A prostate cancer radical surgery postoperative care early warning management system and method

Abstract

The application discloses a prostate cancer radical surgery postoperative nursing early warning management system and method, which comprises a basic information acquisition module, an evaluation module, a core symptom identification module, a risk stratification module, a nursing early warning module, an individualized nursing setting module and a follow-up management module.The evaluation module is used for integrity, logical consistency and abnormal value checking, and is used for calculating symptom severity score and life quality score, and generating patient individual longitudinal change trend chart.The core symptom identification module is used for constructing a regular symptom network, calculating intensity centrality and stability index thereof, and forming a core symptom reference model.The risk stratification module is used for nursing risk stratification, and is used for sending to the nursing early warning module and the individualized nursing setting module.The nursing early warning module is used for generating nursing early warning information.The individualized nursing setting module is used for generating nursing suggestions.The follow-up management module is used for establishing a follow-up archive.The data quality control, stage core symptom identification, individual risk stratification and nursing suggestion output are realized.

Description

Technical Field

[0001] This invention relates to the field of postoperative nursing technology, specifically to a nursing early warning management system and method after radical prostatectomy. Background Technology

[0002] Radical prostatectomy is an important treatment for localized prostate cancer and some locally advanced prostate cancers. In the early postoperative period, patients often experience a variety of symptoms, including pain, fatigue, sleep disturbances, urinary frequency, urgency, incontinence, anxiety, and difficulty with sexual intercourse. These symptoms are often not isolated but rather interact and reinforce each other, collectively affecting the patient's postoperative functional recovery and quality of life.

[0003] Currently, the management of patients after radical prostatectomy mainly includes pain assessment, urinary incontinence management, pelvic floor muscle training, psychological support, health education, and routine follow-up. Existing nursing assessment methods largely rely on patient complaints, individual symptom scores, or the experience of nursing staff. While these methods can identify postoperative symptoms to some extent, they still have the following shortcomings:

[0004] First, existing assessments are mostly single or static, making it difficult to reflect the trajectory of symptom changes in patients from pre-operative to early post-operative stages. The main symptoms faced by patients undergoing radical prostatectomy are not exactly the same before surgery, 7 days after surgery, 1 month after surgery, and 3 months after surgery. If a standardized assessment method is used, it is easy to overlook the phased changes in the focus of symptoms.

[0005] Second, current nursing management focuses primarily on the incidence and severity of symptoms, lacking an understanding of the relationships between them. In reality, there are certain connections between postoperative symptoms such as pain, fatigue, anxiety, urinary incontinence, and sleep disturbances. It is difficult to determine which symptom plays a key role in the overall symptom network based solely on a single symptom score.

[0006] Third, existing follow-up systems primarily focus on recording and reminders, lacking core symptom identification, risk level classification, and nursing early warning functions based on symptom data. Nurses struggle to promptly determine the most urgent symptoms requiring intervention for a particular patient, and also find it difficult to generate individualized nursing recommendations based on different postoperative stages.

[0007] Fourth, existing postoperative care tools for prostate cancer are not sufficiently integrated with quality of life assessments, failing to fully reflect the impact of symptom burden on patients' declining quality of life and hindering the early detection of high-risk patients with significantly impaired quality of life. Summary of the Invention

[0008] This invention aims to address the problems of static postoperative nursing assessment, reliance on experience in determining core symptoms, opaque risk stratification rules, and difficulty in continuously utilizing follow-up data. It proposes a nursing early warning management system and method for radical prostatectomy based on standardized scales, a group symptom network reference model, and a calibrable risk algorithm to achieve data quality control, phased identification of core symptoms, individual risk stratification, and output of nursing recommendations.

[0009] To achieve the above objectives, the present invention provides a postoperative nursing early warning management system for radical prostatectomy, comprising:

[0010] The basic information collection module is used to input the patient's basic information, disease information, treatment information, pre- and post-operative symptoms, and post-operative quality of life.

[0011] The assessment module is used to verify the completeness, logical consistency, and outliers of the collected data, and to calculate the symptom severity score and quality of life score based on the standardized symptom scale and quality of life scale, generating a longitudinal trend chart of individual patients.

[0012] The core symptom identification module is used to construct a regularized symptom network based on group symptom data at the same follow-up time point, calculate the strength centrality and stability index of symptom nodes, and form a core symptom reference model for each stage.

[0013] The risk stratification module is used to stratify patients' nursing risks and simultaneously send the nursing risk stratification information to the nursing early warning module and the individualized nursing settings module.

