Server for predicting determination on diabetic foot on basis of plurality of pieces of data on basis of prediction model, and driving method therefor

Abstract

According to various embodiments, a server for predicting determination on a diabetic foot on the basis of a plurality of pieces of data on the basis of a prediction model, comprises: a communication interface; a memory; and a processor, wherein the processor is configured to: obtain at least one piece of image data and at least one piece of first sensing data from an external server of an external user through the communication interface; obtain first ulcer output data by inputting the at least one piece of image data and the at least one piece of first sensing data to the prediction model; when it is determined that the first ulcer output data exceeds a preset first threshold value on the basis of a result of comparing the first ulcer output data with the preset first threshold value, output that a foot ulcer of the external user is likely to be diabetic foot ulcer; when it is determined that the first ulcer output data exceeds a second threshold value set to be greater than the first threshold value on the basis of a result of comparing the first ulcer output data with the second threshold value, output that the foot ulcer of the external user is highly likely to be the diabetic foot ulcer; and transmit, through the communication interface, result data for the first ulcer output data determined to exceed the first threshold value and / or the second threshold value, and guideline data presenting at least one guideline on the basis of the result data, wherein the prediction model is trained on the basis of a plurality of pieces of image data, a plurality of pieces of first sensing data, and a plurality of pieces of second sensing data, which are obtained from a plurality of users, a plurality of pieces of result data output from the plurality of users, and at least one piece of professional opinion data obtained by observing the plurality of users.

Description

A server for predicting diabetic foot diagnosis based on multiple data and a method for operating the same based on a predictive model.

[0001] Various embodiments of the present invention relate to a server for predicting diabetic foot diagnosis based on a plurality of data based on a prediction model, and a method for operating the same, and more particularly, to a server for predicting diabetic foot diagnosis based on a plurality of data based on a prediction model capable of easily predicting diabetic foot diagnosis of an external user by inputting a plurality of data acquired from an external electronic device into a prediction model and using the output result values, and a method for operating the same.

[0002] Recently, the incidence of diabetic foot disease in patients with type 2 diabetes has been steadily increasing worldwide. The prevalence of diabetic foot disease in Korea has also been reported to have approximately doubled over a 10-year period, from 1.2% in 2002 (Chung et al., 2006) to 2.9% in 2011 (Bae et al., 2016). In particular, it is known that 70% of patients with foot ulcers experience a recurrence within 5 years of ulcer treatment (Armstrong, Boulton, & Bus, 2017), and the treatment of recurrent foot ulcers is worse than the initial outcome (Snyder et al., 2010). Long-term foot ulcers can lead to significant financial burden due to high treatment costs (Hoogeveen, Dorresteijn, Kiregsman, & Valk, 2015). For this reason, prevention of diabetic foot is important, and Bus and van Netten (2016) reported that the incidence of foot ulcers can be prevented by 75% through preventive management of diabetic foot.

[0003] In addition, to reduce the burden associated with diabetic foot complications, the International Working Group on the Diabetic Foot (IWGDF) has recently recommended the latest evidence-based guidelines on foot ulcer prevention and management. The 2019 guidelines suggest, first, 'identifying high-risk feet for foot ulcers' such as loss of protective sensation, peripheral arterial disease, ulcer development history, Charcot joint, and lower extremity amputation history; second, 'regular screening' for foot deformities and pre-ulcer signs in high-risk foot ulcer patients; third, 'education on footwear and foot protection methods' for high-risk patients, their families, and healthcare providers; fourth, 'recommendation for wearing appropriate footwear' according to foot condition; fifth, 'treatment of foot ulcer risk factors'; and sixth, 'provision of integrated foot care' (Bus et al., 2020). This recommends an active prevention strategy that detects high-risk diabetic foot groups early, provides appropriate preventive and therapeutic interventions, and establishes a continuous management system.

[0004] Despite these circumstances, foot care education for diabetic foot ulcer prevention continues to be studied in clinical settings. Domestic research on foot ulcer prevention has explored a variety of methods and subjects, including the effectiveness of foot care education for diabetic patients (Moon, 1999), the effectiveness of foot care education using foot reflexology (Lee, 2003), the effectiveness of foot care education for elderly patients (Kim & Seo, 2019), and the effectiveness of video education for patients with foot ulcers (Kim, 2018). However, these interventions vary widely, and comprehensive evaluations of their effectiveness are lacking.

[0005] Meanwhile, a primary screening is clearly necessary for these methods. This may require distinguishing between simple ulcers and diabetic foot ulcers, and confirming whether a hospital examination is warranted. Recently, due to rising prices, even simple assessments have become costly. However, many elderly patients, despite suffering from these conditions, are unable to afford these costs, making it difficult to visit hospitals due to financial constraints. This can lead to failure to identify these problems and prevent screenings, as described above, which can lead to even more serious problems. Therefore, a system that can overcome these challenges is urgently needed.

[0006] Accordingly, the present embodiment can automatically predict and notify the user of a foot ulcer based on the output result data by applying a plurality of data received from the user to a prediction model, thereby providing a server and a method for operating the server for predicting a foot ulcer based on a plurality of input data based on a prediction model.

[0007] According to various embodiments, a server for diagnosing the progression of diabetic foot disease based on a predictive model comprises: a communication interface; a memory; and a processor; Including, the processor, through the communication interface, obtains at least one image data and at least one first sensing data from an external user's external server, inputs the at least one image data and the at least one first sensing data into the prediction model to obtain first ulcer output data, and when the first ulcer output data is compared with a first threshold value set in advance and it is determined that the first threshold value is exceeded, outputs that the external user's foot ulcer is likely to be the diabetic foot disease, and when the first ulcer output data is compared with a second threshold value set greater than the first threshold value and it is determined that the second threshold value is exceeded, outputs that the external user's foot ulcer is likely to be the diabetic foot disease, and transmits, through the communication interface, result data for the first ulcer output data determined to have exceeded the first threshold value and / or the second threshold value, and guideline data that presents at least one guideline based on the result data, and the prediction model is configured to transmit a plurality of images obtained from a plurality of users. It is learned based on data, a plurality of first sensing data, a plurality of second sensing data, a plurality of result data output from a plurality of users, and at least one expert opinion data that observed a plurality of users.

[0008] According to another various embodiments, in a method for operating a server for diagnosing the progression of diabetic foot disease based on a prediction model, the method comprises: obtaining at least one image data and at least one first sensing data from an external server of an external user through a communication interface; inputting the at least one image data and the at least one first sensing data into the prediction model through a processor to obtain first ulcer output data; comparing the first ulcer output data with a preset first threshold value through the processor, and determining that the preset first threshold value is exceeded, outputting that the external user's foot ulcer is likely to be the diabetic foot disease; comparing the first ulcer output data with a second threshold value set to be greater than the first threshold value through the processor, and determining that the second threshold value is exceeded, outputting that the external user's foot ulcer is likely to be the diabetic foot disease; and, through the processor, through the communication interface, outputting the first ulcer output data determined to have exceeded the first threshold value and / or the second threshold value. The prediction model is set to transmit result data for ulcer output data and guideline data that suggests at least one guideline based on the result data, and the prediction model is learned based on a plurality of image data, a plurality of first sensing data, and a plurality of second sensing data obtained from a plurality of users, a plurality of result data output from a plurality of users, and at least one expert opinion data that observed a plurality of users.

