Rehabilitation management method and system for nausea and vomiting of tumor chemotherapy patient
The main control chip and neural network model predict the degree of vomiting in chemotherapy patients, and the simulated massage hands are controlled according to the vomiting rehabilitation management strategy model, which solves the problem of nausea and vomiting caused by chemotherapy drugs, and achieves accurate rehabilitation management, reducing the physical and mental harm of chemotherapy to patients.
Patent Information
- Application Number
- CN202510404932.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-02
- Publication Date
- 2025-07-18
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The symptoms of nausea and vomiting caused by chemotherapy drugs seriously affect the patient's nutritional status and quality of life, and may lead to fear and difficulty in insisting on subsequent treatment. It is difficult for the existing technology to accurately improve this problem.
The main control chip is combined with the neural network model, and the degree of vomiting is predicted by collecting the patient's attributes and physiological characteristics, and the massage technique, massage sequence, duration, strength and frequency are determined based on the pre-trained vomiting rehabilitation management strategy model, and the simulated massage hands are controlled to massage the Neiguan point of the patient's wrist.
Accurately prevent and improve the nausea and vomiting symptoms of malignant tumor patients after taking chemotherapy drugs, reduce the damage to the physical and mental health of chemotherapy drugs, improve the user experience, and save labor costs.
Smart Images
Figure CN120340756A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of medical technology, and particularly to a rehabilitation management method and system for nausea and vomiting in cancer chemotherapy patients. Background Art
[0002] Malignant tumors are a high-incidence disease. The occurrence of this disease is related to many complex factors such as environmental and lifestyle changes. Its lethality is high and the harm is great. It has become a major global public health problem, causing a heavy economic burden to society and families.
[0003] Currently, chemotherapy drugs can kill tumor cells in patients, thereby improving the survival rate of patients. However, at the same time, chemotherapy drugs will have many adverse effects on the users themselves, such as nausea and vomiting symptoms. The nausea and vomiting symptoms caused by chemotherapy drugs usually affect the patient's appetite. Insufficient food intake by the patient is likely to cause disorders of water and electrolyte and nutritional disorders, and severe vomiting may even cause mucosal damage in the esophagogastric cardia. In short, the nausea and vomiting after chemotherapy not only affect the patient's nutritional status and reduce their quality of life, but even cause the patient to have a fear of chemotherapy and be difficult to adhere to subsequent treatments, seriously endangering the physical and mental health of the patient. Therefore, how to accurately improve the nausea and vomiting symptoms caused by taking chemotherapy drugs in cancer patients to reduce the harm of chemotherapy drugs to the physical and mental health of patients is a problem to be solved at present. Summary of the Invention
[0004] This application provides a rehabilitation management method and system for nausea and vomiting in cancer chemotherapy patients, which is used to solve the problem of how to accurately improve the nausea and vomiting symptoms caused by taking chemotherapy drugs in cancer patients to reduce the harm of chemotherapy drugs to the physical and mental health of patients.
[0005] In a first aspect, this application provides a rehabilitation management method for nausea and vomiting in cancer chemotherapy patients, which is applied to a rehabilitation management system for nausea and vomiting in cancer chemotherapy patients. The system includes a patient sitting / lying area, a main control chip, a human-computer interaction screen, a wearable component, and a simulated massage hand. The method provided by this application includes:
[0006] The main control chip receives the patient attribute characteristics and patient identity information entered by the patient on the human-computer interaction screen. Among them, the patient attribute characteristics at least include patient age information, gender information, height information, and weight information;
[0007] The main control chip obtains the medication characteristics of chemotherapy drugs for malignant tumors associated with the patient identity information from the doctor terminal. Among them, the medication characteristics of chemotherapy drugs for malignant tumors at least include the drug type of each chemotherapy drug and the dosage corresponding to each drug type;
[0008] The main control chip receives the first patient physiological characteristics associated with the precursor of vomiting after a preset duration of the patient taking chemotherapy drugs collected by the wearable component, where the first patient physiological characteristics at least include electrogastrogram, respiratory rate, body temperature, heart rate, and blood pressure waveform;
[0009] The main control chip inputs the patient attribute characteristics, the medication characteristics of the chemotherapy drugs for malignant tumors, and the first patient physiological characteristics into the pre-trained first vomiting degree prediction model to predict the first vomiting degree of the patient. The first vomiting degree prediction model is obtained by training multiple first training samples input into the first neural network. Each first training sample includes historical patient attribute characteristics, historical patient medication characteristics of chemotherapy drugs for malignant tumors, historical patient first patient physiological characteristics, and the corresponding actual first vomiting degree of the historical patient;
[0010] The main control chip inputs the patient attribute characteristics and the first vomiting degree of the patient into the pre-trained vomiting rehabilitation management strategy model to determine various massage techniques for the Neiguan acupoint on the patient's wrist, the massage order of each massage technique, the massage duration of each massage technique, the massage intensity, and the massage frequency. The vomiting rehabilitation management strategy model is obtained by training multiple second training samples input into the second neural network. Each second training sample includes historical patient attribute characteristics, the first vomiting degree of the historical patient, and the corresponding massage order of each historical massage technique that can prevent the patient from vomiting, the historical massage duration of each historical massage technique, the historical massage intensity, and the historical massage frequency;
[0011] The main control chip controls the simulation massage hand to massage the Neiguan acupoint on the patient's wrist according to the determined massage order of each massage technique, the massage duration of each massage technique, the massage intensity, and the massage frequency to complete the nausea and vomiting rehabilitation management.
