in FIG.

[0045] Figure 3 is a diagram illustrating 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 1 and Figure 2 Explanation of the elements in Figure 3 . Reference Figure 3 , a processing pipeline 300 for disease prognosis based on demographic information and anatomical images using a neural network model is shown. In the processing pipeline 300, a sequence of operations is shown that may start at 302 and end at 314. The sequence of operations may be performed by the circuit 202 of the electronic device 102.

[0046] At 302, a demographic information receiving operation may be performed. In the demographic information receiving 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 a 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 on the database 106. The circuit 202 may send a query for the demographic information to the database 106. Based on the received query, the database 106 may extract the demographic information and transmit the extracted demographic information to the electronic device 102. The demographic information may include information associated with the person 112, which the circuit 202 may use to determine a patient 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 (such as male, female, or other gender), nationality (such as the United States, Spain, Germany, India, etc.) or region (such as hilly, tropical, plain, cold, etc.), race (such as Aboriginal, African American, Black, Asian, European American, White, Native American, Native Hawaiian, and Pacific Islander, etc.). Demographic information may also include, but is not limited to, household income (i.e., the total income earned by all members of the household in 12 months), diet type (such as vegetarian, non-vegetarian, vegan, and ketogenic, etc.), or lifestyle type (such as rural, urban, and beach mountain, etc.). Demographic information may also include, but is not limited to, job type (agriculture, business, and salaried employees, etc.), medical history (such as information about allergies, diseases, surgeries, immunizations, physical examinations and test results, etc.), or vaccination information (rotavirus vaccine, nasal flu vaccine, shingles vaccine, chickenpox vaccine, and Covid-19 vaccine, etc.).

[0047] 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 extract the first neural network model 110A from a memory in which the first neural network model 110A may be stored. In the case where the first neural network model 110A is stored in the database 106, the first neural network model 110A may be extracted from the database 106 and stored in the memory 204. In another case, the first neural network model 110A may be pre-stored in the memory 204. In this case, the circuit 202 may extract 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 demographic information, patient information, and anatomical region information associated with a plurality of different persons, but is not limited to. For example, the first neural network model 110A may be trained based on various factors such as demographic information (such as race, nationality, etc.), patient information, and / or anatomical region information associated with a plurality of different persons, so that the application of the first neural network model 110A on the demographic information of the person 112 may help determine the patient associated with the person 112. Circuitry 202 may be configured to apply first neural network model 110A on demographic information of person 112. For application of first neural network model 110A on demographic information associated with person 112, various parameters of the demographic information (e.g., age, gender, region, race, diet type, job type, and medical history) may be fed as inputs to first neural network model 110A.

[0048] At 306, a patient determination operation may be performed. In the patient determination operation, circuitry 202 may be configured to determine a patient associated with anatomical region 308B of person 112. Circuitry 202 may determine a patient associated with person 112 based on application of first neural network model 110A to received demographic information associated with anatomical region 308B of person 112. For example, patients may include, but are not limited to, infectious diseases (such as influenza, measles, HIV, strep throat, and COVID-19), deficiency diseases (such as scurvy, rickets, beriberi, and hypocalcemia), inherited 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, atherosclerosis, stroke, respiratory diseases, obesity, and type 2 diabetes), hormonal diseases (such as acromegaly and cystic fibrosis), or physiological diseases (such as asthma, glaucoma, and diabetes). The anatomical region of the person 112 may include, but is not limited to, an eye region, a subcutaneous region, an epidermal region, a dermal region, a subcutaneous tissue region, a bone region, or a visceral region.

[0049] In an embodiment, first neural network model 110A may be trained based on factors such as demographic information (such as race, nationality, etc.), patient information, and / or anatomical region information associated with a plurality of different persons. An example record of a training data set associated with first neural network model 110A is described in conjunction with Table 1 as follows:

[0050] Table 1: Example training data set for the first neural network model 110A

[0051]

[0052] With reference to Table 1, for example, a training data set may include a first record of an American female in the 50-65 age group, who may be obese, non-vegetarian, retired, and may have a history of type 2 diabetes. According to the first record, a person may suffer from diabetic retinopathy, which may affect the person's eyes. In addition, the training data set may include a second record of an Asian male in the 30-35 age group, who may be an athletic, vegetarian, sedentary desk worker, and may have a history of skin allergies. According to the second record, a person may suffer from acne, which may affect the person's facial skin. In addition, the training data set may include a third record of a European female in the 40-50 age group, who may be overweight, vegan, sedentary desk worker, and may have a history of vitamin deficiency. According to the third record, a person may suffer from calcium deficiency, which may affect the person's bones. It should be noted that the data provided in Table 1 may be considered only as experimental data and should not be construed as limiting the present disclosure.

