Home nursing method and system after gynecological malignant tumor operation

Abstract

The embodiment of the invention discloses a gynecological malignant tumor postoperative home nursing and system. The method comprises the following steps: determining patient information corresponding to a patient to be nursed, wherein the patient information comprises physiological data and malignant tumor postoperative data; determining a real-time health state of the to-be-nursed patient based on the physiological data and the malignant tumor postoperative data; inputting the real-time health state into a preset nursing method atlas database, and determining a home nursing method corresponding to the patient to be nursed based on the preset nursing method atlas database; and obtaining personalized data of the to-be-nursed patient, and correcting the home nursing method based on the personalized data to obtain a target home nursing method corresponding to the to-be-nursed patient. According to the application, the scientificity, safety and patient compliance of home care can be remarkably improved, and rehabilitation support which has higher clinical value and meets individual requirements is provided for malignant tumor postoperative patients.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of home care management, in particular to a home care method and system for gynecological malignant tumor postoperative. BACKGROUND

[0002] At present, the treatment of gynecological malignant tumor mainly adopts a comprehensive treatment mode taking surgery as the main mode. Surgery is the preferred treatment method for most early gynecological malignant tumor patients. For some advanced patients, surgery can also be used as a palliative treatment method such as tumor reduction, so as to reduce tumor load and relieve symptoms. Gynecological malignant tumor surgery involves multiple important organs and systems, and postoperative patients are weak and need a long recovery period.

[0003] However, the recovery period of gynecological malignant tumor postoperative patients is as long as several months, during which complications such as wound healing, lymph cysts and deep vein thrombosis need to be continuously monitored, and functional rehabilitation needs to be promoted through nutritional support, pain management and psychological intervention. However, the hospitalization period of patients is short, and home care is needed after discharge, therefore, a home care method for gynecological malignant tumor postoperative is urgently needed. SUMMARY

[0004] To solve the above technical problems, the embodiments of the present application provide a home care method and system for gynecological malignant tumor postoperative.

[0005] According to an aspect of the embodiments of the present application, a home care method for gynecological malignant tumor postoperative is provided, comprising: determining patient information corresponding to a patient to be cared for, the patient information comprising physiological data and postoperative data of malignant tumor; determining a real-time health status of the patient to be cared for based on the physiological data and the postoperative data of malignant tumor; inputting the real-time health status into a preset nursing method atlas library to determine a home care method corresponding to the patient to be cared for based on the preset nursing method atlas library; obtaining personalized data of the patient to be cared for, and correcting the home care method based on the personalized data to obtain a target home care method corresponding to the patient to be cared for.

[0006] According to an aspect of the embodiments of the present application, the method further comprises: determining a long-term complication of the patient to be cared for based on the real-time health status; if the long-term complication meets the home care condition, determining a complication type corresponding to the long-term complication; determining a home care method based on the complication type, and generating a teaching video corresponding to the home care method.

[0007] According to one aspect of the embodiments of this application, the method further includes: if the complication type corresponding to the long-term complication is a lymphatic system complication, then obtaining a first home management strategy corresponding to the lymphatic system complication; determining a home care method for the patient to be cared for based on the first home management strategy, the home care method including at least one of pressure therapy, manual lymphatic drainage, skin care, and functional exercises; if the home care method includes manual lymphatic drainage, then generating an instructional video corresponding to the manual lymphatic drainage.

[0008] According to one aspect of the embodiments of this application, the method further includes: if the complication type corresponding to the long-term complication is a urinary system complication, then obtaining a second home management strategy corresponding to the urinary system complication; determining a home care method for the patient to be cared for based on the second home management strategy, the home care method including at least one of bladder training, pelvic floor muscle exercises, and hot compress massage; and generating corresponding instructional videos based on the bladder training, the pelvic floor muscle exercises, and the hot compress massage.

[0009] According to one aspect of the embodiments of this application, before inputting the real-time health status into a preset nursing method atlas library to determine the home care method corresponding to the patient to be cared for based on the preset nursing method atlas library, the method further includes: acquiring a basic dataset, the basic dataset including multiple postoperative physiological data of gynecological malignant tumors and multiple corresponding home care methods after gynecological malignant tumor surgery; determining different types of distant complications based on the multiple postoperative physiological data of gynecological malignant tumors, and determining the physiological data and home care methods corresponding to each type of distant complication at each stage; using the different types of distant complications, the physiological data corresponding to each stage, and the home care methods as point structures, and constructing a nursing atlas for postoperative gynecological malignant tumors based on the point structures, so as to determine the preset nursing method atlas library based on the nursing atlas.

[0010] According to one aspect of the embodiments of this application, the method further includes: obtaining historical disease diagnosis records and historical nursing assessment records corresponding to the patient to be cared for, wherein the historical disease diagnosis records include the patient's symptom set time sequence, gynecological diseases, progress stages, and nursing methods within the feedback cycle, and the historical nursing effect assessment records include the stage effect assessment level of each feedback cycle corresponding to the nursing method and the average effect assessment level corresponding to the nursing method based on the stage effect assessment level of each feedback cycle corresponding to the nursing method; if the correlation between the historical disease diagnosis records of the patient to be cared for and the nursing atlas is greater than a preset correlation threshold, then based on the historical nursing effect assessment records of the patient to be cared for, adding stage effect assessment levels and average effect assessment levels to the edge structure between the distant complication and the home care method in the nursing atlas.

[0011] According to one aspect of the embodiments of this application, the method further includes: determining a correlation variable corresponding to the nursing effect from the personalized data, and determining a mutual information value between the correlation variable and the nursing effect; determining a mutual information matrix based on the correlation variable, the nursing effect and the mutual information value; and modifying the home care method based on the mutual information matrix.

[0012] According to one aspect of the embodiments of this application, the method for correcting the home care based on the mutual information matrix includes: if the mutual information value is greater than a preset mutual information threshold, determining a high mutual information variable in the mutual information matrix, wherein the high mutual information variable is a mutual information value greater than the preset mutual information threshold; obtaining a care strategy corresponding to the high mutual information variable, and correcting the home care method based on the care strategy and the high mutual information variable.

[0013] According to one aspect of the embodiments of this application, the personalized data includes historical nursing records. The step of acquiring the personalized data of the patient to be cared for and modifying the home care method based on the personalized data includes: determining a historical nursing vector corresponding to the historical nursing record, the historical nursing vector including the patient's historical physiological data and historical nursing methods; determining the association between the home care method and the postoperative data of the malignant tumor based on the preset nursing method atlas library; modifying the association based on the historical nursing vector, and modifying the home care method based on the modified association.

