Skin ulcer prognosis prediction method and system based on column diagram

Abstract

The invention relates to the technical field of skin ulcers, and discloses a skin ulcer prognosis prediction method and system based on a column diagram, and the method comprises the steps: obtaining a clinical feature data set of a patient; preprocessing the clinical feature data set to obtain a preprocessed clinical feature data set; inputting the preprocessed clinical feature data set into a pre-trained ulcer prognosis prediction model to obtain weight coefficients of independent risk factors; constructing a visual scoring system according to the weight coefficient; and according to a scoring result in the visual scoring system, predicting an ulcer prognosis poor probability. According to the skin ulcer prognosis prediction method and system based on the column diagram, the independent risk factors influencing ulcer prognosis are explored, and the prediction model is established through the regression curve and the column diagram, so that a patient with poor ulcer prognosis is identified, a more reasonable treatment scheme is established in the early stage of a disease, and the healing time of the ulcer is shortened.

Description

Technical Field

[0001] The present invention relates to the technical field of skin ulcers, and in particular to a nomogram-based skin ulcer prognosis prediction method and system. Background Art

[0002] Skin ulcers, also known as epidermal wounds, are characterized by tissue defects extending deep into the dermis and subcutaneous tissue. They are common clinically and often affect patients' quality of life. Severe cases can be life-threatening. They are one of the most common ailments, and nearly everyone experiences them at some point. However, due to the diverse causes and varying degrees of complexity, wound recovery time and prognosis also vary.

[0003] Therefore, scientifically and accurately predicting the prognosis of ulcers in the early stages is of great significance for their treatment, diagnosis and clinical strategy selection. Although some studies have conducted predictive model research on skin ulcers, most of them are aimed at a certain type of ulcer (such as foot ulcers caused by diabetes), and there is a lack of a predictive model for the entire disease of ulcers. Summary of the Invention

[0004] In view of the shortcomings of the existing technology, the present invention proposes a skin ulcer prognosis prediction method and system based on a nomogram to solve the above technical problems.

[0005] First, a nomogram-based method for predicting the prognosis of skin ulcers is provided, comprising: Obtain a dataset of patients’ clinical characteristics; Preprocessing the clinical characteristic data set to obtain a preprocessed clinical characteristic data set; Inputting the pre-processed clinical feature data set into a pre-trained ulcer prognosis prediction model to obtain weight coefficients of independent risk factors; Constructing a visual scoring system according to the weight coefficients; The probability of poor prognosis of ulcer is predicted according to the scoring results in the visual scoring system.

[0006] Furthermore, the clinical characteristic data set includes: age, wound area, course of illness before hospitalization, etiology type, diabetes comorbidity status, formal treatment signs before consultation, and non-prescription drug use signs.

[0007] Furthermore, the etiology types include pyoderma gangrenosum, panniculitis, skin cancer and trauma.

[0008] Furthermore, the clinical feature dataset is preprocessed, including: Calculate the outlier threshold based on the wound area distribution of the training set and delete samples that exceed the preset outlier threshold; Continuous disease variables were converted into dichotomous variables according to the critical value of the medical definition of chronic ulcer.

[0009] Furthermore, the pre-trained ulcer prognosis prediction model includes: Collect historical patient clinical data sets and annotate prognostic labels based on ulcer healing time; Univariate analysis was performed on clinical characteristics, and significant risk factors were screened based on univariate analysis; Binary regression and stepwise regression algorithms were used to determine the weight coefficients of independent risk factors.

[0010] In a second aspect, a method for predicting the prognosis of skin ulcers based on a nomogram according to any one of the above is provided, comprising: an acquisition module configured to acquire a clinical characteristic dataset of a patient; a preprocessing module, configured to preprocess the clinical feature dataset to obtain a preprocessed clinical feature dataset; a data input module configured to input the preprocessed clinical feature data set into a pre-trained ulcer prognosis prediction model to obtain weight coefficients of independent risk factors; A construction module configured to construct a visual scoring system according to the weight coefficients; The prediction module is configured to predict the probability of poor prognosis of ulcer according to the scoring results in the visual scoring system.