[0009] In this embodiment, a plurality of image data directly taken by a user at various angles and at least one first sensing data acquired from an external electronic device of the user are received, and the plurality of received image data and the at least one first sensing data are input into a prediction model to easily determine whether the user has a diabetic foot ulcer based on a predicted result value, thereby reducing costs. In addition, based on the predicted result value, whether the user should receive hospital treatment and guidelines therefor can be provided, so that treatment and delay of the user's diabetic foot ulcer can be performed.

[0010] FIG. 1 illustrates a block diagram of a server and a network according to various embodiments of the present invention.

[0011] FIG. 2 is an exemplary diagram illustrating a method of operating a server according to various embodiments of the present invention.

[0012] FIG. 3 is an exemplary diagram illustrating a user's foot ulcer according to various embodiments of the present invention.

[0013] FIG. 4 is an exemplary diagram briefly explaining a process of driving data acquired by a server based on a prediction model according to various embodiments of the present invention.

[0014] FIG. 5 is another exemplary diagram illustrating a method of operating a server according to various embodiments of the present invention.

[0015] Hereinafter, various embodiments of the present document will be described with reference to the attached drawings. It should be understood that the embodiments and the terms used therein are not intended to limit the technology described in the present document to a specific embodiment, but rather include various modifications, equivalents, and / or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar components. The singular expression may include plural expressions unless the context clearly indicates otherwise. In this document, expressions such as "A or B" or "at least one of A and / or B" may include all possible combinations of the items listed together. Expressions such as "first," "second," "first," or "second," may modify the corresponding components regardless of order or importance, and are only used to distinguish one component from another, but do not limit the corresponding components. When it is said that a component (e.g., a first component) is “(functionally or communicatively) connected” or “connected” to another component (e.g., a second component), said component may be directly connected to said other component, or may be connected via another component (e.g., a third component).

[0016] In this document, "configured to" may be used interchangeably with, for example, "suitable for," "capable of," "modified to," "made to," "capable of," or "designed to," either in hardware or software. In some contexts, the phrase "a device configured to" may mean that the device is "capable of" doing something together with other devices or components. For example, the phrase "a processor configured to perform A, B, and C" may mean a dedicated processor (e.g., an embedded processor) for performing the operations, or a general-purpose processor (e.g., a CPU or application processor) that can perform the operations by executing one or more software programs stored in a memory device.

[0017] A server according to various embodiments of the present document may include, for example, at least one of a smartphone, a tablet PC, a desktop PC, a laptop PC, a netbook computer, a workstation, and a server.

[0018] Referring to FIG. 1, a server (101) within a network environment (100) according to various embodiments is described. The server (101) may include a bus (110), a processor (120), a memory (130), an input / output interface (140), a display (150), and a communication interface (160). In some embodiments, the server (101) may omit at least one of the components or additionally include other components. The bus (110) may include circuitry that interconnects the components (110-170) and transmits communication (e.g., control messages or data) between the components. The processor (120) may include one or more of a central processing unit, an application processor, or a communication processor (CP). The processor (120) may, for example, execute operations or data processing related to control and / or communication of at least one other component of the server (101).

[0019] The memory (130) may include volatile and / or non-volatile memory. The memory (130) may store, for example, commands or data related to at least one other component of the server (101). According to one embodiment, the memory (130) may store software and / or programs (140).

[0020] The input / output interface (140) can, for example, transmit commands or data input from a patient or other external device to other component(s) of the server (101), or output commands or data received from other component(s) of the server (101) to the patient or other external device.

[0021] The display (150) may include, for example, a liquid crystal display (LCD), a light emitting diode (LED) display, an organic light emitting diode (OLED) display, a micro electro mechanical systems (MEMS) display, or an electronic paper display. The display (150) may, for example, display various contents (e.g., text, images, videos, icons, and / or symbols) to the patient. The display (150) may include a touch screen and may receive touch, gesture, proximity, or hovering input using, for example, an electronic pen or a part of the patient's body. The communication interface (160) may, for example, establish communication between the server (101) and an external device (e.g., the first external server (102), the second external server (104), or the server (108)). For example, the communication interface (160) can be connected to a network (162) via wireless communication or wired communication to communicate with an external device (e.g., a second external server (104) or server (108)).

[0022] The wireless communication may include, for example, cellular communication using at least one of LTE, LTE-A (LTE Advance), CDMA (code division multiple access), WCDMA (wideband CDMA), UMTS (universal mobile telecommunications system), WiBro (Wireless Broadband), or GSM (Global System for Mobile Communications). In one embodiment, the wireless communication may include, for example, at least one of WiFi (wireless fidelity), Bluetooth, Bluetooth low energy (BLE), Zigbee, near field communication (NFC), Magnetic Secure Transmission, radio frequency (RF), or body area network (BAN). In one embodiment, the wireless communication may include GNSS. The GNSS may be, for example, GPS (Global Positioning System), Glonass (Global Navigation Satellite System), Beidou Navigation Satellite System (hereinafter “Beidou”), or Galileo, the European global satellite-based navigation system. Hereinafter, in this document, “GPS” may be used interchangeably with “GNSS.” Wired communication may include at least one of, for example, USB (universal serial bus), HDMI (high definition multimedia interface), RS-232 (recommended standard 232), power line communication, or POTS (plain old telephone service).The network (162) may include at least one of a telecommunications network, for example, a computer network (e.g., a LAN or WAN), the Internet, or a telephone network.

[0023] According to various embodiments, the server (108) may operate an application composed of a plurality of execution screens or a website composed of a plurality of web pages, and communicate with an electronic device (e.g., the electronic devices (101, 102, 104, 106) of FIG. 1) (e.g., a smartphone, a laptop, etc.) via a network (161), process a request received from the electronic device (101) regarding the application or the web page, and transmit the requested information to the electronic device (101). The server (108) may utilize a foundation prediction model to generate a motion of a user-customized character and transmit a source code that enables the electronic device (101) to display each execution screen of a dedicated application or website that provides the motion result thereof, and the electronic device (101) may receive the source code and display an execution screen requested by a user of the electronic device (101) through the dedicated application or a web browser. According to one embodiment, the components referred to as electronic devices (101) in the present disclosure may mean a user account that accesses a platform provided by a server (108) through the electronic device.

[0024]

[0025] FIG. 2 is an exemplary diagram illustrating a method of operating a server according to various embodiments of the present invention.

[0026] FIG. 3 is an exemplary diagram illustrating a user's foot ulcer according to various embodiments of the present invention.

[0027] FIG. 4 is an exemplary diagram briefly illustrating how a prediction model acquires and operates data according to various embodiments of the present invention.