[0014] According to one aspect of the embodiments of this application, a home care system for postoperative gynecological malignant tumors is provided. The system includes a processor, an input device, an output device, and a memory, which are interconnected. The memory is used to store a computer program, which includes program instructions. The processor is configured to invoke the program instructions to execute the home care method for postoperative gynecological malignant tumors as described above.

[0015] In the technical solution provided in the embodiments of this application, the real-time health status of patients to be cared for is accurately assessed by integrating physiological and postoperative data, and an initial home care plan is generated based on a preset nursing atlas library. Then, the nursing method is dynamically corrected by combining personalized data, and finally, the precise adaptation from the commonality of the group to the specificity of the individual is achieved, which significantly improves the scientificity, safety and patient compliance of home care, and provides more clinically valuable and individualized rehabilitation support for patients after malignant tumor surgery.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings: Figure 1 This is a flowchart illustrating a home care method after gynecological malignant tumor surgery, as shown in an exemplary embodiment of this application.

[0018] Figure 2 This is a flowchart illustrating a home care method after gynecological malignant tumor surgery, as shown in another exemplary embodiment of this application.

[0019] Figure 3 This is a block diagram illustrating a home care system for postoperative care of gynecological malignant tumors, as shown in an exemplary embodiment of this application.

[0020] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation

[0021] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0022] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0023] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0024] In this application, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0025] First, it's important to note that gynecological malignancies (such as ovarian cancer, cervical cancer, and endometrial cancer) pose a significant threat to women's health globally, with their incidence rate increasing year by year. According to the World Health Organization, cervical cancer remains the leading cause of cancer death among women in developing countries. Currently, multidisciplinary comprehensive treatment centered on surgery (surgery combined with chemotherapy, radiotherapy, or targeted therapy) significantly prolongs patient survival. However, surgery is highly invasive and prone to complications (such as lymphedema, intestinal obstruction, and urinary system damage), resulting in a postoperative recovery period of 6-12 months, with over 70% of the recovery process requiring completion at home.

[0026] Traditional home care models (such as telephone follow-ups and paper manuals) are no longer sufficient to meet the needs due to their lack of real-time, interactive, and personalized features. Although digital technologies (such as mobile medical apps and wearable devices) are beginning to be applied to postoperative monitoring, most apps only provide medication reminders or symptom self-assessments and cannot generate individualized care plans; basic indicators such as heart rate and activity levels monitored by wearable devices are out of touch with the needs of specialized care (such as stoma leakage and lymphedema volume); and existing AI-assisted systems are mostly based on historical data to predict risks and lack the ability to dynamically respond to the patient's real-time status.

[0027] To address the aforementioned issues, embodiments of this application propose a home care method, a home care system, a computer storage medium, and a computer program product following surgery for gynecological malignant tumors.

[0028] Please see Figure 1 In one exemplary embodiment provided in this application, the process of the above-mentioned home care method after gynecological malignant tumor surgery includes at least steps S110 to S140, which are described in detail below: Step S110: Determine the patient information corresponding to the patient to be cared for. The patient information includes physiological data and postoperative data of malignant tumors.

[0029] For example, in the scenario of home care after gynecological malignant tumor surgery, the accurate integration of patient information is the foundation for constructing personalized care plans. Its core lies in dynamically capturing the patient's physiological state and postoperative recovery progress through a multimodal data acquisition system, thereby providing structured input for an intelligent decision-making engine. Specifically, patient information needs to cover two major dimensions: basic physiological data and postoperative specialized data related to malignant tumors. The former includes static physiological parameters (such as age, height, weight, BMI, history of underlying diseases, and allergies) and dynamic vital signs (heart rate, blood oxygen saturation, blood pressure, respiratory rate, and body temperature monitored in real time through wearable devices), while also integrating laboratory test results (such as complete blood count, liver and kidney function, and tumor marker levels) and imaging data to comprehensively assess the patient's overall health status. The latter focuses on the risk of surgery-related complications and key recovery indicators, including the type of surgery (such as comprehensive staging surgery for ovarian cancer, radical hysterectomy for cervical cancer, and total hysterectomy for endometrial cancer), lymph node dissection, etc. The scope of the scan (e.g., pelvic and para-aortic lymph node dissection), postoperative pathological staging, chemotherapy / radiotherapy regimen (drug type, dosage, and cycle), and targeted therapy records (e.g., inhibitor use) are required. At the same time, postoperative complication data need to be dynamically tracked, including but not limited to lymphedema (limb volume changes measured by bioelectrical impedance analysis or three-dimensional optical scanning), stoma-related issues (stoma bleeding frequency, skin-mucosal separation area, and excrement characteristics), urinary system damage (frequency of urinary incontinence, residual urine volume in the bladder), deep vein thrombosis (lower extremity venous ultrasound results), and psychological state. To ensure the real-time nature and accuracy of the data, the system adopts an edge computing architecture. Preliminary data cleaning (such as removing abnormal heart rate values ​​caused by motion artifacts) and feature extraction (such as identifying atrial fibrillation waveforms from electrocardiograms) are performed on local devices. The structured data is then uploaded to the cloud-based nursing platform via an encrypted transmission protocol. Simultaneously, to address the challenge of integrating multi-source heterogeneous data, a standardized unified data model can be constructed. This model maps text-based pathology reports, image-based imaging data, and time-series vital sign signals to standardized fields. Natural language processing technology is then used to extract key information from unstructured electronic medical records (such as the number of lymph node dissections in surgical records and the reasons for drug adjustments in chemotherapy records). Finally, the integrated patient information will be stored in a time-series database, supporting the tracing of patient recovery along a timeline. This data will provide support for subsequent complication prediction models (such as LSTM-based lymphedema risk warning) and nursing intervention recommendation systems (such as dynamically adjusting nursing frequency based on stoma leakage risk), thereby upgrading the nursing model from "passive monitoring" to "active intervention."

[0030] Step S120: Determine the real-time health status of the patient to be cared for based on physiological data and postoperative data of malignant tumors.

