Colorectal cancer patient tracking nursing method and system

Abstract

The invention belongs to the technical field of medical treatment, and particularly relates to a colorectal cancer patient tracking nursing method and system, and the method comprises the steps: obtaining the physiological data of a colorectal cancer patient; analyzing the physiological data, and determining a nursing target and a nursing scheme of the colorectal cancer patient; acquiring nursing data in real time when the colorectal cancer patient is nursed according to the nursing scheme; reading target data in the nursing target, and calculating a nursing deviation between the nursing data and the target data; adjusting the nursing scheme based on the nursing deviation to obtain an optimized nursing scheme, and continuously tracking the nursing condition of the colorectal cancer patient based on the optimized nursing scheme. According to the method, the nursing scheme is intelligently generated according to the postoperative condition of the colorectal cancer patient, the nursing scheme is optimized in real time according to the actual nursing condition, nursing measures matched with the current postoperative condition of the colorectal cancer patient can be provided, other diseases caused by inaccurate and incomplete nursing are avoided, and unnecessary injury to the patient is avoided.

Description

Technical Field

[0001] The present invention relates to the field of medical technology, and in particular to a colorectal cancer patient tracking nursing method and nursing system. Background Art

[0002] Colorectal cancer is a common malignant tumor in the gastrointestinal tract. The early symptoms are not obvious. As the tumor grows, symptoms such as changes in bowel habits, blood in the stool, diarrhea, alternating diarrhea and constipation, and local abdominal pain appear. In the late stage, systemic symptoms such as anemia and weight loss appear. Its morbidity and mortality rate are second only to gastric cancer, esophageal cancer, and primary liver cancer among malignant tumors of the digestive system.

[0003] Surgical treatment is still the first choice for radical treatment of colorectal cancer, that is, surgical removal of the cancerous part to achieve a radical cure. However, after surgical treatment, postoperative care and status tracking of patients are also particularly important. Relevant technologies propose to reduce offline communication and manual information recording and tracking through real-time information recording and sharing, reduce the manpower and time costs of manual collection and confirmation of information, and improve the overall quality and efficiency of postoperative management of patients. However, in the process of nursing tracking based on this method, there is a lack of intelligent adjustment of the nursing plan according to the real-time nursing situation, which may lead to inaccurate nursing measures, thereby aggravating the patient's postoperative symptoms and causing adverse nursing consequences. Summary of the invention

[0004] The present invention provides a colorectal cancer patient tracking nursing method and nursing system, aiming to intelligently generate nursing plans for colorectal cancer patients after surgery and optimize the nursing plans in real time according to actual nursing conditions.

[0005] In order to achieve the above-mentioned object of the invention, the first aspect of the present invention provides a method for tracking and nursing colorectal cancer patients, the method comprising: Acquiring physiological data of colorectal cancer patients, wherein the physiological data includes basic physical sign data and medical examination data of colorectal cancer patients; Analyzing the physiological data to determine the nursing goal and nursing plan for the colorectal cancer patient; Real-time acquisition of nursing data when nursing the colorectal cancer patient according to the nursing plan; Reading target data in the nursing target, and calculating a nursing deviation between the nursing data and the target data; The nursing plan is adjusted based on the nursing deviation to obtain an optimized nursing plan, and the nursing status of the colorectal cancer patient based on the optimized nursing plan is continuously tracked.

[0006] Furthermore, before analyzing the physiological data to determine the nursing goal and nursing plan for the colorectal cancer patient, the method further includes: Acquire a training data set, wherein the training data set includes historical physiological data, historical nursing plans, and historical nursing results of historical colorectal cancer patients, wherein the historical physiological data includes historical basic physical sign data and historical medical examination data, the historical nursing plans are historical nursing measures taken according to the historical basic physical sign data and historical medical examination data, and the historical nursing results are historical nursing effects obtained according to the nursing measures; Importing the training data set into the decision tree model to be trained, wherein the historical basic vital sign data is the first root node, the historical nursing effect is the result-oriented endpoint, the historical nursing measures are decision nodes, and the decision nodes include leaf nodes at multiple levels; Calculate the entropy value between the first root node and the first leaf node according to the entropy calculation formula to obtain a first entropy value; When the first entropy value is greater than or equal to a preset threshold, the leaf nodes are pruned, and the leaf nodes corresponding to values ​​less than the preset threshold are retained; The historical medical examination data is a second root node, and the entropy value between the second root node and the second leaf node is calculated according to the entropy calculation formula to obtain a second entropy value; When the second entropy value is greater than or equal to the preset threshold, pruning the second leaf nodes, and retaining the second leaf nodes corresponding to values ​​less than the preset threshold; The entropy value between each root node and the leaf node of the corresponding level is recursively calculated, and the leaf nodes with entropy values ​​greater than or equal to the preset threshold are pruned until the result-oriented endpoint is reached, thereby obtaining a decision tree model capable of predicting the nursing standards and nursing plan performance of colorectal cancer patients.

[0007] Furthermore, the analyzing of the physiological data to determine the nursing goal and nursing plan for the colorectal cancer patient includes: importing the physiological data into the decision tree model; In the decision tree model, the physiological data is taken as the starting node, and the nursing goal of the physiological data is taken as the end point. The nursing decision judgment is executed from the starting node to the end point to obtain a nursing plan corresponding to the nursing goal of the colorectal cancer patient, wherein the nursing plan includes a first nursing link that executes nursing measures based on the physiological data to produce nursing results.

