Thyroid tumor postoperative intelligent nursing system based on multi-dimensional health data

Abstract

The invention provides a thyroid tumor postoperative intelligent nursing system based on multi-dimensional health data, and relates to the field of medical data processing, and the system comprises a map building module which is used for building a thyroid tumor postoperative complication map; the information acquisition module is used for acquiring multi-dimensional health data of the patient; the scheme generation module is used for determining a thyroid tumor postoperative nursing scheme according to the multi-dimensional health data of the patient and the thyroid tumor postoperative complication atlas; the state monitoring module is used for collecting thyroid tumor postoperative real-time state information of the patient according to the thyroid tumor postoperative nursing scheme of the patient; the nursing prompting module is used for carrying out nursing risk prompting according to the thyroid tumor postoperative real-time state information and the thyroid tumor postoperative complication atlas of the patient; the recurrence follow-up visit module is used for obtaining complication monitoring information of the patient and conducting follow-up visit prompting, and the intelligent nursing system has the advantages that personalized intelligent nursing after the thyroid tumor operation is achieved, and the real-time performance and quality of nursing are improved.

Description

Technical Field

[0001] The present invention relates to the field of medical data processing, and in particular to an intelligent nursing system for thyroid tumor surgery based on multi-dimensional health data. Background Art

[0002] Thyroid cancer is the most common thyroid malignancy, accounting for approximately 1% of all malignant tumors. It comprises four pathological types: papillary, follicular, undifferentiated, and medullary. Papillary carcinoma, with its lower malignancy and better prognosis, is the most common. The vast majority of thyroid cancers originate from follicular epithelial cells. Incidence varies depending on region, race, and gender. Women are more likely to develop the disease, and while it can occur at any age, it is more common in young adults. The vast majority of thyroid cancers arise in a single lobe of the thyroid gland, often presenting as a single tumor.

[0003] The existing postoperative care model for thyroid tumors often relies on medical staff to regularly check the patient's vital signs and wound conditions, and lacks the ability to monitor in real time. This may lead to some abnormal conditions not being discovered and handled in a timely manner. When evaluating the patient's recovery, it usually relies on subjective observations and self-reports from the patient, and lacks objective and accurate evaluation methods. This may lead to inaccurate judgments about the patient's recovery, thereby affecting the formulation and adjustment of nursing measures. Currently, postoperative care for thyroid tumors often adopts standardized nursing processes and lacks personalized care plans for individual patient differences. Different patients have different physical conditions, surgical methods, complication risks and other factors, so standardized nursing processes may not meet the needs of all patients.

[0004] Therefore, it is necessary to provide an intelligent postoperative nursing system for thyroid tumors based on multi-dimensional health data to realize personalized intelligent postoperative nursing for thyroid tumors, reduce manual dependence, and improve the real-time and quality of postoperative nursing for thyroid tumors. Summary of the Invention

[0005] The present invention provides an intelligent postoperative nursing system for thyroid tumors based on multi-dimensional health data, including: a map establishment module for establishing a map of postoperative complications of thyroid tumors, wherein the map of postoperative complications of thyroid tumors is used to record the correlation between different types of patients and various postoperative complications of thyroid tumors and the manifestation characteristics of postoperative complications of thyroid tumors; an information acquisition module for acquiring the multi-dimensional health data of the patient; a plan generation module for determining the postoperative nursing plan for the patient's thyroid tumors based on the patient's multi-dimensional health data and the map of postoperative complications of thyroid tumors; a status monitoring module for collecting the patient's real-time status information of the postoperative thyroid tumors based on the patient's postoperative nursing plan of thyroid tumors; a nursing prompt module for providing nursing risk prompts based on the patient's real-time status information of the postoperative thyroid tumors and the map of postoperative complications of thyroid tumors; a recurrence follow-up module for acquiring the patient's complication monitoring information and providing follow-up prompts based on the patient's complication monitoring information.

[0006] Furthermore, the map establishment module establishes a map of thyroid tumor postoperative complications, including: obtaining multi-dimensional health data and nursing complication information of multiple historical patients; classifying multiple historical patients according to the multi-dimensional health data and nursing complication information of multiple historical patients, and determining multiple patient classes and the central multi-dimensional health data corresponding to each patient class; for each patient class, determining the association between the patient class and multiple thyroid tumor postoperative complications according to the nursing complication information of each historical patient included in the patient class; for each patient class, determining the performance characteristics of the patient class corresponding to the thyroid tumor postoperative complications according to the nursing complication information of each historical patient included in the patient class; establishing the map of thyroid tumor postoperative complications according to the association between each patient class and multiple thyroid tumor postoperative complications and the performance characteristics of the patient class corresponding to the thyroid tumor postoperative complications.