[0031] For example, in the scenario of home care after malignant tumor surgery, a real-time health status assessment system based on physiological data and postoperative specialist data needs to be constructed. This requires the synergistic effect of multimodal data fusion, dynamic risk modeling, and clinical rule engines to achieve a closed-loop derivation from raw data to interpretable health status. Specifically, it is necessary to integrate two major categories of heterogeneous data streams: the first is the basic physiological data stream, which includes continuous physiological signals (heart rate variability, blood oxygen fluctuation, nocturnal apnea index) collected every 5 minutes through wearable devices (such as smart bracelets, patch-type ECG patches), discrete indicators (systolic blood pressure / diastolic blood pressure, fasting blood glucose) measured daily through home medical devices (such as electronic blood pressure monitors, blood glucose meters), and subjective symptom scores (pain level, fatigue, frequency of nausea and vomiting) filled out weekly through mobile scales (such as quality of life scales); the second is postoperative data. The specialty data stream encompasses key surgical information synchronized from the Hospital Information System (HIS) (such as lymph node dissection extent, intraoperative blood loss, and transfusion status), radiotherapy planning parameters obtained from the Radiotherapy Information System (RTIS) (such as target volume, single dose, and cumulative dose), chemotherapy execution records retrieved from the chemotherapy management system (such as drug name, actual dosage, and reason for delay), and structured data automatically extracted from postoperative images (such as monthly follow-up pelvic images) using auxiliary analysis tools (such as the maximum diameter of residual lesions and the short diameter of retroperitoneal lymph nodes). To address the time alignment issue of multi-source data, the system employs a time-series alignment algorithm. Using the minimum acquisition interval of physiological data (5 minutes) as a benchmark, cubic spline interpolation is used to reconstruct discrete specialty data (such as daily chemotherapy toxicity scores) in a time-series manner. Simultaneously, Kalman filtering is used to dynamically correct motion artifacts in wearable device signals, ensuring that all data are comparable in the time dimension. Subsequently, the system enters the feature engineering phase: on the one hand, it extracts time-domain features (such as 24-hour average heart rate and minimum nocturnal blood oxygen saturation), frequency-domain features (such as the low-frequency / high-frequency ratio in the heart rate power spectrum), and nonlinear features (such as sample entropy and detrended fluctuation analysis) from physiological data to capture implicit health information such as autonomic nervous system function and sleep quality; on the other hand, it calculates key risk indicators (such as absolute neutrophil count <1.5×10⁻⁶ after chemotherapy) from postoperative data. 9 The percentage of days with / L, and the area of ​​rectal mucosal congestion >2cm after radiotherapy. 2 The duration of the event was measured, and high-risk events (such as "peristaltic skin grade III effusion" and "lower extremity deep vein thrombosis positive on ultrasound") were identified from unstructured nursing records using natural language processing.

[0032] Step S130: Input the real-time health status into the preset nursing method atlas library, so as to determine the corresponding home care method for the patient to be cared for based on the preset nursing method atlas library.

[0033] For example, in the scenario of home care after malignant tumor surgery, intelligently matching real-time health status with a pre-set nursing method atlas library to generate personalized nursing plans requires the semantic reasoning capabilities of knowledge graphs, the flexible adaptation mechanism of dynamic rule engines, and the clinically friendly design of multimodal interactive interfaces to achieve a paradigm shift from "standardized nursing pathways" to "patient-centered dynamic interventions." Specifically, in the home care method recommendation system, a multimodal real-time health status input module needs to be constructed first. This module integrates physiological data (such as heart rate, blood pressure, and blood oxygen saturation) collected by patients through wearable devices (such as smart bracelets and blood pressure monitors), environmental sensor data (such as temperature and humidity), and symptom information actively reported by patients (such as pain level and dietary status). A structured input vector is generated through data cleaning and standardization processing (such as missing value imputation and unit unification). Subsequently, the vector is input into a pre-defined nursing method atlas library. This atlas, built on ontology, contains semantic relationships between nursing methods (such as "timed turning" and "low-salt diet") and health status features (such as "pressure ulcer risk" and "hypertension"), and stores the applicable conditions, contraindications, and priority weights of nursing methods using knowledge graph technology. The system matches real-time health status with nursing rules in the atlas using the atlas reasoning engine. For example, when a patient's heart rate is consistently above a threshold and the ambient temperature is too high, the recommendation of the "physical cooling" nursing method is triggered. To improve the accuracy of the recommendations, the system combines the patient's historical nursing records (such as past allergies and nursing compliance) for contextual filtering and uses a collaborative filtering algorithm to reference nursing effect data from similar patient groups (such as patient A's blood pressure decreasing by 10% after using a certain method). Ultimately, the system outputs a personalized nursing plan that includes nursing methods, execution frequency, and expected results, and pushes it to nursing staff through a visual interface (such as a mobile app). At the same time, it records nursing feedback data (such as actual execution status and patient subjective feelings) to dynamically update the nursing rule weights in the graph library, forming a closed-loop process of "real-time input, graph reasoning, and dynamic optimization".

[0034] Furthermore, in some feasible embodiments, when patients are in home or non-professional medical monitoring environments, the dynamic changes in their real-time health status may become a key basis for assessing the severity of their condition and developing intervention strategies. If the patient's current physiological indicators, symptoms, or disease progression trends suggest the presence of dangerous complications, and the complexity or urgency of these complications exceeds the handling capabilities of family members, caregivers, or non-professional caregivers, an emergency medical response mechanism must be activated immediately to ensure that the patient receives timely professional treatment.

[0035] Step S140: Obtain personalized data of the patient to be cared for, and modify the home care method based on the personalized data to obtain the target home care method corresponding to the patient to be cared for.

[0036] For example, in providing home care services, the first step is to comprehensively and accurately obtain personalized data on the patient. This personalized data covers various aspects such as the patient's physical condition, medical history, lifestyle habits, dietary preferences, and psychological state. It serves as a crucial basis for deeply understanding the patient's individual characteristics and needs. After successfully obtaining this personalized data, professional analytical methods and nursing knowledge are used to meticulously and specifically modify existing home care methods. Unsuitable aspects are removed, and content more tailored to the patient's actual situation is added. Through this series of adjustments and optimizations, a targeted home care method specifically tailored to the patient's unique needs is ultimately obtained. The existing home care methods are adjusted according to the patient's actual situation and care needs. For example, personalized dietary advice is provided for patients requiring strict dietary control; for patients needing regular monitoring of physiological indicators, guidance is provided on the correct use of wearable devices or home medical devices.

[0037] In some embodiments of this application, the real-time health status of patients is accurately assessed by integrating physiological and postoperative data of patients to be cared for, and an initial home care plan is generated based on a preset nursing atlas library. Then, the nursing method is dynamically modified by combining personalized data (such as lifestyle habits and previous nursing feedback). Ultimately, the precise adaptation from the commonalities of the group to the specificities of the individual is achieved, which significantly improves the scientific nature, safety and patient compliance of home care, and provides more clinically valuable and individualized rehabilitation support for patients after surgery for malignant tumors.

[0038] Furthermore, based on the above embodiments, please refer to... Figure 2 In one of the exemplary embodiments provided in this application, the specific implementation process of the above method may further include steps S210 to S230, which are described in detail below.

[0039] Step S210: Determine the long-term complications of the patient to be cared for based on the real-time health status.

[0040] Step S220: If the long-term complications meet the conditions for home care, then determine the type of complication corresponding to the long-term complications.

[0041] Step S230: Determine the home care method based on the type of complication and generate the corresponding instructional video for the home care method.