[0053] In an example, the demographic information of person 112 may indicate that person 112 is a 55-year-old Latin American female who may be obese and may have a medical condition of diabetes. Referring to Table 1, based on the application of first neural network model 110A on the demographic information of person 112, circuitry 202 may determine that individual features of the demographic information of person 112 may have the highest similarity to the first record of the training data set. Therefore, first neural network model 110A may classify the condition of person 112 as "diabetic retinopathy" and classify the anatomical region of person 112 as an eye of person 112.

[0054] At 308, a first set of image receiving operations may be performed. In the first set of image receiving operations, circuitry 202 may be configured to receive a first set of images (e.g., images 308A) associated with anatomical region 308B of person 112. For example, Figure 3As shown, anatomical region 308B may correspond to the eyes of person 112. The first set of images (e.g., image 308A) may include, but are not limited to, digital images, analog images, two-dimensional images, three-dimensional images, infrared images, X-ray images, and ultrasound images, among others. In an embodiment, the first set of images (e.g., image 308A) may be one or more images associated with the entire anatomical region 308B. In another embodiment, the first set of images (e.g., image 308A) may be one or more images associated with multiple portions of anatomical region 308B. For example, anatomical region 308B may be captured as a whole or a portion of anatomical region 308B associated with person 112 in the first set of images (e.g., image 308A). In an embodiment, the first set of images (e.g., image 308A) may be received from database 106. In another embodiment, the first set of images (e.g., image 308A) may be captured by an image capture device associated with electronic device 102 and may be received from the image capture device. In another case, the first set of images (e.g., image 308A) may be pre-stored on the electronic device 102 in the memory 204 of the electronic device 102. In this case, the first set of images (e.g., image 308A) may be retrieved from the memory 204. The circuit 202 may be configured to select the second neural network model 110B from a set of neural network models. The selection of the second neural network model 110B may be based on the determined patient. For example, the memory 204 and / or the database 106 may store a set of neural network models, wherein each model in the set of neural network models may be associated with a certain patient.

[0055] At 310, a second neural network model application operation may be performed. In the second neural network model application operation, circuit 202 may be configured to apply second neural network model 110B to the received first set of images. Selecting second neural network model 110B from the set of neural network models may be based on the determined patient. Information about the determined patient may be stored in database 106, or may be stored locally in memory 204 of electronic device 102. After second neural network model 110B is selected by circuit 202, circuit 202 may apply the selected second neural network model 110B to the received first set of images associated with anatomical region 308B of person 112.

[0056] In an embodiment, second neural network model 110B may be trained based on a set of images of anatomical region 308B of a plurality of different persons. A set of images may be captured within a predefined time span. Second neural network model 110B may be further trained based on a set of predefined disease severity levels (e.g., latent stage, prodromal stage, acute stage, or recovery stage, etc.) corresponding to a determined patient. An example record of a training data set associated with second neural network model 110B is described in conjunction with Table 2 as follows:

[0057] Table 2: Exemplary training data set for the second neural network model 110B

[0058] People and image identifiers Patients and anatomical regions Stages of disease Person-1; Image-1 Diabetic Retinopathy (Eye) Phase 1 Person-1; Image-2 Diabetic Retinopathy (Eye) Phase 2 Person-2; Image-3 Diabetic Retinopathy (Eye) Phase 2 Person-3; Image-4 Diabetic Retinopathy (Eye) Phase 2 Person-1; Image-5 Diabetic Retinopathy (Eye) Phase 3 Person-2; Image-6 Diabetic Retinopathy (Eye) Phase 4 Person-3; Image-7 Diabetic Retinopathy (Eye) Phase 4

[0059] Referring to Table 2, for example, the second neural network model 110B may be associated with a patient with an eye disease such as diabetic retinopathy. The training data set may include a first record including "image-1" of "person-1", wherein "image-1" may correspond to an image of an eye captured when "person-1" suffers from stage 1 of the disease (i.e., diabetic retinopathy). Similarly, the training data set may include a second record including "image-2" of "person-1", wherein "image-2" may correspond to an image of an eye captured when "person-1" suffers from stage 2 of the disease (i.e., diabetic retinopathy). In addition, the training data set may include other records, such as a third record including "image-3" of "person-2", wherein "image-3" may correspond to an image of an eye captured when "person-2" suffers from stage 2 of the disease (i.e., diabetic retinopathy), and so on. It should be noted that the data provided in Table 2 may be regarded as experimental data only and may not be construed as limiting the present disclosure.

