CN115068737B

CN115068737B - Chemotherapy infusion drug dosage control method, device, system and storage medium

Info

Publication number: CN115068737B
Application number: CN202210890464.9A
Authority: CN
Inventors: 肖亮; 田耕
Original assignee: Shenzhen Second Peoples Hospital
Current assignee: Shenzhen Second Peoples Hospital
Priority date: 2022-07-27
Filing date: 2022-07-27
Publication date: 2022-11-11
Anticipated expiration: 2042-07-27
Also published as: CN115068737A

Abstract

The embodiment of the invention provides a method, a device and a system for controlling the dosage of chemotherapy infusion drugs and a storage medium, and relates to the technical field of artificial intelligence. The chemotherapy infusion drug dose control method comprises the steps of obtaining a drug parameter characteristic value of a patient, inputting the drug parameter characteristic value into a trained drug dose control model to obtain a prediction classification result of drug dose, firstly adjusting a scalp temperature characteristic value within a first preset threshold value range if the prediction classification result is that the drug dose is not appropriate, adjusting a drug infusion speed characteristic value within a second preset threshold value range if the expected effect cannot be achieved, and repeatedly executing until the prediction classification result is that the drug dose is appropriate. According to the embodiment, the scalp temperature control and the medicine infusion speed are guided and adjusted according to the prediction classification result of the medicine dose, so that the chemotherapy infusion medicine absorbed dose on the scalp can not cause alopecia of a patient, and the effects of chemotherapy curative effect, scalp comfort and alopecia reduction can be considered.

Description

Chemotherapy infusion drug dosage control method, device, system and storage medium

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to a method and a device for controlling the dosage of a chemotherapy infusion medicament, a system for controlling the dosage of the chemotherapy infusion medicament and a storage medium.

Background

With the improvement of the life expectancy of people, the incidence rate of tumors is higher and higher nowadays, chemotherapy is the most basic treatment means for tumors, but the chemotherapy method inevitably generates various side effects while saving the lives of patients, and alopecia is one of the common side effects of chemotherapy for tumor patients and is also one of the common reasons for resisting chemotherapy for tumor patients.

Because different individuals have different absorption degrees and tolerance degrees to the drugs, and the requirements of infusion speed and concentration of different chemotherapeutic drugs are different while ensuring the curative effect, the effects on alopecia are different. Although related technologies have devices such as cooling caps for reducing alopecia, such devices have a single function, and simply reduce the temperature of the scalp, which is very likely to cause too low blood circulation at the scalp, frostbite the skin, even skin necrosis, and irreversible damage to the hair, and when the temperature is too low, the absorbed dose of the drug is too low due to vasoconstriction, so that chemotherapy fails, and the treatment effect and the effect of reducing alopecia cannot be considered.

Disclosure of Invention

The embodiment of the invention mainly aims to provide a chemotherapy infusion drug dosage control method, a chemotherapy infusion drug dosage control device, a chemotherapy infusion drug dosage control system and a storage medium, and the method and the device can be used for obtaining the prediction classification result of the drug dosage and guiding the scalp temperature control and the drug infusion speed by obtaining the drug parameter characteristic value of a patient, so that the chemotherapy infusion drug absorbed dosage on the scalp can not cause alopecia of the patient, the curative effect, the comfort and the alopecia reduction effect can be taken into consideration, and the use experience of the patient can be improved.

In order to achieve the above object, a first aspect of the embodiments of the present invention provides a method for controlling dosage of a chemotherapy infusion solution, including:

a method for controlling the dosage of a chemotherapy infusion solution comprises the following steps:

acquiring a drug parameter characteristic value of a patient, wherein the drug parameter characteristic value comprises: a scalp temperature characteristic value and a medicine infusion speed characteristic value;

inputting the characteristic value of the drug parameter into a trained drug dose control model to obtain a prediction classification result of the drug dose, wherein the prediction classification result comprises: proper and improper drug dosage; the dosage of the medicine is suitable for representing that the absorbed dosage of the chemotherapy infusion medicine on the scalp does not cause alopecia, and the dosage of the medicine is not suitable for representing that the absorbed dosage of the chemotherapy infusion medicine on the scalp causes alopecia of a patient;