[0028] FIG. 5 is an exemplary diagram briefly explaining a process of driving data acquired by a server based on a prediction model according to various embodiments of the present invention.

[0029]

[0030] In operation 201, the server (108) (e.g., the processor (120) of FIG. 1) may receive at least one image data and at least one first sensing data from at least one external electronic device (101, 102, 104, 106) of an external user through a communication interface (e.g., the communication interface (160) of FIG. 1). As an example, the image data may include a plurality of image data and a plurality of video data each photographing the foot of the external user from a preset location, as illustrated in FIG. 3. Specifically, the image data may photograph the foot of the external user from multiple angles from at least one external electronic device (101, 102, 104, 106) of the external user. In addition, the server (108) may provide guidelines for various angles at which the user's foot can be photographed to at least one external electronic device (101, 102, 104, 106) through a communication interface (e.g., the communication interface (160) of FIG. 1) as an application (not drawn out). In addition, the external electronic device (101, 102, 104, 106) may photograph at least one image data of the user's foot according to the guidelines, and transmit the photographed at least one image data to the server (108) through the communication interface. As another example, the first sensing data may include, for an external user, at least one pressure data output from a pressure measurement module, at least one temperature data output from a temperature measurement module, and at least one humidity data output by measuring a change in moisture content based on electrical conductivity from a humidity module.Specifically, the external electronic device (101, 102, 104, 106) can obtain pressure data, temperature data, and humidity data for a point where the foot of the external user is photographed, combine the pressure data, temperature data, and humidity data into one first sensing data, and transmit the first sensing data to the server (108) through a communication interface.

[0031] In operation 203, the server (108) (e.g., the processor (120) of FIG. 1) may input at least one image data and at least one first sensing data into a prediction model to output first ulcer output data. As an example, the prediction model may be learned based on a plurality of image data, a plurality of first sensing data, and a plurality of second sensing data acquired from a plurality of users, a plurality of result data output from a plurality of users, and at least one expert opinion data that observed a plurality of users, as illustrated in FIG. 4.

[0032] For example, a predictive model for predicting and outputting the first ulcer output data can be driven by an AI neural network model trained through unsupervised learning on basic data. The predictive model can be configured to increase the ease of data collection and output various data. The predictive model has a structure that outputs image data from text data, and at least one of BigScience's bloom and T0pp, EleutherAI's GPT series, Tsinghua UNIV's GLM series, GOOGLE's UL and T5 series, and META AI's OPT series can be used. According to one embodiment, the predictive model can be implemented using the structure of Microsoft's Chat GPT, Google's BARD series, and NVIDIA's translation service-based Transformer model using multiple cloud foundation models. For example, the predictive model can be trained as a multi-modal model based on at least one of text data, image data, and audio data to implement various image processing. In one embodiment, this can reduce the amount of labeled task-specific training data compared to existing deep learning approaches, and once built, it can be trained on a variety of tasks with a small amount of training data, making data collection and labeling easier and improving accuracy.

[0033] According to another embodiment, the server (108) may perform a learning process of a prediction model for predicting motion type data, motion speed data, motion style data, motion joint position data, and motion joint path data, by obtaining a result value (output data) using a prediction model to which arbitrary weights are assigned, comparing the obtained result value with labeled data of the learning data, and performing backpropagation according to the error to optimize the weights. Specifically, the learning of the prediction model refers to a process of training the prediction model based on the learning data and labeled data or unlabeled data so that the prediction model can determine output data for input data. In other words, the prediction model forms rules for the data and makes a judgment. According to one embodiment, the server (108) may use a plurality of learning algorithms among a plurality of learning algorithms that calculate predicted values. For example, an ensemble method may be used for the prediction model, and better prediction performance may be obtained compared to when learning algorithms are used separately. Training the prediction model may refer to adjusting the weights of the model. According to one embodiment, various methods such as supervised learning, unsupervised learning, reinforcement learning, imitation learning, and federated learning can be used as learning methods.

[0034] Although not shown, the server (108) may include an evaluation step for evaluating the performance of the prediction model during the learning process of the prediction model. In the evaluation step, the prediction model may be evaluated using an evaluation data set. The evaluation of the prediction model may be a step of evaluating the prediction model learned through the learning step and using the prediction model to make predictions on new data. Specifically, the evaluation step may be a step of measuring whether the learned prediction model is capable of generalizing to new data.

[0035] As another example, the plurality of image data may include multiple image data and multiple video data, each capturing the feet of multiple users from a preset location. Specifically, the plurality of image data may be multiple image data obtained directly from a hospital, each capturing the feet of multiple users and patients according to guidelines. Thereafter, the server (108) may input the acquired plurality of image data into a prediction model so that the prediction model can be trained.

[0036] As another example, the plurality of first sensing data may include at least one pressure data output from a pressure measurement module, at least one temperature data output from a temperature measurement module, and at least one humidity data output from a humidity module by measuring a change in moisture content based on electrical conductivity, for a plurality of users. Specifically, the plurality of first sensing data may be a plurality of temperature data, a plurality of humidity data, and a plurality of pressure data each acquired in accordance with guidelines based on the surroundings of the feet of a plurality of users and patients directly at a hospital. Thereafter, the server (108) may combine the acquired plurality of temperature data, the plurality of humidity data, and the plurality of pressure data into a plurality of first sensing data for each user, and input the plurality of first sensing data into a prediction model so that the prediction model can be trained. This may be output as the same data as the plurality of first sensing data and the first sensing data acquired from the external electronic devices (101, 102, 104, 106), so that the prediction model can be compared.

[0037] As another example, the plurality of second sensing data may include, for a plurality of users, a plurality of blood glucose data output from a blood glucose measurement module, a plurality of blood flow data output from a blood flow measurement module, a plurality of oxygen saturation data output from an oxygen saturation measurement module, a plurality of pH data output from a pH measurement module, and a plurality of protease amount measurement data output from a protease amount measurement module. Specifically, the second sensing data may obtain a plurality of blood glucose data, a plurality of blood flow data, a plurality of oxygen saturation data, a plurality of pH data, and a plurality of protease amount measurement data, which are obtained according to each information based on criteria directly obtained for a plurality of users and patients at a hospital. Thereafter, the server (108) may combine the obtained plurality of blood glucose data, the plurality of blood flow data, the plurality of oxygen saturation data, the pH data, and the plurality of protease amount measurement data into a plurality of second sensing data for each user, and may input the plurality of second sensing data into a prediction model so that the prediction model can be trained. This is because, since it is not easy to obtain second sensing data at home and it costs a lot of money to take pictures at a hospital, the second sensing data can clearly find the answer, so that the diabetic ulcer foot of an external user can be judged based on the identity of the first sensing data.

[0038] As another example, multiple result data output from multiple users may be included as result data extracted from a hospital based on multiple image data, multiple first sensing data, and multiple second sensing data. Furthermore, at least one expert opinion data observing multiple users may be output as judgment results for multiple users based on the result data.