[0007] Furthermore, the atlas establishment module classifies multiple historical patients according to the multi-dimensional health data and nursing complication information of multiple historical patients, and determines multiple patient classes and the central multi-dimensional health data corresponding to each patient class, including: S11, calculating the multi-dimensional health data distance between any two historical patients according to the multi-dimensional health data of multiple historical patients; S12, dividing the multiple historical patients into multiple patient units according to the multi-dimensional health data distance between any two historical patients; S13, for each patient unit, determining the nursing complication risk characteristics corresponding to the patient unit according to the nursing complication information of each historical patient included in the patient unit; S14, judging whether the merging condition is met according to the nursing complication risk characteristics corresponding to each patient unit, if not, executing S15, if so, executing S16; S15, judging whether the merging condition is met according to each patient unit The nursing complication risk characteristics corresponding to the patient unit are used to merge at least two patient units, update the multiple patient units, and execute S13; S16. For each patient unit, according to the nursing complication risk characteristics corresponding to the patient unit, determine whether the classification conditions are met. If so, execute S17; if not, treat the patient unit as a patient class; S17. According to the nursing complication information of each historical patient included in the patient unit, calculate the nursing complication distance between any two historical patients, and according to the nursing complication distance between any two historical patients included in the patient unit, classify the multiple historical patients included in the patient unit to determine the multiple patient classes corresponding to the patient unit; S18. For each patient class, according to the multi-dimensional health data of each historical patient included in the patient class, determine the central multi-dimensional health data corresponding to the patient class.

[0008] Furthermore, the map establishment module determines the association relationship between the patient class and multiple thyroid tumor postoperative complications based on the nursing complication information of each historical patient included in the patient class, including: determining the risk thyroid tumor postoperative complications of the patient class based on the nursing complication information of each historical patient included in the patient class; for any two risk thyroid tumor postoperative complications, determining the first co-occurrence association value of any two risk thyroid tumor postoperative complications of the patient class based on the nursing complication information of each historical patient included in the patient class, wherein the association relationship between the patient class and multiple thyroid tumor postoperative complications includes the risk thyroid tumor postoperative complications of the patient class and the first co-occurrence association value of any two risk thyroid tumor postoperative complications of the patient class.

[0009] Furthermore, the plan generation module determines the patient's thyroid tumor postoperative care plan based on the patient's multi-dimensional health data and the thyroid tumor postoperative complications map, including: determining similar patient classes based on the patient's multi-dimensional health data and the central multi-dimensional health data corresponding to each patient class; determining the patient's risk thyroid tumor postoperative complications, the risk parameters of each risk thyroid tumor postoperative complication, and the second co-occurrence correlation value of any two risk thyroid tumor postoperative complications based on the similar patient classes and the thyroid tumor postoperative complications map; determining the patient's thyroid tumor postoperative care plan based on the risk parameters of each risk thyroid tumor postoperative complication, wherein the patient's thyroid tumor postoperative care plan at least includes the status monitoring equipment corresponding to the patient's risk thyroid tumor postoperative complications and the data collection frequency of each status monitoring equipment.

[0010] Furthermore, the status monitoring module includes at least a neck activity monitoring device, wherein the neck activity monitoring device includes a plurality of first vibration sensors and a data analysis device arranged on a nursing belt, the nursing belt includes a support component and a fixing component and a wound pressing component arranged on the support component, and the plurality of first vibration sensors are arranged on the support component; the data analysis device is used to calculate real-time neck activity characteristics based on the first vibration data collected by the plurality of first vibration sensors.

[0011] Furthermore, the status monitoring module includes at least a speech monitoring device, wherein the speech monitoring device includes a plurality of second vibration sensors arranged on the wound compression assembly; the data analysis device is also used to calculate real-time speech features based on the second vibration data collected by the plurality of second vibration sensors.

[0012] Furthermore, the state monitoring module includes at least a respiratory monitoring device, wherein the respiratory monitoring device includes a plurality of first pressure sensors arranged on the wound compression assembly; the data analysis device is also used to calculate real-time respiratory characteristics based on the first pressure data collected by the plurality of first pressure sensors.

[0013] Furthermore, the status monitoring module includes at least a neck hematoma monitoring device, wherein the neck hematoma monitoring device includes a plurality of second pressure sensors arranged on a wound pressing assembly; the data analysis device is also used to calculate real-time hematoma characteristics based on the second pressure data collected by the plurality of second pressure sensors.

[0014] Furthermore, the nursing prompt module provides nursing risk prompts based on the patient's real-time status information after thyroid tumor surgery and the atlas of thyroid tumor postoperative complications, including: determining the real-time single complication risk value of each risk thyroid tumor postoperative complication based on the patient's real-time status information after thyroid tumor surgery; determining the real-time comprehensive risk value of each risk thyroid tumor postoperative complication based on the second co-occurrence association value of any two risk thyroid tumor postoperative complications and the real-time single complication risk value of each risk thyroid tumor postoperative complication; providing nursing risk prompts based on the real-time comprehensive risk value of each risk thyroid tumor postoperative complication; providing nursing risk prompts based on the real-time neck movement characteristics, real-time speaking characteristics, real-time breathing characteristics and real-time hematoma characteristics.