[0012] In some embodiments, before the main control chip inputs the patient attribute characteristics and the first vomiting degree of the patient into the pre-trained vomiting rehabilitation management strategy model to determine various massage techniques for the Neiguan acupoint on the patient's wrist, the massage order of each massage technique, the massage duration of each massage technique, the massage intensity, and the massage frequency, the method provided by the present application further includes:
[0013] Within a preset duration after the main control chip responds to the patient inputting the medication completion instruction, it receives the second patient physiological characteristics of the patient collected by the wearable component at multiple sampling time points. The second patient physiological characteristics at least include electrogastrogram, respiratory rate, body temperature, heart rate, and blood pressure waveform, where the interval duration between every two adjacent sampling time points is the same;
[0014] The main control chip converts the second patient physiological characteristics collected at each sampling time point into a second physiological characteristic space vector;
[0015] The main control chip obtains the standard third physiological characteristics at multiple sampling time points within a preset duration after the patient has taken medicine in the preset history and the standard vomiting degree of the patient's subsequent vomiting, converts the standard third physiological characteristics corresponding to each sampling time point into a third physiological characteristic space vector, and determines the Euclidean distance between the second physiological characteristic space vector and the third physiological characteristic space vector at the same sampling time point;
[0016] The main control chip determines the average Euclidean distance between the second physiological characteristic space vector and the third physiological characteristic space vector at each sampling time point;
[0017] The main control chip inputs the average Euclidean distance and the standard vomiting degree into a pre-trained second vomiting degree prediction model to obtain the second vomiting degree of the patient. The second vomiting degree prediction model is obtained by training multiple third training samples input into a third neural network. Each third training sample includes the historical average Euclidean distance, the historical standard vomiting degree, and the corresponding second vomiting degree of the historical patient;
[0018] The main control chip adjusts the first vomiting degree according to the second vomiting degree.
[0019] In some embodiments, the main control chip adjusts the first vomiting degree according to the second vomiting degree, including:
[0020] The main control chip adjusts the first vomiting degree according to the formula Q = αQ1 + βQ2, where α is a preset first adjustment coefficient, β is a preset second adjustment coefficient, Q1 is the first vomiting degree before adjustment, Q2 is the second vomiting degree before adjustment, and Q is the first vomiting degree after adjustment.
[0021] In some embodiments, before the main control chip obtains the medication characteristics of the chemotherapy drug for malignant tumors associated with the patient identity information from the doctor terminal, the method provided by the present application includes:
[0022] The main control chip obtains the vomiting frequency, vomiting duration, vomit characteristics, and electrolyte levels of multiple historical patients;
[0023] For each historical patient, the main control chip looks up the first vomiting degree score corresponding to the historical patient's vomiting frequency, the second vomiting degree score corresponding to the vomiting duration, the third vomiting degree score corresponding to the vomit characteristics, and the fourth vomit score corresponding to the electrolyte level;
[0024] The main control chip sums up the first vomiting degree score, the second vomiting degree score, the third vomiting degree score, and the fourth vomiting degree score to obtain a comprehensive vomiting degree score, and uses the comprehensive vomiting degree score as the actual first vomiting degree of the historical patient.
[0025] In some embodiments, the second training sample further includes the amount of ginger taken by historical patients.
[0026] The main control chip inputs the patient attribute characteristics and the patient's first vomiting degree into the pre-trained vomiting rehabilitation management strategy model to determine various massage techniques for the Neiguan acupoint on the patient's wrist, the massage sequence of each massage technique, the massage duration of each massage technique, the massage intensity, and the massage frequency, including:
[0027] The main control chip inputs the patient attribute characteristics and the patient's first vomiting degree into the pre-trained vomiting rehabilitation management strategy model to determine the amount of ginger the patient needs to take, various massage techniques for the Neiguan acupoint on the patient's wrist, the massage sequence of each massage technique, the massage duration of each massage technique, the massage intensity, and the massage frequency.
[0028] In a second aspect, the present application further provides a rehabilitation management system for nausea and vomiting in cancer chemotherapy patients, including a patient sitting / lying area, a main control chip, a human-computer interaction screen, a wearable component, and a simulated massage hand. The main control chip is embedded in the patient sitting / lying area, and the human-computer interaction screen, the wearable component, and the simulated massage hand are all arranged on one side of the patient sitting / lying area. The main control chip is used for:
[0029] Receiving the patient attribute characteristics and the patient identity information entered by the patient on the human-computer interaction screen, where the patient attribute characteristics at least include the patient's age information, gender information, height information, and weight information;
[0030] Obtaining from the doctor terminal the medication characteristics of the chemotherapy drugs for malignant tumors associated with the patient identity information, where the medication characteristics of the chemotherapy drugs for malignant tumors at least include the drug type of each chemotherapy drug and the dosage corresponding to each drug type;
[0031] Receiving the first patient physiological characteristics associated with the vomiting precursor after the patient has taken the chemotherapy drugs for a preset duration collected by the wearable component, where the first patient physiological characteristics at least include electrogastrogram, respiratory rate, body temperature, heart rate, and blood pressure waveform;
[0032] Inputting the patient attribute characteristics, the medication characteristics of the chemotherapy drugs for malignant tumors, and the first patient physiological characteristics into the pre-trained first vomiting degree prediction model to predict the patient's first vomiting degree, where the first vomiting degree prediction model is obtained by training a plurality of first training samples into a first neural network, and each first training sample includes historical patient attribute characteristics, the medication characteristics of the chemotherapy drugs for malignant tumors of the historical patient, the first patient physiological characteristics of the historical patient, and the actual first vomiting degree of the corresponding historical patient;
[0033] Input the patient attribute characteristics and the first vomiting degree of the patient into the pre-trained vomiting rehabilitation management strategy model to determine various massage techniques for the Neiguan acupoint on the patient's wrist, the massage sequence of each massage technique, the massage duration, massage intensity, and massage frequency of each massage technique. Among them, the vomiting rehabilitation management strategy model is obtained by training multiple second training samples into a second neural network. Each second training sample includes historical patient attribute characteristics, the first vomiting degree of the historical patient, and the massage sequence of each historical massage technique that can prevent the patient from vomiting, the historical massage duration of each historical massage technique, historical massage intensity, and historical massage frequency;
[0034] According to the determined massage sequence of each massage technique, the massage duration, massage intensity, and massage frequency of each massage technique, control the simulation massage hand to massage the Neiguan acupoint on the patient's wrist to complete the nausea and vomiting rehabilitation management.