[0014] The nursing early warning module is used to generate nursing early warning information based on risk stratification results and core symptoms;

[0015] The individualized nursing settings module is used to generate nursing suggestions and send these suggestions to the attending physician and the responsible nurse through the hospital office management system.

[0016] The follow-up management module is used to establish a continuous follow-up record for patients in the early postoperative period.

[0017] In the above plan: the patient's basic information includes age, marital status, education level, occupation, and medical payment method; disease information includes family history, previous transurethral resection of the prostate (TURP), clinical T stage, Gleason score, comorbid chronic diseases, and smoking and drinking habits; treatment information includes surgical procedures and related information, including whether nerve preservation was performed, whether lymph node dissection was performed, operation time, and catheterization duration; surgical related information includes pathological T stage, resection margin status, postoperative prostate-specific antigen level, and postoperative urinary function; a patient personal file is established through the basic information collection module to provide basic data for subsequent symptom assessment, risk level classification, and follow-up management;

[0018] Preoperative and postoperative symptoms include those of patients undergoing radical prostatectomy 1 day before surgery, 7 days after surgery, 1 month after surgery, and 3 months after surgery. These symptoms include common symptoms of patients undergoing radical prostatectomy such as pain, fatigue, restless sleep, anxiety, frequent urination, urgency, urinary incontinence, difficulty in sexual intercourse, decreased appetite, dry mouth, sweating, and constipation.

[0019] Postoperative quality of life includes scores on the patient's overall health status, functional status, and symptom dimensions, and records the changes relative to the preoperative baseline.

[0020] In the above scheme: when scoring in the scoring module, each symptom is divided into 5 levels according to its severity. Among them, no symptoms are scored as 0 points, and symptoms are scored as 1 point for mild, 2 points for moderate, 3 points for severe and 4 points for very severe. The assessment module statistically analyzes the scores of the severity of each symptom collected from the patients and generates a trend chart.

[0021] This invention also provides a method for early warning management of postoperative care after radical prostatectomy, comprising the following steps:

[0022] S1: Nursing staff establish patient files through the basic information collection module and regularly enter the collected patient information, including general information, disease information, treatment information, pre- and post-operative symptoms, or post-operative quality of life information.

[0023] S2: The assessment module standardizes the preoperative and postoperative symptom data or postoperative quality of life data. The assessment module scores the symptoms of patients undergoing radical prostatectomy, or scores the quality of life based on the collected overall health status, functional status and changes in living status.

[0024] S3: The symptom network construction module calculates the correlation between symptoms based on symptom score data and constructs a symptom correlation matrix;

[0025] S4: The symptom network construction module uses the data analysis system to build a symptom network model with symptoms as nodes and the correlation between symptoms as lines.

[0026] S5: The system calculates the central coefficient index of each symptom node and identifies the core symptoms at each time point;

[0027] S6: Patients are risk-stratified based on core symptoms, symptom severity, decline in quality of life score, and symptom duration using the risk stratification module;

[0028] S7: The nursing early warning module generates nursing early warning information based on the risk stratification results produced by the risk stratification module;

[0029] The nursing early warning information includes the patient's basic information, current core symptoms, symptom severity, decline in quality of life, symptom duration, reasons for risk assessment, and standardized nursing treatment plan.

[0030] S8: The individualized care setting module can be used to develop individualized care programs based on the patient's stage and core symptom type.

[0031] S9: The follow-up management module generates early postoperative dynamic follow-up reports for patients, which nursing staff can use for clinical handover, nursing records, health education, and continuing care management.

[0032] In the above scheme, step S3 also includes the following steps:

[0033] S3-1: Screening and analyzing the indicator set;

[0034] S3-2: Calculate the Spearman correlation matrix or multi-correlation matrix for symptom data, and use the extended Bayesian information criterion, graphical minimum absolute shrinkage, and selection operator EBICglasso to estimate the regularized partial correlation network;

[0035] S3-3: Output the symmetric regularized partial correlation matrix.

[0036] In the above scheme, step S4 also includes the following steps:

[0037] S4-1: Set an association threshold and filter out symptom pairs with correlation coefficients lower than the association threshold, retaining only symptom pairs with statistical and clinical significance.

[0038] S4-2: Construct a node table and an edge table to generate an undirected graph model, and use node strength centrality as the main indicator for core symptom identification.

[0039] S4-3: Use the Fruchterman-Reingold force-directed algorithm to arrange nodes, and the thickness of the edges represents the strength of the association;

[0040] S4-4: The 95% confidence interval of the edge weights is calculated using a nonparametric bootstrap method, and the centrality stability coefficient is calculated using a case deletion bootstrap method; the core symptom ranking is output only when the centrality stability coefficient is not less than 0.50.

