Bromhidrosis postoperative wound infection risk prediction method and system

Abstract

The invention relates to a bromhidrosis postoperative wound infection risk prediction method and a bromhidrosis postoperative wound infection risk prediction system, aims to solve the problems that an existing clinical evaluation method depends on subjective experience and lacks a standardized tool, and performs quantitative prediction on the individual infection risk of a patient by utilizing a column graph model constructed based on multi-factor analysis. The method comprises the following steps: systematically collecting clinical index data of a patient, wherein the clinical index data comprises general data and operation-related indexes; inputting the data into a pre-constructed column graph model, and obtaining a comprehensive risk score by matching a corresponding score for each index and performing accumulation; and finally, the risk level is divided into a low-risk class and a high-risk class according to a preset threshold value, and an intuitive basis is provided for clinical decision making. According to the method, the operation process is standardized, the result output is visual, the method can be effectively integrated into the clinical working process, and a practical auxiliary tool is provided for medical staff to identify high-risk patients and implement targeted prevention and nursing measures, so that the quality and efficiency of postoperative management are expected to be improved.

Description

Technical Field

[0001] This application relates to the technical field, and in particular to a method and system for predicting the risk of wound infection after axillary osmidrosis surgery. Background Technology

[0002] Axillary osmidrosis surgery is a common treatment in dermatology and plastic surgery, but postoperative wound infection is one of the major complications affecting patient recovery quality and satisfaction. Infection prolongs wound healing time, increases patient suffering and medical costs, and may even lead to more serious clinical consequences. Therefore, effectively identifying and predicting the risk of wound infection before or early after surgery is of significant clinical importance for implementing targeted preventative measures and optimizing the allocation of medical resources.

[0003] Currently, the clinical assessment of postoperative infection risk still largely relies on the personal experience and judgment of medical staff, lacking standardized and objective quantitative tools. Although some statistical prediction models based on multivariate analysis exist, these models are usually complex to operate, requiring specialized software for calculation, and are difficult to integrate into busy daily clinical workflows for real-time application. This situation makes it difficult to guarantee the accuracy and consistency of risk assessment, potentially delaying timely intervention for high-risk patients.

[0004] In summary, existing risk assessment methods have significant shortcomings in terms of convenience and clinical applicability. Clinical practice urgently needs a practical tool that can intuitively and quickly translate multiple clinical characteristics of patients into individualized infection risk levels. This tool should require no complex calculations, be easy for healthcare professionals to quickly master and use, and thus provide immediate and objective decision support for developing differentiated postoperative care plans. Summary of the Invention

[0005] To achieve the above objectives, this application provides the following technical solution: According to a first aspect of the present invention, the present invention claims protection for a method for predicting the risk of wound infection after axillary osmidrosis surgery, comprising the following steps: S1, Obtain clinical indicator data of the patient to be predicted, including the patient's general information and surgery-related indicators; S2, input the clinical indicator data into a pre-constructed nomogram model for predicting the risk of wound infection after axillary osmidrosis surgery, the nomogram model being constructed based on multiple influencing factors of wound infection after axillary osmidrosis surgery. S3, calculate the patient's wound infection risk value using the nomogram model, and accumulate the total score based on the corresponding scores of each clinical indicator in the nomogram model; S4. Based on the risk value, determine the risk level of postoperative wound infection of the patient, wherein the risk level is divided into two categories: low risk and high risk.

[0006] Furthermore, it also includes: The general information includes gender, age, body mass index (BMI), smoking history, drinking history, medical history, and axillary osmidrosis (body odor) classification; The Body Mass Index (BMI) is calculated based on the patient's height and weight measurements, which are obtained using standardized medical equipment. The smoking history is defined as whether the patient has a long-term smoking habit, which is confirmed through a structured questionnaire or clinical interview. The drinking history is defined as whether the patient has a regular drinking habit, which is confirmed through a structured questionnaire or clinical interview. The medical history includes at least one of hypertension, diabetes, and coronary heart disease, obtained through medical records or diagnostic reports; The axillary odor grading is divided into grades 0, 1, 2 and 3 according to the Park and Shin diagnostic criteria, and is determined through clinical physician evaluation.

[0007] Furthermore, the surgical-related indicators include surgical method, month of surgery, surgical time, intraoperative blood loss, and antibiotic use; The surgical methods mentioned include one of the following: full-thickness fusiform skin excision, laser cauterization, minimally invasive small-incision apocrine gland excision, and negative pressure aspiration treatment, which are obtained through surgical records; The months for the surgeries are divided into the high-temperature season from May to October and the low-temperature season from November to April of the following year, and are determined by the date of the surgery. The surgical time is the total duration from the start to the end of the surgery, in hours, and is obtained from the operating room records. The amount of blood loss during the operation was estimated by the volume of blood collected by the intraoperative suction device or by weighing gauze, and recorded in milliliters. The information on antibiotic use includes the types and duration of prophylactic antibiotic use before, during, or after surgery, which is obtained through medication records.