[0015] Compared with the existing technology, the intelligent nursing system for thyroid tumor surgery based on multi-dimensional health data provided by the present invention has at least the following beneficial effects: 1. The atlas of thyroid tumor postoperative complications constructed by the atlas establishment module records in detail the associations and manifestation characteristics between different types of patients and various postoperative complications. The information acquisition module collects multi-dimensional health data of patients, including basic information, medical history, surgical information, etc. The plan generation module generates personalized postoperative care plans for patients based on this data and the atlas of thyroid tumor postoperative complications. This ensures the targeted and effective care, can significantly improve the efficiency and accuracy of care, reduce the risk of postoperative complications, enhance patient satisfaction and rehabilitation quality, and optimize the allocation of nursing resources. This is of great significance for improving the postoperative recovery effect and quality of life of thyroid tumor patients.

[0016] 2. By collecting and analyzing multi-dimensional health data and nursing complication information from multiple historical patients, the system can create a personalized thyroid tumor postoperative complication map. This helps more accurately predict the complication risk a specific patient may face. By calculating the multi-dimensional health data distance between historical patients, patients can be finely categorized and the risk characteristics of each patient class can be identified. This further improves the accuracy of complication prediction. Based on the patient's multi-dimensional health data and complication map, a personalized postoperative care plan can be automatically generated. This reduces the workload of nursing staff and improves nursing efficiency. Based on the patient's risk complication, the appropriate status monitoring equipment and data collection frequency are determined. This ensures targeted and effective monitoring and avoids waste of resources. The system can monitor the patient's postoperative status in real time and provide nursing risk alerts based on the complication map. This helps to promptly identify and address potential complications, reducing patient risks. Through personalized care plans and targeted status monitoring, the system can more effectively support patients' postoperative recovery and improve recovery quality. The accumulated large amount of multi-dimensional health data and complication information provides a valuable data resource for nursing research, which will help promote the development of nursing disciplines and enhance the scientific nature of clinical practice. The system can continuously optimize and improve care plans and complication maps based on feedback and data from actual applications, ensuring the system's adaptability and effectiveness.

[0017] 3. The system comprehensively monitors key physiological indicators that may be relevant to thyroid cancer patients after surgery, including neck movement monitoring, speech monitoring, respiration monitoring, and neck hematoma monitoring. Utilizing high-precision devices such as vibration sensors and pressure sensors, the system accurately collects patients' physiological data in real time, providing a reliable basis for subsequent nursing risk alerts. Based on this real-time physiological data, the system rapidly calculates real-time individual and combined risk values ​​for each risk of thyroid cancer postoperative complication, enabling immediate risk assessment. Combined with a thyroid cancer postoperative complication atlas, the system provides patients with personalized nursing risk alerts, ensuring targeted and effective nursing interventions. The neck movement and speech monitoring devices are designed to be lightweight and comfortable, ensuring patients experience no discomfort or restriction while wearing them. Through real-time monitoring and timely risk alerts, the system helps patients identify and address potential complications promptly, thereby accelerating their recovery. The system automatically and continuously monitors patients' physiological data, reducing manual effort required by caregivers and improving monitoring efficiency. By processing and analyzing the collected data through data analysis equipment, the system can provide nursing staff with intuitive and easy-to-understand risk warning information, allowing them to make decisions quickly and allocate nursing resources reasonably. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein: Figure 1 This is a module diagram of an intelligent nursing system for thyroid tumor surgery based on multi-dimensional health data according to some embodiments of this specification; Figure 2 is a schematic diagram of a thyroid tumor postoperative complication atlas according to some embodiments of this specification; Figure 3 This is a flowchart of determining multiple patient classes and central multi-dimensional health data corresponding to each patient class according to some embodiments of this specification. DETAILED DESCRIPTION

[0019] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0020] Figure 1 This is a module diagram of an intelligent nursing system for thyroid tumor surgery based on multi-dimensional health data according to some embodiments of this specification. Figure 1 As shown, the intelligent nursing system for thyroid tumor surgery based on multi-dimensional health data can include a map establishment module, an information acquisition module, a plan generation module, a status monitoring module and a nursing prompt module.

[0021] The atlas building module can be used to build an atlas of complications after thyroid tumor surgery.

[0022] The atlas of thyroid tumor postoperative complications is used to record the relationship between different types of patients and various thyroid tumor postoperative complications and the manifestation characteristics of thyroid tumor postoperative complications. Figure 2 is a schematic diagram of the atlas of complications after thyroid tumor surgery according to some embodiments of this specification, such as Figure 2 As shown, the thyroid tumor postoperative complications map can include three types of nodes. The first node is used to characterize the patient type. The second node is used to characterize the node of the thyroid tumor postoperative complications. When any first node and any other node are connected by an edge, it represents that there is an association between the patient type and the thyroid tumor postoperative complications. The third node is used to characterize the performance characteristics of the patient type corresponding to the thyroid tumor postoperative complications.