[0041] In the above scheme, step S5 also includes the following steps:

[0042] S5-1: Establish symptom networks for different time periods. According to the time points of the collection time, establish symptom networks for each time period separately.

[0043] S5-2: Calculate the strength centrality, betweenness centrality, and tight centrality of all symptom nodes in the network at each time point;

[0044] Among them, strength centrality is the sum of all associated edges of a node, reflecting the strength of direct linkage; betweenness centrality is the frequency of a node being on the shortest path of other symptoms, representing bridge symptoms; and compact centrality is the reciprocal of the average path distance from a node to all other symptoms.

[0045] S5-3: Identify the symptom ranked first in centrality as the core symptom. Intensity centrality is the most important indicator for identifying core symptoms. When the ranking results of different centrality indicators are inconsistent, the ranking result of intensity centrality is usually used as the main basis for judgment.

[0046] Based on the severity of symptoms and changes in quality of life, determine whether the core symptom requires triggering a nursing alert.

[0047] In the above scheme, step S6 further includes the following steps:

[0048] S6-1: Based on clinical experience, assign weights to core symptoms, symptom severity, decline in quality of life, and duration;

[0049] S6-2: Weighted summation yields the patient's overall risk score;

[0050] S6-3: Patients are classified into low, medium, or high risk levels based on their overall risk score;

[0051] S6-4: If any of the following occurs: severe core symptoms, significant decline in quality of life, or symptoms that do not improve over a long period of time, the current risk level will be raised by one level.

[0052] S6-5: The risk stratification module simultaneously sends patient name, risk level, stratification basis, and follow-up time node information to the nursing early warning module and the individualized nursing settings module.

[0053] In the above scheme, step S7 further includes the following steps:

[0054] S7-1: Match the corresponding nursing treatment plan based on the core symptoms;

[0055] S7-2: Match the corresponding prompting plan according to the risk level;

[0056] If the risk level is high, a Level 1 warning will be issued.

[0057] If the risk level is medium, a level-two early warning will be issued.

[0058] If the risk level is low, a Level 3 early warning will be issued.

[0059] In the above scheme, step S8 further includes the following steps:

[0060] S8-1: Constructing basic nursing care programs for each stage;

[0061] S8-2: Obtain the patient's current time stage, current core symptoms, and risk level;

[0062] S8-3: Generate phased nursing care recommendations;

[0063] First, determine the basic nursing care items based on the patient's current time stage; then, determine the intervention measures based on the current core symptoms; finally, supplement or adjust the intervention measures and basic nursing care items according to the risk level.

[0064] S8-4: Periodic nursing recommendations are sent to the attending physician and the responsible nurse through the hospital's office management system.

[0065] In summary, the beneficial effects of this invention are:

[0066] 1. It can achieve dynamic assessment of early symptoms after radical prostatectomy. By continuously monitoring key time points such as 1 day before surgery, 7 days after surgery, 1 month after surgery and 3 months after surgery, it can comprehensively reflect the changes in patients' early symptoms and quality of life after surgery.

[0067] 2. It can identify core symptoms at different time points through the core symptom identification module, which can help nurses determine the symptoms that need to be given the most priority at each stage, and avoid nursing intervention relying solely on experience.

[0068] 3. The risk stratification module can combine symptom severity, symptom network centrality indicators, and changes in quality of life to perform nursing risk stratification and early warning output, which helps to identify patients with heavy symptom burden or significantly reduced quality of life at an early stage.

[0069] 4. It can automatically generate nursing suggestions based on the core symptoms of patients at different stages through the individualized nursing settings module, enabling nursing staff to provide phased and individualized nursing guidance for different problems such as pain, urinary incontinence, anxiety, and sleep disorders;

[0070] 5. When generating individualized nursing recommendations, it can combine symptom management with quality of life assessment, and can promptly identify key symptoms that affect patients' quality of life, providing a basis for nursing staff to carry out targeted interventions, thereby promoting patients' postoperative functional recovery and psychological adaptation, and helping to improve patients' postoperative quality of life.

[0071] 6. It can save the patient's symptom scores, quality of life scores, core symptom identification results, risk level and nursing recommendations at various time points, forming a complete early postoperative follow-up file, which facilitates nursing handover, outpatient follow-up and continuing care management;

[0072] 7. It has good clinical application value and is suitable for urology wards, post-prostate cancer follow-up clinics, nursing clinics, internet nursing platforms and hospital continuing care systems. The operation process is clear, data collection is convenient, and it has strong clinical promotion value. Attached Figure Description

[0073] Figure 1 This is a schematic diagram of the symptom network model generated by the present invention. Detailed Implementation

[0074] The present invention will be further described below with reference to the embodiments and accompanying drawings:

[0075] A postoperative nursing early warning management system for radical prostatectomy includes:

[0076] The basic information collection module is used to input the patient's basic information, disease information, treatment information, pre- and post-operative symptoms, and post-operative quality of life.