[0008] Further, the reading of the target data in the nursing target and calculating the nursing deviation between the nursing data and the target data includes: Reading target data in the nursing target, and calculating a positive deviation and / or a negative deviation between the nursing data and the target data; Calculating the positive deviation based on a first deviation probability of the target data; and / or, The negative deviation is calculated based on a second deviation probability of the target data.

[0009] Further, the reading of the target data in the nursing target and calculating the nursing deviation between the nursing data and the target data includes: If there are complications in the nursing data when the colorectal cancer patient is cared for according to the nursing plan, the nursing data of the complications are recorded as special nursing data, and a preset value is assigned to the special nursing data; calculating an absolute average deviation probability of the first deviation probability and / or the second deviation probability; The absolute average deviation probability is multiplied by the preset value to obtain a third deviation probability of the special care data.

[0010] Further, the adjusting the nursing plan based on the nursing deviation to obtain an optimized nursing plan includes: If any one of the first deviation probability, the second deviation probability and the third deviation probability is greater than or equal to a preset deviation probability, importing the nursing data into the decision tree model; In the decision tree model, the nursing data is taken as the initial node and the nursing goal is taken as the end point, and a nursing decision judgment is performed from the initial node to the end point to obtain a second nursing link that generates a corresponding nursing result by executing nursing measures based on the nursing data; Determining whether the first nursing link is consistent with the second nursing link; If they are inconsistent, the second care link will be used as the optimized care plan.

[0011] Furthermore, the calculation formula of the entropy is:

[0012] in, H(X) represents the entropy of the random variable X; X represents a discrete random variable in a finite range; Represents the levels in the training data set; P i Represents the number of leaf nodes in the i-th layer in the training data set.

[0013] The present application also provides a colorectal cancer patient tracking and nursing system, the system comprising: A first acquisition module is used to acquire physiological data of colorectal cancer patients, wherein the physiological data includes basic physical sign data and medical examination data of colorectal cancer patients; An analysis module, used to analyze the physiological data and determine the nursing goal and nursing plan for the colorectal cancer patient; A second acquisition module is used to acquire in real time the nursing data when the colorectal cancer patient is cared for according to the nursing plan; A reading module, used for reading target data in the nursing target, and calculating the nursing deviation between the nursing data and the target data; An adjustment module is used to adjust the nursing plan based on the nursing deviation to obtain an optimized nursing plan, and continuously track the nursing status of the colorectal cancer patient based on the optimized nursing plan.

[0014] The present application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above-mentioned methods for tracking and caring for colorectal cancer patients when executing the computer program.

[0015] The present application also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above-mentioned methods for tracking and caring for colorectal cancer patients are implemented.

[0016] Beneficial effects: In the present application, by acquiring the physiological data of colorectal cancer patients, the physiological data include the basic vital signs data and medical examination data of colorectal cancer patients; analyzing the physiological data to determine the nursing goals and nursing plans of the colorectal cancer patients; acquiring in real time the nursing data of the colorectal cancer patients when caring for the colorectal cancer patients according to the nursing plan; reading the target data in the nursing goals, and calculating the nursing deviation between the nursing data and the target data; adjusting the nursing plan based on the nursing deviation to obtain an optimized nursing plan, and continuously tracking the nursing situation of the colorectal cancer patients based on the optimized nursing plan, nursing measures that match the postoperative condition of the current colorectal cancer patients can be provided, so as to avoid other diseases caused by inaccurate and incomplete nursing, thereby avoiding unnecessary damage to the patients, and realizing the intelligent generation of nursing plans for the postoperative conditions of colorectal cancer patients, and optimizing the nursing plans in real time according to the actual nursing situation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of an embodiment of a method for tracking and caring for patients with colorectal cancer according to the present application; Figure 2 This is a schematic diagram of the structure of an embodiment of the colorectal cancer patient tracking and nursing system of the present application; Figure 3 This is a schematic block diagram of the structure of an embodiment of a computer device of the present application.

[0018] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0020] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "a", "an", "above", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of features, integers, steps, operations, elements, modules, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, modules, components, and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any module and all combinations of one or more associated listed items.

[0021] Those skilled in the art will understand that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art in the field to which the present invention belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.

[0022] Reference Figure 1 The embodiment of the present invention provides a method for tracking and nursing a patient with colorectal cancer, comprising the following steps S1-S5: S1: Acquire physiological data of colorectal cancer patients, wherein the physiological data includes basic physical sign data and medical examination data of colorectal cancer patients.

[0023] Acquire the physiological data of colorectal cancer patients, which include basic physical sign data and medical examination data of colorectal cancer patients, wherein the basic physical sign data include basic data information such as gender, age, weight, etc.; the medical examination data include blood routine and excrement detection data.

[0024] S2: Analyze the physiological data to determine the nursing goals and nursing plans for the colorectal cancer patient.

[0025] A decision tree model is used to analyze the physiological data. Specifically, the physiological data is imported into the decision tree model. In the decision tree model, the physiological data is used as the starting node, and the nursing goal of the physiological data is recovery as the end point. The nursing decision judgment is executed from the above starting node to the end point, and then a nursing plan with recovery as the nursing goal for the colorectal cancer patient is obtained. The nursing plan includes a series of nursing links that execute nursing measures based on physiological data to produce nursing results.