[0023] In some embodiments, the map building module builds a map of thyroid tumor postoperative complications, including: Obtain multi-dimensional health data and nursing complication information of multiple historical patients; Based on the multi-dimensional health data and nursing complication information of multiple historical patients, multiple historical patients are classified to determine multiple patient classes and the central multi-dimensional health data corresponding to each patient class; For each patient class, the association between the patient class and various thyroid tumor postoperative complications was determined based on the nursing complication information of each historical patient included in the patient class; For each patient class, the performance characteristics of the corresponding patient class for thyroid tumor postoperative complications were determined based on the nursing complication information of each historical patient included in the patient class; A map of thyroid tumor postoperative complications was established based on the correlation between each patient class and various thyroid tumor postoperative complications and the manifestation characteristics of thyroid tumor postoperative complications corresponding to the patient class.

[0024] As an example only, the multi-dimensional health data of historical patients may include the patient's basic information (for example, gender, age, blood pressure, body fat percentage, lifestyle habits (for example, diet, exercise, sleep, etc.), historical medical records (for example, the patient's past medical history, surgical history, drug allergy history, etc.) and thyroid tumor surgery information (for example, tumor information (for example, tumor size, location, nature, etc.), surgical method (for example, total resection, subtotal resection, partial resection, etc.), intraoperative conditions (for example, intraoperative bleeding, degree of surrounding tissue damage, lymph node dissection, etc.), pathological results, etc.).

[0025] Figure 3 This is a flow chart of determining multiple patient classes and central multi-dimensional health data corresponding to each patient class according to some embodiments of this specification, such as Figure 3 As shown, in some embodiments, the atlas building module classifies multiple historical patients based on the multi-dimensional health data and nursing complication information of multiple historical patients, determines multiple patient classes and the central multi-dimensional health data corresponding to each patient class, including: S11. Calculate the multi-dimensional health data distance between any two historical patients based on the multi-dimensional health data of multiple historical patients; S12. Divide the plurality of historical patients into a plurality of patient units according to the multi-dimensional health data distance between any two historical patients. For example, the plurality of historical patients may be divided into a plurality of patient units according to the multi-dimensional health data distance between any two historical patients using a K-means clustering algorithm. S13. For each patient unit, determine the nursing complication risk feature corresponding to the patient unit based on the nursing complication information of each historical patient included in the patient unit; S14. Determine whether a merging condition is met based on the nursing complication risk characteristics corresponding to each patient unit. If not, execute S15. If so, execute S16. The merging condition may be that the nursing complication risk characteristics corresponding to at least two patient units have a nursing complication risk characteristic similarity greater than a nursing complication risk characteristic similarity threshold. S15. Merge at least two patient units based on the nursing complication risk characteristics corresponding to each patient unit, update multiple patient units, and execute S13. Specifically, any two patient units whose nursing complication risk characteristics have a similarity greater than a nursing complication risk characteristics similarity threshold may be merged. S16. For each patient unit, determine whether a classification condition is met based on the nursing complication risk characteristics corresponding to the patient unit. If so, execute S17. If not, treat the patient unit as a patient class, where the classification condition may be that the number of thyroid tumor postoperative complications with an incidence fluctuation value greater than an incidence fluctuation value threshold is greater than a quantity threshold. S17. Calculate the nursing complication distance between any two historical patients based on the nursing complication information of each historical patient included in the patient unit, classify the multiple historical patients included in the patient unit based on the nursing complication distance between any two historical patients included in the patient unit, and determine multiple patient classes corresponding to the patient unit. For example, use a K-means clustering algorithm to classify the multiple historical patients included in the patient unit based on the nursing complication distance between any two historical patients included in the patient unit, and determine multiple patient classes corresponding to the patient unit. S18. For each patient class, determine the central multidimensional health data corresponding to the patient class based on the multidimensional health data of each historical patient included in the patient class. For example, the multidimensional health data of each historical patient included in the patient class can be averaged as the central multidimensional health data corresponding to the patient class.

[0026] Specifically, the following preprocessing is first performed on the multi-dimensional health data of multiple historical patients.

[0027] Data standardization: Because health data from different dimensions may have different dimensions and value ranges, data standardization is often required before distance calculation. Standardization can eliminate the influence of dimension and make data from different dimensions numerically comparable.

[0028] Data normalization can be performed according to the following formula: ; in, is the standardized data, X is the original data, μ is the mean of the dimension, and σ is the standard deviation.

[0029] Missing value processing: For data with missing values, appropriate processing is required, such as filling missing values ​​or deleting samples containing missing values.

[0030] The multi-dimensional health data distance between two historical patients can be calculated according to the following formula: ; in, is the multi-dimensional health data distance between the i-th historical patient and the j-th historical patient, is the weight corresponding to the mth dimension, is the total number of dimensions, is the coordinate value of the i-th historical patient in the m-th dimension, is the coordinate value of the j-th historical patient in the m-th dimension.

[0031] The nursing complication risk characteristics corresponding to the patient unit may include the incidence probability and incidence fluctuation value of each thyroid tumor postoperative complication corresponding to the patient unit.