[0077] Patient basic information includes age, marital status, education level, occupation, and medical payment method.

[0078] Disease information includes family history, previous transurethral resection of the prostate (TURP), clinical T stage, Gleason score, comorbid chronic diseases, and smoking and alcohol consumption. Treatment information includes surgical procedures and related information, including whether nerve preservation was performed, whether lymph node dissection was performed, operation time, and catheterization duration; surgical related information includes pathological T stage, resection margin status, postoperative prostate-specific antigen level, and postoperative urinary function.

[0079] Preoperative and postoperative symptoms include those of patients undergoing radical prostatectomy 1 day before surgery, 7 days after surgery, 1 month after surgery, and 3 months after surgery. These symptoms include common symptoms of patients undergoing radical prostatectomy such as pain, fatigue, restless sleep, anxiety, frequent urination, urgency, urinary incontinence, difficulty in sexual intercourse, decreased appetite, dry mouth, sweating, and constipation.

[0080] Postoperative quality of life includes the patient's overall health status, functional status, and symptom scores, and records the changes relative to the preoperative baseline.

[0081] The assessment module is used to perform completeness, logical consistency and outlier checks on the collected patient data 1 day before surgery, 7 days after surgery, 1 month after surgery or 3 months after surgery, and calculate symptom severity score and quality of life score based on standardized symptom scale and quality of life scale, and generate a longitudinal trend chart of individual patient changes.

[0082] When scoring in the scoring module, each symptom is divided into 5 levels according to its severity. The absence of symptoms is scored as 0 points, and the presence of symptoms is scored as 1 point for mild, 2 points for moderate, 3 points for severe and 4 points for very severe.

[0083] Postoperative quality of life was assessed using the European Organisation for Research and Treatment of Cancer (EORTC) Quality of Life Core Scale (EORTC QLQ-C30), and linearly converted to a score of 0–100 according to the scale’s scoring rules. The assessment module also calculated the absolute and percentage changes of each indicator relative to the preoperative baseline.

[0084] The symptom network construction module is used to construct symptom network models at different time points based on the patient's symptom score data at various time points, using each symptom as a network node and the correlation between symptoms as network connections.

[0085] The system can use correlation analysis methods to calculate the strength of association between symptoms and form a symptom correlation matrix. The stronger the correlation between symptoms, the higher the weight of the network connections. This module allows for a visual display of the interrelationships between symptoms at different postoperative stages, such as... Figure 1 As shown.

[0086] The core symptom identification module is used to construct a regularized symptom network based on group symptom data at the same follow-up time point, calculate the strength centrality and stability index of symptom nodes, and form a core symptom reference model for each stage.

[0087] Calculate the connection strength between each symptom node and other symptom nodes in turn;

[0088] The risk stratification module is used to stratify patients' nursing risks by comprehensively considering the severity of their symptoms, the type of core symptoms, the degree of decline in their quality of life scores, and the duration of their symptoms.

[0089] This includes three levels: low risk, medium risk, and high risk.

[0090] Low risk: Mild symptoms, minimal decline in quality of life, and no significant worsening of core symptoms;

[0091] Medium risk: Moderate symptoms, decreased quality of life, or high core symptom score;

[0092] High risk: Severe symptoms exist, quality of life is significantly reduced, core symptoms persist or worsen, requiring close attention from caregivers.

[0093] The nursing early warning module is used to automatically generate nursing early warning information based on risk stratification results and core symptom types;

[0094] When a patient is identified as medium-risk or high-risk, the system automatically prompts nursing staff to conduct a focused assessment and outputs corresponding nursing tips based on the patient's main problems.

[0095] For example, when pain is the core symptom, the system prompts for enhanced pain assessment, observation of analgesic effects, and guidance on proper activity and rest for the patient.

[0096] When urinary incontinence is the core symptom, the system suggests strengthening pelvic floor muscle training guidance, voiding diary recording, and skin care;

[0097] When anxiety is the core symptom, the system suggests providing psychological support, managing disease recovery expectations, and recommending necessary specialist referrals.

[0098] When sleep disturbance is the core symptom, the system prompts for assessment of related factors such as pain, nocturia, and anxiety, and provides guidance on sleep care.

[0099] The individualized care settings module is used to automatically generate phased care recommendations based on the patient's current time, core symptoms, and risk level.