[0039] In operation 205, the server (108) (e.g., the processor (120) of FIG. 1) may compare the first ulcer output data with a preset first threshold value to determine whether the user's foot is a simple ulcer and / or normal, or has a possibility of a diabetic foot ulcer. For example, the first threshold value may include a plurality of image data extracted as data having a possibility of diabetic foot disease from at least one expert opinion data, a plurality of first sensing data, and a plurality of second sensing data. That is, the first threshold value may be set as a reference value for a case where the plurality of image data having a possibility of diabetic foot disease and the plurality of first sensing data are determined to be identical to or higher than the first ulcer output data. In addition, the server (108) can determine, as illustrated in FIG. 3, whether the brightness of an image determined to be an ulcer in the image of the first ulcer output data is equal to or less than the brightness of the image color of the plurality of image data input to the first threshold value (e.g., brightness value 35 (based on 100)).

[0040] In operation 207, the server (108) (e.g., the processor (120) of FIG. 1) may determine whether the user's foot is a simple ulcer and / or normal. For example, if the server (108) determines that the first ulcer output data does not exceed a first threshold value as a result of the determination, the server (108) may determine that the ulcer on the user's foot is a simple ulcer. Specifically, if the first ulcer output data indicates a lower value than a plurality of image data and a plurality of first sensing data that may be diabetic foot disease, the server (108) may determine that the first ulcer output data does not exceed the first threshold value. That is, if the first ulcer output data does not match the plurality of first sensing data input to the first threshold value and the second threshold value, the server (108) may output that the external user's foot ulcer is a simple ulcer. In addition, the server (108) can determine that the first ulcer output data does not exceed the first threshold value when the brightness of the ulcer image of the first ulcer output data is set to 55 (based on 100) and the standard brightness of the plurality of image data input to the first threshold value is set to 35 (based on 100).

[0041] In operation 209, the server (108) (e.g., the processor (120) of FIG. 1) can transmit data that the user's foot is determined to be a simple ulcer and / or normal to the external electronic device (101, 102, 104, 106) through a communication interface (e.g., the communication interface (160) of FIG. 1). Specifically, as illustrated in FIG. 4, the server (108) can determine that the user's foot is a simple ulcer and / or normal and thus there is no need to hospitalize the user in a separate hospital, and since it is a simple ulcer, there is no need to provide separate treatment guidance, but guidance data on a diet to avoid so as to prevent diabetic foot ulcers in advance can be added, and the determined data and guidance data can be transmitted to the external electronic device (101, 102, 104, 106) through a communication interface (e.g., the communication interface (160) of FIG. 1).

[0042] Meanwhile, in operation 205, if the server (108) (e.g., the processor (120) of FIG. 1) determines that the first ulcer output data exceeds a preset first threshold value, in operation 211, the server (108) (e.g., the processor (120) of FIG. 1) may compare the first ulcer output data with a preset second threshold value to determine that the user's foot has a possibility of having a diabetic foot ulcer or a high possibility of having a diabetic foot ulcer. For example, the second threshold value may include a plurality of image data extracted as data having a possibility of diabetic foot disease from among at least one expert opinion data, a plurality of first sensing data, and a plurality of second sensing data. That is, the second threshold value may be set as a reference value for a case where the plurality of image data having a possibility of diabetic foot disease and the plurality of first sensing data are determined to be equal to or higher than the first ulcer output data. In addition, the server (108) can make a judgment based on the case where the brightness of an image determined to be an ulcer in the image of the first ulcer output data, as illustrated in FIG. 3, is equal to or less than the brightness of the image color of the plurality of image data input to the second threshold value (e.g., brightness value 20 (based on 100)).

[0043] In operation 213, the server (108) (e.g., the processor (120) of FIG. 1) may determine that the user's foot has a possibility of having a diabetic foot ulcer if the first ulcer output data does not exceed a second threshold value. For example, the server (108) may output that the external user's ulcer has a possibility of having diabetic foot disease if the first ulcer output data matches a plurality of first sensing data input to the first threshold value. Specifically, the server (108) may determine that the first ulcer output data has exceeded the first threshold value but has not exceeded the second threshold value if the first ulcer output data has a higher value than the plurality of image data and the plurality of first sensing data that have a possibility of having diabetic foot disease, but has a lower value than the plurality of images and the plurality of first sensing data that have a high possibility of having diabetic foot disease. In addition, the server (108) can determine that the first ulcer output data has exceeded the first threshold value when the brightness of the ulcer image of the first ulcer output data is set to 27 (based on 100) and the reference brightness of the plurality of image data input to the first threshold value is set to 35 (based on 100), but can determine that the first ulcer output data has not exceeded the second threshold value when the reference brightness of the plurality of image data input to the second threshold value is set to 20 (based on 100).

[0044] In operation 215, the server (108) (e.g., the processor (120) of FIG. 1) may transmit data determining that the user's foot has a possibility of developing a diabetic foot ulcer and guidance data for hospital visit for review to an external electronic device (101, 102, 104, 106) via a communication interface (e.g., the communication interface (160) of FIG. 1). As an example, the guideline data may include first hospital guidance data for routine treatment and first diet data suitable for at least one external user whose first ulcer output data exceeds a first threshold but does not exceed a second threshold. This may be first diet data set for specific diet guidance for people who have a possibility of developing a diabetic foot ulcer, as illustrated in FIG. 3, when the server (108) determines that there is a possibility of developing a diabetic foot ulcer based on data predicted by a prediction model and thus guidance for routine treatment may be necessary. In addition, the server (108) may additionally include first treatment guideline data set according to treatment guidelines of patients confirmed in a hospital who exceeded the first threshold but did not exceed the second threshold. As another example, the server (108) may transmit first hospital guidance data and first diet data to an external user whose first ulcer output data exceeded the first threshold but did not exceed the second threshold, and may additionally transmit first treatment guideline data, through a communication interface (e.g., communication interface (160) of FIG. 1), as illustrated in FIG. 4.

[0045] Meanwhile, in operation 211, if the server (108) (e.g., the processor (120) of FIG. 1) determines that the first ulcer output data exceeds a preset second threshold value, then in operation 217, the server (108) (e.g., the processor (120) of FIG. 1) may determine that the user's foot has a high possibility of having a diabetic foot ulcer. For example, if the first ulcer output data matches a plurality of first sensing data input to the second threshold value, the server (108) may output that the external user's foot ulcer has a high possibility of having a diabetic foot ulcer. Specifically, if the first ulcer output data appears as a higher value than the plurality of images and the plurality of first sensing data indicating a high possibility of having a diabetic foot ulcer, the server (108) may determine that the first ulcer output data has exceeded the second threshold value. In addition, the server (108) can determine that the first ulcer output data has exceeded the second threshold value when the brightness of the ulcer image of the first ulcer output data is set to 14 (based on 100) and the standard brightness of the plurality of image data input to the second threshold value is set to 20 (based on 100).