[0032] For example, the incidence probability and incidence fluctuation value can be calculated according to the following formula: ; in, is the incidence probability of the kth thyroid tumor postoperative complication corresponding to the i-th patient unit, is the number of historical patients who had the kth thyroid tumor postoperative complication in the i-th patient unit, is the total number of historical patients included in the i-th patient unit, is the incidence fluctuation value of the kth thyroid tumor postoperative complication corresponding to the i-th patient unit, The incidence mark of the kth thyroid tumor postoperative complication corresponding to the nth historical patient included in the i-th patient unit. If the historical patient develops a thyroid tumor postoperative complication, the incidence mark of the historical patient corresponding to the thyroid tumor postoperative complication is 1, otherwise it is 0.

[0033] The similarity of the nursing complication risk characteristics of the two patient units can be calculated according to the following formula: ; in, is the similarity between the nursing complication risk characteristics corresponding to the i-th patient unit and the nursing complication risk characteristics corresponding to the j-th patient unit, is the preset parameter, greater than 0, is the incidence probability of the kth thyroid tumor postoperative complication corresponding to the jth patient unit, is the incidence fluctuation value of the kth thyroid tumor postoperative complication corresponding to the jth patient unit.

[0034] The nursing complication distance between two historical patients can be calculated according to the following formula: ; in, is the nursing complication distance between the i-th historical patient and the j-th historical patient, is the incidence indicator of the kth thyroid tumor postoperative complication corresponding to the i-th patient unit, is the incidence mark of the kth thyroid tumor postoperative complication corresponding to the jth patient unit, is the total number of complications after thyroid tumor surgery.

[0035] In some embodiments, the atlas building module determines the association between the patient class and various thyroid tumor postoperative complications based on the nursing complication information of each historical patient included in the patient class, including: Determine the risk of thyroid tumor postoperative complications for the patient class based on the nursing complication information for each historical patient included in the patient class; For any two risky postoperative complications of thyroid tumors, the first co-occurrence association value of any two risky postoperative complications of thyroid tumors of the patient class is determined based on the nursing complication information of each historical patient included in the patient class, wherein the association relationship between the patient class and multiple postoperative complications of thyroid tumors includes the risky postoperative complications of thyroid tumors of the patient class and the first co-occurrence association value of any two risky postoperative complications of thyroid tumors of the patient class.

[0036] Specifically, thyroid tumor postoperative complications with an incidence probability greater than an incidence probability threshold and an incidence fluctuation value less than or equal to an incidence fluctuation value threshold can be regarded as risk thyroid tumor postoperative complications of the patient class.

[0037] The first co-occurrence association value of two risk factors for thyroid tumor postoperative complications can be calculated according to the following formula: ; in, is the first co-occurrence association value of the i-th risk thyroid tumor postoperative complication and the j-th risk thyroid tumor postoperative complication corresponding to the g-th patient class, The incidence marker of the i-th thyroid tumor postoperative complication corresponding to the n-th historical patient included in the g-th patient class, The incidence marker of the jth thyroid tumor postoperative complication corresponding to the nth historical patient included in the gth patient class, is the total number of historical patients included in the gth patient class.

[0038] The information acquisition module can be used to obtain multi-dimensional health data of patients.

[0039] The plan generation module can be used to determine the patient's postoperative care plan for thyroid tumors based on the patient's multi-dimensional health data and the thyroid tumor postoperative complication map.

[0040] In some embodiments, the plan generation module determines a postoperative nursing plan for a patient suffering from thyroid tumors based on the patient's multi-dimensional health data and a map of postoperative complications of thyroid tumors, including: Determine similar patient classes based on the patient's multi-dimensional health data and the center's multi-dimensional health data corresponding to each patient class; Based on similar patient classes and thyroid tumor postoperative complication maps, determine the patient's risk of thyroid tumor postoperative complications, the risk parameters of each risk thyroid tumor postoperative complication, and the second co-occurrence association value of any two risk thyroid tumor postoperative complications; Based on the risk parameters of each risky thyroid tumor postoperative complication, the patient's thyroid tumor postoperative care plan is determined, wherein the patient's thyroid tumor postoperative care plan at least includes the status monitoring equipment corresponding to the patient's risky thyroid tumor postoperative complications and the data collection frequency of each status monitoring equipment.

[0041] Specifically, the multidimensional health data distance between the patient and the patient class can be calculated based on the patient's multidimensional health data and the central multidimensional health data corresponding to each patient class, and the patient class whose multidimensional health data distance is less than the multidimensional health data distance threshold is regarded as a similar patient class.

[0042] The risk of postoperative complications of thyroid tumors for similar patient classes can be used as the risk of postoperative complications of thyroid tumors for the patient.

[0043] For each risk of postoperative complication of thyroid tumor, the incidence probability of the corresponding risk of postoperative complication of thyroid tumor for similar patient groups can be averaged as the risk parameter of the risk of postoperative complication of thyroid tumor.

[0044] For any two risky thyroid tumor postoperative complications, the first co-occurrence association values ​​of the two risky thyroid tumor postoperative complications corresponding to similar patient classes can be averaged as the second co-occurrence association value of the two risky thyroid tumor postoperative complications.