[0011] Furthermore, it also includes a verification module configured to generate an ROC curve and calculate the area under the curve; and output the contribution value of the clinical impact curve quantification model to clinical decision-making.

[0012] In a third aspect, a computer device is provided, comprising a processor, an input device, an output device, and a memory, wherein the processor, input device, output device, and memory are interconnected, wherein the memory is used to store a computer program, the computer program comprising program instructions, and the processor is configured to call the program instructions to execute the steps of the nomogram-based skin ulcer prognosis prediction method as described in any one of the foregoing items.

[0013] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program enables a computer to execute some or all steps of the nomogram-based skin ulcer prognosis prediction method as described in any one of the above items.

[0014] The invention adopting the above technical solution has the following advantages: The present invention explores the independent risk factors that affect the prognosis of ulcers and establishes a prediction model through regression curves and nomograms, thereby identifying patients with poor ulcer prognosis, and then establishing a more reasonable treatment plan in the early stages of the disease, shortening the healing time of ulcers. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the specific embodiments of the present invention, the following briefly introduces the drawings required for use in the specific embodiments. In all the drawings, each element or part is not necessarily drawn according to the actual scale.

[0016] Figure 1 This is a visualization diagram showing the prediction results in the skin ulcer prognosis prediction method and system based on the nomogram of the present invention; Figure 2 The figure is a ROC curve diagram of the skin ulcer prognosis prediction method and system based on the nomogram of the present invention; Figure 3 This is a calibration curve diagram in the nomogram-based skin ulcer prognosis prediction method and system of the present invention; Figure 4 A clinical decision curve diagram in the nomogram-based skin ulcer prognosis prediction method and system of the present invention; Figure 5 A graph showing a clinical impact curve in the nomogram-based skin ulcer prognosis prediction method and system of the present invention; Figure 6 Flowchart of the nomogram-based skin ulcer prognosis prediction method of the present invention; Figure 7 This is a structural diagram of an electronic device for predicting the prognosis of skin ulcers based on a nomogram according to the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0018] The terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0019] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0020] like Figures 1-7 As shown, the nomogram-based skin ulcer prognosis prediction method of the present invention comprises: Step S01: Obtain a patient's clinical characteristic data set; Step S02: preprocessing the clinical feature data set to obtain a preprocessed clinical feature data set; Step S03: inputting the pre-processed clinical feature data set into the pre-trained ulcer prognosis prediction model to obtain the weight coefficients of independent risk factors; Step S04: constructing a visual scoring system based on the weight coefficients; Step S05: predicting the probability of poor prognosis of ulcer according to the scoring results in the visual scoring system.

[0021] Specifically, skin ulcers are tissue defects deep into the dermis and subcutaneous tissue caused by various reasons. They are relatively common clinically and most of them will affect the patient's quality of life and even result in high medical expenses. Severe symptoms may threaten the patient's life.

[0022] Based on etiology, ulcers can be categorized as vascular, traumatic, infectious, chemical, radiation, pressure, neurodystrophy, and diabetic. Many factors contribute to the difficulty in healing ulcers, including systemic factors (such as malnutrition and concurrent systemic diseases like diabetes) and local factors (such as local medication irritation, specific infections, poor blood supply, and inappropriate treatment). Some causes remain unknown.

[0023] Explore the independent risk factors that affect the prognosis of ulcers, and establish a prediction model through regression curves and nomograms to help clinicians identify patients with poor ulcer prognosis more scientifically and accurately in the early stages, so as to establish more reasonable treatment plans in the early stages of the disease, shorten the healing time of ulcers, and improve the quality of life of patients.

[0024] In some embodiments, the clinical characteristic dataset includes: age, wound area, course of illness before hospitalization, etiology type, diabetes comorbidity, pre-hospitalization regular treatment markers, and non-prescription drug use markers.

[0025] In some embodiments, etiology types include pyoderma gangrenosum, panniculitis, skin cancer, and trauma.