[0060] In another embodiment, second neural network model 110B may be trained based on a set of images of anatomical region 308B of the same person, and further trained based on a predefined set of disease severity corresponding to the determined patient. A set of images of a particular person may be captured within a predefined time span. Another example of a record of a training data set associated with second neural network model 110B is described in conjunction with Table 3 as follows:

[0061] Table 3: Another exemplary training data set for the second neural network model 110B

[0062] People and image identifiers Patients and anatomical regions Stages of disease Person-1; Image-1 Diabetic retinopathy (eye) Phase 1 Person-1; Image-2 Diabetic retinopathy (eye) Phase 2 Person-1; Image-3 Diabetic Retinopathy (Eye) Phase 2 Person-1; Image-4 Diabetic Retinopathy (Eye) Phase 2 Person-1; Image-5 Diabetic Retinopathy (Eye) Phase 3 Person-1; Image-6 Diabetic Retinopathy (Eye) Phase 4 Person-1; Image-7 Diabetic retinopathy (eye) Phase 4

[0063] Referring to Table 3, for example, the second neural network model 110B may be associated with a patient with an eye disease such as diabetic retinopathy. The training data set may include images of the eyes of the same person, such as "Person-1". For example, the training data set may include "Image-1" which may correspond to stage 1 of the disease (i.e., diabetic retinopathy). Similarly, the training data set may include multiple images corresponding to stage 2 of the disease. Examples of these images may include "Image-2", "Image-3", and "Image-4". In addition, the training data set may include "Image-5" corresponding to stage 3 of the disease, and may include "Image-6" and "Image-7" which may correspond to stage 4 of the disease. It should be noted that the data provided in Table 3 may be regarded as experimental data only and may not be construed as limiting the present disclosure.

[0064] At 312, a first disease severity determination operation may be performed. In the first disease severity determination operation, circuit 202 may be configured to determine a first disease severity corresponding to a patient determined to be associated with anatomical region 308B of person 112. The determination of the first disease severity of the determined patient may be based on the application of second neural network model 110B. For example, based on the determination of a patient (such as an infectious disease, a defect disease) associated with an anatomical structure (such as an eye, skin, etc.) of person 112, circuit 202 may receive a first set of images associated with anatomical region 308B of person 112. In addition, circuit 202 may be configured to apply second neural network model 110B on the received first set of images to determine a first disease severity corresponding to a patient determined to be associated with anatomical region 308B of person 112.

[0065] In an example, a received first set of images (e.g., images 308A) may be fed to a second neural network model 110B. The second neural network model 110B may be, for example, a convolutional neural network model or a deep learning model. The second neural network model 110B may convert each of the received first set of images into image features associated with the corresponding image. For example, the features may include edges, lines, predetermined shapes, brightness, hue, saturation, and contours. Based on the training of the second neural network model 110B, the second neural network model 110B may include predetermined weights of nodes and biases at each layer and hyperparameters of the second neural network model 110B. The circuit 202 may 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 predefined disease severities. The circuit 202 may compare the determined prediction score with a predefined threshold to determine the stage of a disease associated with the person 112. For example, based on the received set of images (e.g., images 308A), the circuit 202 may determine that the person 112 suffers from stage 1 of diabetic retinopathy.

[0066] At 314, an operation of displaying disease severity and patient status may be performed. In the operation of displaying disease severity and patient status, the circuit 202 may be configured to control the display device 208 to present information about the determined disease severity and the determined patient status. For example, the circuit 202 may display the disease severity and the determined patient status on the display device 208 via the user interface.

[0067] Conventional disease prognosis techniques may require a person to go to a testing facility in person for diagnosis. In addition, existing techniques may require physical contact and / or insertion of medical / surgical instruments to collect samples. After the samples are collected, various pathological tests may be performed on the collected samples. The duration of performing the pathological test may depend on the type of test and the number of physiological parameters to be tested. In addition, since the pathological test may be performed by a radiologist / pathologist, there may be a possibility of human error.

[0068] In contrast, electronic device 102 may utilize demographic information and anatomical images associated with a person for automatic disease prognosis. Based on the application of first neural network model 110A on demographic information, patients associated with the anatomical region of the person may be automatically determined. Based on the determined patient, a second neural network model 110B (i.e., different from first neural network model 110A) may be selected from a set of neural network models. Second neural network model 110B may be applied to a first set of images (e.g., image 308A) associated with the anatomical region 308B of the person to determine a first disease severity corresponding to the determined patient. Information about the determined first disease severity and the determined patient may be displayed to the person. Electronic device 102 may use first neural network model 110A to automatically determine patients that may infect the person, and may also determine the anatomical region of the patient based on demographic information associated with the person. Thus, a first level of screening or filtering of common patients that a person may be susceptible to may be identified for further examination. Thereafter, after the patient and anatomical region are determined, the person may be prompted to capture an image of the anatomical region, or upload a previously captured image of the anatomical region, for further examination. The image of the anatomical region can be analyzed by the second neural network model 110B to automatically determine the severity of the disease corresponding to the patient. Therefore, the process of disease prognosis can be automated based on the system identification of the human patient and the subsequent image-based diagnosis corresponding to the severity of the disease of the patient. The person may not need to go to the pathology test in person and wait for the test report. The electronic device 102 can perform disease prognosis remotely and non-invasively, and can give accurate results in a short time, which is crucial for the further treatment of the person.