[0046] In operation 219, the server (108) (e.g., the processor (120) of FIG. 1) may transmit data indicating that the user's foot is likely to have a diabetic foot ulcer and guidance data for hospital visit for treatment to an external electronic device (101, 102, 104, 106) through a communication interface (e.g., the communication interface (160) of FIG. 1). For example, the guideline data may include second hospital guidance data for hospitalization and second diet data suitable for at least one external user whose first ulcer output data exceeds a second threshold. This may be second diet data set for specific diet guidance for people with a high possibility of diabetic foot ulcers, as shown in FIG. 3, when the server (108) determines that the user has a high possibility of diabetic foot ulcers based on data predicted by a prediction model and thus guidance for hospitalization treatment may be necessary. In addition, the server (108) may additionally include second treatment guideline data set according to the treatment guidelines of patients confirmed at the hospital who have exceeded the second threshold value. As another example, the server (108) may transmit second hospital guidance data and second diet data to an external user whose first ulcer output data has exceeded the second threshold value, and may additionally transmit second treatment guideline data, through a communication interface (e.g., the communication interface (160) of FIG. 1), as illustrated in FIG. 4.

[0047]

[0048] In this embodiment, a plurality of image data directly taken by a user at various angles and at least one first sensing data acquired from an external electronic device (101, 102, 104, 106) of the user are received, and the plurality of received image data and the at least one first sensing data are input into a prediction model to easily determine whether the user has a diabetic foot ulcer based on a predicted result value, thereby reducing costs. In addition, based on the predicted result value, whether the user needs hospital treatment and guidelines therefor can be provided, so that treatment and delay of the user's diabetic foot ulcer can be performed.

[0049]

[0050] FIG. 5 is another exemplary diagram illustrating a method of operating a server according to various embodiments of the present invention.

[0051]

[0052] In operation 501, the server (108) (e.g., the processor (120) of FIG. 1) may receive at least one image data, at least one first sensing data, and at least one second sensing data from at least one external electronic device (101, 102, 104, 106) of the user through a communication interface (e.g., the communication interface (160) of FIG. 1). This allows the external user to additionally obtain the second sensing data through a commonly used examination, and the server (108) may additionally receive the second sensing data from the external electronic device (101, 102, 104, 106) through the communication interface (e.g., the communication interface (160) of FIG. 1). In addition, the second sensing data may be set to the same data value as the plurality of second sensing data above.

[0053] In operation 503, the server (108) (e.g., the processor (120) of FIG. 1) may input at least one image data, at least one first sensing data, and at least one second sensing data into a prediction model to output second ulcer output data. That is, the server (108) may additionally input at least one second sensing data into the prediction model to obtain second ulcer output data. Here, the prediction model may be used as the same model as the prediction model above, and thus specific details may be omitted.

[0054] In operation 505, the server (108) (e.g., the processor (120) of FIG. 1) may compare the second ulcer output data with a preset third threshold value to determine whether the user's foot is a simple ulcer and / or normal, or has a high possibility of a diabetic foot ulcer. For example, the third threshold value may include a plurality of image data, a plurality of first sensing data, and a plurality of second sensing data extracted as data having a high possibility of diabetic foot disease from at least one expert opinion data. That is, the third threshold value may be set as a reference value for a case where the plurality of image data, the plurality of first sensing data, and the plurality of second sensing data having a high possibility of diabetic foot disease are determined to be identical to or higher than the second ulcer output data. In addition, the server (108) may determine, as illustrated in FIG. 3, based on a case where the brightness of an image determined to be an ulcer in the image of the second ulcer output data is equal to or less than the brightness of the image color of a plurality of image data input to the third threshold value (e.g., brightness value 35 (based on 100)), and the second sensing data of the second ulcer output data may be equal to or greater than a plurality of second sensing data values ​​set as the third threshold value. This is because the second ulcer output data is set as more accurate data than the first ulcer output data, an accurate result value can be extracted therefor, and when it exceeds the third threshold value, it can be determined that there is a high possibility of diabetic foot disease.

[0055] In operation 507, the server (108) (e.g., the processor (120) of FIG. 1) may determine that the user's foot is a simple ulcer and / or normal. As an example, the server (108) may determine the same as operation 207, and thus specific details may be omitted.

[0056] In operation 509, the server (108) (e.g., the processor (120) of FIG. 1) may transmit data determining whether the user's foot is a simple ulcer and / or normal to an external electronic device via a communication interface (e.g., the communication interface (160) of FIG. 1). As an example, the server (108) may make the same determination as in operation 209, and thus specific details may be omitted.

[0057] Meanwhile, in operation 505, if the server (108) (e.g., the processor (120) of FIG. 1) determines that the first ulcer output data exceeds a preset third threshold value, in operation 511, the server (108) (e.g., the processor (120) of FIG. 1) may compare the first ulcer output data with a preset fourth threshold value to determine that the user's foot has a high possibility of having a diabetic foot ulcer or is a diabetic foot ulcer. As an example, the fourth threshold value may include a plurality of image data extracted as data having a possibility of diabetic foot disease from at least one expert opinion data, a plurality of first sensing data, and a plurality of second sensing data. That is, the fourth threshold value may be set as a reference value for a case where the plurality of image data having a possibility of diabetic foot disease and the plurality of first sensing data are determined to be equal to or greater than the second ulcer output data. In addition, the server (108) can determine based on the case where the brightness of the image determined to be an ulcer in the image of the second ulcer output data, as illustrated in FIG. 3, is equal to or less than the brightness of the image color of the plurality of image data input to the fourth threshold value (e.g., brightness value 20 (based on 100)), and the second sensing data of the second ulcer output data can be equal to or greater than the plurality of second sensing data values ​​set to the fourth threshold value.

[0058] In operation 513, the server (108) (e.g., the processor (120) of FIG. 1) may determine that the user's foot has a high possibility of having a diabetic foot ulcer. For example, the server (108) may output that the external user's ulcer has a high possibility of having diabetic foot disease if the second ulcer output data matches a plurality of third sensing data input to a third threshold value. Specifically, the server (108) may determine that the second ulcer output data exceeds the third threshold value but does not exceed the fourth threshold value if the second ulcer output data has a high value compared to a plurality of image data and a plurality of first sensing data having a high possibility of having diabetic foot disease, but has a low value compared to a plurality of images and a plurality of first sensing data determined to have diabetic foot disease. In addition, the server (108) can determine that the second ulcer output data has exceeded the third threshold value when the brightness of the ulcer image of the second ulcer output data is set to 27 (based on 100) and the reference brightness of the plurality of image data input to the third threshold value is set to 35 (based on 100), but can determine that the second ulcer output data has exceeded the third threshold value when the reference brightness of the plurality of image data input to the fourth threshold value is set to 20 (based on 100) and the second sensing data of the second ulcer output data has exceeded the plurality of second sensing data values ​​set to the third threshold value but has not exceeded the plurality of second sensing data values ​​set to the fourth threshold value.