[0026] In some embodiments, preprocessing the clinical feature dataset includes: Calculate the outlier threshold based on the wound area distribution of the training set and delete samples that exceed the preset outlier threshold; Continuous disease variables were converted into dichotomous variables according to the critical value of the medical definition of chronic ulcer.

[0027] In some embodiments, the pre-trained ulcer prognosis prediction model comprises: Collect historical patient clinical data sets and annotate prognostic labels based on ulcer healing time; Univariate analysis was performed on clinical characteristics, and significant risk factors were screened based on univariate analysis; Binary regression and stepwise regression algorithms were used to determine the weight coefficients of independent risk factors.

[0028] Specifically, multiple cases of ulcer patients were selected.

[0029] Inclusion criteria: ①Meet the diagnostic criteria for skin ulcer; ②Diagnosed with skin ulcer upon admission.

[0030] Exclusion criteria: ① No complete laboratory data.

[0031] Analytical methods Based on the etiology of ulcers and the risk factors affecting ulcer healing, a "Statistical Table of Ulcer Patients" was compiled, summarizing the patients' clinical data. Based on their post-hospital healing status, patients were divided into two groups: a good prognosis group (healing time ≤ 30 days) and a poor prognosis group (healing time > 30 days). Differences in medical records between the two groups were compared, and risk factors affecting ulcer healing were screened and regression analyzed. A clinical prediction model nomogram was constructed, and its accuracy and predictive efficacy were analyzed.

[0032] Observation indicators ① Demographic data: age and gender ② Treatment before admission: whether the patient received formal medical treatment before admission, and whether the patient used over-the-counter drugs on his own before admission.

[0033] ③Disease characteristics: ulcer wound area, ulcer location (upper limbs, lower limbs, face and trunk), ulcer cause (trauma, pyoderma gangrenosum, seborrheic dermatitis and skin cancer) and ulcer course.

[0034] ④ Associated diseases: diabetes, vascular diseases and tumors.

[0035] ⑤ Bacterial infection: whether there is concurrent bacterial infection, the number of infected bacteria, and the types of infected bacteria (Staphylococcus aureus, Pseudomonas aeruginosa, methicillin-resistant Staphylococcus aureus, non-tuberculosis bacilli and other bacteria).

[0036] ⑥Disease prognosis: good prognosis (healing time ≤ 30 days) and poor prognosis (healing time > 30 days).

[0037] Statistical analysis and model building Data processing and statistical analysis: A total of 497 patient samples were collected, and outliers were removed (values ​​greater than the upper quartile plus 1.5 times the interquartile range, based on wound area, were defined as outliers), resulting in 453 samples remaining. The pre-admission disease course was converted to a dichotomous variable based on the median (cutoff: 60 days). Based on previous studies, skin ulcers that did not heal for more than 1 month were defined as chronic ulcers.

[0038] Therefore, patients were divided into a good prognosis group (healing time ≤ 30 days) and a poor prognosis group (healing time > 30 days), with 30 days as the cutoff point. SPSS 22.0 statistical software was used for data processing and analysis.

[0039] Enumeration data were expressed as number of cases (percentages) and univariate analysis was performed using the chi-square test. Measurement data were expressed as median (interquartile range) and normal distribution was tested using the Kolmogorov-Smirnov test.

[0040] Model Development and Predictive Validation: Binary logistic regression analysis was performed on risk factors selected based on univariate analysis, and variables were selected using backward stepwise regression. A nomogram for predicting ulcer prognosis was constructed. The total score of the nomogram was the sum of the scores assigned to each risk factor. The score corresponded to the incidence of poor prognosis. Higher scores indicated a greater incidence of poor ulcer prognosis and a longer time to ulcer recovery.

[0041] The calibration curve of the model was drawn, the C index was calculated to further measure the accuracy of the model, and the receiver operating specificity curve was drawn to more comprehensively evaluate the sensitivity and specificity of the model; the clinical decision curve and clinical impact curve were used to further determine the clinical effectiveness of the prediction model.