[0026] S3: Acquire in real time the nursing data of the colorectal cancer patient when being cared for according to the nursing plan.

[0027] In order to control the actual effectiveness of nursing care for colorectal cancer patients according to the nursing plan, it is necessary to obtain the nursing data of colorectal cancer patients in real time. The real-time acquisition can be periodic data information acquisition. For example, for severe patients, the data acquisition cycle is set to every day. For mild patients, the cycle can be set to one month, two months or even three months, depending on the patient's physical condition. When collecting nursing data for colorectal cancer patients, their basic vital signs data and medical examination data must be collected at the same time.

[0028] S4: Read the target data in the nursing target, and calculate the nursing deviation between the nursing data and the target data.

[0029] In order to timely discover abnormalities in the postoperative nursing of colorectal cancer patients, the nursing deviation between the postoperative nursing data of colorectal cancer patients and the target data can be calculated to determine the abnormalities in their nursing. The calculation of the nursing deviation includes the positive and negative deviations of the nursing data relative to the target data, as well as the deviation probabilities of the positive and negative deviations.

[0030] S5: Adjust the nursing plan based on the nursing deviation to obtain an optimized nursing plan, and continue to track the nursing status of the colorectal cancer patient based on the optimized nursing plan.

[0031] When it is confirmed that there are inappropriate nursing measures in the postoperative nursing plan for colorectal cancer patients, a new nursing plan (i.e., optimized nursing plan) is reconstructed based on the current nursing data of the colorectal cancer patient, and the colorectal cancer patient is provided with follow-up care based on the optimized nursing plan. At the same time, the care of the colorectal cancer patient based on the optimized nursing plan is tracked to ensure that the postoperative nursing measures for colorectal cancer patients are optimal, to avoid other diseases caused by inaccurate and incomplete nursing, and to cause unnecessary damage to the patient.

[0032] The present embodiment provides a method for tracking and nursing care for patients with colorectal cancer, by acquiring physiological data of patients with colorectal cancer, wherein the physiological data include basic vital signs data and medical examination data of patients with colorectal cancer; analyzing the physiological data to determine the nursing goal and nursing plan of the patients with colorectal cancer; acquiring in real time the nursing data when the patients with colorectal cancer are cared for according to the nursing plan; reading the target data in the nursing goal, and calculating the nursing deviation between the nursing data and the target data; adjusting the nursing plan based on the nursing deviation to obtain an optimized nursing plan, and continuously tracking the nursing situation of the patients with colorectal cancer based on the optimized nursing plan, so as to provide nursing measures matching the postoperative condition of the current patients with colorectal cancer, avoid other diseases caused by inaccurate and incomplete nursing, and further avoid unnecessary damage to the patients, thereby realizing the intelligent generation of nursing plans for the postoperative conditions of patients with colorectal cancer, and optimizing the nursing plans in real time according to the actual nursing situation.

[0033] In one embodiment, before analyzing the physiological data to determine the nursing goal and nursing plan for the colorectal cancer patient, the method further includes: S21. Obtain a training data set, wherein the training data set includes historical physiological data, historical nursing plans, and historical nursing results of historical colorectal cancer patients, wherein the historical physiological data includes historical basic vital signs data and historical medical examination data, the historical nursing plans are historical nursing measures taken based on the historical basic vital signs data and historical medical examination data, and the historical nursing results are historical nursing effects obtained based on the nursing measures.

[0034] The training data set was extracted from the data of patients who underwent colorectal cancer surgery in the anorectal surgery department of a tertiary hospital through sample size estimation and sampling methods. The patients who underwent colorectal cancer surgery included male and female patients of different ages. The training data set covered the historical physiological data, historical nursing plans, and medical case-related data of historical nursing results of patients with rectal cancer. The historical physiological data included basic vital signs data and medical examination data of different patients. The basic vital signs data referred to the gender and age of the patients, and the medical examination data included routine blood test data, B-ultrasound images, etc. The historical nursing plans included nursing measures taken for patients of different genders and different ages. The historical nursing results were the results of nursing care taken by corresponding nursing measures for patients of different genders and different ages.

[0035] S22. Import the training data set into the decision tree model to be trained, wherein the historical basic vital signs data is the first root node, the historical nursing effect is the result-oriented endpoint, the historical nursing measures are decision nodes, and the decision nodes include leaf nodes of multiple levels.

[0036] The decision tree model consists of nodes and directed edges. When using the decision tree for classification, we first start from the root node and test the corresponding attributes of the instance at the node. Then, according to the test results, the instance will be assigned to its child node; then, the process is continued at the child node, and the instance is recursively tested and assigned until the leaf node is reached; finally, the instance will be classified into the result indicated by the leaf node. In this embodiment, the patient's gender and age are set as the first root node, and the nursing measures taken for different genders and age groups are leaf nodes. The leaf nodes include leaf nodes of multiple levels. Specifically, the nursing measures for different genders are used as sub-leaf nodes of a certain level, and the nursing measures for different age groups are used as sub-leaf nodes of another level, or vice versa, depending on the actual setting; taking nursing measures for patients to achieve the nursing effect of recovery is the result-oriented end point.