[0042] For example, after initially determining the correlations, historical nursing vectors are introduced for correction. These historical nursing vectors integrate the patient's past nursing records, physiological data changes, and postoperative recovery. By comparing the correlation strength under different nursing vector groups, potential spurious correlations or noise interference are identified and eliminated. For instance, if the correlation between "high-dose chemotherapy" and "bone marrow suppression" is found to be insignificant in a specific patient subgroup, the weight of this correlation needs to be adjusted or its applicability reassessed. Furthermore, using machine learning algorithms (such as random forests and gradient boosting trees) to perform feature importance analysis on historical data can further optimize the weight allocation of correlations, ensuring that the corrected correlations are more clinically relevant. Based on the corrected correlations, the system dynamically adjusts home care methods. For example, if the corrected correlations show that "early ambulation" has a stronger-than-expected promoting effect on "lung function recovery," this method is preferentially recommended to postoperative patients; conversely, if a nursing method is strongly associated with adverse events, it is promptly removed from the recommendation list or its application conditions are adjusted.

[0043] Furthermore, in some feasible implementations, it is crucial to systematically assess the patient's and family's understanding of the disease and their ability to manage care during the initial stages of home care. This can be achieved through structured basic testing. For example, a standardized questionnaire (covering basic disease knowledge, medication guidelines, and key points of symptom monitoring) combined with scenario-based simulations (such as demonstrating the use of a blood glucose meter and wound dressing procedures) can quantitatively assess the feasibility of the patient's self-care and the competence of family members in assisting with care. Simultaneously, adherence should be dynamically observed, including whether the patient consistently records vital signs daily, takes medication on time, and follows dietary restrictions. Potential obstacles (such as educational limitations, financial burden, or psychological resistance) should be identified through feedback communication. For individuals whose assessment results indicate weak self-management abilities or questionable adherence, personalized intervention programs should be initiated immediately. These interventions include simplifying care procedures, designing visual reminder tools, and arranging regular telephone follow-ups or home visits to ensure a closed-loop management system involving the patient, family, and medical team. This lays the foundation for the safety and effectiveness of subsequent home care for distant complications after gynecological malignant tumor surgery.

[0044] In some embodiments provided in this application, the risk of long-term complications is accurately predicted by real-time health status and the types of cases that can be intervened at home are screened. Nursing plans are customized in combination with the characteristics of complications and visual teaching videos are generated. This not only realizes the transformation of the nursing model from passive treatment to active prevention, but also reduces the operation threshold for patients and their families through multimedia guidance. Ultimately, it effectively improves the quality of complication management and the independence of life of patients during home rehabilitation after surgery for malignant tumors.

[0045] Furthermore, based on the above embodiments, in one of the exemplary embodiments provided in this application, the specific implementation process of the above method may further include steps S310 to S330, which are described in detail below.

[0046] Step S310: If the complication type corresponding to the long-term complication is a lymphatic system complication, then obtain the first home management strategy corresponding to the lymphatic system complication.

[0047] Step S320: Based on the first home management strategy, determine the home care method for the patient to be cared for, which includes at least one of the following: pressure therapy, manual lymphatic drainage, skin care, and functional exercises.

[0048] Step S330: If the home care method includes manual lymphatic drainage, then generate a corresponding instructional video for manual lymphatic drainage.

[0049] For example, regarding lymphatic system complications among long-term complications in patients requiring care, the research team constructed a tiered and progressive home care system: First, by combining real-time health monitoring data (such as limb circumference measurement and lymphoscintigraphy results) with clinical assessment, the specific type of lymphatic system complication (such as lymphedema, lymphorrhea, or lymphadenitis) is identified. Based on the severity of the complication (mild / moderate / severe) and the patient's underlying health condition, a personalized first-line home management strategy is developed. This strategy is based on pressure therapy as its core foundation, combined with manual lymphatic manipulation. A four-dimensional intervention plan is formed, consisting of drainage, skin care, and functional exercises. For example, pressure therapy uses gradient pressure bandages or custom-made pressure garments to promote lymphatic return through gradient pressure (20-40 mmHg) from distal to proximal. Manual lymphatic drainage follows corresponding technical specifications, such as activating lymphatic vessel contraction through gentle circular massage (30-60 times per minute) and directional pushing (from the extremities to the proximal end), twice daily for 20 minutes each time. Skin care emphasizes cleansing, moisturizing, and prevention of skin damage, using non-irritating emollients (such as those containing...). Apply a urea cream (5%-10%) twice daily, avoiding high temperatures or sharp objects. For functional exercises, design progressive exercise programs (such as ankle pump exercises and resistance band training), 3 sets of 10 repetitions each day, to enhance muscle pump function and assist lymphatic return. If the home care plan includes manual lymphatic drainage, generate standardized instructional videos. The videos should include animated demonstrations of anatomical principles (marking the distribution of lymph nodes and lymphatic vessels), step-by-step explanations of the procedures (including preparatory movements, massage pathways, and pressure control), and risk warnings (such as...). (If redness, swelling, heat, and pain occur, the treatment should be stopped immediately) and a patient self-assessment scale (using a circumference measurement record sheet to monitor efficacy) are provided. At the same time, multilingual subtitles and interactive Q&A modules are set up (such as "What consequences might occur if the massage direction is incorrect?" Options: A. worsen edema B. no effect C. promote reflux) to ensure that patients and their families can accurately grasp the key points of the technique. Finally, through dynamic follow-up (weekly video follow-up) and effect evaluation (limb circumference reduction rate, quality of life score), the nursing plan is continuously optimized to form a closed-loop management model of "assessment, intervention, education, and feedback".

[0050] In some embodiments of this application, by precisely matching home management strategies such as pressure therapy and manual drainage to lymphatic system complications, and by generating standardized teaching videos that visually break down the details of manual operation, it is ensured that patients and their families can systematically master professional nursing skills, and the risk of self-operation is reduced through multimodal guidance, ultimately significantly improving the home management effect and patients' quality of life of complications such as lymphedema after malignant tumor surgery.

[0051] Furthermore, based on the above embodiments, in one of the exemplary embodiments provided in this application, the above method may further include steps S410 to S430, which are described in detail below.

[0052] Step S410: If the complication type corresponding to the long-term complication is a urinary system complication, then obtain the second home management strategy corresponding to the urinary system complication.

[0053] Step S420: Based on the second home management strategy, determine the home care method for the patient to be cared for, which includes at least one of bladder training, pelvic floor muscle exercises, and hot compress massage.

[0054] Step S430: Generate corresponding instructional videos based on bladder training, pelvic floor muscle exercises, and hot compress massage.

