KR-20260067893-A - Apparatus and Method for Diagnosing Psoriasis and Diabetes in Connection

KR20260067893AKR 20260067893 AKR20260067893 AKR 20260067893AKR-20260067893-A

Abstract

The present invention relates to an apparatus and method for diagnosing psoriasis and diabetes in conjunction. More specifically, the apparatus comprises an input unit for inputting a skin image and a blood sample of a user’s skin, a psoriasis diagnosis unit for diagnosing psoriasis using a psoriasis diagnosis model based on the skin image, a diabetes diagnosis unit for diagnosing diabetes using a diabetes diagnosis model based on the blood sample when the user is diagnosed with psoriasis by the psoriasis diagnosis unit, and a result providing unit for providing the diagnosis results and diagnostic information of the diagnosis unit. By providing a specialized diabetes diagnosis model for patients with psoriasis, the apparatus can perform a more precise and accurate diagnosis.

Inventors

양오석

Assignees

강원대학교산학협력단

Dates

Publication Date: 20260513
Application Date: 20241106

Claims (10)

Input unit for inputting a skin image and blood sample captured from the user's skin; A diagnosis unit comprising a psoriasis diagnosis unit that diagnoses psoriasis using a psoriasis diagnosis model based on the above skin image, and a diabetes diagnosis unit that diagnoses diabetes using a diabetes diagnosis model based on the above blood sample when the user is diagnosed with psoriasis in the above psoriasis diagnosis unit; and A result providing unit that provides the diagnosis results and diagnosis information of the above-mentioned diagnosis unit; A device for diagnosing psoriasis and diabetes in combination, characterized by including
In paragraph 1, The above psoriasis diagnostic model is a model trained using time-series data of cross-sectional image groups of diseased areas in the early, middle, and late stages of psoriasis patients, and The above diabetes diagnosis model is a model trained based on blood test data including diabetes levels of the above psoriasis patients, and A device for diagnosing psoriasis and diabetes in conjunction, characterized in that the above psoriasis diagnostic model and the above diabetes diagnostic model are composed of a single deep learning model.
In paragraph 2, A device for diagnosing psoriasis and diabetes in conjunction, characterized in that the above blood test data is data labeled and preprocessed from detailed time-series data related to liver function tests for diabetes Hepa-9 products for each psoriasis patient, including ALT(T), AST(T), GGT(T), TBIL(T), TP(T), DBIL(T), ALB(T), and ALP_IF(T).
In paragraph 1, A device for diagnosing psoriasis and diabetes in conjunction, characterized by further including a personalization unit that performs fine tuning of the diagnostic unit based on data from the input unit to provide a personalized model for the user.
In paragraph 1, A device for diagnosing psoriasis and diabetes in conjunction, characterized in that the result providing unit provides the user with one or more diagnostic information, such as a diagnostic result including a psoriasis type and a diabetes status, and recommended cosmetics, health functional foods, and treatments.
A step of acquiring a user's skin image and blood sample from an input unit; A step of diagnosing psoriasis using a psoriasis diagnosis model based on the skin image in the psoriasis diagnosis unit; A step of diagnosing diabetes using a diabetes diagnosis model based on the blood sample when the user is diagnosed with psoriasis in the diabetes diagnosis unit; and A step of providing diagnostic results and diagnostic information to the above user at the result provision unit; A method for diagnosing psoriasis and diabetes in combination, characterized by including
In paragraph 6, The above psoriasis diagnostic model is a model trained using time-series data of cross-sectional image groups of diseased areas in the early, middle, and late stages of psoriasis patients, and The above diabetes diagnosis model is a model trained based on blood test data including diabetes levels of the above psoriasis patients, and A method for diagnosing psoriasis and diabetes in conjunction, characterized in that the above psoriasis diagnostic model and the above diabetes diagnostic model are composed of a single deep learning model.
In Paragraph 7, A method for diagnosing psoriasis and diabetes in conjunction, characterized in that the above blood test data is data labeled and preprocessed from detailed time series data related to liver function tests for diabetes Hepa-9 products for each psoriasis patient, including ALT(T), AST(T), GGT(T), TBIL(T), TP(T), DBIL(T), ALB(T), and ALP_IF(T).
In paragraph 6, A method for diagnosing psoriasis and diabetes in conjunction, characterized by further including the step of generating a personalized deep learning model by fine-tuning the psoriasis diagnostic model and the diabetes diagnostic model using the skin image and blood sample.
In paragraph 1, A method for diagnosing psoriasis and diabetes in conjunction, characterized by the step of providing the above-mentioned diagnostic results and diagnostic information to the user, which includes providing one or more diagnostic results including psoriasis type and diabetes status and diagnostic information such as recommended cosmetics, health functional foods, and treatments to the user.