[0059] In operation 515, the server (108) (e.g., the processor (120) of FIG. 1) may transmit data indicating that the user's foot is likely to have a diabetic foot ulcer and guidance data for hospital visit for review to an external electronic device (101, 102, 104, 106) via a communication interface (e.g., the communication interface (160) of FIG. 1). For example, the guideline data may include second hospital guidance data for hospitalization and second diet data suitable for at least one external user whose second ulcer output data exceeds a third threshold. This may be second diet data set for specific diet guidance for people with a high possibility of diabetic foot ulcers, as illustrated in FIG. 3, when the server (108) determines that the user has a high possibility of diabetic foot ulcers based on data predicted by a prediction model and thus guidance for hospitalization treatment may be necessary. In addition, the server (108) may additionally include second treatment guideline data set according to the treatment guidelines of patients confirmed at the hospital who have exceeded the third threshold value. As another example, the server (108) may transmit second hospital guidance data and second diet data to an external user whose second ulcer output data has exceeded the third threshold value, and may additionally transmit second treatment guideline data, through a communication interface (e.g., the communication interface (160) of FIG. 1), as illustrated in FIG. 4.

[0060] Meanwhile, in operation 511, if the server (108) (e.g., the processor (120) of FIG. 1) determines that the first ulcer output data exceeds a preset fourth threshold value, then in operation 517, the server (108) (e.g., the processor (120) of FIG. 1) may determine that the user's foot has a diabetic foot ulcer. For example, if the second ulcer output data matches a plurality of first sensing data input to the fourth threshold value, the server (108) may output that the external user's foot ulcer is diabetic foot disease. Specifically, if the second ulcer output data appears to have a numerical value that is the same as or higher than a plurality of images of diabetic foot disease and a plurality of first sensing data, the server (108) may determine that the second ulcer output data exceeds the fourth threshold value. In addition, the server (108) can determine that the second ulcer output data has exceeded the fourth threshold value when the brightness of the ulcer image of the first ulcer output data is set to 14 (based on 100), the reference brightness of the plurality of image data input to the second threshold value is set to 20 (based on 100), and the second sensing data of the second ulcer output data has exceeded the plurality of second sensing data values ​​set to the fourth threshold value.

[0061] In operation 519, the server (108) (e.g., the processor (120) of FIG. 1) may transmit data that determines that the user's foot has a diabetic foot ulcer and guidance data for hospital visit for treatment to an external electronic device via a communication interface (e.g., the communication interface (160) of FIG. 1). This may be third diet data set for specific diet guidance for people with diabetic foot ulcers, as shown in FIG. 3, when the server (108) determines that the user's foot has a diabetic foot ulcer based on data predicted by a prediction model, and guidance for hospitalization treatment may be required. In addition, the server (108) may additionally include third treatment guideline data set according to treatment guidelines for patients confirmed at a hospital who have exceeded a fourth threshold value. As another example, the server (108) may transmit second hospital guidance data and third diet data to an external user whose second ulcer output data exceeds a fourth threshold value, and may additionally transmit third treatment guideline data, through a communication interface (e.g., communication interface (160) of FIG. 1), as illustrated in FIG. 4.

[0062]

[0063] According to various embodiments, a server for predicting diabetic foot diagnosis based on a plurality of data based on a prediction model comprises: a communication interface; a memory; and a processor; Including, the processor, through the communication interface, obtains at least one image data and at least one first sensing data from an external user's external server, inputs the at least one image data and the at least one first sensing data into the prediction model to obtain first ulcer output data, and when the first ulcer output data is compared with a first threshold value set in advance and it is determined that the first threshold value is exceeded, outputs that the external user's foot ulcer is likely to be the diabetic foot disease, and when the first ulcer output data is compared with a second threshold value set greater than the first threshold value and it is determined that the second threshold value is exceeded, outputs that the external user's foot ulcer is likely to be the diabetic foot disease, and transmits, through the communication interface, result data for the first ulcer output data determined to have exceeded the first threshold value and / or the second threshold value, and guideline data that presents at least one guideline based on the result data, and the prediction model is configured to transmit a plurality of images obtained from a plurality of users. It is learned based on data, a plurality of first sensing data, a plurality of second sensing data, a plurality of result data output from a plurality of users, and at least one expert opinion data that observed a plurality of users.

[0064] According to various embodiments, the image data includes a plurality of image data and a plurality of video data each photographing the foot of the external user from a preset location, and the first sensing data includes, for the external user, at least one pressure data output from a pressure measurement module, at least one temperature data output from a temperature measurement module, and at least one humidity data output by measuring a change in moisture content based on electrical conductivity from a humidity module.

[0065] According to various embodiments, the plurality of image data includes a plurality of image data and a plurality of video data each photographing the feet of the plurality of users from a preset location, the plurality of first sensing data includes, for the plurality of users, at least one pressure data output from a pressure measurement module, at least one temperature data output from a temperature measurement module, and at least one humidity data output by measuring a change in moisture content based on electrical conductivity from a humidity module, and the plurality of second sensing data includes, for the plurality of users, a plurality of blood sugar data output from a blood sugar measurement module, a plurality of blood flow data output from a blood flow measurement module, a plurality of oxygen saturation data output from an oxygen saturation measurement module, pH data output from a pH measurement module, and a plurality of protease amount measurement data output from a protease amount measurement module.

[0066] According to various embodiments, the first threshold value includes the plurality of image data extracted as data having a possibility of diabetic foot disease from among the at least one specialist opinion data, the plurality of first sensing data, and the plurality of second sensing data, and the second threshold value includes the plurality of image data extracted as data having a possibility of diabetic foot disease from among the at least one specialist opinion data, the plurality of first sensing data, and the plurality of second sensing data, and the processor outputs the ulcer of the external user as having a possibility of diabetic foot disease if the first ulcer output data matches the plurality of first sensing data input to the first threshold value, outputs the ulcer of the external user as having a high possibility of diabetic foot disease if the first ulcer output data matches the plurality of first sensing data input to the second threshold value, and outputs the ulcer of the external user as having a high possibility of diabetic foot disease if the first ulcer output data does not match the plurality of first sensing data input to the first threshold value and the second threshold value. The ulcer is set to output as a simple ulcer.

[0067] According to various embodiments, the processor is configured to additionally obtain at least one second sensing data from the external server through the communication interface, additionally input the at least one second sensing data into the prediction model to obtain second ulcer output data, and if the second ulcer output data is compared with the first threshold value and it is determined that the second threshold value is exceeded, output that the external user's foot ulcer is likely to be the diabetic foot disease, and if the second ulcer output data is compared with a fourth threshold value set to be greater than the third threshold value and it is determined that the second threshold value is exceeded, output that the external user's foot ulcer is the diabetic foot disease.