[0008] Furthermore, step S2 also includes: S21, Identify the scale line in the nomogram model corresponding to each clinical indicator, with each scale line marked with a score corresponding to a different numerical range; S22, For each clinical indicator, match its data value with the numerical range of the corresponding scale line to determine the specific score of the indicator; S23, sum the scores of all clinical indicators to obtain the total score as the risk value; The layout of the scale lines in the nomogram model is designed based on the statistical correlation of historical patient data, ensuring that the score contribution of each indicator is positively correlated with the risk of wound infection.

[0009] Furthermore, step S4 also includes: The risk value is compared with a preset threshold, which is obtained through statistical analysis of the risk distribution of historical patient data. If the risk value is below the threshold, it is judged as low risk, indicating that the probability of wound infection is low; If the risk value is equal to or higher than the threshold, it is considered high risk, indicating a high probability of wound infection. The preset threshold is adjusted periodically based on new clinical data to maintain predictive accuracy.

[0010] Furthermore, prior to step S1, a data verification step is also included: Check the completeness and logical consistency of the clinical indicator data; missing data should be handled by re-collecting or appropriate interpolation. Verify the reliability of the data source to ensure that all data comes from standardized medical records or authoritative measurement tools; Outliers are marked and verified to eliminate data with obvious errors.

[0011] Furthermore, following step S4, a result output step is also included: The risk level is presented in a visual form, including a graphical nodal chart model interface or a numerical scoring report; The prediction results are automatically transmitted to the nursing team's terminal through the medical information system for clinical decision support. Generate personalized care recommendation documents, including wound care frequency, activity restriction requirements, and follow-up plans.

[0012] Furthermore, the method also includes a model validation step: The discrimination of the nomogram model was tested periodically using independent validation group patient data, and the area under the curve (AUC) was calculated using receiver operating characteristic (ROC) curve analysis. The model calibration was evaluated, and the Hosmer-Lemeshow test was used to compare the consistency between the predicted risk and the actual infection rate. Optimize the scale line scores and thresholds of the nomogram model based on the validation results to ensure prediction stability.

[0013] Furthermore, the score accumulation process of the nodal graph model is implemented manually or by automated software; If calculated manually, a standardized scoring sheet should be used to assist in summing the scores; If it is automated software, the risk value is output in real time through an embedded algorithm, but the algorithm does not involve model training or data preprocessing; The method described is based solely on single-center medical data, and all clinical indicator data are derived from the standardized collection process of the same medical institution. The application of the nomogram model is limited to the surgical treatment of axillary osmidrosis and is not extended to other diseases or non-surgical patients.

[0014] According to a second aspect of the present invention, the present invention claims protection for a system for predicting the risk of wound infection after axillary osmidrosis surgery, comprising: One or more processors; A memory having stored one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the method for predicting the risk of wound infection after axillary osmidrosis surgery.

[0015] This invention relates to a method and system for predicting the risk of wound infection after axillary osmidrosis surgery. It aims to address the problems of existing clinical assessment methods relying on subjective experience and lacking standardized tools. Utilizing a nomogram model constructed based on multifactorial analysis, it quantifies and predicts the individualized infection risk of each patient. The method involves systematically collecting patients' clinical indicator data, covering two main categories: general information and surgery-related indicators. The data is then input into a pre-constructed nomogram model. By matching corresponding scores to each indicator and accumulating these scores, a comprehensive risk score is obtained. Finally, the risk level is divided into low-risk and high-risk categories based on preset thresholds, providing an intuitive basis for clinical decision-making. This invention features a standardized operating procedure and intuitive results output, effectively integrating into clinical workflows. It provides a practical auxiliary tool for medical staff to identify high-risk patients and implement targeted preventative care measures, thereby potentially improving the quality and efficiency of postoperative management. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the workflow of a method for predicting the risk of wound infection after axillary osmidrosis surgery, as claimed in an embodiment of this application. Figure 2 This is a second flowchart of a method for predicting the risk of wound infection after axillary osmidrosis surgery, as claimed in an embodiment of this application. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0018] The terms "first," "second," and "third" in this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. All directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of this application are only used to explain the relative positional relationships and movements between components in a specific orientation (as shown in the figures). If the specific orientation changes, the directional indications also change accordingly. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

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

[0020] According to the first embodiment of the present invention, referring to Figure 1 This invention claims protection for a method for predicting the risk of wound infection after axillary osmidrosis surgery, comprising the following steps: S1, Obtain clinical indicator data of the patient to be predicted, including the patient's general information and surgery-related indicators; S2, input the clinical indicator data into a pre-constructed nomogram model for predicting the risk of wound infection after axillary osmidrosis surgery, the nomogram model being constructed based on multiple influencing factors of wound infection after axillary osmidrosis surgery. S3, calculate the patient's wound infection risk value using the nomogram model, and accumulate the total score based on the corresponding scores of each clinical indicator in the nomogram model; S4. Based on the risk value, determine the risk level of postoperative wound infection of the patient, wherein the risk level is divided into two categories: low risk and high risk.

[0021] In this embodiment, clinical indicator data includes the patient's general information and surgery-related indicators. Data acquisition requires extraction from standardized medical documents such as the patient's electronic health record, surgical record, and nursing assessment forms. General information and surgery-related indicators should be entered using structured tables to ensure each data point has a clear definition and source. During data collection, operators must verify patient identification information (such as medical record number) to ensure the data corresponds to the correct patient. If the data is scattered across different systems, data integration is necessary to avoid duplication or omissions.