repeatedly executing the following steps until the classification result is predicted to be that the medicine dose is proper:

if the predicted classification result is that the drug dose is not appropriate, adjusting the scalp temperature characteristic value within a first preset threshold value range to update the drug parameter characteristic value, and inputting the drug parameter characteristic value into the drug dose control model again to obtain the predicted classification result of the drug dose;

if the adjusted scalp temperature characteristic value exceeds the first preset threshold range and the obtained predicted classification result of the medicine dosage is that the medicine dosage is not appropriate, the medicine infusion speed characteristic value is adjusted within the second preset threshold range to update the medicine parameter characteristic value, and the medicine parameter characteristic value is input into the medicine dosage control model again to obtain the predicted classification result of the medicine dosage.

In order to achieve the above object, a second aspect of the present invention provides a chemotherapy infusion drug dosage control device, comprising:

the characteristic value acquisition module is used for acquiring the medicine parameter characteristic values of the patient, and the medicine parameter characteristic values comprise: scalp temperature characteristic value and medicine infusion speed characteristic value;

the input module is used for inputting the characteristic value of the drug parameter into the trained drug dose control model to obtain the prediction classification result of the drug dose, and the prediction classification result comprises: proper and improper drug dosage; the dosage of the medicine is suitable for representing that the absorbed dosage of the chemotherapy infusion medicine on the scalp does not cause alopecia, and the dosage of the medicine is not suitable for representing that the absorbed dosage of the chemotherapy infusion medicine on the scalp causes alopecia of a patient;

the adjusting module is used for repeatedly executing the following steps until the classification result is predicted to be that the medicine dosage is proper:

if the scalp temperature characteristic value is adjusted to exceed the first preset threshold range, and the obtained medicine dose prediction classification result is that the medicine dose is not appropriate, the medicine infusion speed characteristic value is adjusted within the second preset threshold range to update the medicine parameter characteristic value, and the medicine parameter characteristic value is input into the medicine dose control model again to obtain the medicine dose prediction classification result.

To achieve the above object, a third aspect of the present invention provides a chemotherapy infusion drug dosage control system, comprising:

the external cooling device comprises a scalp temperature sensor, a temperature control unit and a cooling unit, wherein the temperature control unit controls the scalp temperature sensor to acquire the scalp temperature at the current moment according to a temperature control instruction, calculates the temperature difference value between the scalp temperature at the current moment and the scalp temperature corresponding to the scalp temperature characteristic value, and then adjusts the temperature of cooling liquid in the cooling unit according to the temperature difference value, so that the cooling unit adjusts the scalp temperature through heat exchange with the scalp;

the liquid pump flow control device is used for receiving a speed control instruction and controlling the medicine infusion speed;

and the processor unit is respectively connected with the external cooling device and the liquid pump flow control device and is used for receiving the characteristic value of the drug parameter and inputting the characteristic value into the trained drug dose control model to obtain a predicted classification result of the drug dose, and sending a temperature control instruction to the external cooling device to adjust a temperature control instruction of the scalp temperature characteristic value and/or sending a speed control instruction to the liquid pump flow control device to adjust a speed control instruction of the drug infusion speed characteristic value until the predicted classification result is that the drug dose is proper.

In order to achieve the above object, a fourth aspect of the present invention provides a chemotherapy infusion drug dosage control system, comprising:

the external cooling device comprises a scalp temperature sensor, a temperature control unit and cooling liquid, wherein the temperature control unit controls the scalp temperature sensor to acquire the scalp temperature at the current moment according to a temperature control instruction, calculates the temperature difference value between the scalp temperature at the current moment and the scalp temperature corresponding to the scalp temperature characteristic value, and then adjusts the temperature of the cooling liquid in the cooling unit according to the temperature difference value, so that the cooling liquid exchanges heat with the scalp to adjust the scalp temperature;

and the processor unit is respectively connected with the external cooling device and the liquid pump flow control device and is used for executing the chemotherapy infusion drug dosage control method in any one of the first aspect so as to control the external cooling device and the liquid pump flow control device and realize chemotherapy infusion drug dosage control.