[0037] S23. Calculate the entropy value between the first root node and the first leaf node according to the entropy calculation formula to obtain a first entropy value.

[0038] In the decision tree model, each colorectal cancer patient will have multiple nursing plans after surgery to ensure that the patient can enjoy good nursing effects and fast cures during surgery. However, among multiple nursing plans, there may be nursing plans with large side effects of drug efficacy, time-consuming and labor-intensive nursing methods, but general nursing effects. Based on this, it is necessary to screen out nursing plans with small side effects of drug efficacy and can ensure unchanged nursing effects, and / or nursing plans that save time and effort and have good nursing effects. For the screening of nursing plans, they can be screened by calculating the entropy value, where entropy is a measure of the uncertainty of random variables. To put it simply, it is the degree of chaos inside the object, that is, calculating the matching degree between the nursing measures in the nursing plan and the nursing situation currently required by the patient, that is, calculating the entropy value between the root node and the leaf node.

[0039] S24. When the first entropy value is greater than or equal to a preset threshold, the leaf nodes are pruned and the leaf nodes corresponding to values ​​less than the preset threshold are retained.

[0040] Since the larger the entropy value, the more chaotic things are, it is necessary to prune the leaf nodes corresponding to the entropy value greater than or equal to the acceptable threshold (preset threshold), and only retain the leaf nodes with small entropy values, thereby ensuring the hierarchical selection of features and measuring the rationality of feature selection.

[0041] S25. The historical medical examination data is a second root node, and the entropy value between the second root node and the second leaf node is calculated according to the entropy calculation formula to obtain a second entropy value.

[0042] The patient's medical examination data is used as the second root node, such as blood routine examination data, B-ultrasound images, etc.; there are corresponding nursing measures for abnormal blood routine results; there are also corresponding nursing measures for abnormal excrement, etc. Based on this, the nursing measures for abnormal blood routine results can be set as decision nodes (leaf nodes) of a certain level, and the nursing measures corresponding to abnormal excrement can be set as decision nodes (leaf nodes) of another level, depending on the actual settings.

[0043] S26. When the second entropy value is greater than or equal to the preset threshold, the second leaf nodes are pruned, and the second leaf nodes corresponding to the values ​​less than the preset threshold are retained.

[0044] S27. Recursively calculate the entropy value between each root node and the leaf node of the corresponding level, and prune the leaf nodes whose entropy value is greater than or equal to the preset threshold until the result-oriented endpoint is reached, thereby obtaining a decision tree model capable of predicting the nursing standards and nursing plan performance of colorectal cancer patients.

[0045] As mentioned above, the decision tree is a classification and regression method. It is a graphical method that constructs a decision tree based on the conditions required for various situations to achieve expected maximization. In order to accurately provide reasonable and efficient nursing plans for patients with colorectal cancer after surgical treatment, the postoperative nursing measures of recovered patients and the patient's physical sign data and medical data are used as training data sets, and the decision tree model is trained using the training data set, so that the decision tree model has the performance of predicting the nursing standards and nursing plans for colorectal cancer patients, and can provide reliable nursing measures for patients after surgical treatment. Recommendations, to avoid other diseases caused by inaccurate and incomplete nursing after surgical treatment, and thus cause unnecessary damage to patients.

[0046] In one embodiment, the above-mentioned analysis of the physiological data to determine the nursing goal and nursing plan for the colorectal cancer patient includes: S28. Importing the physiological data into the decision tree model.

[0047] S29. In the decision tree model, the physiological data is taken as the starting node, and the nursing goal of the physiological data is taken as the end point. The nursing decision judgment is executed from the starting node to the end point to obtain a nursing plan corresponding to the nursing goal of the colorectal cancer patient, wherein the nursing plan includes a first nursing link that executes nursing measures based on the physiological data to produce nursing results.

[0048] As described above, the physiological data of colorectal cancer patients are imported into the decision tree model. The physiological data of colorectal cancer patients include basic vital signs data and medical examination data. The basic vital signs data refers to basic information such as whether the patient is male or female and his or her age group. The medical examination data includes examination data for blood, excrement, B-ultrasound, etc.; since the postoperative nursing goal of colorectal cancer patients is recovery, that is, the medical examination data are all within the range of normal and healthy data indicators, the patient's basic vital signs data and current medical examination data are used as the starting node (root node) and recovery is the end point. Recursive decision judgments are made in the decision tree model to generate a nursing link that executes nursing measures according to the postoperative physiological data of colorectal cancer patients to achieve the nursing effect of recovery. The nursing link is the postoperative nursing plan for the patient.

[0049] In one embodiment, the step of reading the target data in the nursing target and calculating the nursing deviation between the nursing data and the target data includes: S41. Read the target data in the nursing target, and calculate the positive deviation and / or negative deviation between the nursing data and the target data.

[0050] After receiving surgical treatment, patients still need nursing care that requires drug-assisted treatment. In this case, different patients show different nursing responses under the same nursing situation due to different age groups and physical conditions. For example, in medical examination data, routine blood test data exceeds the standard numerical range of routine blood test, and the excrement test results exceed the standard numerical range of the content of various substances in excrement, etc. Among them, the value of the medical examination data may be higher or lower than the standard numerical range. Based on this, it is necessary to calculate the difference between the value of the medical examination data and the standard value when the patient is cared for according to the nursing measures after surgery. Among them, for values ​​higher than the standard, it is counted as a positive deviation of the nursing data from the target data; for values ​​lower than the standard, it is counted as a negative deviation of the nursing data from the target data.