[0035] In some embodiments, the main control chip is further configured to:
[0036] Within a preset duration after responding to the patient's input of the medicine-taking completion instruction, receive the second patient physiological characteristics of the patient collected by the wearable component at multiple sampling time points. The second patient physiological characteristics at least include electrogastrogram, respiratory rate, body temperature, heart rate, and blood pressure waveform. Among them, the interval duration between every two adjacent sampling time points is the same;
[0037] Convert the second patient physiological characteristics collected at each sampling time point into a second physiological characteristic space vector;
[0038] Obtain the standard third physiological characteristics of the patient at multiple sampling time points within the preset duration after taking medicine in history and the corresponding standard vomiting degree of the patient's subsequent vomiting, convert the standard third physiological characteristics corresponding to each sampling time point into a third physiological characteristic space vector, and determine the Euclidean distance between the second physiological characteristic space vector and the third physiological characteristic space vector at the same sampling time point;
[0039] The main control chip determines the average Euclidean distance between the second physiological characteristic space vector and the third physiological characteristic space vector at each sampling time point;
[0040] Input the average Euclidean distance and the standard vomiting degree into the pre-trained second vomiting degree prediction model to obtain the second vomiting degree of the patient. Among them, the second vomiting degree prediction model is obtained by training multiple third training samples into a third neural network. Among them, each third training sample includes the historical average Euclidean distance, historical standard vomiting degree, and the corresponding second vomiting degree of the historical patient;
[0041] Adjust the first vomiting degree according to the second vomiting degree.
[0042] In some embodiments, the main control chip is specifically configured to:
[0043] Adjust according to the first vomiting degree.
[0044] In some embodiments, the main control chip is further configured to
[0045] Obtain the vomiting frequency, vomiting duration, vomitus characteristics, and electrolyte levels of multiple historical patients;
[0046] For each historical patient, find the first vomiting degree score corresponding to the vomiting frequency of the historical patient, the second vomiting degree score corresponding to the vomiting duration, the third vomiting degree score corresponding to the vomitus characteristics, and the fourth vomitus score corresponding to the electrolyte level;
[0047] Sum up the first vomiting degree score, the second vomiting degree score, the third vomiting degree score, and the fourth vomiting degree score to obtain a comprehensive vomiting degree score, and use the comprehensive vomiting degree score as the actual first vomiting degree of the historical patient.
[0048] In some embodiments, the second training sample further includes the ginger intake of historical patients, and the main control chip is specifically configured to:
[0049] Input the patient attribute characteristics and the first vomiting degree of the patient into the pre-trained vomiting rehabilitation management strategy model to determine the amount of ginger the patient needs to take, the various massage techniques for the Neiguan acupoint on the patient's wrist, the massage sequence of each massage technique, the massage duration, massage intensity, and massage frequency of each massage technique.
[0050] This application provides a rehabilitation management method and system for nausea and vomiting in tumor chemotherapy patients. The main control chip can input the patient attribute characteristics, the medication characteristics of the chemotherapy drugs for malignant tumors, and the first patient physiological characteristics into the pre-trained first vomiting degree prediction model to predict the first vomiting degree of the patient. Since the first vomiting degree prediction model is obtained by training multiple first training samples into the first neural network, and each first training sample includes the historical patient attribute characteristics, the medication characteristics of the chemotherapy drugs for malignant tumors of the historical patient, the first patient physiological characteristics of the historical patient, and the corresponding actual first vomiting degree of the historical patient, the accuracy of the predicted first vomiting degree of the patient is high.
[0051] The main control chip inputs the patient attribute characteristics and the first vomiting degree of the patient into the pre-trained vomiting rehabilitation management strategy model to determine various massage techniques for the Neiguan acupoint on the patient's wrist, the massage sequence of each massage technique, the massage duration, massage intensity, and massage frequency of each massage technique. Further, since the vomiting rehabilitation management strategy model is obtained by training multiple second training samples input into the second neural network, each second training sample includes historical patient attribute characteristics, the first vomiting degree of the historical patient, and the massage sequence of each historical massage technique that can prevent the patient from vomiting, the historical massage duration of each historical massage technique, the historical massage intensity, and the historical massage frequency. Therefore, the accuracy of determining various massage techniques for the Neiguan acupoint on the patient's wrist, the massage sequence of each massage technique, the massage duration, massage intensity, and massage frequency of each massage technique is also high. Finally, the main control chip controls the simulation massage hand to massage the Neiguan acupoint on the patient's wrist according to the determined massage sequence of each massage technique, the massage duration, massage intensity, and massage frequency of each massage technique to complete the nausea and vomiting rehabilitation management. In this way, it is possible to accurately prevent and improve the nausea and vomiting symptoms caused by chemotherapy drugs in cancer patients, reduce the harm of chemotherapy drugs to the physical and mental health of patients, and without relying on doctors, improve the patient's usage experience and save labor costs. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.
[0053] Figure 1 FIG. is a schematic structural diagram of a rehabilitation management system for nausea and vomiting in cancer chemotherapy patients provided by an embodiment of the present application;
[0054] Figure 2 FIG. is a flowchart of a rehabilitation management method for nausea and vomiting in cancer chemotherapy patients provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0055] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments of the present application, all other embodiments made by those of ordinary skill in the art under the inspiration of this embodiment belong to the scope of protection of the present application.