To achieve the above object, a fifth aspect of the present invention provides a storage medium which is a computer-readable storage medium storing computer-executable instructions for causing a computer to perform:

as in the method of the first aspect above.

According to the method, the device, the equipment and the storage medium for controlling the drug dosage of the chemotherapy infusion, the drug parameter characteristic value of a patient is acquired, the drug parameter characteristic value is input into a trained drug dosage control model, the prediction classification result of the drug dosage is obtained, if the prediction classification result is that the drug dosage is not appropriate, the scalp temperature characteristic value is firstly adjusted within a first preset threshold range, if the expected effect cannot be achieved, the drug infusion speed characteristic value is adjusted within a second preset threshold range, and the operation is repeated until the prediction classification result is that the drug dosage is appropriate. According to the embodiment, the scalp temperature control and the medicine infusion speed are guided and adjusted according to the prediction classification result of the medicine dose, so that the chemotherapy infusion medicine can not cause alopecia of a patient in the absorbed dose on the scalp, the chemotherapy curative effect, the scalp comfort and the alopecia reduction effect can be considered, the treatment experience of the patient is improved, and the treatment effect is improved in the psychology.

Drawings

Fig. 1 is a schematic structural diagram of a chemotherapy infusion drug dosage control system provided by an embodiment of the invention.

Fig. 2 is a schematic structural diagram of an external cooling device of a chemotherapy infusion drug dosage control system according to an embodiment of the present invention.

Fig. 3 is a schematic view of a usage scenario of a chemotherapy infusion drug dosage control system according to an embodiment of the present invention.

Fig. 4 is a flowchart of a method for controlling the dosage of a chemotherapeutic infusion solution according to an embodiment of the present invention.

Fig. 5 is a flow chart of a method for controlling the dosage of a chemotherapeutic infusion solution according to another embodiment of the present invention.

FIG. 6 is a flow chart of a method for controlling the dosage of a chemotherapeutic infusion solution according to another embodiment of the present invention.

FIG. 7 is a schematic diagram of a first preset threshold range of a method for controlling the dosage of a chemotherapeutic infusion solution according to another embodiment of the present invention.

Fig. 8 is a flowchart of a method for controlling the dosage of a chemotherapeutic infusion solution according to another embodiment of the present invention.

FIG. 9 is a diagram illustrating a second preset threshold range of a method for controlling the dosage of a chemotherapeutic infusion solution according to another embodiment of the present invention.

FIG. 10 is a flow chart of a method for controlling the dosage of a chemotherapeutic infusion solution according to another embodiment of the present invention.

Fig. 11 is a training flowchart of a drug dose control model of a method for controlling the dose of a chemotherapy infusion solution according to another embodiment of the present invention.

Fig. 12 is a flowchart illustrating the training of a drug dose control model of a method for controlling the dose of a chemotherapeutic infusion solution according to another embodiment of the present invention.

Fig. 13 is a flowchart of a method for controlling the dosage of a chemotherapeutic infusion solution according to another embodiment of the present invention.

Fig. 14 is a schematic structural diagram of an external cooling device in a method for controlling the dosage of a chemotherapeutic infusion solution according to another embodiment of the present invention.

Fig. 15 is a block diagram showing the configuration of a chemotherapy infusion drug dosage control device according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

It is noted that while functional block divisions are provided in device diagrams and logical sequences are shown in flowcharts, in some cases, steps shown or described may be performed in sequences other than block divisions within devices or flowcharts.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to be limiting of the invention.