[0045] A plan generation model can be used to determine a patient's postoperative care plan for thyroid tumors based on risk parameters of each risk thyroid tumor postoperative complication, wherein the plan generation model can be a machine learning model.

[0046] The status monitoring module can be used to collect the patient's real-time status information after thyroid tumor surgery based on the patient's thyroid tumor postoperative care plan.

[0047] Specifically, the real-time status information of the patient after thyroid tumor surgery may include at least body temperature, blood pressure, heart rate, thyroid hormone level, etc.

[0048] In some embodiments, the status monitoring module includes at least a neck activity monitoring device, wherein the neck activity monitoring device includes a plurality of first vibration sensors and a data analysis device arranged on a nursing belt, the nursing belt includes a support component and a fixing component and a wound pressing component arranged on the support component, and the plurality of first vibration sensors are arranged on the support component.

[0049] The data analysis device is used to calculate real-time neck movement characteristics based on the first vibration data collected by the plurality of first vibration sensors, wherein the real-time neck movement characteristics may at least include movement amplitude, frequency, etc.

[0050] Specifically, the data analysis device may calculate the real-time neck movement characteristics based on the first vibration data collected by the plurality of first vibration sensors using a neck movement analysis model, wherein the neck movement analysis model may be a long short-term memory network model.

[0051] In some embodiments, the state monitoring module includes at least a speech monitoring device, wherein the speech monitoring device includes a plurality of second vibration sensors disposed on the wound compression assembly.

[0052] The data analysis device is further configured to calculate real-time speech features based on the second vibration data collected by the plurality of second vibration sensors, wherein the real-time speech features may include at least speech duration, volume, etc.

[0053] Specifically, the data analysis device may calculate real-time speech features based on the second vibration data collected by the plurality of second vibration sensors using a speech analysis model, wherein the speech analysis model may be a long short-term memory network model.

[0054] In some embodiments, the state monitoring module includes at least a respiratory monitoring device, wherein the respiratory monitoring device includes a plurality of first pressure sensors disposed on the wound compression assembly.

[0055] The data analysis device is further configured to calculate real-time respiratory characteristics based on the first pressure data collected by the plurality of first pressure sensors, wherein the real-time respiratory characteristics may include at least respiratory frequency, rhythm, and depth.

[0056] Specifically, the data analysis device may calculate the real-time speech features based on the first pressure data collected by the plurality of first pressure sensors using a breathing analysis model, wherein the breathing analysis model may be a long short-term memory network model.

[0057] In some embodiments, the status monitoring module includes at least a neck hematoma monitoring device, wherein the neck hematoma monitoring device includes a plurality of second pressure sensors arranged on the wound compression assembly.

[0058] The data analysis device is further configured to calculate real-time hematoma characteristics based on the second pressure data collected by the plurality of second pressure sensors. The real-time hematoma characteristics may include hematoma size, hematoma growth rate, etc.

[0059] Specifically, the data analysis device may calculate the real-time speech features based on the first pressure data collected by the plurality of first pressure sensors using a neck hematoma analysis model, wherein the neck hematoma analysis model may be a long short-term memory network model.

[0060] The nursing reminder module can be used to provide nursing risk reminders based on the patient's real-time status information after thyroid tumor surgery and the atlas of complications after thyroid tumor surgery.

[0061] In some embodiments, the nursing prompt module provides nursing risk prompts based on the patient's real-time postoperative status information of thyroid tumors and the postoperative complication map of thyroid tumors, including: Based on the patient's real-time status information after thyroid tumor surgery, determine the real-time single complication risk value for each risk thyroid tumor postoperative complication; According to the second co-occurrence association value of any two risk thyroid tumor postoperative complications and the real-time single complication risk value of each risk thyroid tumor postoperative complication, the real-time comprehensive risk value of each risk thyroid tumor postoperative complication is determined; Provide nursing risk reminders based on the real-time comprehensive risk value of each risk thyroid tumor postoperative complication; Nursing risk warnings are provided based on real-time neck movement characteristics, real-time speaking characteristics, real-time breathing characteristics, and real-time hematoma characteristics.

[0062] Specifically, the real-time single complication risk value of each risk thyroid tumor postoperative complication can be determined based on the patient's real-time status information after thyroid tumor surgery through a risk prediction model, wherein the risk prediction model can be a long short-term memory network model.

[0063] The real-time single complication risk value of each risk thyroid tumor postoperative complication is corrected using a risk correction model based on the second co-occurrence association value of any two risk thyroid tumor postoperative complications and the real-time single complication risk value of each risk thyroid tumor postoperative complication to determine a real-time comprehensive risk value for each risk thyroid tumor postoperative complication. The risk correction model may be a convolutional neural network model.

[0064] When the real-time comprehensive risk value of at least one risk thyroid tumor postoperative complication is greater than the corresponding real-time comprehensive risk value threshold, a nursing risk prompt can be issued.