[0051] S42, calculating the first deviation probability of the positive deviation based on the target data; and / or, In order to further confirm the adverse effects on patients when there is a difference between the medical examination data of the patient's postoperative care and the standard value, it is necessary to further calculate the deviation between the difference and the standard value, that is, divide the positive deviation by the standard value to determine the maximum and minimum proportion of the positive deviation in the standard value. If the positive deviation is zero, it means that the patient's postoperative care is appropriate, his or her physiological indicator data is normal, and no adverse reactions occur; but the greater the proportion of the positive deviation in the standard value, it indicates that the nursing measures in the nursing plan are not appropriate and the nursing plan needs to be adjusted.

[0052] S43, calculating a second deviation probability of the negative deviation based on the target data.

[0053] Similarly, for negative deviations, divide the negative deviations by the standard values ​​to determine the maximum and minimum proportions of the negative deviations in the standard values. When the negative deviation is zero, it means that the patient's postoperative care is appropriate, their physiological index data are normal, and no adverse reactions occur. However, the greater the proportion of the negative deviation in the standard value, it indicates that the nursing measures in the nursing plan are not appropriate and the nursing plan needs to be adjusted.

[0054] As mentioned above, in the process of nursing patients after surgical treatment, if the various indicators in the patient's medical examination data are higher than the standard value (positive deviation) or lower than the standard value (negative deviation), it will affect the patient's recovery. For example, if a certain blood routine indicator is far below the standard value or higher than the standard value, it is likely to cause other complications. Based on this, it is necessary to pay real-time attention to the deviation of the physiological indicator data of the patient's postoperative care relative to the standard indicator data (standard value), so as to ensure that the patient is receiving nursing measures that suit his or her own situation, so as to achieve the nursing effect of recovery as soon as possible.

[0055] In one embodiment, the step of reading the target data in the nursing target and calculating the nursing deviation between the nursing data and the target data includes: S44. If, in the nursing data, there are complications arising when caring for the colorectal cancer patient according to the nursing plan, the nursing data of the complications are recorded as special nursing data, and a preset value is assigned to the special nursing data.

[0056] Among colorectal cancer patients, there may be cases where the patient also suffers from other underlying diseases. When other underlying diseases exist, in order to treat the underlying disease and colorectal cancer at the same time, the drugs and / or chemotherapy measures taken by the patient may have more serious adverse reactions than conventional ones, which may then cause new complications. Moreover, the complications are not like complications caused simply by drug treatment and care for colorectal cancer patients. They are not common and cannot be avoided by conventional nursing measures. The abnormal nursing data caused by the complications are recorded as special nursing data. The data volume of the special nursing data is insufficient relative to the conventional nursing data, and the deviation value and deviation probability of the special nursing data cannot be calculated by referring to the calculation method of the conventional nursing data. Therefore, the deviation value of the special nursing data is replaced by assigning a preset value to the special nursing data. The preset value should be a sufficiently small value, such as 0.001, 0.0001, etc. According to the actual setting, the preset value is set to a sufficiently small value so that the deviation of the special nursing data is not ignored and can be distinguished from the conventional nursing data.

[0057] S45: Calculate the absolute average deviation probability of the first deviation probability and / or the second deviation probability.

[0058] Special care data cannot be calculated by adding or subtracting medical examination data from standard values ​​like conventional care data. However, in order to associate special care data with conventional care data, the deviation probability of special care data can be obtained by calculating the absolute average deviation probability of the first deviation probability and / or the second deviation probability and then using the absolute average deviation probability as the deviation probability of the special care data.

[0059] S46. Multiply the absolute average deviation probability by the preset value to obtain a third deviation probability of the special care data.

[0060] A sufficiently small preset value is assigned to the special care data, and then the sufficiently small preset value is multiplied by the absolute average deviation probability, so as to calculate the third deviation probability of the special care data which is distinguishable from the conventional care data but does not ignore its existence.

[0061] As mentioned above, when there are patients who suffer from other underlying diseases and receive surgical treatment for colorectal cancer, they are more likely to develop other complications due to the existence of the underlying disease. The nursing data of this complication is not common compared to the nursing data of regular colorectal cancer patients after surgery, and it cannot be avoided by conventional nursing measures. The abnormal nursing data caused by this complication is recorded as special nursing data. The database of this special nursing data is not as sufficient as the nursing data of regular colorectal cancer patients after surgery. The deviation value and deviation probability of the special nursing data cannot be calculated by referring to the calculation method of conventional nursing data. For this reason, a sufficiently small preset value is assigned to the special care data, and then the preset value is multiplied by the absolute average deviation probability of the first deviation probability and / or the second deviation probability, so as to obtain a third deviation probability that is associated with and reasonable for conventional nursing data.

[0062] In one embodiment, the above-mentioned adjusting the nursing plan based on the nursing deviation to obtain an optimized nursing plan includes: S51. If any one of the first deviation probability, the second deviation probability and the third deviation probability is greater than or equal to a preset deviation probability, the nursing data is imported into the decision tree model.