[0100] Preoperative stage: Focus on preoperative assessment of urinary symptoms, disease awareness assessment, psychological support, and postoperative recovery expectation education.

[0101] The 7-day postoperative period: Focus on pain, fatigue, sleep disturbances, catheter-related discomfort, and early mobilization guidance.

[0102] One month post-surgery: Focus on urinary incontinence, anxiety, adherence to pelvic floor muscle training, and recovery of quality of life.

[0103] Three months post-surgery: Focus on persistent urinary incontinence, anxiety, difficulty with sexual activity, and recovery of social function.

[0104] The system can generate nursing advice reports based on the above information, which can be used by nursing staff for health education, follow-up communication, and continuing care management.

[0105] The follow-up management module is used to establish a continuous follow-up record for patients in the early postoperative period.

[0106] The follow-up management module automatically generates follow-up reminders at milestones such as 7 days, 1 month, and 3 months post-surgery, and records symptom scores, quality of life scores, core symptoms, risk levels, and nursing recommendations for each follow-up visit.

[0107] This module allows nursing staff to continuously observe patients' early postoperative recovery, enabling a shift from single-assessment to dynamic management.

[0108] This invention also provides a method for early warning management of postoperative care after radical prostatectomy, comprising the following steps:

[0109] S1: Nursing staff establish patient files through the basic information collection module and regularly enter the collected patient information, including general information, disease information, treatment information, pre- and post-operative symptoms, or post-operative quality of life information.

[0110] S2: The assessment module standardizes the preoperative and postoperative symptom data or postoperative quality of life data to form an individual patient symptom change table and a group symptom database. The assessment module then scores the symptoms of patients undergoing radical prostatectomy, or scores the quality of life based on the collected overall health status, functional status and changes in living status.

[0111] S3: The symptom network construction module calculates the correlation between symptoms based on symptom score data and constructs a symptom correlation matrix;

[0112] S3-1: Screening and analyzing the indicator set;

[0113] S3-2: Calculate the Spearman correlation matrix or multi-correlation matrix for symptom data, and use the extended Bayesian information criterion, graphical minimum absolute shrinkage, and selection operator EBICglasso to estimate the regularized partial correlation network;

[0114] S3-3: Output the symmetric regularized partial correlation matrix.

[0115] Suppose there are k symptom indicators, and the matrix size is k×k; where the first row and first column of the matrix are symptom names, and the values ​​of the remaining cells are the correlation coefficients of the symptoms in the corresponding rows and columns;

[0116] S4: The symptom network construction module uses the data analysis system to build a symptom network model with symptoms as nodes and the correlation between symptoms as lines.

[0117] S4-1: Set an association threshold and filter out symptom pairs with correlation coefficients lower than the association threshold, retaining only symptom pairs with statistical and clinical significance.

[0118] S4-2: Construct a node table and an edge table to generate an undirected graph model, and use node strength centrality as the main indicator for core symptom identification.

[0119] S4-3: Use the Fruchterman-Reingold force-directed algorithm to arrange nodes, and the thickness of the edges represents the strength of the association;

[0120] S4-4: The 95% confidence interval for edge weights is calculated using a nonparametric bootstrap method, and the centrality stability coefficient is calculated using a case deletion bootstrap method; the core symptom ranking is output only when the centrality stability coefficient is not less than 0.50.

[0121] S5: The system calculates the central coefficient index of each symptom node and identifies the core symptoms at each time point.

[0122] S5-1: Establish symptom networks for different time periods. According to the time points of the collection time, such as 1 day before surgery, 7 days after surgery, 1 month after surgery, and 3 months after surgery, establish symptom networks for each time period separately.

[0123] S5-2: Calculate the strength centrality, betweenness centrality, and tight centrality of all symptom nodes in the network at each time point; this can be done using Python.

[0124] Among them, strength centrality represents the sum of the weights of all adjacent edges of a node, reflecting the overall association load and total influence of the node; betweenness centrality represents the "hub node" that controls the flow of information in the network, and many shortest paths between two points must pass through it. Removing it will break the network path; compact centrality means that the closer a node is to all points in the network, the faster the information is transmitted, and it is at the center of the network.

[0125] S5-3: Mark the top 3 symptoms in terms of intensity centrality and those with median centrality higher than the mean as the core symptoms at this time point;

[0126] Based on the severity of symptoms and changes in quality of life, determine whether the core symptom requires triggering a nursing alert;

[0127] For example, based on the characteristics of symptom changes at different stages after radical prostatectomy, it can be identified that the preoperative stage focuses on urinary symptoms such as urinary frequency and urgency, the postoperative 7 days focus on acute recovery symptoms such as pain and fatigue, and the postoperative 1 month to 3 months focus on symptoms related to functional recovery and psychological adaptation such as anxiety and urinary incontinence.