[0056] An embodiment of the present application provides a rehabilitation management method for nausea and vomiting in cancer chemotherapy patients, which is applied to a rehabilitation management system for nausea and vomiting in cancer chemotherapy patients. As Figure 1 shown, the rehabilitation management system for nausea and vomiting in cancer chemotherapy patients includes a patient sitting / lying area 101, a main control chip 102, a human-computer interaction screen 103, a wearable component 104, and a simulation massage hand 105. The main control chip 102 is embedded in the patient sitting / lying area 101, and the human-computer interaction screen 103, the wearable component 104, and the simulation massage hand 105 are all arranged on one side of the patient sitting / lying area 101. As Figure 2 shown, the method provided by the embodiment of the present application includes:
[0057] S201: The main control chip 102 receives the patient attribute characteristics and patient identity information entered by the patient on the human-computer interaction screen 103.
[0058] Among them, the patient attribute characteristics at least include patient age information, gender information, height information, and weight information.
[0059] S202: The main control chip 102 obtains the medication characteristics of chemotherapy drugs for malignant tumors associated with the patient identity information from the doctor terminal.
[0060] Among them, the medication characteristics of chemotherapy drugs for malignant tumors at least include the drug type of each chemotherapy drug and the dosage corresponding to each drug type.
[0061] For example, the drug types of chemotherapy drugs can include cyclophosphamide, carmustine, or lomustine, etc., and the dosage of chemotherapy drugs for each drug type is used according to the doctor's advice.
[0062] S203: The main control chip 102 receives the first patient physiological characteristics associated with the precursor of vomiting after the patient has taken chemotherapy drugs for a preset duration, collected from the wearable component 104.
[0063] Among them, the first patient physiological characteristics at least include electrogastrogram, respiratory rate, body temperature, heart rate, and blood pressure waveform.
[0064] Exemplarily, the wearable component 104 can include multiple electrodes for collecting electrogastrogram (such as including recording electrodes, reference electrodes, and grounding electrodes) and an electrogastrogram recorder, a respiratory inductive plethysmograph for collecting respiratory rate, a thermometer for collecting body temperature, a heart rate acquisition module for collecting heart rate, and a sphygmomanometer for collecting blood pressure waveform.
[0065] S204: The main control chip 102 inputs the patient attribute characteristics, the medication characteristics of chemotherapy drugs for malignant tumors, and the first patient physiological characteristics into a pre-trained first vomiting degree prediction model to predict the first vomiting degree of the patient.
[0066] Among them, the first vomiting degree prediction model is obtained by training multiple first training samples in a first neural network. Each first training sample includes historical patient attribute features, the medication characteristics of the historical patient for chemotherapy drugs for malignant tumors, the first physiological characteristics of the historical patient, and the actual first vomiting degree of the corresponding historical patient.
[0067] The first vomiting degree can characterize the vomiting frequency, vomiting duration, vomitus characteristics, and electrolyte levels of the vomiting that the patient may experience subsequently.
[0068] For example, the sum of the first vomiting degree score corresponding to the vomiting frequency, the second vomiting degree score corresponding to the vomiting duration, the third vomiting degree score corresponding to the vomitus characteristics, and the fourth vomitus score corresponding to the electrolyte levels is obtained to get the comprehensive vomiting degree score, and the comprehensive vomiting degree score is used as the actual first vomiting degree of the historical patient. For example, if the first vomiting degree score is 2 points, the second vomiting degree score is 2 points, the third vomiting degree score is 1 point, and the fourth vomiting degree score is 3 points, then the obtained comprehensive vomiting degree score is 8 points.
[0069] S205: The main control chip 102 inputs the patient attribute features and the first vomiting degree of the patient into the pre-trained vomiting rehabilitation management strategy model to determine various massage techniques for the Neiguan acupoint on the patient's wrist, the massage sequence of each massage technique, the massage duration of each massage technique, the massage strength, and the massage frequency.
[0070] Among them, the vomiting rehabilitation management strategy model is obtained by training multiple second training samples in a second neural network. Each second training sample includes historical patient attribute features, the first vomiting degree of the historical patient, and the massage sequence of each historical massage technique that can avoid the patient's vomiting, the historical massage duration of each historical massage technique, the historical massage strength, and the historical massage frequency. It can be understood that different patient attribute features and the first vomiting degree of the patient correspond to different massage techniques for the Neiguan acupoint on the patient's wrist, the massage sequence of each massage technique, the massage duration of each massage technique, the massage strength, and the massage frequency.
[0071] S206: The main control chip 102 controls the simulation massage hand 105 to massage the Neiguan acupoint on the patient's wrist according to the determined massage sequence of each massage technique, the massage duration of each massage technique, the massage strength, and the massage frequency to complete the nausea and vomiting rehabilitation management.
[0072] Exemplarily, in some embodiments, the second training sample further includes the ginger intake of historical patients. S206 can be specifically implemented as the main control chip 102 inputting the patient attribute features and the first vomiting degree of the patient into the pre-trained vomiting rehabilitation management strategy model to determine the amount of ginger the patient needs to take, the various massage techniques for the Neiguan acupoint on the patient's wrist, the massage sequence of each massage technique, the massage duration of each massage technique, the massage intensity, and the massage frequency. In this way, the anti-vomiting treatment method that combines pressing the Neiguan acupoint and eating ginger can more accurately improve the patient's nausea and vomiting symptoms.