First, several terms related to the present invention are analyzed:

chemotherapy: chemical medicine treatment is a treatment method of malignant tumor, i.e. the antitumor medicine is used to kill tumor cells all over the body. Since even if most tumors are surgically removed, tumor cells may be present in the vicinity of the tumor or elsewhere in the body, and chemotherapy is used to control tumor growth or to alleviate the symptoms associated with the tumor. Chemotherapeutic drugs must reach tumor cells through the bloodstream to be effective. Therefore, intravenous drip is the most common method, i.e., the infusion solution is slowly infused into the vein of the arm of the patient after the drug is dissolved and mixed in the infusion solution.

A neural network: neural networks are a type of machine learning that models the human brain. Neural networks are capable of performing deep learning. The basic component of an artificial neural network is a sensor, which can perform simple signal processing and then connect to a large mesh network. The neural network with deep learning ability can not directly program to complete tasks, and needs to learn the information, and the general learning methods have three types: 1) Supervised learning, in which the computer modifies the model according to the labeled data set until the data set can be processed to obtain the desired result; 2) Unsupervised learning, no labeled data set available for learning exists, the neural network analyzes the data set, then a cost function is used for telling how far the neural network is away from a target, and then the neural network adjusts to improve the accuracy of the algorithm; 3) Reinforcement learning, in which the positive results of the neural network are reinforced and a negative result is penalized, forcing the neural network to learn over time.

And (3) logistic regression: the method is also called logistic regression analysis, is a generalized linear regression analysis model, belongs to supervised learning in machine learning, and is mainly used for solving a two-classification problem (also can solve a multi-classification problem). The model is trained over a given set of n data sets (training set) and the given set or sets of data (test set) are classified after training is complete. Wherein each group of data is composed of p indexes. If the data has two indexes, the data can be represented by points of a plane, if the data has three indexes, the data can be represented by points in a space, and basically, the model after logistic regression training is a straight line (p = 2) of the plane or a plane (p = 3) and a hyperplane (p > 3), and the line or the plane divides a scatter point in the space into two halves, and the data belonging to the same class are mostly distributed on the same side of the curve or the plane.

Activation function: a function, running on a neuron of an artificial neural network, is responsible for mapping the input of the neuron to an output. In a computational network, the activation function of a node defines the output of the node at a given input or set of inputs, and in an artificial neural network, this function is also referred to as the transfer function.

The anti-tumor drug given to a patient during chemotherapy has toxicity, the drug is brought to the whole body through blood vessels and has influence on all cells of the body, the chemotherapy drug can kill the cells which proliferate faster, for example, the malignant tumor is actually a malignant cell which proliferates faster, and the chemotherapy drug can effectively kill the cells. However, the human body also has some cells which proliferate faster, for example, hair follicle cells also proliferate faster, so that the human body is sensitive to chemotherapy drugs, and the chemotherapy drugs also severely inhibit the proliferation of the cells, so that hairs are separated from hair bulbs and fall off, and therefore alopecia can be caused after chemotherapy. Although this loss can be recovered within months after chemotherapy has ceased, it can have a major negative impact on the patient's mind, as the patient sees his own hair loss, and feels the disease serious, which can be detrimental to the patient's ability to maintain an active mind to combat the disease.

Because different individuals have different absorption degrees and tolerance degrees to the drugs, and the requirements of infusion speed and concentration of different chemotherapeutic drugs are different while ensuring the curative effect, the effects on alopecia are different. In fact, not all chemotherapy causes hair loss, nor is it to say that the hair must lose light after chemotherapy. The same drugs can cause severe alopecia in some people, but not in others, which is related to the physical condition and tolerance of patients. Some drugs have severe hair loss, some drugs have light hair loss, and chemotherapy drugs which are most easy to cause hair loss comprise adriamycin, etoposide, vincristine, cyclophosphamide and cisplatin with large dose, and the like. And the hair loss of oxaliplatin, gemcitabine, albumin nano paclitaxel and the like is relatively less. The degree of hair loss is related to the condition of the patient himself, the tolerance to drugs, the type of drugs and the dosage of drugs.