[0128] S6: Patients are risk-stratified based on core symptoms, symptom severity, decline in quality of life score, and symptom duration using the risk stratification module;

[0129] S6-1: Read the standardized severity score of symptoms, the difference in quality of life decline, and the duration of symptoms, and uniformly perform dimensionless standardization.

[0130] S6-1: Based on clinical experience, assign weights to core symptoms, symptom severity, decline in quality of life, and duration;

[0131] S6-2: Weighted summation yields the patient's overall risk score;

[0132] S6-3: Patients are classified into low, medium, or high risk levels based on their overall risk score;

[0133] Among them, low risk: mild symptoms, no significant decline in quality of life, and no obvious core symptoms that continue to worsen;

[0134] Medium risk: Moderate symptoms, decreased quality of life, or high core symptom score;

[0135] High risk: Severe symptoms exist, quality of life is significantly reduced, core symptoms persist or worsen, requiring close attention from caregivers.

[0136] S6-4: If any of the following occurs: severe core symptoms, significant decline in quality of life, or symptoms that do not improve over a long period of time, the current risk level will be raised by one level.

[0137] S6-5: The risk stratification module simultaneously sends the patient's name, risk level (low, medium, high), stratification criteria (core symptoms, symptom severity, decline in quality of life, duration of symptoms), and follow-up time points to the nursing early warning module and the individualized nursing settings module.

[0138] S7: The nursing early warning module generates nursing early warning information based on the risk stratification results produced by the risk stratification module;

[0139] The nursing early warning information includes the patient's basic information, current core symptoms, symptom severity, decline in quality of life, symptom duration, reasons for risk assessment, and standardized nursing treatment plan.

[0140] S7-1: Match the corresponding nursing treatment plan based on the core symptoms;

[0141] When pain is the core symptom, the nursing early warning module will prompt patients to strengthen pain assessment, observe the analgesic effect, and guide patients to engage in proper activities and rest.

[0142] When urinary incontinence is the core symptom, the nursing warning module will suggest strengthening pelvic floor muscle training guidance, recording a voiding diary, and skin care;

[0143] When anxiety is the core symptom, the nursing early warning module will suggest providing psychological support, managing disease recovery expectations, and recommending necessary specialist referrals.

[0144] When sleep disturbance is the core symptom, the nursing early warning module prompts the assessment of related factors such as pain, nocturia, and anxiety, and provides guidance on sleep care.

[0145] S7-2: Match the corresponding prompting plan according to the risk level;

[0146] If it is a high-risk situation, the nursing warning information will be sent to the nurse station and the personal systems of the responsible nurse and nursing team leader of the corresponding patient through the hospital office management system, and will be displayed through the red pop-up window on the large screen of the nurse station;

[0147] If the risk level is medium, the nursing alert information will be sent to the to-do list of the corresponding patient's responsible nurse through the hospital's office management system;

[0148] If the risk level is low, routine follow-up reminders will be sent to the patient's responsible nurse through the hospital's office management system.

[0149] Personalized care settings module: The system develops individualized care programs based on the patient's stage and core symptom type.

[0150] S8-1: Constructing basic nursing care programs for each stage;

[0151] In the preoperative stage, the focus is on preoperative urinary symptom assessment, disease awareness assessment, psychological support, and postoperative recovery expectation education.

[0152] The 7-day postoperative period focuses on pain, fatigue, sleep disturbances, catheter-related discomfort, and early mobilization guidance.

[0153] During the first month after surgery, the focus is on urinary incontinence, anxiety, compliance with pelvic floor muscle training, and the recovery of quality of life.

[0154] During the three-month postoperative period, the focus is on persistent urinary incontinence, anxiety, difficulty with sexual intercourse, and the recovery of social function.

[0155] S8-2: Obtain the patient's current time stage, current core symptoms, and risk level;

[0156] S8-3: Generate phased nursing care recommendations;

[0157] First, determine the basic nursing care items based on the patient's current time stage; then, determine the intervention measures based on the current core symptoms; finally, supplement or adjust the intervention measures and basic nursing care items according to the risk level.

[0158] S8-4: Periodic nursing recommendations are sent to the attending physician and the responsible nurse through the hospital's office management system;

[0159] If the patient returns for a follow-up visit, the stage, core symptoms, and risk level will be updated, and the individualized nursing care settings module will automatically invalidate the old plan and generate new nursing care recommendations for the next stage.