[0073] In summary, for a rehabilitation management method for nausea and vomiting in cancer chemotherapy patients provided by an embodiment of the present application, the main control chip 102 can input the patient attribute features, the medication characteristics of the chemotherapy drugs for malignant tumors, and the first physiological characteristics of the first patient into the pre-trained first vomiting degree prediction model to predict the first vomiting degree of the patient. Since the first vomiting degree prediction model is obtained by training multiple first training samples input into the first neural network, and each first training sample includes historical patient attribute features, the medication characteristics of the chemotherapy drugs for malignant tumors of the historical patient, the first physiological characteristics of the historical patient, and the actual first vomiting degree of the corresponding historical patient, the accuracy of the predicted first vomiting degree of the patient is high.
[0074] The main control chip 102 inputs the patient attribute features and the first vomiting degree of the patient into the pre-trained vomiting rehabilitation management strategy model to determine the various massage techniques for the Neiguan acupoint on the patient's wrist, the massage sequence of each massage technique, the massage duration of each massage technique, the massage intensity, and the massage frequency. Further, since the vomiting rehabilitation management strategy model is obtained by training multiple second training samples input into the second neural network, and each second training sample includes historical patient attribute features, the first vomiting degree of the historical patient, and the massage sequence of each historical massage technique that can prevent the patient from vomiting, the historical massage duration of each historical massage technique, the historical massage intensity, and the historical massage frequency. Therefore, the accuracy of the determined various massage techniques for the Neiguan acupoint on the patient's wrist, the massage sequence of each massage technique, the massage duration of each massage technique, the massage intensity, and the massage frequency is also high. Finally, the main control chip 102 controls the simulation massage hand 105 to massage the Neiguan acupoint on the patient's wrist according to the determined massage sequence of each massage technique, the massage duration of each massage technique, the massage intensity, and the massage frequency to complete the nausea and vomiting rehabilitation management. In this way, it can accurately prevent and improve the nausea and vomiting symptoms caused by cancer patients taking chemotherapy drugs, reduce the harm of chemotherapy drugs to the physical and mental health of patients, and without relying on doctors, improve the patient's usage experience and save labor costs.
[0075] In some embodiments, before S205, the method provided by the embodiments of the present application may further include:
[0076] Step 1: Within a preset duration after the master control chip 102 responds to the patient's input to complete the medication-taking instruction, the master control chip 102 receives the second physiological characteristics of the patient collected by the wearable component 104 at multiple sampling time points.
[0077] The second physiological characteristics of the patient at least include electrogastrogram, respiratory rate, body temperature, heart rate, and blood pressure waveform, wherein the interval duration between every two adjacent sampling time points is the same.
[0078] Step 2: The master control chip 102 converts the second physiological characteristics of the patient collected at each sampling time point into a second physiological characteristic space vector.
[0079] Step 3: The master control chip 102 obtains the standard third physiological characteristics of the patient at multiple sampling time points within a preset duration after the patient completes taking the medicine in the preset history and the corresponding standard vomiting degree of the patient after vomiting, converts the standard third physiological characteristics corresponding to each sampling time point into a third physiological characteristic space vector, and determines the Euclidean distance between the second physiological characteristic space vector and the third physiological characteristic space vector at the same sampling time point.
[0080] Step 4: The master control chip 102 determines the average Euclidean distance between the second physiological characteristic space vector and the third physiological characteristic space vector at each sampling time point.
[0081] Exemplarily, the master control chip 102 determines the average Euclidean distance between the second physiological characteristic space vector and the third physiological characteristic space vector at each sampling time point according to the formula where d1 is the Euclidean distance between the second physiological characteristic space vector and the third physiological characteristic space vector at the first sampling time point, d2 is the Euclidean distance between the second physiological characteristic space vector and the third physiological characteristic space vector at the second sampling time point, d3 is the Euclidean distance between the second physiological characteristic space vector and the third physiological characteristic space vector at the third sampling time point, d
[0082] is the Euclidean distance between the second physiological characteristic space vector and the third physiological characteristic space vector at the nth sampling time point, n is the total number of sampling time points within the preset duration, n is the average Euclidean distance. is the average Euclidean distance.
[0083] Step 5: The main control chip 102 inputs the average Euclidean distance and the standard vomiting degree into a pre-trained second vomiting degree prediction model to obtain the second vomiting degree of the patient. The second vomiting degree prediction model is obtained by training a third neural network with multiple third training samples. Each third training sample includes a historical average Euclidean distance, a historical standard vomiting degree, and the corresponding second vomiting degree of the historical patient. It can be understood that the average Euclidean distance represents the similarity degree between the second physiological feature space vector and the third physiological feature space vector. The higher the similarity degree, the more similar the patient's vomiting degree is to the standard vomiting degree. On the contrary, the lower the similarity degree, the less similar the patient's vomiting degree is to the standard vomiting degree. Therefore, the reliability of the second vomiting degree determined by the average Euclidean distance and the standard vomiting degree is also high.
[0084] Step 6: The main control chip 102 adjusts the first vomiting degree according to the second vomiting degree.
[0085] In this way, a more accurate first vomiting degree can be obtained.
[0086] Specifically, the main control chip 102 can adjust the first vomiting degree according to the formula Q = αQ1 + βQ2, where α is a preset first adjustment coefficient, β is a preset second adjustment coefficient, Q1 is the first vomiting degree before adjustment, Q2 is the second vomiting degree before adjustment, and Q is the first vomiting degree after adjustment. For example, α = 0.4, β = 0.6; or α = 0.6, β = 0.4.
[0087] It can be understood that a more accurate first vomiting degree can be obtained based on the above steps 1 - 6.
[0088] In some embodiments, before S201, the method provided by the embodiments of the present application includes:
[0089] Step A: The main control chip 102 obtains the vomiting frequency, vomiting duration, vomit characteristics, and electrolyte levels of multiple historical patients.
[0090] Step B: For each historical patient, the main control chip 102 looks up the first vomiting degree score corresponding to the vomiting frequency of the historical patient, the second vomiting degree score corresponding to the vomiting duration, the third vomiting degree score corresponding to the vomit characteristics, and the fourth vomit score corresponding to the electrolyte levels.