[0069] Figure 4is a diagram illustrating an exemplary processing pipeline for determining patient progression according to an embodiment of the present disclosure. Figure 1 , Figure 2 and Figure 3 Explanation of the elements in Figure 4 . Reference Figure 4 , a processing pipeline 400 for determining patient progress is shown. In the processing pipeline 400, a sequence of operations is shown that may start at 402 and end at 410. The sequence of operations may be performed by the circuit 202 of the electronic device 102.

[0070] At 402, a first disease severity determination operation may be performed. In the first disease severity determination, circuit 202 may be configured to determine a first disease severity corresponding to a determined patient associated with anatomical region 308B of person 112. Circuit 202 may be configured to receive demographic information associated with person 112. Based on the application of first neural network model 110A to the demographic information, a patient associated with anatomical region 308B of the person may be determined. Based on the determined patient, a second neural network model 110B may be selected from a set of neural network models. Second neural network model 110B may be applied to a received first set of images associated with anatomical region 308B of the person to determine a first disease severity corresponding to the determined patient. The received first set of images may correspond to a first moment in time (or may be captured at a first moment in time). For example, at Figure 3 The determination of the first disease severity is further described in (at 310 and 312).

[0071] At 404, a second disease severity determination operation may be performed. In the second disease severity determination, circuit 202 may be configured to determine a second disease severity corresponding to a determined patient associated with anatomical region 308B of person 112. Circuit 202 may be configured to receive demographic information associated with person 112. Based on the application of first neural network model 110A on the demographic information, a patient associated with anatomical region 308B of person 112 may be determined. Based on the determined patient, a second neural network model 110B may be selected from a set of neural network models. Second neural network model 110B may be applied to a received second set of images associated with anatomical region 308B of person 112 to determine a second disease severity corresponding to the determined patient. The received second set of images may correspond to a second moment in time, which may be after the first moment in time. As, for example, at Figure 3 As further described in (at 310 and 312), the determination of the second disease severity can be similar to the determination of the first disease severity.

[0072] At 406, a disease severity comparison operation may be performed. In the disease severity comparison operation, the circuit 202 may be configured to compare a determined first disease severity and a determined second disease severity. As discussed, the first disease severity corresponds to a first set of images captured at a first moment in time, and the second disease severity corresponds to a second set of images captured at a second moment in time. The circuit 202 may compare the first disease severity and the second disease severity to determine the progression of the disease from the first moment in time to the second moment in time. For example, a person 112 who may be infected with a disease may wish to know the progression of the disease from a first moment in time (the time when the disease was initially detected) to a second moment in time (a later time). Based on the determination of the progression of the disease, it may be apparent whether the person 112 is in the process of recovery, whether the patient has been cured, or whether the patient has deteriorated.

[0073] At 408, a patient progression determination operation may be performed. In the patient progression determination, the circuit 202 may be configured to determine the progression of a disease associated with the person 112 based on a comparison of a first disease severity (at a first moment) with a second disease severity (at a second moment). Those skilled in the art will appreciate that since the first disease severity is determined based on a first set of images at a first moment, the second disease severity is determined based on a second set of images at a second moment, and the second moment is after the first moment, the comparison of the first disease severity and the second disease severity helps to monitor or analyze the progression of the patient. For example, for a patient of the determined person 112, it may be necessary to monitor the progression of the patient in order to effectively treat the determined patient. In some cases, the process of determining patient progression to monitor the treatment of the patient may be iterated until the determined patient is completely cured.

[0074] At 410, a patient progress display operation may be performed. In the patient progress display operation, the circuitry 202 may be configured to control the display device 208 to present information regarding the determined progress of the determined patient. The information regarding the determined progress of the determined patient for the person 112 may enable the person 112 to have a follow-up consultation with a medical practitioner, or to adjust the patient's treatment plan based on a previous consultation with a medical practitioner.

[0075] Figure 5 is a diagram illustrating an exemplary processing pipeline for determining treatment recommendations according to an embodiment of the present disclosure. Figure 1 , Figure 2 , Figure 3 and Figure 4 Explanation of the elements in Figure 5 . Reference Figure 5, a processing pipeline 500 for determining a treatment recommendation is shown. In the processing pipeline 500, a sequence of operations is shown that may start at 502 and end at 508. The sequence of operations may be performed by the circuit 202 of the electronic device 102.

[0076] At 502, a patient and progression determination operation may be performed. In the patient and progression determination operation, the circuit 202 may be configured to determine the progression of the determined patient based on a comparison of a first disease severity determined at a first time and a second disease severity determined at a second time. For example, Figure 4 The patient progress determination operation is further described in (at 406 and 408).