[0022] A nomogram model is a visual chart, typically presented in paper or electronic form, where each clinical indicator corresponds to an axis, with numerical ranges and corresponding scores marked on the axis. When inputting data, operators must refer to the model layout and match the value of each clinical indicator with the scale on the corresponding axis. The model is built based on historical patient data, and its scale design reflects the statistical association between each indicator and infection risk. The input process requires operators to be familiar with the model structure to ensure accurate data mapping.

[0023] The calculation process involves assigning a score to each clinical indicator: based on the indicator value's position on the corresponding axis, the score within that range is read. For example, in the age indicator, 30 years old might correspond to a specific score. After all indicator scores are determined, they are simply added together to obtain the total score. The total score is the risk value, and the calculation process requires careful verification to avoid misreading scores or calculation errors. If electronic tools are used, the calculation may be automated, but the core logic remains the same: score accumulation.

[0024] Risk levels are categorized into low and high risk. The determination process involves comparing the total score with a preset threshold: the threshold is derived from historical data statistics, such as analyzing the relationship between past patients' total scores and actual infection events. If the total score is below the threshold, it is classified as low risk; if it is equal to or higher than the threshold, it is classified as high risk. The classification results are directly used for clinical decision-making, such as adjusting postoperative care plans.

[0025] Furthermore, it also includes: The general information includes gender, age, body mass index (BMI), smoking history, drinking history, medical history, and axillary osmidrosis (body odor) classification; The Body Mass Index (BMI) is calculated based on the patient's height and weight measurements, which are obtained using standardized medical equipment. The smoking history is defined as whether the patient has a long-term smoking habit, which is confirmed through a structured questionnaire or clinical interview. The drinking history is defined as whether the patient has a regular drinking habit, which is confirmed through a structured questionnaire or clinical interview. The medical history includes at least one of hypertension, diabetes, and coronary heart disease, obtained through medical records or diagnostic reports; The axillary odor grading is divided into grades 0, 1, 2 and 3 according to the Park and Shin diagnostic criteria, and is determined through clinical physician evaluation.

[0026] In this embodiment, the general data includes the following indicators, and the data processing logic for each indicator is as follows: Gender: Record as male or female, data from medical records or patient self-report. When entering data, ensure consistency with the patient's identity; in case of ambiguity, verify through medical documents.

[0027] Age: The patient's actual age at the time of surgery, expressed in years. This is calculated from the birth date and surgery date recorded in the medical records, or directly from the patient's self-reported age. Age data must be an integer; decimals are rounded off.

[0028] Body Mass Index (BMI): Calculated based on height and weight. Height and weight are measured using standard medical equipment (such as a height chart and weighing scale). Patients must remove their shoes and wear light clothing during measurement. The BMI value is obtained by dividing weight (in kilograms) by the square of height (in meters), and the result is rounded to one decimal place. The measurement process must follow institutional procedures to ensure accuracy.

[0029] Smoking history: defined as having or not having a long-term smoking habit. Long-term smoking refers to smoking daily for more than 6 months. Data is obtained through structured questionnaires (e.g., frequency, amount, duration of smoking) or clinical interviews, during which healthcare professionals ask and record the information. Data is stored in binary categories (yes / no).

[0030] Drinking history: defined as having or not having a regular drinking habit. Regular drinking is defined as drinking at least once a week for more than 3 months. It is obtained in the same way as smoking history, confirmed through questionnaires or interviews, and recorded in a binary category.

[0031] Medical history: Includes at least one of hypertension, diabetes, or coronary heart disease. Data should be obtained from the diagnosis list or report in medical records, clearly recording the name of the disease and the date of diagnosis. If the patient has multiple diseases, record all of them but do not score them repeatedly.

[0032] Axillary osmidrosis (body odor) is graded according to the Park and Shin diagnostic criteria: Grade 0 (no odor), Grade 1 (mild odor), Grade 2 (moderate odor), and Grade 3 (severe odor). The grade is determined by a clinician before surgery through olfactory assessment or symptom history taking, and the results are recorded in an assessment form.

[0033] Furthermore, the surgical-related indicators include surgical method, month of surgery, surgical time, intraoperative blood loss, and antibiotic use; The surgical methods mentioned include one of the following: full-thickness fusiform skin excision, laser cauterization, minimally invasive small-incision apocrine gland excision, and negative pressure aspiration treatment, which are obtained through surgical records; The months for the surgeries are divided into the high-temperature season from May to October and the low-temperature season from November to April of the following year, and are determined by the date of the surgery. The surgical time is the total duration from the start to the end of the surgery, in hours, and is obtained from the operating room records. The amount of blood loss during the operation was estimated by the volume of blood collected by the intraoperative suction device or by weighing gauze, and recorded in milliliters. The information on antibiotic use includes the types and duration of prophylactic antibiotic use before, during, or after surgery, which is obtained through medication records.

[0034] In this embodiment, the surgery-related indicators include the following indicators, and the data processing logic for each indicator is as follows: Surgical methods include one of the following: full-thickness fusiform skin excision, laser cauterization, minimally invasive small-incision apocrine gland excision, and negative pressure aspiration. Data is extracted from the surgical record, recording the specific technique name and details. If the record is unclear, please consult the surgeon for confirmation.