[0091] Step C: The main control chip 102 sums up the first vomiting degree score, the second vomiting degree score, the third vomiting degree score, and the fourth vomiting degree score to obtain a comprehensive vomiting degree score, and uses the comprehensive vomiting degree score as the actual first vomiting degree of the historical patient.
[0092] Understandably, through the above steps A - C, the actual first vomiting degree of historical patients can be determined more precisely.
[0093] In addition, still refer to Figure 1 , the embodiment of the present application also provides a rehabilitation management system for nausea and vomiting in tumor chemotherapy patients. It should be noted that the basic principle and technical effects of the cardiovascular and cerebrovascular rehabilitation intelligent assistance system provided in the embodiment of the present application are the same as those of the above embodiment. For a brief description, for the parts not mentioned in the embodiment of the present application, reference can be made to the corresponding content in the above embodiment. The rehabilitation management system for nausea and vomiting in tumor chemotherapy patients includes a patient sitting and lying area 101, a main control chip 102, a human - machine interaction screen 103, a wearable component 104, and a simulation massage hand 105. The main control chip 102 is embedded in the patient sitting and lying area 101, and the human - machine interaction screen 103, the wearable component 104, and the simulation massage hand 105 are all arranged on one side of the patient sitting and lying area 101. The main control chip 102 is used for:
[0094] Receiving the patient attribute characteristics and patient identity information entered by the patient on the human - machine interaction screen 103, where the patient attribute characteristics at least include patient age information, gender information, height information, and weight information;
[0095] Obtaining the medication characteristics of chemotherapy drugs for malignant tumors associated with the patient identity information from the doctor terminal, where the medication characteristics of chemotherapy drugs for malignant tumors at least include the drug type of each chemotherapy drug and the dosage corresponding to each drug type;
[0096] Receiving the first patient physiological characteristics associated with the vomiting precursor after a preset duration of taking chemotherapy drugs by the patient collected by the wearable component 104, where the first patient physiological characteristics at least include electrogastrogram, respiratory rate, body temperature, heart rate, and blood pressure waveform;
[0097] Inputting the patient attribute characteristics, the medication characteristics of chemotherapy drugs for malignant tumors, and the first patient physiological characteristics into a pre - trained first vomiting degree prediction model to predict the first vomiting degree of the patient, where the first vomiting degree prediction model is obtained by training multiple first training samples into a first neural network, and each first training sample includes historical patient attribute characteristics, historical patient medication characteristics of chemotherapy drugs for malignant tumors, historical patient first patient physiological characteristics, and the corresponding actual first vomiting degree of the historical patient;
[0098] Input the patient attribute characteristics and the first vomiting degree of the patient into the pre-trained vomiting rehabilitation management strategy model to determine various massage techniques for the Neiguan acupoint on the patient's wrist, the massage sequence of each massage technique, the massage duration, massage intensity, and massage frequency of each massage technique. Among them, the vomiting rehabilitation management strategy model is obtained by training multiple second training samples input into the second neural network. Each second training sample includes historical patient attribute characteristics, the first vomiting degree of the historical patient, and the massage sequence of each historical massage technique that can prevent the patient from vomiting, the historical massage duration of each historical massage technique, historical massage intensity, and historical massage frequency;
[0099] According to the determined massage sequence of each massage technique, the massage duration, massage intensity, and massage frequency of each massage technique, control the simulation massage hand 105 to massage the Neiguan acupoint on the patient's wrist to complete the nausea and vomiting rehabilitation management.
[0100] In some embodiments, the main control chip 102 is further configured to:
[0101] Within a preset duration after responding to the patient's input of the medicine-taking completion instruction, receive the second patient physiological characteristics of the patient collected by the wearable component 104 at multiple sampling time points. The second patient physiological characteristics at least include electrogastrogram, respiratory rate, body temperature, heart rate, and blood pressure waveform. Among them, the interval duration between every two adjacent sampling time points is the same;
[0102] Convert the second patient physiological characteristics collected at each sampling time point into a second physiological characteristic space vector;
[0103] Obtain the standard third physiological characteristics of the patient at multiple sampling time points within a preset duration after taking medicine in history and the corresponding standard vomiting degree of the patient's subsequent vomiting, convert the standard third physiological characteristics corresponding to each sampling time point into a third physiological characteristic space vector, and determine the Euclidean distance between the second physiological characteristic space vector and the third physiological characteristic space vector at the same sampling time point;
[0104] Determine the average Euclidean distance between the second physiological characteristic space vector and the third physiological characteristic space vector at each sampling time point;
[0105] Input the average Euclidean distance and the standard vomiting degree into the pre-trained second vomiting degree prediction model to obtain the second vomiting degree of the patient. Among them, the second vomiting degree prediction model is obtained by training multiple third training samples input into the third neural network. Among them, each third training sample includes historical average Euclidean distance, historical standard vomiting degree, and the corresponding second vomiting degree of the historical patient;
[0106] Adjust the first vomiting degree according to the second vomiting degree.
[0107] In some embodiments, the main control chip 102 is specifically configured to determine the average Euclidean distance between the second physiological feature space vector and the third physiological feature space vector at each sampling time point according to the arithmetic formula where d1 is the Euclidean distance between the second physiological feature space vector and the third physiological feature space vector at the first sampling time point, d2 is the Euclidean distance between the second physiological feature space vector and the third physiological feature space vector at the second sampling time point, d3 is the Euclidean distance between the second physiological feature space vector and the third physiological feature space vector at the third sampling time point, and d n is the Euclidean distance between the second physiological feature space vector and the third physiological feature space vector at the nth sampling time point, and n is the total number of sampling time points within the preset duration, is the average Euclidean distance.