[0077] At 504, a third neural network model application operation may be performed. In the third neural network model application operation, the circuit 202 may be configured to apply the third neural network model 110C to the determined patient and the determined progress of the determined patient. The third neural network model 110C may be trained based on demographic information, patient information, disease progression information, disease severity information, or treatment plan information associated with a plurality of different people. For example, data on demographic information (such as age, gender, nationality, region, race, family income, etc.), patient information (such as infectious diseases, defect diseases, genetic diseases, etc.), patient progression information (such as recovery or deterioration, etc.), disease severity information (such as latent stage, prodromal stage, acute stage, or recovery stage, etc.), or treatment plan information (such as medication recommendations, dosage recommendations, therapy recommendations, etc.) associated with a plurality of different people may be used to train the third neural network model 110C.

[0078] At 506, a treatment suggestion generation operation may be performed. In the treatment suggestion generation operation, the circuitry may be configured to generate treatment suggestions based on the application of the third neural network model 110C. The treatment suggestions may include, but are not limited to, medication suggestions, dosage suggestions, therapy suggestions, diet suggestions, physical exercise suggestions, breathing exercise suggestions, sleep suggestions, activity suggestions, meditation / yoga suggestions, walking / jogging / running suggestions, bicycling suggestions, swimming suggestions, training suggestions, music suggestions, or entertainment suggestions. The third neural network model 110C when trained may be capable of generating treatment suggestions based on the application of the third neural network model 110C to the determined patient and the determined progression of the determined patient.

[0079] For example, person 112 may have a condition such as diabetic retinopathy, and the condition may be cured from stage 3 (at the first time) to stage 4 (at the second time) (i.e., progression of the disease). Based on the application of the third neural network model 110C to information about the condition (i.e., diabetic retinopathy) and the progression of the disease (from stage 3 to stage 4), circuit 202 may generate a treatment recommendation, such as a dose of a certain insulin medication, a diabetic diet, or a certain eye drop to treat diabetic retinopathy.

[0080] At 508, a treatment recommendation display operation may be performed. In the treatment recommendation display operation, circuitry 202 may be configured to control display device 208 to present information regarding the determined treatment recommendation. Information regarding the determined treatment recommendation may enable person 112 to adjust the treatment plan for the patient and conduct a follow-up consultation with a medical practitioner if necessary.

[0081] Figure 6 is a flow chart illustrating an exemplary operation of disease prognosis based on demographic information and anatomical images using a neural network model according to an embodiment of the present disclosure. Figure 6 , showing a flow chart 600. Figure 1 , Figure 2 , Figure 3 , Figure 4 and Figure 5 The elements in 600 are described in flowchart 600. Flowchart 600 may include operations from 602 to 618 and may be implemented in electronic device 102 or circuit 202. The method described in flowchart 600 may start at 602 and proceed to 604.

[0082] At 604, demographic information associated with person 112 may be received. The demographic information associated with person 112 may be received as user input from person 112 via I / O device 206 of electronic device 102. In another embodiment, the demographic information may be stored on database 106. Circuit 202 may send a query for the demographic information to database 106. Based on the received query, database 106 may extract the demographic information and transmit the extracted demographic information to electronic device 102. The demographic information may include information associated with person 112, which circuit 202 may use to determine a patient associated with anatomical region 308B of person 112. For example, in Figure 3 The receipt of demographic information is further described in (at 302).

[0083] At 606, the first neural network model may be applied to the received demographic information. Circuitry 202 may be configured to apply first neural network model 110A to the demographic information of person 112. To apply first neural network model 110A to the demographic information associated with person 112, various parameters of the demographic information (e.g., age, gender, region, race, diet type, job type, and medical history) may be fed as inputs to first neural network model 110A. Application of first neural network model 110A to the demographic information of person 112 may help determine a patient associated with person 112. For example, in Figure 3 The application of the first neural network model 110A is further described in (at 304).

[0084] At 608, patients associated with the anatomical region of person 112 may be determined based on the application of first neural network model 110A to the received demographic information. Circuitry 202 may be configured to determine patients associated with anatomical region 308B based on the application of first neural network model 110A. For example, Figure 3 The determination of the patient is further described in (at 306).

[0085] At 610, the second neural network model 110B may be selected from a set of neural network models based on the determined patient. The circuit 202 may be configured to select the second neural network model 110B from a set of neural network models based on the determined patient. For example, Figure 3 The selection of the second neural network model 110B is further described in (at 308 and 310).

[0086] At 612, a first set of images associated with an anatomical region of person 112 may be received. In an embodiment, circuit 202 may be configured to receive a first set of images associated with anatomical region 308B of person 112. The first set of images may include, but are not limited to, digital images, analog images, two-dimensional images, three-dimensional images, infrared images, X-ray images, ultrasound images, etc. For example, Figure 3 The receiving of the first set of images is further described in (at 308).