[0035] Surgery months are divided into May to October (high-temperature season) and November to April of the following year (low-temperature season). The month is determined by the surgery date, and then categorized into the corresponding season. Date data comes from the surgical scheduling system or anesthesia records.

[0036] Surgical time: The total duration of the surgery from the start (e.g., the first incision) to the end (e.g., suturing completed), in hours, rounded to one decimal place. Data is obtained from operating room records, such as anesthesia sheets or surgical logs. If the record is in minutes, it needs to be converted to hours (e.g., 120 minutes is recorded as 2.0 hours).

[0037] Intraoperative blood loss: Estimated by the volume of blood collected during surgery using a suction device (directly measured in milliliters) or by weighing gauze. The gauze weighing method involves comparing the weight of dry gauze before surgery with the weight of blood-soaked gauze after surgery, converting the weight to volume based on blood density. Data should be recorded in the surgical nursing record, ensuring consistency in units.

[0038] Antibiotic use: This includes the type and duration of prophylactic antibiotic use before, during, or after surgery. Data is extracted from medication records, recording the antibiotic name (e.g., cephalosporins), the time of administration (e.g., 30 minutes before surgery), and the total duration (e.g., 3 days). If no antibiotic was used, it is clearly recorded as "None".

[0039] Furthermore, referring to Figure 2 Step S2 further includes: S21, Identify the scale line in the nomogram model corresponding to each clinical indicator, with each scale line marked with a score corresponding to a different numerical range; S22, For each clinical indicator, match its data value with the numerical range of the corresponding scale line to determine the specific score of the indicator; S23, sum the scores of all clinical indicators to obtain the total score as the risk value; The layout of the scale lines in the nomogram model is designed based on the statistical correlation of historical patient data, ensuring that the score contribution of each indicator is positively correlated with the risk of wound infection.

[0040] In this embodiment, the nomogram model consists of multiple parallel axes, each representing a clinical indicator (such as age or BMI). Operators must first familiarize themselves with the model layout and locate the axis corresponding to each indicator. Each axis is marked with a numerical range (e.g., age 20-30 years) and a corresponding score (e.g., 5 points). The scale design is based on historical data to ensure that high-risk indicator values ​​correspond to high scores.

[0041] For each clinical indicator, its actual value (e.g., age 35 years) is compared with the range of values ​​on the corresponding axis to find the range containing that value, and the score for that range is read. If the value falls exactly on the boundary of the range, it is processed according to preset rules (e.g., assigned to the previous range). The score is recorded on the scoring sheet.

[0042] Sum the scores of all clinical indicators step by step to avoid omissions. The total score serves as a risk value, which can be calculated manually or with the aid of a calculator. The model design ensures that the summed scores are positively correlated with the risk of infection.

[0043] Furthermore, step S4 also includes: The risk value is compared with a preset threshold, which is obtained through statistical analysis of the risk distribution of historical patient data. If the risk value is below the threshold, it is judged as low risk, indicating that the probability of wound infection is low; If the risk value is equal to or higher than the threshold, it is considered high risk, indicating a high probability of wound infection. The preset threshold is adjusted periodically based on new clinical data to maintain predictive accuracy.

[0044] In this embodiment, the determination of the risk level includes: The preset thresholds are derived from analyzing historical patient data, such as collecting total scores and actual infection outcomes from past patients, and using statistical methods (such as distribution analysis) to determine the optimal cutoff point. The thresholds are stored numerically and reviewed periodically.

[0045] Comparison process: The patient's total score is directly compared to a threshold. During the comparison, it is essential to ensure the score calculation is accurate. If the score is below the threshold, the patient is considered low-risk, indicating a low probability of infection; if the score is equal to or above the threshold, the patient is considered high-risk, indicating a high probability of infection.

[0046] Threshold adjustment: At regular intervals (e.g., annually), new patient data is collected, and the thresholds are re-analyzed to determine if adjustment is necessary. Adjustments are based on changes in data distribution and are performed by statisticians.

[0047] Furthermore, prior to step S1, a data verification step is also included: Check the completeness and logical consistency of the clinical indicator data; missing data should be handled by re-collecting or appropriate interpolation. Verify the reliability of the data source to ensure that all data comes from standardized medical records or authoritative measurement tools; Outliers are marked and verified to eliminate data with obvious errors.

[0048] In this embodiment, a data verification step is included before step S1: Check for completeness and logical consistency: Verify that each clinical indicator has a value and that there are no missing values. For example, numerical indicators such as age and BMI cannot be empty. Logical consistency checks include verifying the reasonableness of the data (e.g., age does not exceed 100 years). Missing data should be retrieved by re-checking medical records or contacting the patient; if this is not feasible, use appropriate imputation (e.g., fill with the average value of similar patients).

[0049] Verify the reliability of data sources: Ensure data comes from authoritative sources, such as electronic health record systems and standardized measurement equipment. Patient-reported data (such as smoking history) must be verified by healthcare professionals.