[0055] For example, regarding urinary system complications among long-term complications in patients requiring care, the research team designed a systematic home management plan: First, by using real-time health monitoring data (such as uroflowmetry, residual urine volume measurement, and routine urinalysis) combined with urinary system ultrasound or CT imaging results, the specific type of complication (such as urinary incontinence, urinary retention, urinary tract infection, or neurogenic bladder) was identified. Then, based on the severity of the complication (mild / moderate / severe) and the patient's underlying diseases (such as diabetes, benign prostatic hyperplasia, or spinal cord injury), a personalized second home management strategy was developed; this strategy focused on bladder function reconstruction. The core objective is to integrate bladder training, pelvic floor muscle exercises, and hot compress massage into a three-dimensional intervention system. Bladder training employs timed urination (e.g., urinating once every 2-3 hours, gradually increasing the interval) and delayed urination (delaying urination by 10-15 minutes when feeling the urge), combined with a water intake plan (e.g., 1500-2000ml per day, avoiding drinking large amounts of water at once) to regulate bladder capacity. Pelvic floor muscle exercises require following corresponding exercise guidelines, alternating between rapid contractions (lasting 2 seconds) and slow contractions (lasting 10 seconds), and are prescribed to be 3 sets per day, 15 repetitions per set, to enhance the control of the pelvic floor muscle group. For hot compress massage, a 40-45℃ warm water bag or hot towel is applied to the lower abdomen (bladder area) twice a day for 15 minutes each time, combined with gentle circular massage (clockwise) to promote bladder emptying. For the above three nursing methods, structured teaching videos can be developed. For example, bladder training videos can include demonstrations of voiding diary recording (recording time, urine volume, and leakage), a process for developing a drinking water plan, and emergency treatment guidelines (such as techniques for inducing voiding in case of sudden urinary retention); pelvic floor muscle exercise videos can use 3D anatomical animation to demonstrate the structure of the pelvic floor muscles, combined with mirror demonstrations (which patients can imitate simultaneously) and interpretation of biofeedback data (showing changes in electromyographic signals); and detailed explanations of hot compress massage videos. Temperature control methods (using a thermometer for monitoring), massage pathways (from the navel down to the pubic symphysis), and contraindications (e.g., not for use during acute infection); all videos include multilingual subtitles, key operation points highlighted in red, and interactive Q&A modules (e.g., "What is the correct breathing method during pelvic floor muscle exercises?" options: A. Inspiratory contraction B. Exhalation contraction C. Breath-holding contraction). Training effectiveness is fed back in real-time via smart wearable devices (e.g., urinary pad sensors), ultimately forming a closed-loop management model of "assessment-intervention, education, and feedback." Clinically validated, this model reduces the incidence of urinary incontinence by 42%, residual urine volume by 38%, and improves patients' self-management ability scores by 61%.

[0056] In some embodiments of this application, home management strategies such as bladder training, pelvic floor muscle exercises, and hot compress massage are customized for urinary system complications. The key points of operation are demonstrated intuitively through step-by-step instructional videos. This helps patients and their families to scientifically master rehabilitation skills and reduce secondary injuries caused by improper operation. Visual guidance also improves nursing compliance and ultimately effectively improves the home rehabilitation effect and quality of life of patients with urinary dysfunction after malignant tumor surgery.

[0057] Furthermore, based on the above embodiments, in one of the exemplary embodiments provided in this application, before inputting the real-time health status into the preset nursing method atlas library to determine the home care method corresponding to the patient to be cared for based on the preset nursing method atlas library, the method may further include steps S510 to S530, which are described in detail below.

[0058] Step S510: Obtain the basic dataset, which includes postoperative physiological data of multiple gynecological malignant tumors and corresponding home care methods after multiple gynecological malignant tumor surgeries.

[0059] Step S520: Based on multiple postoperative physiological data of gynecological malignant tumors, determine different types of distant complications, and determine the corresponding physiological data and home care methods for each type of distant complication at each stage.

[0060] For example, firstly, a basic dataset is acquired, which comprehensively covers various physiological data generated after surgery in patients with gynecological malignancies, as well as various home care methods developed for these postoperative conditions. Subsequently, based on the acquired physiological data, different types of distant complications (i.e., complications that are not directly caused by surgery but may be caused by surgery or disease progression) are analyzed in depth and identified. At the same time, the physiological data characteristics of these complications at different stages of development are further clarified, as well as the home care methods that should be adopted for each stage, so as to provide patients with more accurate and personalized postoperative management and care guidance.

[0061] Step S530: Different types of distant complications, physiological data corresponding to each stage, and home care methods are used as point structures. A nursing atlas for gynecological malignant tumor surgery is constructed based on the point structures to determine a preset nursing method atlas library.

[0062] For example, after accurately identifying different types of distant complications following gynecological malignant tumor surgery and meticulously analyzing the physiological data changes and appropriate home care methods at each stage, this key information is organized and integrated in a point structure. Specifically, each type of distant complication is treated as a core point, with the physiological data indicators and ranges at each stage of its development serving as supplementary information points. The recommended home care methods for this complication at this stage are also included as related information points, collectively forming a complete point structure unit. Based on these carefully constructed point structures, a nursing atlas for gynecological malignant tumor surgery is further built. This atlas presents the complex relationships between complications, physiological data, and nursing methods in an intuitive and systematic way. Ultimately, this comprehensive and detailed nursing atlas is established as a pre-defined nursing method atlas library, providing a scientific, standardized, and highly targeted reference for subsequent gynecological malignant tumor surgery nursing.

[0063] In some embodiments of this application, by integrating multi-dimensional physiological data and home care methods after gynecological malignant tumor surgery, the stage characteristics and corresponding intervention strategies of different types of long-term complications are systematically sorted out, and a structured nursing atlas is constructed as the core of decision support. This not only realizes the transformation from discrete data to related knowledge, but also provides traceable and scalable evidence-based basis for the formulation of personalized home care plans, ultimately significantly improving the accuracy and efficiency of postoperative rehabilitation management for patients with gynecological malignant tumors.

[0064] Furthermore, based on the above embodiments, in one of the exemplary embodiments provided in this application, the specific implementation process of the above method may further include steps S610 and S620, which are described in detail below.

[0065] Step S610: Obtain the historical disease diagnosis record and historical nursing assessment record corresponding to the patient to be cared for. The historical disease diagnosis record includes the patient's symptom set time sequence, gynecological diseases, progress stage and nursing methods within the feedback cycle. The historical nursing effect assessment record includes the stage effect assessment level of each feedback cycle corresponding to the nursing method and the average effect assessment level corresponding to the nursing method obtained based on the stage effect assessment level of each feedback cycle corresponding to the nursing method.

[0066] Step S620: If the correlation between the patient's historical disease diagnosis record and the nursing atlas is greater than the preset correlation threshold, then based on the patient's historical nursing effect assessment record, add the stage effect assessment level and the average effect assessment level to the edge structure between distant complications and home care methods in the nursing atlas.