[0042] In other embodiments, a nomogram-based skin ulcer prognosis prediction method according to any of the above items is provided, comprising: an acquisition module configured to acquire a clinical characteristic dataset of a patient; a preprocessing module configured to preprocess the clinical feature dataset to obtain a preprocessed clinical feature dataset; a data input module configured to input the preprocessed clinical feature data set into the pre-trained ulcer prognosis prediction model to obtain weight coefficients of independent risk factors; A building module configured to build a visual scoring system based on weight coefficients; The prediction module is configured to predict the probability of poor prognosis of ulcer according to the scoring results in the visual scoring system.

[0043] In some embodiments, the method further includes a verification module configured to generate an ROC curve and calculate the area under the curve; and output a clinical impact curve to quantify the contribution of the model to clinical decision-making.

[0044] In other embodiments, a computer device is provided, comprising a processor, an input device, an output device, and a memory, wherein the processor, the input device, the output device, and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the steps of any of the nomogram-based skin ulcer prognosis prediction methods described above.

[0045] In other embodiments, a computer-readable storage medium is provided, wherein a computer program product includes a non-transitory computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute some or all steps of the nomogram-based skin ulcer prognosis prediction method as described above.

[0046] in conclusion: Comparison of demographic data A total of 453 samples were included in this study, including 246 males and 207 females. The favorable prognosis group consisted of 234 patients with a mean age of 52 years, including 134 males and 100 females. The unfavorable prognosis group consisted of 112 patients with a mean age of 61 years, including 112 males and 107 females. The unfavorable prognosis group was significantly older than the favorable prognosis group (P) (Table 1).

[0047] Comparison of disease characteristics Most patients present with ulcers due to trauma, while ulcers caused by other causes have a poorer prognosis (p). Ulcers due to pyoderma gangrenosum and skin cancer both have a poor prognosis, but due to the small number of skin cancer patients, this difference was not statistically significant. Patient prognosis was not significantly associated with ulcer location, but was potentially associated with wound size, duration of illness before hospitalization, prior treatment, and self-use of over-the-counter medications. In the poor prognosis group, the median wound area was 8.0 cm², significantly higher than in the good prognosis group.

[0048] In addition, the proportion of patients with a pre-hospitalization course of more than 60 days in the poor prognosis group was significantly higher than that in the good prognosis group. Patients with other comorbidities can also affect the prognosis of ulcers. This study primarily investigated the impact of diabetes, vascular disease, and tumors on prognosis. The results showed that among patients with these three diseases, the proportion of patients with poor ulcer prognosis was significantly higher than that in the good prognosis group. Among patients with ulcer wounds complicated by a bacterial infection, the proportion of patients with poor prognosis was significantly higher than that in the good prognosis group. Furthermore, patients with non-tuberculosis infections all had poor prognosis, while no significant differences were observed in infections with Staphylococcus aureus, aeruginosa, MRSA, and other types of bacteria (Table 1).

[0049] Table 1 Comparison of patient characteristics in different prognostic groups Establishment of clinical prediction model The relevant risk factors revealed by univariate analysis were subjected to binary logistic regression analysis, and variables were screened according to the backward stepwise regression method. The analysis results showed that age, wound area, pre-hospitalization course, etiology, concomitant diabetes, pre-treatment treatment, and self-use of over-the-counter drugs were independent risk factors for poor prognosis of ulcer (Table 2).

[0050] The "plot" function was used to generate a nomogram for the above-mentioned independent risk factors to further analyze the impact of each factor on the poor prognosis of ulcers. The results showed that the risk factor with the highest score was a wound area of ​​35 cm, which was 100 points; followed by age, and then self-use of over-the-counter drugs, etiology, a course of illness greater than 60 days before admission, no formal treatment before treatment, and concomitant diabetes. As shown in the figure, as the risk factors increase, the incidence of poor prognosis increases significantly (e.g. Figure 1 shown).