[0050] Handling outliers: Outliers refer to data that is clearly inconsistent with the norm (e.g., a BMI of 100). Mark these values ​​and review the original records: if it is an entry error, correct it; if it cannot be confirmed, exclude the data point and record the reason.

[0051] Furthermore, following step S4, a result output step is also included: The risk level is presented in a visual form, including a graphical nodal chart model interface or a numerical scoring report; The prediction results are automatically transmitted to the nursing team's terminal through the medical information system for clinical decision support. Generate personalized care recommendation documents, including wound care frequency, activity restriction requirements, and follow-up plans.

[0052] In this embodiment, after step S4, a result output step is also included: Visualization: Risk levels are displayed in a graphical nodal chart interface, highlighting the scores of each indicator and the total score; or a digital scoring report is generated, including the risk category and a brief description. Display methods include the hospital information system interface or printed documents.

[0053] Automatic transmission to the nursing team: Predictive results are automatically sent to relevant nursing team terminals (such as electronic dashboards at nurse workstations) via the medical information system. Basic patient information is included during transmission to ensure timely updates.

[0054] Generate personalized care recommendations: Based on risk level, generate documented recommendations: low-risk patients are advised to receive standard care (e.g., weekly dressing changes); high-risk patients are advised to receive enhanced care (e.g., daily dressing changes, activity restrictions). Recommendations are generated from system templates and are based on clinical guidelines.

[0055] Furthermore, the method also includes a model validation step: The discrimination of the nomogram model was tested periodically using independent validation group patient data, and the area under the curve (AUC) was calculated using receiver operating characteristic (ROC) curve analysis. The model calibration was evaluated, and the Hosmer-Lemeshow test was used to compare the consistency between the predicted risk and the actual infection rate. Optimize the scale line scores and thresholds of the nomogram model based on the validation results to ensure prediction stability.

[0056] In this embodiment, the method further includes a model verification step: Discrimination test: The model's ability to distinguish between infected and non-infected patients is periodically tested using independent patient data (not used for model building). The area under the receiver operating characteristic (AUC) curve is calculated using receiver operating characteristic (ROC) curve analysis; a higher AUC value indicates better discrimination. The test is performed by statisticians.

[0057] Calibration assessment: The Hosmer-Lemeshow test was used to compare the consistency between predicted risk groupings and actual infection rates. The test grouped patients according to predicted risk and compared the actual infection rate in each group to assess model calibration.

[0058] Model optimization: If validation shows a performance degradation (e.g., a decrease in AUC value), adjust the scale scores and thresholds of the nomogram model. Optimize based on new data statistics to ensure the stability of model predictions.

[0059] Furthermore, the score accumulation process of the nodal graph model is implemented manually or by automated software; If calculated manually, a standardized scoring sheet should be used to assist in summing the scores; If it is automated software, the risk value is output in real time through an embedded algorithm, but the algorithm does not involve model training or data preprocessing; The method described is based solely on single-center medical data, and all clinical indicator data are derived from the standardized collection process of the same medical institution. The application of the nomogram model is limited to the surgical treatment of axillary osmidrosis and is not extended to other diseases or non-surgical patients.

[0060] In this embodiment, the score accumulation process of the line graph model adopts the following method: Manual calculation: A standardized scoring sheet is used. Operators record the score for each indicator on the sheet and then add them up manually. The calculation must be checked by two people to avoid errors.

[0061] Automated software: Implemented via embedded software, the software has built-in lookup logic: after inputting clinical indicator values, the software automatically matches scores and adds them up. The software does not involve model training or data preprocessing, only performing simple queries and additions.

[0062] The implementation of this method is limited to the following scope: Single-center medical data: All clinical indicator data originate from the same medical institution, ensuring standardized data collection processes (e.g., using uniform measurement tools and recording formats). The model is built based on the institution's historical data and is not applicable to other institutions.

[0063] Limited to the treatment of axillary osmidrosis surgery: The method is only used to predict the risk of wound infection after axillary osmidrosis surgery (such as excision or laser treatment), and is not used for other types of surgery (such as abdominal surgery) or non-surgical patients (such as patients receiving drug treatment).

[0064] According to a second embodiment of the present invention, the present invention claims protection for a system for predicting the risk of wound infection after axillary osmidrosis surgery, comprising: One or more processors; A memory having stored one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the method for predicting the risk of wound infection after axillary osmidrosis surgery.

[0065] The following is a specific example: The embodiments are based on a hypothetical medical scenario, covering all the claims, and focusing on the procedural logic, data processing, and clinical practice details. The embodiments avoid using specific numerical data, code, formulas, algorithms, and descriptions of functional effects, focusing solely on the operational flow. Example

[0066] This embodiment was implemented in the dermatology surgery center of a single medical institution (such as a general hospital). This institution has established a standardized medical record system, and all patient data is collected through a unified process. This embodiment uses a typical patient undergoing axillary osmidrosis surgery as an example to demonstrate the entire risk prediction process.