[0108] In some embodiments, the main control chip 102 is specifically configured to:
[0109] Adjust the first vomiting degree according to the arithmetic formula Q = αQ1 + βQ2, where α is a preset first adjustment coefficient, β is a preset second adjustment coefficient, Q1 is the first vomiting degree before adjustment, q2 is the second vomiting degree before adjustment, and q is the first vomiting degree after adjustment.
[0110] In some embodiments, the main control chip 102 is further configured to
[0111] Obtain the vomiting frequency, vomiting duration, vomitus characteristics, and electrolyte levels of multiple historical patients;
[0112] For each historical patient, find the first vomiting degree score corresponding to the vomiting frequency of the historical patient, the second vomiting degree score corresponding to the vomiting duration, the third vomiting degree score corresponding to the vomitus characteristics, and the fourth vomitus score corresponding to the electrolyte level;
[0113] Sum the first vomiting degree score, the second vomiting degree score, the third vomiting degree score, and the fourth vomiting degree score to obtain a comprehensive vomiting degree score, and use the comprehensive vomiting degree score as the actual first vomiting degree of the historical patient.
[0114] In some embodiments, the second training sample further includes the ginger intake of historical patients, and the main control chip 102 is specifically configured to:
[0115] Input the patient attribute characteristics and the first vomiting degree of the patient into the pre-trained vomiting rehabilitation management strategy model to determine the amount of ginger that the patient needs to take, the various massage techniques for the Neiguan acupoint on the patient's wrist, the massage sequence of each massage technique, the massage duration, massage intensity, and massage frequency of each massage technique.
[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.
Claims
1. A rehabilitation management method for nausea and vomiting in cancer chemotherapy patients, characterized in that, A rehabilitation management system for nausea and vomiting in cancer chemotherapy patients. The system includes a patient sitting / lying area, a main control chip, a human-computer interaction screen, a wearable component, and a simulation massage hand. The method includes: The main control chip receives the patient attribute characteristics and patient identity information entered by the patient on the human-computer interaction screen; The main control chip obtains the medication characteristics of the chemotherapy drugs for malignant tumors associated with the patient identity information from the doctor terminal; The main control chip receives the first patient physiological characteristics associated with the precursor of vomiting from the wearable component after the patient has taken the chemotherapy drugs for a preset duration; The main control chip inputs the patient attribute characteristics, the medication characteristics of the chemotherapy drugs for malignant tumors, and the first patient physiological characteristics into a pre-trained first vomiting degree prediction model to predict the first vomiting degree of the patient. Among them, the first vomiting degree prediction model is obtained by training multiple first training samples into a first neural network. Each first training sample includes historical patient attribute characteristics, the medication characteristics of the chemotherapy drugs for malignant tumors of the historical patient, the first patient physiological characteristics of the historical patient, and the actual first vomiting degree of the corresponding historical patient; The main control chip inputs the patient attribute characteristics and the first vomiting degree of the patient into a pre-trained vomiting rehabilitation management strategy model to determine various massage techniques for the Neiguan acupoint on the patient's wrist, the massage order of each massage technique, the massage duration, massage intensity, and massage frequency of each massage technique; The main control chip controls the simulation massage hand to massage the Neiguan acupoint on the patient's wrist according to the determined massage order of each massage technique, the massage duration, massage intensity, and massage frequency of each massage technique to complete the rehabilitation management of nausea and vomiting.
2. The method according to claim 1, wherein Before the main control chip inputs the patient attribute characteristics and the first vomiting degree of the patient into a pre-trained vomiting rehabilitation management strategy model to determine various massage techniques for the Neiguan acupoint on the patient's wrist, the massage order of each massage technique, the massage duration, massage intensity, and massage frequency of each massage technique, the method further includes: The main control chip receives the second patient physiological characteristics of the patient collected by the wearable component at multiple sampling time points within the preset duration after responding to the patient's input of the medication completion instruction; The main control chip converts the second patient physiological characteristics collected at each sampling time point into a second physiological characteristic space vector; The main control chip obtains the standard third physiological characteristics of the patient at multiple sampling time points within the preset duration after taking the medicine in history and the corresponding standard vomiting degree of the patient when vomiting occurs later, converts the standard third physiological characteristics corresponding to each sampling time point into a third physiological characteristic space vector, and determines the Euclidean distance between the second physiological characteristic space vector and the third physiological characteristic space vector at the same sampling time point; The master control chip determines the average Euclidean distance between the second physiological feature space vector and the third physiological feature space vector at each sampling time point; The master control chip inputs the average Euclidean distance and the standard vomiting degree into a pre-trained second vomiting degree prediction model to obtain the second vomiting degree of the patient. The second vomiting degree prediction model is obtained by training a third neural network with a plurality of third training samples. Each third training sample includes a historical average Euclidean distance, a historical standard vomiting degree, and the second vomiting degree of the corresponding historical patient; The master control chip adjusts the first vomiting degree according to the second vomiting degree.
3. The method according to claim 2, wherein The master control chip adjusts the first vomiting degree according to the second vomiting degree, including: The master control chip adjusts the first vomiting degree according to the formula Q = αQ1 + βQ2, where α is a preset first adjustment coefficient, β is a preset second adjustment coefficient, Q1 is the first vomiting degree before adjustment, Q2 is the second vomiting degree before adjustment, and Q is the first vomiting degree after adjustment.
4. The method according to claim 1, characterized in that, Before the master control chip obtains the medication characteristics of the chemotherapy drug for malignant tumors associated with the patient identity information from the doctor terminal, the method includes: The master control chip obtains the vomiting frequency, vomiting duration, vomit characteristics, and electrolyte levels of a plurality of historical patients; For each historical patient, the master control chip looks up the first vomiting degree score corresponding to the vomiting frequency of the historical patient, the second vomiting degree score corresponding to the vomiting duration, the third vomiting degree score corresponding to the vomit characteristics, and the fourth vomit score corresponding to the electrolyte level; The master control chip sums up the first vomiting degree score, the second vomiting degree score, the third vomiting degree score, and the fourth vomiting degree score to obtain a comprehensive vomiting degree score, and uses the comprehensive vomiting degree score as the actual first vomiting degree of the historical patient.