[0051] Table 2 Results of binary logistic regression analysis Evaluation of the accuracy and predictive efficiency of the nomogram model The accuracy of the nomogram model was evaluated by ROC curve and C index. The analysis and calculation results showed that the C index was 0.814 and the 95% confidence interval was 0.775-0.853 (e.g. Figure 2 As shown in the figure, the model calibration curve coincides well with the actual curve, and the constructed model has good consistency with the ideal model (as shown in the figure). Figure 3 In terms of clinical application value, Figure 4As shown, the decision curve analysis showed that the net benefit was 0 when there was no intervention, i.e. the None straight line in the figure. When there was full intervention, the net benefit was as shown in the All curve in the figure. The nomogram curve was the achievable benefit of the risk prediction model we constructed. The clinical decision curve showed that the prediction model could provide clinical benefits for clinical participants at a decision threshold of 0-0.9. The clinical impact curve showed that the nomogram model could provide good clinical impact for clinical participants to a certain extent (e.g. Figure 5 As shown).

[0052] This study collected and collated the clinical data of patients with ulcers through a retrospective study, drew a nomogram, and established a prediction model for poor prognosis of ulcer patients, to provide a basis for timely and effective intervention for ulcer patients with poor prognosis.

[0053] The prediction model for poor prognosis of ulcers established in this study has strong accuracy. Through the backward stepwise method to screen variables, this model finally included age, wound area, pre-hospital course, etiology, diabetes, regular disposal before treatment, and abuse of non-prescription drugs. These seven independent risk factors are consistent with the clinical characteristics of patients with poor prognosis of ulcers, suggesting that the model has strong relevance to clinical reality.

[0054] The highest score in the model is the wound area. The larger the wound area of the patient, the higher the risk of poor prognosis. Generally speaking, wound area is a recognized risk factor for poor prognosis of ulcers. Larger wound area not only directly leads to more difficulty in recovery of patients, but also makes the wound more susceptible to other factors (such as bacterial infection, decreased mobility, limited treatment options, etc.), thus leading to more difficulty in recovery. This study found that age is also an important factor affecting the prognosis of ulcers. Changes in the dermis and epidermis caused by aging make it more difficult for patients to heal ulcers. In addition, the weak immune ability of older patients makes the wound more susceptible to bacterial infection, thus further exacerbating the development of ulcers.

[0055] Furthermore, this study found that etiology is also a significant factor influencing ulcer prognosis. The etiologies analyzed in this study included pyoderma gangrenosum, panniculitis, and skin cancer. Of these, only pyoderma gangrenosum was strongly associated with a poor ulcer prognosis. Pyoderma gangrenosum is a non-infectious skin disease characterized by abnormal neutrophil chemotaxis. Its etiology remains unclear, but it is often associated with systemic diseases. It is currently hypothesized that its etiology is likely related to immune dysfunction. A hyperactive immune environment secretes a large amount of inflammatory factors, which is detrimental to granulation tissue formation and ulcer wound healing, leading to a poor ulcer prognosis. Therefore, timely improvement of the hyperactive immune environment in ulcers caused by pyoderma gangrenosum is necessary. Concomitant diabetes mellitus is also a contributing factor to the poor prognosis of ulcers. Due to abnormal blood sugar levels, diabetic patients often suffer from peripheral neurovascular abnormalities, resulting in poor blood supply to the ulcer, insufficient nutritional support for wound regeneration and healing, and a poor prognosis. Therefore, for patients with ulcers and diabetes, reasonable and timely control of blood sugar levels is of great significance for the healing of ulcer wounds.

[0056] The course of illness and treatment prior to hospitalization also significantly impact the prognosis of ulcers. A long course prior to hospitalization often indicates that the patient's ulcer is inherently difficult to heal, and the patient's lack of attention and irregular treatment can lead to the ulcer becoming even more difficult to heal. In particular, many patients fail to take ulcers seriously and self-use over-the-counter medications, leading to a poor prognosis for the ulcer. These medications are mostly ground traditional Chinese herbal remedies or ointments. These medications not only fail to promote healing of ulcer wounds, but can further irritate the wound, causing it to remain unhealed for a prolonged period. Therefore, strengthening the popularization of relevant medical knowledge and enhancing patients' understanding of ulcer-related knowledge are essential for reducing the poor prognosis of ulcers.