[0067] S1. Obtain clinical indicator data of the patient to be predicted. Upon admission, nurses collect general information and surgery-related indicators through the electronic health record system. General information includes gender, age, body mass index (BMI), smoking history, alcohol consumption history, medical history, and axillary osmidrosis (bromhidrosis) grade. Surgery-related indicators include surgical procedure, month of surgery, surgical time, intraoperative blood loss, and antibiotic use. Data sources include patient admission questionnaires, preoperative assessment forms, surgical records, and nursing logs. Nurses verify patient identification (e.g., medical record number) to ensure data accuracy. All data is entered into a structured spreadsheet and stored in the hospital database.

[0068] S2. Input clinical indicator data into the pre-built nomogram model. The nomogram model is stored at the nurses' station in paper form. The chart contains multiple parallel axes, each corresponding to a clinical indicator (such as age or BMI). Nurses locate the value of each indicator on the model using the data collected in S1. For example, for the age indicator, they locate the age axis and determine the corresponding position based on the patient's age range. The model is built based on historical patient data, and the scale design reflects the statistical correlation between each indicator and infection risk. The input process requires nurses to be familiar with the model layout to avoid misinterpretation.

[0069] S3. Calculate wound infection risk values ​​using a nomogram model. The calculation process assigns a score to each indicator: nurses read the score corresponding to each indicator value on the nomogram model (e.g., a specific score corresponds to a certain age range). All scores are recorded on a scoring sheet, and then a simple arithmetic sum is performed to obtain the total score. The summation is done manually by the nurses, with the aid of a calculator for verification to ensure no omissions or errors. The total score is the risk value, used for subsequent risk classification.

[0070] S4. Determine the risk level based on the risk value. Risk level classification is based on preset thresholds: these thresholds are derived by analyzing historical patient data, such as the relationship between past total patient scores and the distribution of actual infection events. Nurses compare the total score to the thresholds: if it is below the threshold, it is classified as low risk; if it is equal to or above the threshold, it is classified as high risk. The classification results are recorded in the patient's care plan to guide postoperative care.

[0071] Gender: Obtained from the patient's identification or self-report, recorded as male or female. Cross-validated with medical records during data entry.

[0072] Age: Actual age, expressed in years, is calculated based on the patient's date of birth and surgery date. Age data is sourced from the electronic health record system to ensure consistency with the surgery date.

[0073] Body Mass Index (BMI): Height and weight are measured using standard hospital equipment (such as a height chart and weight scale). Patients should remove their shoes and wear light clothing during the measurement. BMI values ​​are calculated automatically by the system or manually, and the results are rounded to one decimal place.

[0074] Smoking history: Obtained through a structured questionnaire, which inquired about the frequency, duration, and amount of smoking. This was defined as having or not having a long-term smoking habit (e.g., smoking daily for a certain period). Data was recorded after confirmation through nurse interviews.

[0075] Drinking history: Similar to smoking history, regular drinking habits (such as drinking a certain number of times per week) are confirmed through questionnaires or interviews and recorded as binary data.

[0076] Medical history: Extract diagnostic information such as hypertension, diabetes, and coronary heart disease from medical records. Nurses verify diagnostic reports or medication records to ensure the accuracy of the medical history.

[0077] Axillary osmidrosis grading: The attending physician assesses the patient preoperatively according to the Park and Shin diagnostic criteria, classifying it from grade 0 to 3 through olfactory testing or symptom consultation. The results are recorded on the preoperative assessment form.

[0078] Surgical procedure: Extract the specific technique name from the surgical record, such as fusiform full-thickness skin resection or laser cauterization. If the record is unclear, the nurse should consult with the surgeon for clarification.

[0079] Surgery month: The month is determined based on the surgery date and categorized as either the hot season (e.g., May to October) or the cold season (e.g., November to April of the following year). Date data is obtained from the surgery scheduling system.

[0080] Surgical time: Obtained from the anesthesia record or surgical log, recording the total duration from the start to the end of the surgery, in hours. If recorded in minutes, it needs to be converted to hours.

[0081] Intraoperative blood loss: The volume of blood collected by the intraoperative suction device is recorded directly, or estimated by weighing gauze (comparing the difference in gauze weight before and after surgery). The data is recorded by the surgical nurse on the nursing record sheet.

[0082] Antibiotic use: Extract details of antibiotic use before, during, or after surgery from the medication record, including the type of drug, the time of administration, and the duration. If no antibiotic was used, clearly record it as "None".

[0083] S2.1. Identifying the scale lines in the nomogram model: Nurses should first familiarize themselves with the layout of the nomogram model, where each indicator axis is marked with a numerical range and a corresponding score. For example, the age axis has multiple intervals, each interval corresponding to a score. The scale line design is based on historical data statistics to ensure that high-risk values ​​correspond to high scores.

[0084] S2.2. Matching Data Values ​​and Determining Scores: For each clinical indicator, the nurse matches the patient's actual value with the corresponding range on the axis. For example, if the age value falls into a certain range, the score for that range is read. The matching process must be careful to avoid errors in range boundaries.

[0085] S2.3. Accumulating Scores to Obtain the Total Score: After all indicator scores are determined, the nurse adds them up one by one on the scoring sheet. The addition process is carried out step by step, and if necessary, another medical staff member will review the scores to ensure accuracy.

[0086] The preset threshold is determined by statistically analyzing historical patient data: collecting total scores and actual infection outcomes from past patients, and using distribution analysis methods (such as percentiles) to determine the threshold. The threshold is reviewed periodically (e.g., annually).