[0068] According to various embodiments, the guideline data includes first hospital guidance data for general treatment, second hospital guidance data for hospitalization, first diet data suitable for at least one external user whose first ulcer output data exceeds a first threshold value but does not exceed a second threshold value, and second diet data suitable for at least one external user whose first ulcer output data exceeds a second threshold value or whose second ulcer output data exceeds a third threshold value, and the processor is configured to transmit, through the communication interface, the first hospital guidance data and the first diet data to the external user whose first ulcer output data exceeds the first threshold value but does not exceed the second threshold value, and to transmit, through the communication interface, the second hospital guidance data and the second diet data to the external user whose first ulcer output data exceeds the second threshold value or whose second ulcer output data exceeds the third threshold value, and to transmit, through the communication interface, the second hospital emergency guidance data to the external user whose second ulcer output data exceeds the fourth threshold value.

[0069] According to another various embodiments, a method for driving a server for predicting a diabetic foot condition based on a plurality of data based on a prediction model, the method comprises: obtaining at least one image data and at least one first sensing data from an external server of an external user through a communication interface; inputting the at least one image data and the at least one first sensing data into the prediction model through a processor to obtain first ulcer output data; comparing the first ulcer output data with a preset first threshold value through the processor, and determining that the preset first threshold value is exceeded, outputting that the external user's foot ulcer is likely to be the diabetic foot condition; comparing the first ulcer output data with a second threshold value set to be greater than the first threshold value through the processor, and determining that the second threshold value is exceeded, outputting that the external user's foot ulcer is likely to be the diabetic foot condition; and, through the processor, through the communication interface, outputting the first ulcer output data determined to have exceeded the first threshold value and / or the second threshold value. The prediction model is set to transmit result data for ulcer output data and guideline data that suggests at least one guideline based on the result data, and the prediction model is learned based on a plurality of image data, a plurality of first sensing data, and a plurality of second sensing data obtained from a plurality of users, a plurality of result data output from a plurality of users, and at least one expert opinion data that observed a plurality of users.

[0070]

[0071] The term "module" or "part" used in this document includes a unit composed of hardware, software, or firmware, and can be used interchangeably with terms such as logic, logic block, component, or circuit, for example. The "module" or "part" can be an integrally configured component or a minimum unit or a part thereof that performs one or more functions. The "module" or "part" can be implemented mechanically or electronically, and can include, for example, an ASIC (application-specific integrated circuit) chip, FPGAs (field-programmable gate arrays), or a programmable logic device, known or to be developed in the future, that performs certain operations, and can be executed by the processor (120). At least a part of the device (e.g., modules or functions thereof) or method (e.g., operations) according to various embodiments can be implemented as instructions stored in a computer-readable storage medium (e.g., memory (130)) in the form of a program module. When the above command is executed by a processor (e.g., processor (120)), the processor can perform a function corresponding to the command. The computer-readable recording medium may include a hard disk, a floppy disk, a magnetic medium (e.g., a magnetic tape), an optical recording medium (e.g., a CD-ROM, a DVD, a magneto-optical medium (e.g., a floptical disk), a built-in memory, etc. The command may include a code generated by a compiler or a code executable by an interpreter. A module or program module according to various embodiments may include at least one or more of the above-described components, some of which may be omitted, or other components may be further included. Operations performed by a module, a program module, or other components according to various embodiments may be executed sequentially, in parallel, iteratively, or heuristically, or at least some operations may be executed in a different order, omitted, or other operations may be added.

[0072] The embodiments disclosed in this document are presented for the purpose of explaining and understanding the disclosed technical content, and do not limit the scope of the present disclosure. Therefore, the scope of the present disclosure should be interpreted to include all modifications or various other embodiments based on the technical concepts of the present disclosure.

[0073]

[0074] This PCT patent application is being filed with support from the Regional Innovation Cluster program of the Ministry of Trade, Industry and Energy, a national research and development program of the Ministry of Science and ICT of the Republic of Korea. Furthermore, this PCT patent application is being filed based on the following private information.

[0075] Project Name: Regional Innovation Cluster

[0076] Assignment ID: 1415188707

[0077] Assignment Number: P0025898

[0078] Ministry Name: Ministry of Trade, Industry and Energy

[0079] Project Management (Professional) Agency Name: Korea Institute for Advancement of Technology

[0080] Research Project Name: Regional Innovation Cluster Development (R&D)

[0081] Research Project Name: Development of Customized Health Promotion Management Services

[0082] Research period: August 1, 2023 - December 31, 2025.

[0083] Additionally, this PCT patent application is being filed with support from the Ministry of Science and ICT's Incubation Program, a national research and development program of the Ministry of Science and ICT of the Republic of Korea. Furthermore, this PCT patent application is being filed based on the following private information.

[0084] Project Name: Incubating

[0085] Assignment ID: 1711177174

[0086] Project Number: 2024 Incubating 1-02-01

[0087] Ministry of Science and ICT

[0088] Project Management (Professional) Organization Name: Korea Science and Technology Promotion Agency (KSTPA)

[0089] Research Project Name: Industry-Academia-Research Cooperation Activation Support Project

[0090] Research Project Name: Establishment of an AI-Based Customized Health Promotion / Management System

[0091] Research period: January 1, 2024 - October 31, 2024.

Claims

1. In a server that predicts diabetic foot diagnosis based on multiple data based on a prediction model, communication interface; memory; and Processor; including, The above processor, Through the above communication interface, at least one image data and at least one first sensing data are acquired from an external server of an external user, Inputting the at least one image data and the at least one first sensing data into the prediction model to obtain the first ulcer output data, If the first ulcer output data is compared with a preset first threshold value and it is determined that the preset first threshold value is exceeded, it is output that the external user's foot ulcer is likely to be diabetic foot disease. When the first ulcer output data is compared with a second threshold value set to be greater than the first threshold value and the second threshold value is determined to be exceeded, the external user's foot ulcer is output as having a high possibility of being diabetic foot disease, and Through the communication interface, the result data for the first ulcer output data determined to exceed the first threshold value and / or the second threshold value, and the guideline data presenting at least one guideline based on the result data are set to be transmitted, The above prediction model is, Learning is performed based on a plurality of image data, a plurality of first sensing data, and a plurality of second sensing data obtained from a plurality of users, a plurality of result data output from a plurality of users, and at least one expert opinion data that observed a plurality of users. Server.

2. In paragraph 1, The above image data is, Includes multiple image data and multiple video data each photographing the user's feet from a preset location, The above first sensing data is, For the external user, at least one pressure data output from a pressure measurement module, at least one temperature data output from a temperature measurement module, and at least one humidity data output by measuring a change in moisture content based on electrical conductivity from a humidity module. Server.

3. In paragraph 2, The above multiple image data, Includes multiple image data and multiple video data each photographing the feet of multiple users from a preset location, The above plurality of first sensing data are, For the above multiple users, at least one pressure data output from a pressure measurement module, at least one temperature data output from a temperature measurement module, and at least one humidity data output by measuring a change in moisture content based on electrical conductivity from a humidity module are included. The above plurality of second sensing data are, For the above multiple users, a plurality of blood sugar data output from a blood sugar measurement module, a plurality of blood flow data output from a blood flow measurement module, a plurality of oxygen saturation data output from an oxygen saturation measurement module, a plurality of pH data output from a pH measurement module, and a plurality of protease amount measurement data output from a protease amount measurement module are included. Server.