[0087] At 614, the selected second neural network model 110B may be applied to the received first set of images, wherein the second neural network model 110B is different from the first neural network model 110A. 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. For example, Figure 3 Applying the second neural network to determine disease severity is further described in (at 310).

[0088] At 616, a first disease severity level (such as a latent stage, a prodromal stage, an acute stage, or a recovery stage, etc.) corresponding to the determined condition associated with anatomical region 308B of person 112 may be determined based on the application of second neural network model 110B to the received first set of images. Circuitry 202 may be configured to determine the first disease severity level corresponding to the determined condition associated with anatomical region 308B of person 112 based on the application of second neural network model 110B to the received first set of images. For example, in Figure 3 The application of the second neural network model 110B to the determination of the disease severity of the determined patient is further described (at 312).

[0089] At 618, a display device associated with the electronic device 102 may be controlled to present information about the determined disease severity and the determined patient. The circuit 202 may be configured to control the display device 208 to present information about the determined disease severity and the determined patient. Control may be passed to end.

[0090] Although flowchart 600 is shown as discrete operations, such as 604, 606, 608, 610, 612, 614, 616, and 618, the present disclosure is not limited thereto. Therefore, in some embodiments, such discrete operations may be further divided into additional operations, combined into fewer operations, or eliminated, depending on the specific implementation, without departing from the essence of the disclosed embodiments.

[0091] Various embodiments of the present disclosure may provide non-transitory computer-readable media and / or storage media having computer-executable instructions stored thereon, which instructions may be executed by a machine and / or a computer to operate an electronic device (e.g., Figure 1The electronic device 102 may include receiving demographic information associated with a person (e.g., person 112). Such instructions may cause the electronic device 102 to perform operations that may include receiving demographic information associated with a person (e.g., person 112). The operations may also include applying a first neural network model (e.g., first neural network model 110A) to the received demographic information. The operations may also include determining a patient associated with an anatomical region (e.g., anatomical region 308B) of person 112 based on the application of the first neural network model 110A to the received demographic information. The operations may also include selecting a second neural network model (e.g., second neural network model 110B) from a set of neural network models based on the determined patient. The operations may also include receiving a first set of images associated with anatomical region 308B of person 112. The operations may also include applying the selected second neural network model 110B to the received first set of images. Here, the second neural network model 110B may be different from the first neural network model 110A. The operations may also include determining a first disease severity corresponding to the patient determined to be associated with anatomical region 308B of person 112 based on the application of the second neural network model 110B to the received first set of images. Operations may also include controlling a display device (eg, display device 208 ) associated with the electronic device 102 to present information regarding the determined severity of the disease and the determined patient.

[0092] Exemplary aspects of the present disclosure may provide an electronic device (such as a Figure 1Electronic device 102 of circuit 202). Circuit 202 may be configured to receive demographic information associated with a person (e.g., person 112). Circuit 202 may also be configured to apply a first neural network model (e.g., first neural network model 110A) on the received demographic information. Circuit 202 may also be configured to determine a patient associated with an anatomical region (e.g., anatomical region 308B) of person 112 based on the application of first neural network model 110A on the received demographic information. Circuit 202 may also be 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 patient. Circuit 202 may also be configured to receive a first set of images associated with anatomical region 308B of person 112. Circuit 202 may also be configured to apply the selected second neural network model 110B on the received first set of images. Here, second neural network model 110B may be different from first neural network model 110A. Circuitry 202 may also be configured to determine, based on application of second neural network model 110B to the received first set of images, a first disease severity corresponding to a determined condition associated with anatomical region 308B of person 112. Circuitry 202 may also be configured to control a display device (e.g., display device 208) associated with electronic device 102 to present information regarding the determined disease severity and the determined condition.

[0093] In an embodiment, the anatomical region may include at least one of an eye region, a subcutaneous region, an epidermal region, a dermal region, a subcutaneous tissue region, a bone region, or a visceral region. In addition, demographic information associated with the person may include at least one of age, gender, nationality, region, race, family income, diet type, lifestyle type, work type, medical history, or vaccination information. In addition, the patient may include at least one of an infectious disease, a defect disease, a genetic disease, a genetic disease, a non-genetic disease, a lifestyle-related disease, a hormonal disease, or a physiological disease.

[0094] In an embodiment, the first neural network model 110A may be trained based on at least one of demographic information, patient information, and anatomical region information associated with a plurality of different persons.

[0095] In an embodiment, circuit 202 may also be configured to receive a second set of images associated with anatomical region 308B of person 112. The received first set of images may correspond to a first moment in time, and the received second set of images may correspond to a second moment in time. The second moment in time may be after the first moment in time. Circuit 202 may also be configured to apply the selected second neural network model 110B to the received second set of images. Circuit 202 may also be configured to determine a second disease severity corresponding to the determined disease associated with the anatomical region of the person based on the application of the second neural network model 110B to the received second set of images.