[0087] Comparison process: Nurses directly compare the patient's total score with the threshold. Before comparison, the nurse confirms the score calculation is correct. Low risk indicates a low probability of infection, and high risk indicates a high probability of infection. The results are used for clinical decision-making; for example, high-risk patients require more intensive monitoring.

[0088] Threshold adjustment: New patient data is collected periodically, and statisticians re-analyze the thresholds. If the data distribution changes, the thresholds are adjusted accordingly to maintain predictive stability.

[0089] Prior to S1, nurses performed data validation: Check for completeness and logical consistency: Ensure that every clinical indicator has a value and no missing data. For example, check if age, BMI, etc., are entered. Logical consistency verification includes data reasonableness (e.g., age is within a reasonable range). Missing data should be handled by re-querying records or adding patients; if this is not feasible, use appropriate imputation (e.g., the average value of similar patients).

[0090] Verify the reliability of data sources: Confirm that the data comes from standardized sources, such as electronic health record systems or authoritative measurement tools. Patient self-reported data is verified by healthcare professionals.

[0091] Handling outliers: Mark obviously erroneous data (such as extremely high BMI values) and review the original records. If it is an entry error, correct it; if it cannot be confirmed, exclude the data and record the reason.

[0092] After S4, output the prediction results: Visualization: Risk levels are displayed in a graphical nodal chart interface on the hospital information system terminal, or a digital scoring report is generated. The report includes a total score, risk category, and brief description.

[0093] Automatic transmission to the nursing team: Predictive results are automatically sent to the nursing team's terminals (such as electronic dashboards at nurse workstations) via the medical information system. Basic patient information is included during transmission to ensure timely updates to the nursing plan.

[0094] Generate personalized care recommendations: Based on risk level, the system generates care recommendation documents. Standard care (such as regular dressing changes) is recommended for low-risk patients; enhanced measures (such as increased dressing change frequency and activity restrictions) are recommended for high-risk patients. Recommendations are based on clinical guideline templates.

[0095] The method involves periodically validating the model: Discrimination test: Independent patient data (not used for model building) was used to test the model's discrimination ability. The area under the receiver operating characteristic (ROC) curve was calculated using receiver operating characteristic (ROC) analysis to assess the model's ability to distinguish between infected and non-infected patients. The test was performed by statisticians.

[0096] Calibration assessment: The Hosmer-Lemeshow test was used to compare the consistency between predicted risk groupings and actual infection rates. Patients were grouped according to predicted risk, and the actual infection rate in each group was compared to assess the model's calibration.

[0097] Model optimization: If validation shows a performance degradation (e.g., a decrease in the area under the curve), adjust the scale scores and thresholds of the nomogram model. Optimization is based on new data statistics and is a collaborative effort between the clinical team and statisticians.

[0098] The score is accumulated in two ways: Manual calculation: Nurses use standardized scoring sheets to manually record the scores for each indicator, and then add them up arithmetically. The calculation process is double-checked to reduce errors.

[0099] Automated software: Implemented through embedded software within the hospital information system. The software has built-in lookup logic: after inputting clinical indicator values, the software automatically matches and accumulates the scores. The software does not involve model training or data preprocessing; it only performs simple queries and additions.

[0100] The method is implemented based solely on single-center medical data: all clinical indicator data are derived from standardized collection procedures within the same medical institution, such as uniform measurement tools and recording formats. The model is built based on historical data from this institution and is not applicable to other institutions.

[0101] This method is limited to the surgical treatment of axillary osmidrosis: it is only used to predict the risk of wound infection after axillary osmidrosis surgery (such as excision or laser treatment) and is not extended to patients with other diseases or non-surgical patients. When applying this method, ensure that the patient meets the indications for axillary osmidrosis surgery.

[0102] This embodiment demonstrates in detail the entire process of predicting the risk of wound infection after axillary osmidrosis surgery, covering everything from data acquisition to result output. The implementation logic is tight, the steps are explained in detail, and clinical operational details are emphasized to ensure the method is repeatable and stable.

[0103] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0104] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units. The above are merely embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made based on the description and drawings of this application, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

[0105] The specific embodiments of the invention have been described in detail above, but they are only examples, and this application is not limited to the specific embodiments described above. For those skilled in the art, any equivalent modifications or substitutions to the invention are also within the scope of this application. Therefore, all equivalent changes, modifications, and improvements made without departing from the spirit and principles of this application should be covered within the scope of this application.

Claims

1. A method for predicting the risk of wound infection after axillary osmidrosis surgery, characterized in that, Includes the following steps: S1, Obtain clinical indicator data of the patient to be predicted, including the patient's general information and surgery-related indicators; S2, input the clinical indicator data into a pre-constructed nomogram model for predicting the risk of wound infection after axillary osmidrosis surgery, the nomogram model being constructed based on multiple influencing factors of wound infection after axillary osmidrosis surgery. S3, calculate the patient's wound infection risk value using the nomogram model, and accumulate the total score based on the corresponding scores of each clinical indicator in the nomogram model; S4. Based on the risk value, determine the risk level of postoperative wound infection of the patient, wherein the risk level is divided into two categories: low risk and high risk.