The related art has cooling caps and the like for reducing hair loss. When a chemotherapy patient wears an ice cap to treat alopecia caused by chemotherapy, the scalp temperature of the patient is kept below 15 ℃ through the disease cap, blood vessels near the hair roots are contracted rapidly, and the absorption degree of chemotherapy drugs by hair follicles is reduced, so that the damage to the scalp and the hair is reduced. Such cooling caps typically include a sandwich cavity for receiving cold water, and the target temperature may be maintained by intermittently supplying cold water to the sandwich cavity and removing some of the superheated water from the sandwich cavity, for example, to maintain the temperature of the cold water in the sandwich cavity at 15 c, and when the temperature of the cold water in the sandwich cavity exceeds 15 c, it is necessary to supply cold water at a lower temperature to the sandwich cavity to maintain the temperature at a lower temperature. However, the device has a single function, only reduces the scalp temperature simply, and is very easy to cause excessively low blood circulation at the scalp part, frostbite the skin, even cause skin necrosis and irreversible damage to the hair in the process of injecting low-temperature cold water, and when the temperature is excessively low, the absorbed dose of the drug is excessively low due to vasoconstriction, so that chemotherapy fails, cost is saved, and the effects of curative effect and hair loss reduction cannot be considered.

Based on this, the embodiment of the present invention provides a method and an apparatus for controlling a dosage of a chemotherapy infusion drug, a system for controlling a dosage of a chemotherapy infusion drug, and a storage medium, wherein the method for controlling a dosage of a chemotherapy infusion drug obtains a drug parameter characteristic value of a patient, inputs the drug parameter characteristic value into a trained drug dosage control model, obtains a prediction classification result of a drug dosage, first adjusts a scalp temperature characteristic value within a first preset threshold range if the prediction classification result indicates that the drug dosage is not appropriate, and adjusts a drug infusion speed characteristic value within a second preset threshold range if the expected effect cannot be achieved, and repeatedly executes the method until the prediction classification result indicates that the drug dosage is appropriate. According to the prediction classification result of the drug dose, the scalp temperature control and the drug infusion speed are guided to be adjusted, so that the chemotherapy infusion drug absorbed dose on the scalp can not cause alopecia of a patient, the chemotherapy curative effect, the scalp comfort and the effect of reducing the alopecia can be considered, the treatment experience of the patient is improved, and the treatment effect is improved in a psychological level.

The embodiment of the invention can acquire and process related data based on an artificial intelligence technology. Among them, artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.

The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

The embodiments of the present invention provide a method and an apparatus for controlling a dosage of a chemotherapy infusion drug, a system for controlling a dosage of a chemotherapy infusion drug, and a storage medium, and are specifically described with reference to the following embodiments, first, a system for controlling a dosage of a chemotherapy infusion drug in an embodiment of the present invention is described.

Referring to fig. 1, fig. 1 shows a schematic structural diagram of a chemotherapeutic infusion drug dosage control system according to an embodiment of the invention.

The embodiment of the invention provides a chemotherapy infusion medicine dosage control system, which comprises: the external cooling device 110, the input device 120, the display device 170, the liquid pump flow control device 130, the electrocardiograph monitoring device 140, the armpit temperature sensor 150 and the processor unit 160.

Referring to fig. 2, the external cooling device 110 includes: the scalp temperature control unit 1102 controls the scalp temperature sensor 1101 to acquire the scalp temperature at the current moment according to a temperature control instruction sent by the processor unit 160, calculates a temperature difference value between the scalp temperature at the current moment and the scalp temperature corresponding to the scalp temperature characteristic value, and then adjusts the temperature of the cooling liquid in the cooling unit 1103 according to the temperature difference value, so that the cooling unit 1103 adjusts the scalp temperature through heat exchange with the scalp.

The input device 120 is used for receiving part of the medical parameters of the patient, such as patient information, tumor type and drug type, and can be connected to the display device 170 for displaying interactive information, i.e. corresponding patient information.