[0160] S9: The follow-up management module generates early postoperative dynamic follow-up reports for patients, which nursing staff can use for clinical handover, nursing records, health education and continuing care management.

[0161] The follow-up management simulation automatically calculates each follow-up time point based on the surgery date, generates pending follow-up work orders in advance, and pushes them to the responsible nurse through the hospital's office management system; overdue follow-ups are marked with an early warning, which is simultaneously linked to the nursing early warning module;

[0162] Follow-up time points include preoperative, 7 days postoperatively, 1 month, 3 months, 6 months, and 12 months; each time point is bound to the following mandatory data collection items: symptom scale, quality of life score, core symptoms, risk stratification, and nursing intervention record;

[0163] During follow-up, the system automatically acquires and archives data from the entire process, such as standardized symptom scores, core symptoms of the symptom network, risk levels, individualized nursing recommendations, and nursing intervention records.

Claims

1. A postoperative nursing early warning management system for radical prostatectomy, characterized in that, include: The basic information collection module is used to input the patient's basic information, disease information, treatment information, pre- and post-operative symptoms, and post-operative quality of life. The assessment module is used to verify the completeness, logical consistency, and outliers of the collected data, and to calculate the symptom severity score and quality of life score based on the standardized symptom scale and quality of life scale, generating a longitudinal trend chart of individual patients. The core symptom identification module is used to construct a regularized symptom network based on group symptom data at the same follow-up time point, calculate the strength centrality and stability index of symptom nodes, and form a core symptom reference model for each stage. The risk stratification module is used to stratify patients' nursing risks and simultaneously send the nursing risk stratification information to the nursing early warning module and the individualized nursing settings module. The nursing early warning module is used to generate nursing early warning information based on risk stratification results and core symptoms; The individualized nursing settings module is used to generate nursing suggestions and send these suggestions to the attending physician and the responsible nurse through the hospital office management system. The follow-up management module is used to establish a continuous follow-up record for patients in the early postoperative period.

2. The postoperative nursing early warning management system for radical prostatectomy as described in claim 1, characterized in that: The patient's basic information includes age, marital status, education level, occupation, and medical payment method. Disease information includes family history, previous transurethral resection of the prostate (TURP), clinical T stage, Gleason score, comorbid chronic diseases, and smoking and alcohol consumption. Treatment information includes surgical procedures and related information, including whether nerve preservation was performed, whether lymph node dissection was performed, operation time, and catheterization duration. Surgical-related information includes pathological T stage, surgical margin status, postoperative prostate-specific antigen (PSA) level, and postoperative urinary function. A patient personal file is established through the basic information collection module, providing foundational data for subsequent symptom assessment, risk classification, and follow-up management. Preoperative and postoperative symptoms include those of patients undergoing radical prostatectomy 1 day before surgery, 7 days after surgery, 1 month after surgery, and 3 months after surgery. These symptoms include common symptoms of patients undergoing radical prostatectomy such as pain, fatigue, restless sleep, anxiety, frequent urination, urgency, urinary incontinence, difficulty in sexual intercourse, decreased appetite, dry mouth, sweating, and constipation. Postoperative quality of life includes scores on the patient's overall health status, functional status, and symptom dimensions, and records the changes relative to the preoperative baseline.

3. The postoperative nursing early warning management system for radical prostatectomy according to claim 2, characterized in that: When scoring in the scoring module, each symptom is divided into 5 levels according to its severity. The absence of symptoms is scored as 0 points, and the presence of symptoms is scored as 1 point for mild, 2 points for moderate, 3 points for severe, and 4 points for very severe. The assessment module statistically analyzes the severity scores of each patient's symptoms and generates a trend chart.

4. A method for early warning management of postoperative care after radical prostatectomy for prostate cancer, characterized in that, Includes the following steps: S1: Nursing staff establish patient files through the basic information collection module and regularly enter the collected patient information, including general information, disease information, treatment information, pre- and post-operative symptoms, or post-operative quality of life information. S2: The assessment module standardizes the preoperative and postoperative symptom data or postoperative quality of life data. The assessment module scores the symptoms of patients undergoing radical prostatectomy, or scores the quality of life based on the collected overall health status, functional status and changes in living status. S3: The symptom network construction module calculates the correlation between symptoms based on symptom score data and constructs a symptom correlation matrix; S4: The symptom network construction module uses the data analysis system to build a symptom network model with symptoms as nodes and the correlation between symptoms as lines. S5: The system calculates the central coefficient index of each symptom node and identifies the core symptoms at each time point; S6: Patients are risk-stratified based on core symptoms, symptom severity, decline in quality of life score, and symptom duration using the risk stratification module; S7: The nursing early warning module generates nursing early warning information based on the risk stratification results produced by the risk stratification module; The nursing early warning information includes the patient's basic information, current core symptoms, symptom severity, decline in quality of life, symptom duration, reasons for risk assessment, and standardized nursing treatment plan. S8: The individualized care setting module can be used to develop individualized care programs based on the patient's stage and core symptom type. S9: The follow-up management module generates early postoperative dynamic follow-up reports for patients, which nursing staff can use for clinical handover, nursing records, health education, and continuing care management.