4. In paragraph 3, The above first threshold value is, Including the plurality of image data, the plurality of first sensing data, and the plurality of second sensing data extracted as data having a possibility of diabetic foot disease among the at least one expert opinion data, The above second threshold value is, Including the plurality of image data, the plurality of first sensing data, and the plurality of second sensing data extracted as data having a possibility of diabetic foot disease among the at least one expert opinion data, The above processor, If the first ulcer output data matches the plurality of first sensing data input to the first threshold value, the external user's ulcer is output as having a possibility of being diabetic foot disease, If the first ulcer output data matches the plurality of first sensing data input to the second threshold value, the external user's ulcer is output as having a high possibility of being diabetic foot disease, and If the first ulcer output data does not match the plurality of first sensing data input to the first threshold value and the second threshold value, the external user's foot ulcer is set to be output as a simple ulcer. Server.

5. In paragraph 1, The above processor, additionally acquiring at least one second sensing data from the external server through the communication interface, By additionally inputting at least one second sensing data into the prediction model, second ulcer output data is obtained, If the second ulcer output data is compared with the first threshold value and it is determined that the predetermined third threshold value is exceeded, it is output that the external user's foot ulcer is likely to be diabetic foot disease, and When the second ulcer output data is compared with a fourth threshold value set to be greater than the third threshold value and it is determined that the second threshold value is exceeded, the external user's foot ulcer is set to be output as the diabetic foot disease. Server.

6. In paragraph 5, The above guideline data is, It includes first hospital guidance data for general treatment, second hospital guidance data for hospitalization, first diet data suitable for at least one external user whose first ulcer output data exceeds a first threshold value but does not exceed a second threshold value, and second diet data suitable for at least one external user whose first ulcer output data exceeds a second threshold value or whose second ulcer output data exceeds a third threshold value. The above processor, Through the communication interface, the first ulcer output data is transmitted to the external user who exceeds the first threshold value but does not exceed the second threshold value, and the first hospital guidance data and the first diet data are transmitted; and Through the communication interface, the second hospital guidance data and the second diet data are transmitted to the external user when the first ulcer output data exceeds the second threshold value or the second ulcer output data exceeds the third threshold value, and Through the communication interface, the second ulcer output data is set to transmit the second hospital emergency guidance data to the external user who exceeds the fourth threshold value. Server.

7. A method for operating a server that predicts diabetic foot diagnosis based on multiple data based on a prediction model, The above method, Through a communication interface, at least one image data and at least one first sensing data are acquired from an external server of an external user, Through the processor, inputting the at least one image data and the at least one first sensing data into the prediction model to obtain the first ulcer output data, Through the processor, if the first ulcer output data is compared with a preset first threshold value and it is determined that the preset first threshold value is exceeded, it is output that the external user's foot ulcer is likely to be diabetic foot disease. Through the processor, if the first ulcer output data is compared with a second threshold value set to be greater than the first threshold value and the second threshold value is determined to be exceeded, the external user's foot ulcer is output as having a high possibility of being diabetic foot disease, and Through the processor, through the communication interface, the result data for the first ulcer output data determined to exceed the first threshold value and / or the second threshold value, and the guideline data presenting at least one guideline based on the result data are set to be transmitted, The above prediction model is, Learning is performed based on a plurality of image data, a plurality of first sensing data, and a plurality of second sensing data obtained from a plurality of users, a plurality of result data output from a plurality of users, and at least one expert opinion data that observed a plurality of users. method.

8. In paragraph 7, The above image data is, Includes multiple image data and multiple video data each photographing the user's feet from a preset location, The above first sensing data is, For the external user, at least one pressure data output from a pressure measurement module, at least one temperature data output from a temperature measurement module, and at least one humidity data output by measuring a change in moisture content based on electrical conductivity from a humidity module. method.

9. In paragraph 8, The above multiple image data, Includes multiple image data and multiple video data each photographing the feet of multiple users from a preset location, The above plurality of first sensing data are, For the above multiple users, at least one pressure data output from a pressure measurement module, at least one temperature data output from a temperature measurement module, and at least one humidity data output by measuring a change in moisture content based on electrical conductivity from a humidity module are included. The above plurality of second sensing data are, For the above multiple users, a plurality of blood sugar data output from a blood sugar measurement module, a plurality of blood flow data output from a blood flow measurement module, a plurality of oxygen saturation data output from an oxygen saturation measurement module, a plurality of pH data output from a pH measurement module, and a plurality of protease amount measurement data output from a protease amount measurement module are included. method.

10. In paragraph 9, The above first threshold value is, Including the plurality of image data, the plurality of first sensing data, and the plurality of second sensing data extracted as data having a possibility of diabetic foot disease among the at least one expert opinion data, The above second threshold value is, Including the plurality of image data, the plurality of first sensing data, and the plurality of second sensing data extracted as data having a possibility of diabetic foot disease among the at least one expert opinion data, The above method, If the first ulcer output data matches the plurality of first sensing data input to the first threshold value, the external user's ulcer is output as having a possibility of being diabetic foot disease, If the first ulcer output data matches the plurality of first sensing data input to the second threshold value, the external user's ulcer is output as having a high possibility of being diabetic foot disease, and If the first ulcer output data does not match the plurality of first sensing data input to the first threshold value and the second threshold value, the external user's foot ulcer is set to be output as a simple ulcer. method.

11. In paragraph 7, The above method, additionally acquiring at least one second sensing data from the external server through the communication interface, By additionally inputting at least one second sensing data into the prediction model, second ulcer output data is obtained, If the second ulcer output data is compared with the first threshold value and it is determined that the predetermined third threshold value is exceeded, it is output that the external user's foot ulcer is likely to be diabetic foot disease, and When the second ulcer output data is compared with a fourth threshold value set to be greater than the third threshold value and it is determined that the second threshold value is exceeded, the external user's foot ulcer is set to be output as the diabetic foot disease. method.

12. In paragraph 11, The above guideline data is, It includes first hospital guidance data for general treatment, second hospital guidance data for hospitalization, first diet data suitable for at least one external user whose first ulcer output data exceeds a first threshold value but does not exceed a second threshold value, and second diet data suitable for at least one external user whose first ulcer output data exceeds a second threshold value or whose second ulcer output data exceeds a third threshold value. The above method, Through the communication interface, the first ulcer output data is transmitted to the external user who exceeds the first threshold value but does not exceed the second threshold value, and the first hospital guidance data and the first diet data are transmitted; and Through the communication interface, the second hospital guidance data and the second diet data are transmitted to the external user when the first ulcer output data exceeds the second threshold value or the second ulcer output data exceeds the third threshold value, and Through the communication interface, the second ulcer output data is set to transmit the second hospital emergency guidance data to the external user who exceeds the fourth threshold value. method.

Images