[0096] In an embodiment, the second neural network model 110B may be trained based on a set of images of the anatomical region 308B of a plurality of different persons, and further based on a set of predefined disease severity levels corresponding to the determined patient. The set of images may be captured within a predefined time span.

[0097] In an embodiment, the second neural network model 110B may be trained based on a set of images of the anatomical region 308B of the same person and further trained based on a predefined set of disease severity corresponding to the determined patient. The set of images may be captured within a predefined time span.

[0098] In an embodiment, each of the determined first disease severity and the determined second disease severity may correspond to at least one of a latent stage, a prodromal stage, an acute stage, or a recovery stage.

[0099] In an embodiment, the circuit 202 may be further configured to compare the determined first disease severity and the determined second disease severity. The circuit 202 may be further configured to determine the determined progression of the patient based on the comparison of the determined first disease severity and the determined second disease severity. The circuit 202 may be further configured to control a display device 208 associated with the electronic device to present information about the determined progression of the patient.

[0100] In an embodiment, circuit 202 may also be configured to apply a third neural network model (e.g., third neural network model 110C) to the determined patient and the determined progression of the determined patient. Circuit 202 may also be configured to generate a treatment recommendation based on the application of third neural network model 110C to the determined patient and the determined progression. Circuit 202 may also be configured to control display device 208 associated with electronic device 102 to present information about the determined progression of the determined patient.

[0101] In an embodiment, the treatment suggestion may correspond to at least one of a medication suggestion, a dosage suggestion, a therapy suggestion, a diet suggestion, a physical exercise suggestion, a breathing exercise suggestion, a sleep suggestion, an activity suggestion, a meditation / yoga suggestion, a walking / jogging / running suggestion, a cycling suggestion, a swimming suggestion, a training suggestion, a music suggestion, or an entertainment suggestion.

[0102] In an embodiment, the third neural network model 110C may be trained based on demographic information, patient information, disease progression information, disease severity information, or treatment plan information associated with a plurality of different persons.

[0103] The present disclosure may be implemented in hardware or in a combination of hardware and software. The present disclosure may be implemented in a centralized manner in at least one computer system or in a distributed manner in which different elements may be distributed across several interconnected computer systems. A computer system or other device suitable for implementing the methods described herein may be suitable. The combination of hardware and software may be a general-purpose computer system with a computer program that, when loaded and executed, may control the computer system so that it implements the methods described herein. The present disclosure may be implemented in hardware that includes a portion of an integrated circuit that also performs other functions.

[0104] The present disclosure may also be embedded in a computer program product comprising all the features enabling the implementation of the methods described herein and capable of carrying out these methods when loaded into a computer system. In this context, a computer program means any expression of a set of instructions in any language, code or notation that is intended to cause a system with information processing capabilities to perform certain functions, either directly or after either or both of the following: a) conversion into another language, code or notation; b) reproduction in a different material form.

[0105] Although the present disclosure is described with reference to certain embodiments, it will be appreciated by those skilled in the art that various changes may be made and equivalents may be substituted without departing from the scope of the present disclosure. In addition, many modifications may be made to adapt specific circumstances or materials to the teachings of the present disclosure without departing from its scope. Therefore, it is intended that the present disclosure is not limited to the specific embodiments disclosed, but that the present disclosure includes all embodiments falling within the scope of the appended claims.

Claims

1. An electronic device, comprising: A circuit, the circuit being configured as: receiving demographic information associated with a person; applying a first neural network model on the received demographic information; determining a patient associated with an anatomical region of the person based on application of the first neural network model to the received demographic information; selecting a second neural network model from a group of neural network models based on the determined patient; receiving a first set of images associated with an anatomical region of a person; Applying a selected second neural network model on the received first set of images, wherein the second neural network model is different from the first neural network model; Determining a first disease severity for the patient corresponding to the determined condition associated with the anatomical region of the person based on application of the second neural network model to the received first set of images; and A display device associated with the electronic device is controlled to present information about the determined first disease severity and the determined patient.

2. The electronic device according to claim 1, wherein: The anatomical region includes at least one of an ocular region, a subcutaneous region, an epidermal region, a dermal region, a subcutaneous tissue region, a bone region, or a visceral region.

3. The electronic device according to claim 1, wherein: The demographic information associated with the person includes at least one of age, gender, nationality, region, race, household income, diet type, lifestyle type, job type, medical history, or vaccination information.

4. The electronic device according to claim 1, wherein: The patient includes at least one of an infectious disease, a defect disease, a hereditary disease, a genetic disease, a non-genetic disease, a lifestyle-related disease, a hormonal disease or a physiological disease.

5. The electronic device according to claim 1, wherein: The first neural network model is trained based on at least one of demographic information, patient information, and anatomical region information associated with a plurality of different persons.