2. The method for predicting the risk of wound infection after axillary osmidrosis surgery as described in claim 1, characterized in that, Also includes: The general information includes gender, age, body mass index (BMI), smoking history, drinking history, medical history, and axillary osmidrosis (body odor) classification; The Body Mass Index (BMI) is calculated based on the patient's height and weight measurements, which are taken using standardized medical equipment. The smoking history is defined as whether the patient has a long-term smoking habit, which is confirmed through a structured questionnaire or clinical interview. The drinking history is defined as whether the patient has a regular drinking habit, which is confirmed through a structured questionnaire or clinical interview. The medical history includes at least one of hypertension, diabetes, and coronary heart disease, obtained through medical records or diagnostic reports; The axillary odor grading is divided into grades 0, 1, 2 and 3 according to the Park and Shin diagnostic criteria, and is determined through clinical physician evaluation.

3. The method for predicting the risk of wound infection after axillary osmidrosis surgery as described in claim 1, characterized in that, The surgical-related indicators include surgical method, month of surgery, surgical time, intraoperative blood loss, and antibiotic use; The surgical methods mentioned include one of the following: full-thickness fusiform skin excision, laser cauterization, minimally invasive small-incision apocrine gland excision, and negative pressure aspiration treatment, which are obtained through surgical records; The months for the surgeries are divided into the high-temperature season from May to October and the low-temperature season from November to April of the following year, and are determined by the date of the surgery. The surgical time is the total duration from the start to the end of the surgery, in hours, and is obtained from the operating room records. The amount of blood loss during the operation was estimated by the volume of blood collected by the intraoperative suction device or by weighing gauze, and recorded in milliliters. The information on antibiotic use includes the types and duration of prophylactic antibiotic use before, during, or after surgery, which is obtained through medication records.

4. The method for predicting the risk of wound infection after axillary osmidrosis surgery as described in claim 1, characterized in that, Step S2 also includes: S21, Identify the scale line in the nomogram model corresponding to each clinical indicator, with each scale line marked with a score corresponding to a different numerical range; S22, For each clinical indicator, match its data value with the numerical range of the corresponding scale line to determine the specific score of the indicator; S23, sum the scores of all clinical indicators to obtain the total score as the risk value; The layout of the scale lines in the nomogram model is designed based on the statistical correlation of historical patient data, ensuring that the score contribution of each indicator is positively correlated with the risk of wound infection.

5. The method for predicting the risk of wound infection after axillary osmidrosis surgery as described in claim 1, characterized in that, Step S4 also includes: The risk value is compared with a preset threshold, which is obtained through statistical analysis of the risk distribution of historical patient data. If the risk value is below the threshold, it is judged as low risk, indicating that the probability of wound infection is low; If the risk value is equal to or higher than the threshold, it is considered high risk, indicating a high probability of wound infection. The preset threshold is adjusted periodically based on new clinical data to maintain predictive accuracy.

6. The method for predicting the risk of wound infection after axillary osmidrosis surgery as described in claim 1, characterized in that, Before step S1, a data verification step is also included: Check the completeness and logical consistency of the clinical indicator data; missing data should be handled by re-collecting or appropriate interpolation. Verify the reliability of the data source to ensure that all data comes from standardized medical records or authoritative measurement tools; Outliers are marked and verified to eliminate data with obvious errors.

7. The method for predicting the risk of wound infection after axillary osmidrosis surgery as described in claim 1, characterized in that, Following step S4, a result output step is also included: The risk level is presented in a visual form, including a graphical nodal chart model interface or a numerical scoring report; The prediction results are automatically transmitted to the nursing team's terminal through the medical information system for clinical decision support. Generate personalized care recommendation documents, including wound care frequency, activity restriction requirements, and follow-up plans.

8. The method for predicting the risk of wound infection after axillary osmidrosis surgery as described in claim 1, characterized in that, The method also includes a model validation step: The discrimination of the nomogram model was tested periodically using independent validation group patient data, and the area under the curve (AUC) was calculated using receiver operating characteristic (ROC) curve analysis. The model calibration was evaluated, and the Hosmer-Lemeshow test was used to compare the consistency between the predicted risk and the actual infection rate. Optimize the scale line scores and thresholds of the nomogram model based on the validation results to ensure prediction stability.

9. The method for predicting the risk of wound infection after axillary osmidrosis surgery as described in claim 4, characterized in that, The score accumulation process of the nodal graph model is implemented by manual calculation or automated software. If calculated manually, a standardized scoring sheet should be used to assist in summing the scores; If it is automated software, the risk value is output in real time through an embedded algorithm, but the algorithm does not involve model training or data preprocessing; The method described is based solely on single-center medical data, and all clinical indicator data are derived from the standardized collection process of the same medical institution. The application of the nomogram model is limited to the surgical treatment of axillary osmidrosis and is not extended to other diseases or non-surgical patients.

10. A system for predicting the risk of wound infection after axillary osmidrosis surgery, characterized in that, include: One or more processors; A memory having stored one or more programs that, when executed by one or more processors, cause the one or more processors to implement a method for predicting the risk of wound infection after axillary osmidrosis surgery according to any one of claims 1 to 9.

Images