The input device 120 is used for receiving input of a user. Typically, the input device 120 may be a mouse, a keyboard, or the like, and in some cases, may be a touch-sensitive display screen that provides a user with the ability to input and display content, and thus in such an example, the input device 120 and the display device 170 are integrated. Of course, in some instances, the input device 120 may even be a voice input device or the like that brings about recognition of speech.

The display device 170 may be used to display information. In some embodiments, the input device 120 may be integrated with a display device, and in some embodiments, the input device 120 may also be connected to a computer device (e.g., a computer) to display information through a display unit (e.g., a display screen) of the computer device, which are all within the scope of the present disclosure defined and protected by the display device 170.

The liquid pump flow control device 130 is used for receiving the speed control command sent by the processor unit 160 and controlling the drug infusion speed.

The electrocardiograph monitoring device 140 is used for performing electrocardiograph monitoring and obtaining an electrocardiograph monitoring result to represent the current heart rate of the user. The heart rate and the blood flow rate are generally in a positive correlation, and the inflow cardiac output per minute = cardiac output x heart rate per beat, generally speaking, the blood pressure is constant, and the blood pressure = cardiac output per minute + peripheral vascular resistance, and assuming that the myocardial contractility is constant, theoretically, the smaller the vessel diameter (i.e., the higher the peripheral vascular resistance), the faster the blood flow rate, but at the same time, the greater the resistance the heart receives per contraction, so the cardiac output is decreased, and the blood pressure is constant. The method can perform Fourier transform on the acquired electrocardiogram monitoring result to obtain a frequency domain amplitude, and judge the heart rate of the patient according to the frequency domain amplitude.

The underarm temperature sensor 150 acquires the underarm temperature for characterizing the body temperature. On one hand, the temperature of the scalp can be reduced when the scalp is cooled, the armpit body temperature can be collected to monitor whether the body temperature state of the user is normal, and the temperature of the scalp cooler can be adjusted and controlled when the body temperature is abnormal; on the other hand, the effect of body temperature on blood flow rate may also affect drug concentration, thus necessitating the detection of axillary temperature.

Processor unit 160, processor unit 160 may be a neural center and a command center of a chemotherapy infusion drug dosage control system, or a command center of a chemotherapy infusion drug dosage control system responsible for infusion control or temperature control. The processor unit 160 may generate operation control signals according to the instruction operation code and the timing signal, so as to complete the control of instruction fetching and instruction execution. The processor unit 160 is connected to the external cooling device 110, the input device 120, the display device 170, the liquid pump flow rate control device 130, the electrocardiographic monitoring device 140, and the underarm temperature sensor 150, and is configured to receive the patient information, the tumor type, and the drug type acquired by the input device 120, receive the heart rate of the patient sent by the electrocardiographic monitoring device 140, receive the underarm temperature of the patient sent by the underarm temperature sensor 150, and receive the drug infusion rate sent by the liquid pump flow rate control device 130, generate a drug parameter characteristic value according to the acquired medical parameter, input the drug parameter characteristic value to the trained drug dose control model, obtain a predicted classification result of the drug dose, and send a temperature control instruction to the external cooling device 110 to adjust a temperature control instruction of the scalp temperature characteristic value when the predicted classification result is that the drug dose is not appropriate, and/or send a speed control instruction to the liquid pump flow rate control device 130 to adjust a speed control instruction of the drug infusion rate characteristic value until the predicted classification result is appropriate for the drug dose.

The chemotherapy infusion drug dosage control system guides the external cooling device and the liquid pump flow control device to adjust scalp temperature control and drug infusion speed according to the prediction classification result of the drug dosage output by the processor unit, so that the chemotherapy infusion drug cannot cause alopecia of a patient at the absorbed dosage of the scalp, the chemotherapy treatment effect, the scalp comfort and the alopecia reduction effect can be considered, the treatment experience of the patient is improved, and the treatment effect is improved on the psychology level.