6. The electronic device according to claim 1, wherein: The circuit is configured as: receiving a second set of images associated with an anatomical region of a person, wherein: The first set of images received corresponds to a first moment in time, the second set of images received corresponds to a second moment in time, and The second moment is after the first moment; applying the selected second neural network model on the received second set of images; and Based on application of the second neural network model to the received second set of images, a second disease severity corresponding to the determined condition associated with the anatomical region of the person is determined.

7. The electronic device according to claim 6, wherein: The second neural network model is trained based on a set of images of anatomical regions of a plurality of different persons and further trained based on a predefined set of disease severity levels corresponding to the determined patient, and The set of images is captured within a predefined time span.

8. The electronic device according to claim 6, wherein: A second neural network model is trained based on a set of images of an anatomical region of the same person and is further trained based on a predefined set of disease severity levels corresponding to the determined patient, and The set of images is captured within a predefined time span.

9. The electronic device according to claim 6, wherein: Each of the determined first disease severity and the determined second disease severity corresponds to at least one of a latent stage, a prodromal stage, an acute stage, or a recovery stage.

10. The electronic device according to claim 6, wherein: The circuit is configured as: comparing the determined first disease severity and the determined second disease severity; determining progression of the determined patient condition based on a comparison of the determined first disease severity and the determined second disease severity; as well as The display device associated with the electronic device is controlled to present information regarding the determined progress of the determined patient.

11. The electronic device according to claim 10, wherein: The circuit is configured as: applying a third neural network model to the identified patient and the determined progression of the identified patient; generating treatment recommendations based on application of a third neural network model to the identified patients and identified progression; as well as The display device associated with the electronic device is controlled to present information regarding the generated treatment recommendation.

12. The electronic device according to claim 11, wherein: The treatment suggestion corresponds to at least one of a medication suggestion, a dosage suggestion, a therapy suggestion, a diet suggestion, a physical exercise suggestion, a breathing exercise suggestion, a sleep suggestion, an activity suggestion, a meditation / yoga suggestion, a walking / jogging / running suggestion, a cycling suggestion, a swimming suggestion, a training suggestion, a music suggestion, or an entertainment suggestion.

13. The electronic device according to claim 11, wherein: The third neural network model is trained based on demographic information, patient information, patient progression information, disease severity information, or treatment plan information associated with a plurality of different persons.

14. A method comprising: In electronic devices: receiving demographic information associated with a person; applying a first neural network model on the received demographic information; determining a patient associated with an anatomical region of the person based on application of the first neural network model to the received demographic information; selecting a second neural network model from a group of neural network models based on the determined patient; receiving a first set of images associated with an anatomical region of a person; Applying a selected second neural network model on the received first set of images, wherein the second neural network model is different from the first neural network model; Determining a first disease severity for the patient corresponding to the determined condition associated with the anatomical region of the person based on application of the second neural network model to the received first set of images; and A display device associated with the electronic device is controlled to present information regarding the determined disease severity and the determined patient.

15. The method according to claim 14, wherein: The first neural network model is trained based on at least one of demographic information, patient information, and anatomical region information associated with a plurality of different persons.

16. The method according to claim 14, further comprising: receiving a second set of images associated with an anatomical region of a person, wherein: The first set of images received corresponds to a first moment in time, the second set of images received corresponds to a second moment in time, and The second moment is after the first moment; applying the selected second neural network model on the received second set of images; and Based on application of the second neural network model to the received second set of images, a second disease severity corresponding to the determined condition associated with the anatomical region of the person is determined.

17. The method according to claim 16, wherein: The second neural network model is trained based on a set of images of anatomical regions of a plurality of different persons and further trained based on a predefined set of disease severity levels corresponding to the determined patient, and The set of images is captured within a predefined time span.

18. The method according to claim 14, further comprising: applying a third neural network model to the identified patients and the identified patient progression; generating treatment recommendations based on application of a third neural network model to the identified patients and identified progression; as well as The display device associated with the electronic device is controlled to present information regarding the determined progress of the determined patient.

19. The method according to claim 14, wherein: The third neural network model is trained based on demographic information, patient information, disease progression information, disease severity information, or treatment plan information associated with a plurality of different persons.

20. A non-transitory computer-readable medium having computer-executable instructions stored thereon, the instructions, when executed by an electronic device, causing the electronic device to perform operations, the operations comprising: receiving demographic information associated with a person; applying a first neural network model on the received demographic information; determining a patient associated with an anatomical region of the person based on application of the first neural network model to the received demographic information; selecting a second neural network model from a group of neural network models based on the determined patient; receiving a first set of images associated with an anatomical region of a person; Applying a selected second neural network model on the received first set of images, wherein: The second neural network model is different from the first neural network model; Determining a first disease severity for the patient corresponding to the determined condition associated with the anatomical region of the person based on application of the second neural network model to the received first set of images; and A display device associated with the electronic device is controlled to present information regarding the determined disease severity and the determined patient.

Images