5. The method for early warning management of postoperative care after radical prostatectomy for prostate cancer according to claim 4, characterized in that: Step S3 also includes the following steps: S3-1: Screening and analyzing the indicator set; S3-2: Calculate the Spearman correlation matrix or multi-correlation matrix for symptom data, and use the extended Bayesian information criterion, graphical minimum absolute shrinkage, and selection operator EBICglasso to estimate the regularized partial correlation network; S3-3: Output the symmetric regularized partial correlation matrix.

6. The postoperative nursing early warning management method for radical prostatectomy according to claim 4, characterized in that: Step S4 also includes the following steps: S4-1: Set an association threshold and filter out symptom pairs with correlation coefficients lower than the association threshold, retaining only symptom pairs with statistical and clinical significance. S4-2: Construct a node table and an edge table to generate an undirected graph model, and use node strength centrality as the main indicator for core symptom identification. S4-3: Use the Fruchterman-Reingold force-directed algorithm to arrange nodes, and the thickness of the edges represents the strength of the association; S4-4: The 95% confidence interval of the edge weights is calculated using a nonparametric bootstrap method, and the centrality stability coefficient is calculated using a case deletion bootstrap method; the core symptom ranking is output only when the centrality stability coefficient is not less than 0.

50.

7. The postoperative nursing early warning management method for radical prostatectomy according to claim 4, characterized in that: Step S5 also includes the following steps: S5-1: Establish symptom networks for different time periods. According to the time points of the collection time, establish symptom networks for each time period separately. S5-2: Calculate the strength centrality, betweenness centrality, and tight centrality of all symptom nodes in the network at each time point; Among them, strength centrality is the sum of all associated edges of a node, reflecting the strength of direct linkage; betweenness centrality is the frequency of a node being on the shortest path of other symptoms, representing bridge symptoms; and compact centrality is the reciprocal of the average path distance from a node to all other symptoms. S5-3: Identify the symptom ranked first in centrality index as the core symptom. Intensity centrality is the most important indicator for identifying core symptoms. When the ranking results of different centrality indicators are inconsistent, the ranking result of intensity centrality is usually used as the main basis for judgment. Based on the severity of symptoms and changes in quality of life, determine whether the core symptom requires triggering a nursing alert.

8. The method for early warning management of postoperative care after radical prostatectomy for prostate cancer according to claim 4, characterized in that: Step S6 also includes the following steps: S6-1: Based on clinical experience, assign weights to core symptoms, symptom severity, decline in quality of life, and duration; S6-2: Weighted summation yields the patient's overall risk score; S6-3: Patients are classified into low, medium, or high risk levels based on their overall risk score; S6-4: If any of the following occurs: severe core symptoms, significant decline in quality of life, or symptoms that do not improve over a long period of time, the current risk level will be raised by one level. S6-5: The risk stratification module simultaneously sends patient name, risk level, stratification basis, and follow-up time node information to the nursing early warning module and the individualized nursing settings module.

9. A method for early warning management of postoperative care after radical prostatectomy for prostate cancer according to claim 4, characterized in that: Step S7 also includes the following steps: S7-1: Match the corresponding nursing care plan based on the core symptoms; S7-2: Match the corresponding prompting plan according to the risk level; If the risk level is high, a Level 1 warning will be issued. If the risk level is medium, a level-two early warning will be issued. If the risk level is low, a Level 3 early warning will be issued.

10. A method for early warning management of postoperative care after radical prostatectomy for prostate cancer according to claim 4, characterized in that: Step S8 also includes the following steps: S8-1: Constructing basic nursing care programs for each stage; S8-2: Obtain the patient's current time stage, current core symptoms, and risk level; S8-3: Generate phased nursing care recommendations; First, determine the basic nursing care items based on the patient's current time stage; then, determine the intervention measures based on the current core symptoms; finally, supplement or adjust the intervention measures and basic nursing care items according to the risk level. S8-4: Periodic nursing recommendations are sent to the attending physician and the responsible nurse through the hospital's office management system.

Images