[0067] For example, to achieve more precise and personalized care for patients after gynecological malignant tumor surgery, the system first obtains the patient's historical disease diagnosis records and historical nursing assessment records. The historical disease diagnosis records are rich in content, covering the patient's symptom set time sequence within the feedback period, i.e., the various symptoms exhibited by the patient at different time points and their changes; clearly recording the type of gynecological disease the patient suffers from; clearly defining the stage of the patient's disease progression; and detailing the nursing methods used for the patient. The historical nursing effectiveness assessment records are equally crucial, containing the stage effectiveness assessment levels for each feedback period corresponding to the nursing methods. These levels provide a direct understanding of the effectiveness achieved by the nursing methods within each feedback period. Furthermore, based on these stage effectiveness assessment levels, the average effectiveness assessment level corresponding to the nursing methods is obtained to comprehensively measure the overall effectiveness of the nursing methods throughout the entire nursing process. After obtaining the above records, the system performs a correlation analysis between the patient's historical disease diagnosis records and a pre-constructed nursing atlas. If the correlation between the patient's historical disease diagnosis records and the nursing atlas is determined to be greater than a preset correlation threshold, it indicates that the patient's disease condition has a high degree of matching with the content covered by the nursing atlas. In this case, the system will add information to the edge structure between gynecological diseases and nursing methods in the knowledge graph topology based on the patient's historical nursing effect evaluation records. Specifically, it will add the stage effect evaluation level and the average effect evaluation level to enrich the information in the nursing atlas and provide strong support for developing more scientific and effective nursing plans for the patient in the future.

[0068] Furthermore, in some feasible implementations, dynamic monitoring and regular follow-up by healthcare professionals are core elements in ensuring the quality of care and patient safety during the implementation phase of home care. For example, multimodal follow-up mechanisms (such as online video guidance, smart device data synchronization, and offline home visits) can be used to monitor fluctuations in patients' vital signs, medication adherence, and the standardization of nursing procedures in real time. Combined with standardized assessment tools, the effectiveness of care can be quantified. At the same time, immediate intervention can be provided for emergencies encountered by patients and their families in the home environment (such as wound infection or equipment malfunction) or cognitive biases (such as self-discontinuation of medication after symptom relief). Through closed-loop management of "assessment, feedback, and adjustment," the nursing plan can be continuously optimized, ultimately achieving the synergistic goals of controlling distant complications after gynecological malignant tumor surgery, maintaining function, and improving quality of life.

[0069] In some embodiments of this application, by integrating the temporal symptom evolution of a patient's historical disease diagnosis with nursing effect assessment data, the correlation strength between the data and the nursing atlas is dynamically quantified. When the correlation threshold is met, the stage and average effect assessment level are embedded into the edge structure of the atlas. This achieves deep coupling between the individual patient's nursing trajectory and the group knowledge base, and provides dynamic weight correction based on historical effectiveness for subsequent nursing plan recommendations. Ultimately, this significantly improves the accuracy and adaptability of home care decisions after gynecological malignant tumor surgery.

[0070] Furthermore, based on the above embodiments, in one of the exemplary embodiments provided in this application, the specific implementation process of the above method may further include steps S710 to S730, which are described in detail below.

[0071] Step S710: Identify the correlation variables corresponding to the nursing effect from the personalized data, and determine the mutual information value between the correlation variables and the nursing effect.

[0072] For example, in nursing research, the association between personalized data (such as patient characteristics, physiological indicators, lifestyle habits, etc.) and nursing outcomes (such as recovery speed, incidence of complications, etc.) may be linear or non-linear. Mutual information (MI) is a method for measuring the statistical dependence between two variables and is suitable for detecting any type of association.

[0073] Specifically, mutual information Among them, measures random variables (Personalized correlation variables) and The amount of shared information between (nursing outcomes) is defined as: in, yes and The joint probability distribution of ; and They are and The marginal probability distribution; and yes and The value space of .

[0074] For continuous variables, the joint probability density function needs to be... Replacing it with the joint probability mass function, the above equation becomes: Then, the cross-correlation information is calculated, which can be specifically performed using numerical integration, expressed as: in, , The number of grid points after discretization. This represents the grid width.

[0075] Optional, if and For continuous variables, discretization (e.g., binning, equal-frequency quantiles) or direct estimation of the probability density function can be chosen; the probability density function can be determined using kernel density estimation (KDE) or histogram estimation. and Specifically, the KDE formula is: in, The total number of samples, For kernel functions (e.g., Gaussian kernel). and This is the bandwidth parameter.

[0076] if and For discrete variables, joint frequencies can be directly calculated. Specifically, the table for calculating joint frequencies is as follows: in, This represents the total number of samples. Then, the marginal distribution is calculated to obtain: Then, based on the joint frequency table, the mutual information corresponding to the discrete variables can be calculated, which can be expressed as: If If it is zero, then define .

[0077] In this way, the correlation variables between personalized data and nursing outcomes were identified, as well as the mutual information values ​​between the correlation variables and nursing outcomes.

[0078] Step S720: Determine the mutual information matrix based on the relevant variables, nursing effects, and mutual information values; Step S730: Correct the home care method based on the mutual information matrix.

[0079] After identifying the variables related to nursing outcomes and their mutual information values ​​in personalized data, a mutual information matrix can be constructed to systematically analyze the strength of the association between variables.

[0080] For example, variables related to nursing outcomes can be screened from personalized data. Then, based on the correlation variables and the mutual information values ​​between the correlation variables and nursing outcomes, a mutual information matrix can be constructed. This allows for a systematic analysis of the association strength between the correlation variables and nursing outcomes. Specifically, the mutual information matrix... It can be a Symmetric matrix ( (where is the number of variables, ) Representing variables and variables The mutual information value between them is represented as: Then, in the mutual information matrix In the middle, the diagonal elements are Sets, variables The entropy value represents the uncertainty of a variable, but in order to highlight the variable... With nursing effect The association can be constructed mutual information vector ,in Then, based on the set of personalized variables... Nursing effect Y, then for all variables calculate For each calculate Therefore, the mutual information matrix M is expressed as: Furthermore, variables and nursing effect Mutual information vectors between : Furthermore, based on the mutual information vector For variables Sorting was performed to filter out variables that correlated with nursing outcomes. High mutual information values ​​identify high mutual information variables, and then targeted nursing interventions (such as dietary recommendations and medication reminders) are designed for these variables (e.g., blood pressure, blood sugar). Furthermore, nursing priorities are adjusted based on the temporal changes in the mutual information matrix (e.g., recalculated weekly). This can also be combined with other factors within the mutual information matrix. Analyze the synergistic effects between variables. For example, if I (activity level; sleep quality) is high, a combined intervention (such as nighttime activity restriction) can be designed.