5. The method according to any one of claims 1-4, characterized in that The second training sample further includes the ginger intake of the historical patient, The master control chip inputs the patient attribute characteristics and the first vomiting degree of the patient into a pre-trained vomiting rehabilitation management strategy model to determine various massage techniques for the Neiguan acupoint on the patient's wrist, the massage sequence of each massage technique, the massage duration of each massage technique, the massage intensity, and the massage frequency, including: The master control chip inputs the patient attribute characteristics and the first vomiting degree of the patient into a pre-trained vomiting rehabilitation management strategy model to determine the amount of ginger the patient needs to take, various massage techniques for the Neiguan acupoint on the patient's wrist, the massage sequence of each massage technique, the massage duration of each massage technique, the massage intensity, and the massage frequency.
6. A rehabilitation management system for nausea and vomiting in tumor chemotherapy patients, characterized in that, The system includes a patient sitting / lying area, a master control chip, a human-computer interaction screen, a wearable component, and a simulation massage hand. The master control chip is embedded in the patient sitting / lying area, and the human-computer interaction screen, the wearable component, and the simulation massage hand are all arranged on one side of the patient sitting / lying area. The master control chip is used for: Receive the patient attribute characteristics and patient identity information entered by the patient on the human-computer interaction screen; Obtain the medication characteristics of chemotherapy drugs for malignant tumors associated with the patient identity information from the doctor terminal; Receive the first patient physiological characteristics associated with the precursor of vomiting after the patient has taken the chemotherapy drug for a preset duration, collected by the wearable component; Input the patient attribute characteristics, the medication characteristics of the chemotherapy drugs for malignant tumors, and the first patient physiological characteristics into a pre-trained first vomiting degree prediction model to predict the first vomiting degree of the patient. Among them, the first vomiting degree prediction model is obtained by training multiple first training samples into a first neural network. Each first training sample includes historical patient attribute characteristics, the medication characteristics of the historical patient's chemotherapy drugs for malignant tumors, the first patient physiological characteristics of the historical patient, and the corresponding actual first vomiting degree of the historical patient; Input the patient attribute characteristics and the first vomiting degree of the patient into a pre-trained vomiting rehabilitation management strategy model to determine various massage techniques for the Neiguan acupoint on the patient's wrist, the massage order of each massage technique, the massage duration of each massage technique, the massage strength, and the massage frequency; Control the simulated massage hand to massage the Neiguan acupoint on the patient's wrist according to the determined massage order of each massage technique, the massage duration of each massage technique, the massage strength, and the massage frequency to complete the rehabilitation management of nausea and vomiting.
7. The system according to claim 6, wherein The main control chip is further used for: Within the preset duration after responding to the patient's input of the medication completion instruction, receive the second patient physiological characteristics of the patient collected by the wearable component at multiple sampling time points, where the interval duration between every two adjacent sampling time points is the same; Convert the second patient physiological characteristics collected at each sampling time point into a second physiological characteristic space vector; Obtain the standard third physiological characteristics of the patient at multiple sampling time points within the preset duration after taking the medication in history and the corresponding standard vomiting degree of the patient's subsequent vomiting, convert the standard third physiological characteristics corresponding to each sampling time point into a third physiological characteristic space vector, and determine the Euclidean distance between the second physiological characteristic space vector and the third physiological characteristic space vector at the same sampling time point; Determine the average Euclidean distance between the second physiological characteristic space vector and the third physiological characteristic space vector at each sampling time point; Input the average Euclidean distance and the standard vomiting degree into a pre-trained second vomiting degree prediction model to obtain the second vomiting degree of the patient. Among them, the second vomiting degree prediction model is obtained by training multiple third training samples into a third neural network. Each third training sample includes the historical average Euclidean distance, the historical standard vomiting degree, and the corresponding second vomiting degree of the historical patient; Adjust the first vomiting degree according to the second vomiting degree.
8. The system according to claim 7, wherein The main control chip is specifically used for: Adjust the first vomiting degree according to the formula Q = αQ1 + βQ2, where α is a preset first adjustment coefficient, β is a preset second adjustment coefficient, Q1 is the first vomiting degree before adjustment, Q2 is the second vomiting degree before adjustment, and Q is the first vomiting degree after adjustment.
9. The system according to claim 6, wherein The main control chip is further configured to obtain the vomiting frequency, vomiting duration, vomitus characteristics, and electrolyte levels of multiple historical patients; for each historical patient, find the first vomiting degree score corresponding to the vomiting frequency of the historical patient, the second vomiting degree score corresponding to the vomiting duration, the third vomiting degree score corresponding to the vomitus characteristics, and the fourth vomitus score corresponding to the electrolyte level; sum up the first vomiting degree score, the second vomiting degree score, the third vomiting degree score, and the fourth vomiting degree score to obtain a comprehensive vomiting degree score, and use the comprehensive vomiting degree score as the actual first vomiting degree of the historical patient.
10. The system according to any one of claims 6-9, characterized in that, The second training sample further includes the ginger intake of historical patients, and the main control chip is specifically configured to: input the patient attribute characteristics and the first vomiting degree of the patient into a pre-trained vomiting rehabilitation management strategy model to determine the amount of ginger the patient needs to take, various massage techniques for the Neiguan acupoint on the patient's wrist, the massage sequence of each massage technique, the massage duration of each massage technique, the massage strength, and the massage frequency.