[0063] In the process of patient care, when the medical examination data in the patient's physiological data deviates from the standard value, whether it is a positive deviation, a negative deviation or a special deviation, it may be due to improper postoperative care for the patient, and whether to change the care plan should be considered. Therefore, when any deviation occurs, the decision tree model must be used to re-evaluate the patient's care plan.

[0064] S52. In the decision tree model, with the nursing data as the initial node and the nursing goal as the end point, a nursing decision is executed from the initial node to the end point to obtain a second nursing link that executes nursing measures based on the nursing data to generate corresponding nursing results.

[0065] The nursing data generated by the existing nursing plan for colorectal cancer patients is imported into the decision tree model. With the nursing data as the initial node and the nursing goal - recovery as the end point, recursive decision-making is performed in the decision tree model to generate a new nursing link that executes nursing measures based on the existing nursing data of colorectal cancer patients to achieve the nursing effect of recovery. This new nursing link is the second nursing link.

[0066] S53: Determine whether the first nursing link is consistent with the second nursing link.

[0067] S54: If they are inconsistent, the second nursing link is used as the optimized nursing plan.

[0068] When the postoperative nursing data of colorectal cancer patients deviate from the standard values, and their nursing plans are inconsistent with the newly generated new nursing plans, the new nursing plan is generated based on the new physiological indicator data in the patient's nursing data, which is more in line with the nursing measures currently required by the patient. Therefore, the new nursing plan is used as the optimized nursing plan for subsequent care of the patient.

[0069] As described above, in the process of caring for patients, when the medical examination data in the patient's physiological data deviates from the standard value, any deviation requires the use of a decision tree model to re-evaluate the patient's care plan, that is, the care data generated by the colorectal cancer patient based on the existing care plan is imported into the decision tree model, and recursive decision judgments are made in the decision tree model to generate a new care link that executes care measures based on the existing care data of the colorectal cancer patient to achieve a cure; if the old care plan (first care link) is inconsistent with the new care plan (second care link), the new care plan is used as the optimized care plan for subsequent care of the patient.

[0070] In one embodiment, the calculation formula of the above entropy is:

[0071] in, H(X) represents the entropy of the random variable X; X represents a discrete random variable in a finite range; Represents the levels in the training data set; P iRepresents the number of leaf nodes in the i-th layer in the training data set.

[0072] As mentioned above, entropy depends only on the distribution of X and has nothing to do with its value. Since the probability density p of the random variable X is i ∈[0, 1], so logp i ∈ (−∞,0 ]. At this time, if in log p i Add a minus sign in front of it, and we have − logp i ∈ [ 0 ,∞ ). So,

[0073] When a set contains multiple categories, k is large, 𝑝 𝑖 There are too many; and the overall 𝑝 𝑖 Will generally become smaller due to the excessive size of k, which makes the value of 𝐻(X) too large, which conforms to the definition of "the larger the entropy value, the more chaotic things are". Therefore, when screening leaf nodes, only leaf nodes with entropy values ​​less than the preset threshold need to be retained.

[0074] Reference Figure 2 The embodiment of the present invention further provides a colorectal cancer patient tracking and nursing system, comprising: A first acquisition module 10 is used to acquire physiological data of colorectal cancer patients, wherein the physiological data includes basic physical sign data and medical examination data of colorectal cancer patients; An analysis module 20 is used to analyze the physiological data and determine the nursing goal and nursing plan for the colorectal cancer patient; The second acquisition module 30 is used to acquire in real time the nursing data when the colorectal cancer patient is cared for according to the nursing plan; A reading module 40 is used to read the target data in the nursing target and calculate the nursing deviation between the nursing data and the target data; The adjustment module 50 is used to adjust the nursing plan based on the nursing deviation to obtain an optimized nursing plan, and continuously track the nursing status of the colorectal cancer patient based on the optimized nursing plan.

[0075] As described above, the colorectal cancer patient tracking and nursing system can implement the colorectal cancer patient tracking and nursing method.

[0076] In one embodiment, the above-mentioned parsing module 20 further includes: Acquire a training data set, wherein the training data set includes historical physiological data, historical nursing plans, and historical nursing results of historical colorectal cancer patients, wherein the historical physiological data includes historical basic physical sign data and historical medical examination data, the historical nursing plans are historical nursing measures taken according to the historical basic physical sign data and historical medical examination data, and the historical nursing results are historical nursing effects obtained according to the nursing measures; Importing the training data set into the decision tree model to be trained, wherein the historical basic vital sign data is the first root node, the historical nursing effect is the result-oriented endpoint, the historical nursing measures are decision nodes, and the decision nodes include leaf nodes at multiple levels; Calculate the entropy value between the first root node and the first leaf node according to the entropy calculation formula to obtain a first entropy value; When the first entropy value is greater than or equal to a preset threshold, the leaf nodes are pruned, and the leaf nodes corresponding to values ​​less than the preset threshold are retained; The historical medical examination data is a second root node, and the entropy value between the second root node and the second leaf node is calculated according to the entropy calculation formula to obtain a second entropy value; When the second entropy value is greater than or equal to the preset threshold, pruning the second leaf nodes, and retaining the second leaf nodes corresponding to values ​​less than the preset threshold; The entropy value between each root node and the leaf node of the corresponding level is recursively calculated, and the leaf nodes with entropy values ​​greater than or equal to the preset threshold are pruned until the result-oriented endpoint is reached, thereby obtaining a decision tree model capable of predicting the nursing standards and nursing plan performance of colorectal cancer patients.