It should be noted that the structure of the chemotherapy infusion solution drug dosage control system described in the embodiment of the present invention is for more clearly illustrating the technical solution of the embodiment of the present invention, and does not constitute a limitation to the technical solution provided in the embodiment of the present invention, and it is known to those skilled in the art that the technical solution provided in the embodiment of the present invention is also applicable to similar technical problems with the evolution of the device architecture and the emergence of new application scenarios.

It will be appreciated by those skilled in the art that the chemotherapy infusion drug dosage control system shown in fig. 1 is not intended to be limiting of embodiments of the present invention and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components.

Referring to fig. 3, a schematic view of a usage scenario of the chemotherapy infusion drug dosage control system of the present application is shown. The external cooling device 110 in fig. 3 is illustrated in a form of a wearable helmet, fig. 3 shows that when a patient 180 infuses, the input device 120 acquires general medical information of the patient, in this embodiment, the input device 120 and the display device 170 are integrated, the armpit temperature sensor 150 acquires the armpit temperature of the patient in real time, the electrocardiograph monitoring device 140 acquires the heart rate of the patient in real time, and transmits acquired data to the processor unit 160 for processing in real time, the infusion tube 190 is clamped by the liquid pump flow control device 130, the infusion tube 190 is connected with an infusion bag, and the infusion bag contains chemotherapy drugs. The processor unit 160 generates a temperature control instruction and a speed control instruction according to the processing result, and sends the temperature control instruction and the speed control instruction to the external cooling device 110 and the liquid pump flow control device 130 for adjustment, so that the absorbed dose of the chemotherapy infusion drugs on the scalp does not cause alopecia of the patient, the chemotherapy curative effect, the scalp comfort and the effect of reducing alopecia can be considered, the treatment experience of the patient is improved, and the treatment effect is improved on the psychological level.

The dosage control method of the chemotherapy infusion drug of the embodiment of the application is specifically described below.

The embodiment of the invention provides a method for controlling the dosage of a chemotherapy infusion solution, and relates to the technical field of artificial intelligence. The method for controlling the dosage of the chemotherapy infusion medicine provided by the embodiment of the invention can be applied to a terminal, a server side and software running in the terminal or the server side. Wherein the terminal communicates with the server via a network. The chemotherapy infusion drug dosage control method can be executed by a terminal or a server, or executed by the terminal and the server in a coordinated mode. Here, the method for controlling the dose of the chemotherapy infusion solution will be described by taking an example of terminal execution: the terminal adopts the technical scheme.

In some embodiments, the terminal may be a smartphone, tablet, laptop, desktop computer, or smart watch, among others. The server can be an independent server, and can also be a cloud server providing basic cloud computing services such as cloud service, a cloud database, cloud computing, a cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, content Delivery Network (CDN), big data and artificial intelligence platform and the like; or may be service nodes in a block chain system, where the service nodes in the block chain system form a Peer-To-Peer (P2P) network, and the P2P Protocol is an application layer Protocol running on a Transmission Control Protocol (TCP). The server may be installed with a server of the demand management system, and the server may interact with the terminal through the server, for example, corresponding software is installed on the server, and the software may be an application for implementing a chemotherapy infusion drug dosage control method, but is not limited to the above form. The terminal and the server may be connected through communication connection manners such as bluetooth, USB (Universal Serial Bus), or a network, which is not limited in this embodiment.

The invention is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

Fig. 4 is an alternative flow chart of a method for controlling the dosage of a chemotherapeutic infusion solution according to an embodiment of the present invention, and the method in fig. 4 may include, but is not limited to, steps S110 to S130.

Step S110: and acquiring the characteristic value of the drug parameter of the patient.

In one embodiment, the drug parameter characteristic value is characterized by a medical parameter of the patient.

In one embodiment, step S110 includes steps S111 to S112 with reference to fig. 5.

Step S111: medical parameters of a patient are acquired.