[0065] A risk warning generation model can be used to provide nursing risk warnings based on real-time neck movement characteristics, real-time speaking characteristics, real-time breathing characteristics, and real-time hematoma characteristics. The risk warning generation model can be a convolutional neural network model.

[0066] The recurrence follow-up module is used to obtain the patient's complication monitoring information and provide follow-up reminders based on the patient's complication monitoring information.

[0067] Specifically, patient complication monitoring information can include thyroid function indicators, including serum thyroid-stimulating hormone (TSH), triiodothyronine (T3T), thyroxine (T4), free T3T, and free thyroxine (FT4), which are used to assess thyroid function. After thyroidectomy, these indicators may change, reflecting hypothyroidism or hyperthyroidism. For patients with thyroid cancer, especially differentiated thyroid cancer (such as papillary and follicular thyroid cancer), serum thyroglobulin levels are important indicators for monitoring tumor recurrence or metastasis. Elevated or persistently rising levels may indicate tumor recurrence. Serum calcium, phosphorus, and parathyroid hormone levels are used to assess parathyroid function. The parathyroid glands are adjacent to the thyroid gland and may be damaged during surgery, leading to hypoparathyroidism and symptoms of hypocalcemia. Thyroid ultrasound can demonstrate the morphology, size, and structure of the thyroid gland, as well as the recovery of the surgical site. Observing the remaining thyroid tissue for recurrence of nodules or masses, assessing cervical lymph node enlargement, and evaluating blood flow in the surgical area can help detect complications promptly. Patient complication monitoring information can include clinical symptoms and signs, such as dyspnea, hoarseness, numbness in the hands and feet, and convulsions, which may be manifestations of postoperative complications. Monitoring these symptoms and signs is important for timely detection and management of complications. Patient complication monitoring information can also include other biochemical indicators, such as vascular endothelial growth factor, TSH receptor, leukocyte antigen monoclonal antibody system, and thyroid peroxidase.

[0068] The recurrence follow-up module can predict the patient's complication recurrence risk based on the patient's complication monitoring information through a recurrence prediction model. When the complication recurrence risk is greater than the complication recurrence risk threshold, a follow-up prompt is issued, wherein the recurrence prediction model can be a convolutional neural network model.

[0069] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly described and illustrated in this specification.

Claims

1. An intelligent nursing system for thyroid tumor surgery based on multi-dimensional health data, characterized by: include: A map establishment module is used to establish a map of thyroid tumor postoperative complications, wherein the map is used to record the association between different types of patients and various thyroid tumor postoperative complications and the manifestation characteristics of thyroid tumor postoperative complications; Information acquisition module, used to obtain multi-dimensional health data of patients; A plan generation module is used to determine a postoperative nursing plan for a patient with a thyroid tumor based on the patient's multi-dimensional health data and the postoperative complication map of the thyroid tumor; A status monitoring module is used to collect the patient's thyroid tumor postoperative real-time status information according to the patient's thyroid tumor postoperative care plan; The nursing reminder module is used to provide nursing risk reminders based on the patient's real-time status information after thyroid tumor surgery and the atlas of thyroid tumor postoperative complications; The recurrence follow-up module is used to obtain the patient's complication monitoring information and provide follow-up reminders based on the patient's complication monitoring information.

2. The intelligent nursing system for thyroid tumor surgery based on multi-dimensional health data according to claim 1 is characterized in that: The atlas building module builds an atlas of complications after thyroid tumor surgery, including: Obtain multi-dimensional health data and nursing complication information of multiple historical patients; Based on the multi-dimensional health data and nursing complication information of multiple historical patients, multiple historical patients are classified to determine multiple patient classes and the central multi-dimensional health data corresponding to each patient class; For each patient class, determining the association between the patient class and multiple thyroid tumor postoperative complications based on nursing complication information of each historical patient included in the patient class; For each patient class, determining the performance characteristics of the patient class corresponding to the postoperative complications of thyroid tumor surgery based on the nursing complication information of each historical patient included in the patient class; The thyroid tumor postoperative complications atlas is established based on the correlation between each patient class and various thyroid tumor postoperative complications and the manifestation characteristics of the thyroid tumor postoperative complications corresponding to the patient class.

3. The intelligent nursing system for thyroid tumor surgery based on multi-dimensional health data according to claim 2 is characterized in that: The graph building module classifies multiple historical patients based on their multi-dimensional health data and nursing complication information, and determines multiple patient classes and central multi-dimensional health data corresponding to each patient class, including: S11. Calculate the multi-dimensional health data distance between any two historical patients based on the multi-dimensional health data of multiple historical patients; S12. Divide the plurality of historical patients into a plurality of patient units according to the multi-dimensional health data distance between any two historical patients; S13. For each patient unit, determine the nursing complication risk feature corresponding to the patient unit based on the nursing complication information of each historical patient included in the patient unit; S14. Determine whether the merging conditions are met based on the nursing complication risk characteristics corresponding to each patient unit. If not, execute S15. If so, execute S16. S15. Merge at least two patient units according to the nursing complication risk characteristics corresponding to each patient unit, update the multiple patient units, and execute S13; S16. For each patient unit, determine whether the classification condition is met based on the nursing complication risk characteristics corresponding to the patient unit. If so, execute S17. If not, treat the patient unit as a patient class. S17. Calculate the nursing complication distance between any two historical patients based on the nursing complication information of each historical patient included in the patient unit; classify the multiple historical patients included in the patient unit based on the nursing complication distance between any two historical patients included in the patient unit, and determine multiple patient classes corresponding to the patient unit; S18. For each patient class, determine the central multi-dimensional health data corresponding to the patient class based on the multi-dimensional health data of each historical patient included in the patient class.