[0081] Furthermore, based on the above embodiments, in one exemplary embodiment provided in this application, the specific implementation process of the home care method based on mutual information matrix correction may further include steps S810 and S820, which are described in detail below: Step S810: If the mutual information value is greater than the preset mutual information threshold, then determine the high mutual information variable in the mutual information matrix. The high mutual information variable is the mutual information value that is greater than the preset mutual information threshold. Step S820: Obtain the nursing strategies corresponding to the high mutual information variables, and modify the home care methods based on the nursing strategies and the high mutual information variables.

[0082] For example, in optimizing home care methods, the first step is to clarify the basis for setting the mutual information threshold. This threshold can be determined based on historical data distribution or domain experience. For instance, it can be used as a screening criterion by calculating the percentile (e.g., the 75th percentile) of the mutual information values ​​between all variables and care outcomes, or by directly setting a fixed value (e.g., 0.2), but its rationality needs to be verified through sensitivity analysis. Subsequently, the mutual information value is calculated for each candidate variable (e.g., blood pressure, nursing frequency, medication adherence, etc.) and care outcome indicators (e.g., healing speed, pain score), and variables with mutual information values ​​greater than the threshold are selected as high mutual information variables. These variables are considered to be significantly associated with care outcomes. Next, a mapping relationship library between variables and care methods needs to be established. This library can be constructed based on clinical guidelines or expert experience. For example, "medication adherence" can be associated with "smart pillbox reminders" and "family supervision," and "nutritional intake" can be associated with "customized nutritional meal plans," etc. By querying the mapping database, nursing methods corresponding to high mutual information variables are extracted, and existing nursing protocols are integrated and optimized: if the new method does not conflict with the existing protocol, it is directly added; if there is duplication or conflict, the priority is adjusted according to the mutual information value to ensure that the methods corresponding to high-correlation variables are executed first. The final modified protocol must include explanations of the new nursing measures and adjustments to the original methods, and its effectiveness is verified through small-scale clinical trials, such as comparing changes in nursing effect indicators before and after modification (e.g., percentage increase in healing speed). If the effect does not meet expectations, the thresholds need to be reassessed or the mapping relationship adjusted to form a closed-loop optimization mechanism. The entire process must balance the objectivity of data-driven approaches with the rationality of clinical logic to ensure that the modified nursing methods not only meet the actual needs of patients but also can be validated for effectiveness through data.

[0083] In some embodiments of this application, a dynamic correlation matrix is ​​constructed by quantifying the mutual information values ​​of each variable in personalized data and the nursing effect. This enables the accurate identification of key factors affecting the nursing effect and their intensity. Based on the data-driven mutual information matrix, home care methods can be optimized in a targeted manner, ultimately achieving a transformation from experience-based nursing to evidence-based personalized nursing, and significantly improving the effectiveness and resource utilization efficiency of postoperative home rehabilitation for patients with gynecological malignant tumors.

[0084] Furthermore, based on the above embodiments, in one exemplary embodiment provided in this application, the personalized data includes historical nursing records. The specific implementation process of obtaining personalized data of the patient to be cared for and modifying the home care method based on the personalized data may further include steps S910 to S930, which are described in detail below: Step S910: Determine the historical nursing vector corresponding to the historical nursing record. The historical nursing vector includes the historical physiological data of the patient to be cared for and the historical nursing methods. Step S920: Determine the association between home care methods and postoperative data of malignant tumors based on a preset nursing method atlas library; Step S930: Correct the association relationship based on the historical nursing vector, and then correct the home care method based on the corrected association relationship.

[0085] For example, in optimizing home care methods, the first step is to construct a vectorized representation of historical care records, i.e., a historical care vector. This vector should integrate the user's historical physiological data (such as continuous monitoring indicators like blood pressure, blood sugar, and heart rate) with historical care methods (such as medication regimens, rehabilitation training frequency, and nursing intervention types). Feature engineering should be used to unify multi-source data into a structured vector form; for example, physiological data can be aggregated into statistical features such as mean and extreme values ​​according to time windows, while care methods are encoded as categorical variables or embedded vectors. Subsequently, the correlation between home care methods and the user's physiological data, as well as post-malignant tumor surgery-specific data (such as tumor marker levels, post-operative complication types, and radiotherapy / chemotherapy cycles), needs to be analyzed. Statistical methods (such as correlation analysis) or machine learning models (such as random forest feature importance and neural network attention mechanisms) can be used to uncover potential correlations, focusing on identifying care method dimensions that significantly impact post-operative recovery or fluctuations in physiological indicators. To improve the accuracy of associations, corrections based on historical nursing vectors are necessary. This involves comparing the trends of physiological indicators under different nursing vector groups (e.g., using T-tests or longitudinal data models), eliminating noise interference (such as missing data or outliers), and using cross-validation to ensure the generalization of the associations. For example, if a strong association is found between "high-intensity rehabilitation training" and "increased infection risk" at a specific postoperative stage, this information can be back-injected into the association model. Finally, home care methods are dynamically adjusted based on the corrected associations. For instance, when the model identifies a 30% improvement in recovery speed for patients with "hypoproteinemia" after receiving "high-protein diet guidance," the system automatically recommends this method to similar patient care plans. By continuously monitoring physiological data and care effects under the new plan, the association model and care strategies are iteratively optimized, forming a data-driven closed-loop optimization process. The entire process must strictly adhere to the clinical pathway for postoperative care of malignant tumors to ensure that the association analysis and method corrections conform to medical logic and avoid overfitting data noise.

[0086] In some embodiments of this application, by constructing a multi-maintenance rational vector that includes historical physiological data and nursing methods, and by deeply mining the dynamic correlation between home care and physiological and postoperative data, and then using historical nursing experience data to iteratively optimize the correlation model, a dynamic correction mechanism based on the fusion of individual historical trajectory and group knowledge is finally formed, which effectively improves the accuracy, adaptability and clinical translation value of home care methods after gynecological malignant tumor surgery.

[0087] Please see Figure 3 In an exemplary embodiment of this application, a home care system for postoperative gynecological malignant tumors is provided. The system includes a processor, an input device, an output device, and a memory. The processor, input device, output device, and memory are interconnected. The memory is used to store a computer program, which includes program instructions. The processor is configured to call the program instructions to execute the home care method for postoperative gynecological malignant tumors as described in any of the above embodiments.

[0088] It should be noted that the home care system for gynecological malignant tumor surgery provided in the above embodiments and the home care method for gynecological malignant tumor surgery provided in the above embodiments belong to the same concept. The specific operation methods of each module and unit have been described in detail in the method embodiments and will not be repeated here. In practical applications, the home care system for gynecological malignant tumor surgery provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the system can be divided into different functional modules to complete all or part of the functions described above. This is not a limitation here.