Description

Apparatus and Method for Diagnosing Psoriasis and Diabetes in Connection The present invention relates to an apparatus and method for diagnosing psoriasis and diabetes in conjunction, and specifically, to an apparatus and method for diagnosing psoriasis using artificial intelligence and diagnosing diabetes in conjunction with psoriasis disease. To respond to rapid changes in the business environment and gain a competitive edge over hardware-centric computing systems such as big data, cloud IoT, and robots, companies have put forward 'digital transformation' as a primary core strategy. Furthermore, with the recent advancement of AI technology, the strategy of 'AI transformation' is becoming increasingly important as companies seek to secure a competitive edge through mega-AI solutions that utilize deep learning algorithms based on generative AI across all business operations and business models. In line with this paradigm of 'AI transformation,' research into utilizing AI solutions is also accelerating in the medical and health-related markets, and the AI market size is also predicted to grow from $17.2 billion in 2022 to over $12.2 billion in 2028, achieving an average annual growth rate of 38%. The medical platform market is emerging as a major issue within the paradigm of 'AI transformation,' with significant interest focused particularly on diagnostic methods for skin and blood diseases within the medical and health sectors. However, diagnostic methods for skin and blood diseases generally utilize average data to provide information to an unspecified number of patients; furthermore, skin and blood diseases are classified as separate conditions and provided independently. For the reasons mentioned above, dry skin is treated at the dermatology department, while blood disorders such as diabetes are treated separately at the endocrinology department. Consequently, prescriptions for each condition are issued independently, often leading to the unnecessary consumption of multiple medications. However, studies are emerging that report an increased risk of circulatory and cerebrovascular diseases in psoriasis patients, leading to growing calls to evaluate the cardiovascular disease risk in conjunction with psoriasis. This can be said to be a correlation based on the fact that diabetes develops due to problems with insulin regulation, as the fat cells of psoriasis patients do not function normally and interfere with insulin regulation; therefore, a solution for this is needed. FIG. 1 is a drawing showing a device for diagnosing psoriasis and diabetes in combination according to one embodiment of the present invention. FIG. 2 is a diagram illustrating a data set for learning a psoriasis diagnosis unit of a device for diagnosing psoriasis and diabetes in conjunction according to one embodiment of the present invention. FIG. 3 is a diagram illustrating a data set for learning a diabetes diagnosis unit of a device for diagnosing psoriasis and diabetes in conjunction according to one embodiment of the present invention. FIG. 4 is a flowchart illustrating a method for diagnosing psoriasis and diabetes in combination according to one embodiment of the present invention. The present invention is capable of various modifications and may have various embodiments, and specific embodiments are illustrated in the drawings and described in detail. However, this is not intended to limit the invention to specific embodiments, and it should be understood that it includes all modifications, equivalents, and substitutions that fall within the spirit and scope of the invention. The terms used in this application are used merely to describe specific embodiments and are not intended to limit the invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, terms such as "comprising" or "having" are intended to specify the presence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof. Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the present invention pertains. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application. Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the attached drawings. In order to facilitate an overall understanding of the present invention, the same reference numerals are used for identical components in the