[0077] In one embodiment, the above-mentioned parsing module 20 further includes: importing the physiological data into the decision tree model; In the decision tree model, the physiological data is taken as the starting node, and the nursing goal of the physiological data is taken as the end point. The nursing decision judgment is executed from the starting node to the end point to obtain a nursing plan corresponding to the nursing goal of the colorectal cancer patient, wherein the nursing plan includes a first nursing link that executes nursing measures based on the physiological data to produce nursing results.

[0078] In one embodiment, the reading module 40 further includes: Reading target data in the nursing target, and calculating a positive deviation and / or a negative deviation between the nursing data and the target data; Calculating the positive deviation based on a first deviation probability of the target data; and / or, The negative deviation is calculated based on a second deviation probability of the target data.

[0079] In one embodiment, the reading module 40 further includes: If there are complications in the nursing data when the colorectal cancer patient is cared for according to the nursing plan, the nursing data of the complications are recorded as special nursing data, and a preset value is assigned to the special nursing data; calculating an absolute average deviation probability of the first deviation probability and / or the second deviation probability; The absolute average deviation probability is multiplied by the preset value to obtain a third deviation probability of the special care data.

[0080] In one embodiment, the adjustment module 50 further includes: If any one of the first deviation probability, the second deviation probability and the third deviation probability is greater than or equal to a preset deviation probability, importing the nursing data into the decision tree model; In the decision tree model, the nursing data is taken as the initial node and the nursing goal is taken as the end point, and a nursing decision judgment is performed from the initial node to the end point to obtain a second nursing link that generates a corresponding nursing result by executing nursing measures based on the nursing data; Determining whether the first nursing link is consistent with the second nursing link; If they are inconsistent, the second care link will be used as the optimized care plan.

[0081] In one embodiment, the entropy calculation formula is:

[0082] in, H(X) represents the entropy of the random variable X; X represents a discrete random variable in a finite range; Represents the levels in the training data set; P i Represents the number of leaf nodes in the i-th layer in the training data set.

[0083] Reference Figure 3 The embodiment of the present invention further provides a computer device, the internal structure of which can be as follows Figure 3As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor designed for the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating device, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store relevant data on the tracking and nursing methods for colorectal cancer patients, etc. The network interface of the computer device is used to communicate with an external terminal through a network connection. Furthermore, the above-mentioned computer device can also be provided with an input device and a display screen, etc. When the above-mentioned computer program is executed by the processor to implement a method for tracking and caring for colorectal cancer patients, the method includes the following steps: obtaining physiological data of colorectal cancer patients, the physiological data including basic vital signs data and medical examination data of colorectal cancer patients; analyzing the physiological data to determine the care goals and care plans of the colorectal cancer patients; obtaining in real time the care data of the colorectal cancer patients when caring for them according to the care plans; reading the target data in the care goals, and calculating the care deviation between the care data and the target data; adjusting the care plan based on the care deviation to obtain an optimized care plan, and continuously tracking the care of the colorectal cancer patients based on the optimized care plan. Those skilled in the art will understand that Figure 3 The structure shown in is merely a block diagram of a portion of the structure related to the present application solution, and does not constitute a limitation on the computer device on which the present application solution is photographed.

[0084] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, a method for tracking and caring for colorectal cancer patients is implemented, including the following steps: obtaining physiological data of colorectal cancer patients, the physiological data including basic physical sign data and medical examination data of colorectal cancer patients; parsing the physiological data to determine the nursing goals and nursing plans of the colorectal cancer patients; obtaining in real time the nursing data when caring for the colorectal cancer patients according to the nursing plans; reading the target data in the nursing goals, and calculating the nursing deviation between the nursing data and the target data; adjusting the nursing plan based on the nursing deviation to obtain an optimized nursing plan, and continuously tracking the nursing situation of the colorectal cancer patients based on the optimized nursing plan. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0085] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0086] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0087] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for tracking and nursing colorectal cancer patients, characterized in that: include: Acquiring physiological data of colorectal cancer patients, wherein the physiological data includes basic physical sign data and medical examination data of colorectal cancer patients; Analyzing the physiological data to determine the nursing goal and nursing plan for the colorectal cancer patient; Real-time acquisition of nursing data when nursing the colorectal cancer patient according to the nursing plan; Reading target data in the nursing target, and calculating a nursing deviation between the nursing data and the target data; The nursing plan is adjusted based on the nursing deviation to obtain an optimized nursing plan, and the nursing status of the colorectal cancer patient based on the optimized nursing plan is continuously tracked.