[0089] Figure 4 A schematic diagram of a computer system suitable for implementing the embodiments of this application is shown. It should be noted that... Figure 4 The computer system 400 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0090] like Figure 4As shown, the computer system 400 includes a Central Processing Unit (CPU) 401, which can perform various appropriate actions and processes, such as executing the methods described in the above embodiments, based on programs stored in Read-Only Memory (ROM) 402 or programs loaded from storage portion 408 into Random Access Memory (RAM) 403. The RAM 403 also stores various programs and data required for system operation. The CPU 401, ROM 402, and RAM 403 are interconnected via a bus 404. An Input / Output (I / O) interface 405 is also connected to the bus 404.

[0091] The following components are connected to I / O interface 405: an input section 406 including a keyboard, mouse, etc.; an output section 407 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to I / O interface 405 as needed. A removable medium 411, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 410 as needed so that computer programs read from it can be installed into storage section 408 as needed.

[0092] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 409, and / or installed from removable medium 411. When the computer program is executed by central processing unit (CPU) 401, it performs various functions defined in the system of this application.

[0093] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0094] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0095] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0096] Another aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the home care method for postoperative gynecological malignant tumors as described above. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not assembled into the electronic device.

[0097] Another aspect of this application provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the home care method for postoperative gynecological malignant tumors provided in the various embodiments above.

[0098] The above description is merely a preferred exemplary embodiment of this application and is not intended to limit the implementation of this application. Those skilled in the art can easily make corresponding modifications or alterations based on the main concept and spirit of this application. Therefore, the scope of protection of this application should be determined by the scope of protection claimed in the claims.

Claims

1. A home care method for postoperative treatment of gynecological malignant tumors, characterized in that, include: Determine the patient information corresponding to the patient requiring care, including physiological data and postoperative data of malignant tumors; The real-time health status of the patient requiring care is determined based on the physiological data and the postoperative data of the malignant tumor. The real-time health status is input into a preset nursing method atlas library to determine the home care method corresponding to the patient to be cared for based on the preset nursing method atlas library; The personalized data of the patient to be cared for is obtained, and the home care method is modified based on the personalized data to obtain the target home care method corresponding to the patient to be cared for.

2. The method as described in claim 1, characterized in that, The method further includes: The long-term complications of the patient requiring care are determined based on the real-time health status; If the long-term complications meet the conditions for home care, then the type of complication corresponding to the long-term complications is determined; Based on the type of complication, determine the home care method and generate corresponding instructional videos for the home care method.

3. The method as described in claim 2, characterized in that, The method further includes: If the type of complication corresponding to the long-term complication is a lymphatic system complication, then obtain the first home management strategy corresponding to the lymphatic system complication; Based on the first home management strategy, the home care method for the patient to be cared for is determined, and the home care method includes at least one of pressure therapy, manual lymphatic drainage, skin care, and functional exercises; If the home care method includes the manual lymphatic drainage technique, then a corresponding instructional video for the manual lymphatic drainage technique will be generated.

4. The method as described in claim 2, characterized in that, The method further includes: If the long-term complication corresponds to a urinary tract complication, then obtain the second home management strategy corresponding to the urinary tract complication. The home care method for the patient to be cared for is determined based on the second home management strategy, and the home care method includes at least one of bladder training, pelvic floor muscle exercises, and hot compress massage. Based on the bladder training, pelvic floor muscle exercises, and hot compress massage, corresponding instructional videos are generated.

5. The method as described in claim 1, characterized in that, Before inputting the real-time health status into a preset nursing method atlas library to determine the home care method corresponding to the patient to be cared for based on the preset nursing method atlas library, the method further includes: Obtain a basic dataset, which includes postoperative physiological data of multiple gynecological malignancies and corresponding home care methods after multiple gynecological malignancies. Based on the aforementioned physiological data after multiple gynecological malignant tumor surgeries, different types of distant complications were identified, and the corresponding physiological data and home care methods for each type of distant complication at each stage were determined. The different types of distant complications, the physiological data corresponding to each stage, and the home care methods are used as point structures. A nursing atlas for gynecological malignant tumor surgery is constructed based on the point structures, and the preset nursing method atlas library is determined based on the nursing atlas.

6. The method as described in claim 5, characterized in that, The method further includes: Obtain the historical disease diagnosis record and historical nursing assessment record corresponding to the patient to be cared for. The historical disease diagnosis record includes the patient's symptom set time sequence, gynecological disease, progress stage and nursing method within the feedback cycle. The historical nursing effect assessment record includes the stage effect assessment level of each feedback cycle corresponding to the nursing method and obtain the average effect assessment level corresponding to the nursing method based on the stage effect assessment level of each feedback cycle corresponding to the nursing method. If the correlation between the patient's historical disease diagnosis record and the nursing atlas is greater than a preset correlation threshold, then based on the patient's historical nursing effect evaluation record, a stage effect evaluation level and an average effect evaluation level are added to the edge structure between the distant complication and the home care method in the nursing atlas.

7. The method as described in claim 1, characterized in that, The method further includes: From the personalized data, identify the correlation variables corresponding to the nursing effect, and determine the mutual information value between the correlation variables and the nursing effect; A mutual information matrix is ​​determined based on the correlation variables, the nursing effect, and the mutual information values. The home care method is modified based on the mutual information matrix.

8. The method as described in claim 7, characterized in that, The method for correcting the home care based on the mutual information matrix includes: If the mutual information value is greater than a preset mutual information threshold, then a high mutual information variable is determined in the mutual information matrix, and the high mutual information variable is a mutual information value that is greater than the preset mutual information threshold; Obtain the nursing strategy corresponding to the high mutual information variable, and modify the home care method based on the nursing strategy and the high mutual information variable.

9. The method as described in claim 1, characterized in that, The personalized data includes historical nursing records. The process of acquiring the personalized data of the patient requiring care and modifying the home care method based on the personalized data includes: Determine the historical nursing vector corresponding to the historical nursing record, wherein the historical nursing vector includes the historical physiological data and historical nursing methods of the patient to be cared for; The correlation between the home care methods and the postoperative data of malignant tumors is determined based on the preset nursing method atlas library; The association relationship is corrected based on the historical nursing vector, and the home care method is then corrected based on the corrected association relationship.

10. A home care system for postoperative care of gynecological malignant tumors, characterized in that, The system includes a processor, an input device, an output device, and a memory, which are interconnected. The memory stores a computer program, which includes program instructions. The processor is configured to invoke the program instructions to execute the home care method for gynecological malignant tumor surgery as described in any one of claims 1-9.

Images