4. The intelligent nursing system for thyroid tumor surgery based on multi-dimensional health data according to claim 2 is characterized in that: The atlas building module determines the association between the patient class and various thyroid tumor postoperative complications based on the nursing complication information of each historical patient included in the patient class, including: determining the risk of thyroid tumor postoperative complications for the patient class according to nursing complication information of each historical patient included in the patient class; For any two risky postoperative complications of thyroid tumors, the first co-occurrence association value of any two risky postoperative complications of thyroid tumors of the patient class is determined based on the nursing complication information of each historical patient included in the patient class, wherein the association relationship between the patient class and multiple postoperative complications of thyroid tumors includes the risky postoperative complications of thyroid tumors of the patient class and the first co-occurrence association value of any two risky postoperative complications of thyroid tumors of the patient class.

5. The intelligent nursing system for thyroid tumor surgery based on multi-dimensional health data according to any one of claims 2 to 4, characterized in that: The plan generation module determines the patient's thyroid tumor postoperative care plan based on the patient's multi-dimensional health data and the thyroid tumor postoperative complications map, including: Determine similar patient classes based on the patient's multi-dimensional health data and the center's multi-dimensional health data corresponding to each patient class; Determining the patient's risk of thyroid tumor postoperative complications, the risk parameter of each risk thyroid tumor postoperative complication, and the second co-occurrence association value of any two risk thyroid tumor postoperative complications based on the similar patient class and the thyroid tumor postoperative complication atlas; Based on the risk parameters of each risky thyroid tumor postoperative complication, the patient's thyroid tumor postoperative care plan is determined, wherein the patient's thyroid tumor postoperative care plan at least includes the status monitoring equipment corresponding to the patient's risky thyroid tumor postoperative complications and the data collection frequency of each status monitoring equipment.

6. The intelligent nursing system for thyroid tumor surgery based on multi-dimensional health data according to claim 5 is characterized in that: The status monitoring module at least includes a neck movement monitoring device, wherein the neck movement monitoring device includes a plurality of first vibration sensors and a data analysis device provided on a nursing belt, the nursing belt including a support assembly and a fixing assembly and a wound compression assembly provided on the support assembly, the plurality of first vibration sensors being provided on the support assembly; The data analysis device is used to calculate real-time neck movement characteristics based on the first vibration data collected by the multiple first vibration sensors.

7. The intelligent nursing system for thyroid tumor surgery based on multi-dimensional health data according to claim 6 is characterized in that: The state monitoring module comprises at least a speech monitoring device, wherein the speech monitoring device comprises a plurality of second vibration sensors disposed on the wound compression assembly; The data analysis device is further configured to calculate real-time speech features based on the second vibration data collected by the plurality of second vibration sensors.

8. The intelligent nursing system for thyroid tumor surgery based on multi-dimensional health data according to claim 7 is characterized in that: The state monitoring module comprises at least a respiratory monitoring device, wherein the respiratory monitoring device comprises a plurality of first pressure sensors disposed on the wound compression assembly; The data analysis device is further configured to calculate real-time respiratory characteristics based on the first pressure data collected by the plurality of first pressure sensors.

9. The intelligent nursing system for thyroid tumor surgery based on multi-dimensional health data according to claim 8 is characterized in that: The state monitoring module includes at least a neck hematoma monitoring device, wherein the neck hematoma monitoring device includes a plurality of second pressure sensors provided on a wound compression assembly; The data analysis device is also used to calculate real-time hematoma characteristics based on the second pressure data collected by the multiple second pressure sensors.

10. The intelligent nursing system for thyroid tumor surgery based on multi-dimensional health data according to claim 9 is characterized in that: The nursing prompt module provides nursing risk prompts based on the patient's real-time status information after thyroid tumor surgery and the thyroid tumor surgery complication map, including: Based on the patient's real-time status information after thyroid tumor surgery, determine the real-time single complication risk value for each risk thyroid tumor postoperative complication; According to the second co-occurrence association value of any two risk thyroid tumor postoperative complications and the real-time single complication risk value of each risk thyroid tumor postoperative complication, the real-time comprehensive risk value of each risk thyroid tumor postoperative complication is determined; Provide nursing risk reminders based on the real-time comprehensive risk value of each risk thyroid tumor postoperative complication; Nursing risk prompts are provided based on the real-time neck movement characteristics, real-time speaking characteristics, real-time breathing characteristics and real-time hematoma characteristics.

Images