2. A colorectal cancer patient tracking and nursing method according to claim 1, characterized in that: Before analyzing the physiological data to determine the nursing goal and nursing plan for the colorectal cancer patient, the method further includes: Acquire a training data set, wherein the training data set includes historical physiological data, historical nursing plans, and historical nursing results of historical colorectal cancer patients, wherein the historical physiological data includes historical basic physical sign data and historical medical examination data, the historical nursing plans are historical nursing measures taken according to the historical basic physical sign data and historical medical examination data, and the historical nursing results are historical nursing effects obtained according to the nursing measures; Importing the training data set into the decision tree model to be trained, wherein the historical basic vital sign data is the first root node, the historical nursing effect is the result-oriented endpoint, the historical nursing measures are decision nodes, and the decision nodes include leaf nodes at multiple levels; Calculate the entropy value between the first root node and the first leaf node according to the entropy calculation formula to obtain a first entropy value; When the first entropy value is greater than or equal to a preset threshold, the leaf nodes are pruned, and the leaf nodes corresponding to values ​​less than the preset threshold are retained; The historical medical examination data is a second root node, and the entropy value between the second root node and the second leaf node is calculated according to the entropy calculation formula to obtain a second entropy value; When the second entropy value is greater than or equal to the preset threshold, pruning the second leaf nodes, and retaining the second leaf nodes corresponding to values ​​less than the preset threshold; The entropy value between each root node and the leaf node of the corresponding level is recursively calculated, and the leaf nodes with entropy values ​​greater than or equal to the preset threshold are pruned until the result-oriented endpoint is reached, thereby obtaining a decision tree model capable of predicting the nursing standards and nursing plan performance of colorectal cancer patients.

3. A colorectal cancer patient tracking and nursing method according to claim 2, characterized in that: The step of analyzing the physiological data to determine the nursing goal and nursing plan for the colorectal cancer patient includes: importing the physiological data into the decision tree model; In the decision tree model, the physiological data is taken as the starting node, and the nursing goal of the physiological data is taken as the end point. The nursing decision judgment is executed from the starting node to the end point to obtain a nursing plan corresponding to the nursing goal of the colorectal cancer patient, wherein the nursing plan includes a first nursing link that executes nursing measures based on the physiological data to produce nursing results.

4. A colorectal cancer patient tracking and nursing method according to claim 3, characterized in that: The step of reading the target data in the nursing target and calculating the nursing deviation between the nursing data and the target data includes: Reading target data in the nursing target, and calculating a positive deviation and / or a negative deviation between the nursing data and the target data; Calculating the positive deviation based on a first deviation probability of the target data; and / or, The negative deviation is calculated based on a second deviation probability of the target data.

5. A colorectal cancer patient tracking and nursing method according to claim 4, characterized in that: The step of reading the target data in the nursing target and calculating the nursing deviation between the nursing data and the target data includes: If the nursing data shows that the colorectal cancer patient has malnutrition symptoms when being cared for according to the nursing plan, obtaining indicator measurement data of the malnutrition symptoms; Performing a nutritional risk assessment on the colorectal cancer patient according to the indicator measurement data in combination with the GLIM standard to obtain the nutritional level of the colorectal cancer patient, wherein the nutritional level includes a primary nutritional risk, a secondary nutritional risk, and a tertiary nutritional risk, wherein the primary nutritional risk is less than the secondary nutritional risk, which is less than the tertiary nutritional risk; If the nutritional level of the colorectal cancer patient is the first-level nutritional risk, the nursing deviation calculation of the indicator measurement data is not performed; If the nutritional level of the colorectal cancer patient is the secondary nutritional risk, assigning a first preset value to the secondary nutritional risk; or, If the nutritional level of the colorectal cancer patient is the third-level nutritional risk, a second preset value is assigned to the third-level nutritional risk, and the first preset value is greater than the second preset value; calculating an absolute average deviation probability of the first deviation probability and / or the second deviation probability; Multiplying the absolute average deviation probability by the first preset value to obtain a third deviation probability of the indicator measurement data; or, The absolute average deviation probability is multiplied by the second preset value to obtain a third deviation probability of the indicator measurement data.

6. A colorectal cancer patient tracking and nursing method according to claim 5, characterized in that: The step of adjusting the nursing plan based on the nursing deviation to obtain an optimized nursing plan includes: If any one of the first deviation probability, the second deviation probability and the third deviation probability is greater than or equal to a preset deviation probability, importing the nursing data into the decision tree model; In the decision tree model, the nursing data is taken as the initial node and the nursing goal is taken as the end point, and a nursing decision judgment is performed from the initial node to the end point to obtain a second nursing link that generates a corresponding nursing result by executing nursing measures based on the nursing data; Determining whether the first nursing link is consistent with the second nursing link; If they are inconsistent, the second care link will be used as the optimized care plan.

7. A colorectal cancer patient tracking and nursing method according to claim 2, characterized in that: The calculation formula of the entropy is: ； in, H(X) represents the entropy of the random variable X; X represents a discrete random variable in a finite range; Represents the levels in the training data set; P i Represents the number of leaf nodes in the i-th layer in the training data set.

8. A colorectal cancer patient tracking and nursing system, characterized in that: The system comprises: A first acquisition module is used to acquire physiological data of colorectal cancer patients, wherein the physiological data includes basic physical sign data and medical examination data of colorectal cancer patients; An analysis module, used to analyze the physiological data and determine the nursing goal and nursing plan for the colorectal cancer patient; A second acquisition module is used to acquire in real time the nursing data when the colorectal cancer patient is cared for according to the nursing plan; A reading module, used for reading target data in the nursing target, and calculating the nursing deviation between the nursing data and the target data; An adjustment module is used to adjust the nursing plan based on the nursing deviation to obtain an optimized nursing plan, and continuously track the nursing status of the colorectal cancer patient based on the optimized nursing plan.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of a method for tracking and caring for colorectal cancer patients as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for tracking and caring for colorectal cancer patients as described in any one of claims 1 to 7 are implemented.

Images