[0057] In summary, seven factors—advanced age, larger wound area, longer prehospitalization course, etiology (pyoderma gangrenosum), concurrent diabetes, lack of proper treatment prior to presentation, and over-the-counter medication abuse—all increase the likelihood of a poor ulcer prognosis. The prediction model developed in this study is hoped to help clinicians identify patients with a poor ulcer prognosis early on and provide timely and effective intervention based on their disease characteristics, thereby reducing the onset of ulcers, minimizing the use of medical resources, and improving patients' quality of life while alleviating their financial burden.

[0058] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0059] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0060] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0061] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0062] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software program modules.

[0063] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk, or optical disk, etc., various media that can store program code.

[0064] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which may include: a flash drive, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0065] The above is a detailed introduction to the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A nomogram-based method for predicting the prognosis of skin ulcers, characterized in that: include: Obtain a dataset of patients’ clinical characteristics; Preprocessing the clinical characteristic data set to obtain a preprocessed clinical characteristic data set; Inputting the pre-processed clinical feature data set into a pre-trained ulcer prognosis prediction model to obtain weight coefficients of independent risk factors; Constructing a visual scoring system according to the weight coefficients; The probability of poor prognosis of ulcer is predicted according to the scoring results in the visual scoring system.

2. The method for predicting the prognosis of skin ulcers based on a nomogram according to claim 1, wherein: The clinical characteristic data set includes: age, wound area, course of illness before admission, etiology type, diabetes comorbidity, pre-treatment formal treatment signs, and over-the-counter drug use signs.

3. The method for predicting the prognosis of skin ulcers based on a nomogram according to claim 2, wherein: The etiological types include pyoderma gangrenosum, panniculitis, skin cancer and trauma.

4. The method for predicting the prognosis of skin ulcers based on a nomogram according to claim 1, wherein: The clinical feature dataset is preprocessed, including: Calculate the outlier threshold based on the wound area distribution of the training set and delete samples that exceed the preset outlier threshold; Continuous disease variables were converted into dichotomous variables according to the critical value of the medical definition of chronic ulcer.

5. The method for predicting the prognosis of skin ulcer based on a nomogram according to claim 1, characterized in that: The pre-trained ulcer prognosis prediction model includes: Collect historical patient clinical data sets and annotate prognostic labels based on ulcer healing time; Univariate analysis was performed on clinical characteristics, and significant risk factors were screened based on univariate analysis; Binary regression and stepwise regression algorithms were used to determine the weight coefficients of independent risk factors.

6. A nomogram-based skin ulcer prognosis prediction system, characterized in that: The method for predicting the prognosis of skin ulcers based on a nomogram according to any one of claims 1 to 5, comprising: an acquisition module configured to acquire a clinical characteristic dataset of a patient; a preprocessing module, configured to preprocess the clinical feature dataset to obtain a preprocessed clinical feature dataset; a data input module configured to input the preprocessed clinical feature data set into a pre-trained ulcer prognosis prediction model to obtain weight coefficients of independent risk factors; A construction module configured to construct a visual scoring system according to the weight coefficients; The prediction module is configured to predict the probability of poor prognosis of ulcer according to the scoring results in the visual scoring system.

7. The skin ulcer prognosis prediction system based on nomogram according to claim 5, characterized in that: The method also includes a validation module configured to generate a ROC curve and calculate the area under the curve; and output a clinical impact curve to quantify the contribution of the model to clinical decision-making.

8. A computer device comprising a processor, an input device, an output device, and a memory, wherein the processor, the input device, the output device, and the memory are interconnected, wherein: The memory is used to store a computer program, which includes program instructions. The processor is configured to call the program instructions to execute the steps of the nomogram-based skin ulcer prognosis prediction method according to any one of claims 1 to 5.

9. A computer-readable storage medium, a computer program product comprising a non-transitory computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute part or all of the steps of the nomogram-based skin ulcer prognosis prediction method according to any one of claims 1 to 5.

Images