Because different individuals have different absorption degrees and tolerance degrees to the drugs, and the requirements of infusion speed and concentration of different chemotherapeutic drugs are different while ensuring the curative effect, the effects on alopecia are different. Not all chemotherapy causes alopecia, and the same drugs cause severe alopecia in some people and not in others, which is related to the physical condition and tolerance of the patients themselves. Some drugs have severe hair loss, some drugs have light hair loss, and chemotherapy drugs which are most easy to cause hair loss comprise adriamycin, etoposide, vincristine, cyclophosphamide and cisplatin with large dose, and the like. And the hair loss of oxaliplatin, gemcitabine, albumin nano paclitaxel and the like is relatively less. The degree of hair loss is related to the condition of the patient himself, the tolerance to drugs, the type of drugs, and the dosage of drugs.

Therefore, in this embodiment, the medical parameters of the patient selected include: scalp temperature, drug infusion rate, patient information, tumor type, drug type, patient heart rate, and axillary temperature. The patient information may include individual information such as patient age, patient sex, and patient hair quality, for example, the patient hair quality may be divided into: dry hair, oily hair, mixed dry and oily hair, and the like can be distinguished according to actual conditions.

Step S112: and carrying out data preprocessing on the medical parameters to obtain characteristic values of the drug parameters.

In an embodiment, the step of characterizing the medical parameters obtained in step S111 to obtain corresponding characteristic values of the medication parameters includes: comprises a scalp temperature characteristic value, a medicine infusion speed characteristic value, a patient information characteristic value, a tumor type characteristic value, a medicine type characteristic value, a patient heart rate characteristic value and an armpit temperature characteristic value.

In one embodiment, the characterization is data normalization. The data normalization process is described below.

1) The scalp temperature characteristic, i.e., scalp temperature, may be in degrees fahrenheit, and commonly used temperatures are quantified as simple numbers, such as "20 degrees celsius" by "1", 20.5 degrees celsius "by" 2", and so on.

2) The medicine infusion speed is obtained, and the proper dropping number range is defined according to the dropping number of the standard infusion tube in unit time. Different numbers of drops correspond to different input concentrations of the drug. For example, the unit time is 10s, the infusion range is defined as 1: (1 to 3) dripping/10 s; infusion range 2: (4 to 8) drops/10 s; infusion range 3: (9 to 12) drip/10 s 8230, etc., each range is expressed in numerical values, for example, "1" represents an infusion range 1, "2" represents an infusion range 2, "3" represents an infusion range 3 8230, etc., and the drug infusion speed is characterized as a drug infusion speed characteristic value by analogy.

3) The patient information includes: patient age, patient gender, patient hair quality, and the like. As described above, the patient's age can be directly expressed numerically or divided into age groups, such as "children aged 0 to 3" as "1", children aged 3 to 6 "as" 2", children aged 6 to 10" as "3", 8230, and adults aged 40 to 45 "as" 7", and the division criteria can be determined according to actual needs. When the sex of the patient is characterized, "1" indicates "male" and "2" indicates "female". When the hair quality of a patient is characterized, the classification standard can be determined according to actual requirements, such as "dry hair quality" represented by "1", "oily hair quality" represented by "2", and "oil-in-oil hair quality" represented by "3". By analogy, a patient information characteristic value is obtained, and the patient information characteristic value can be in an array form. It can be understood that, in practical applications, other personal information of the patient may be added according to a requirement, and this embodiment is not limited in particular.

4) Obtaining the tumor types of the patients, such as lung cancer, liver cancer, lymph cancer, skin cancer, stomach cancer or ovarian cancer, and digitizing the set tumor types as described above to obtain the tumor type characteristic values, such as number "1" representing lung cancer, number "2" representing liver cancer, etc.

5) The drug class is the class of drug included in the selected treatment regimen for the patient's tumor species. The drug type may be simply the name of the drug, i.e. when characterized, each drug is represented by a number. The drug type may also be a chemotherapy regimen in combination with the corresponding drug name, i.e. when characterized, the first position of the drug type characteristic value array represents a chemotherapy regimen, and is represented by a number, and the second position of the drug type characteristic value array represents a drug used in the chemotherapy regimen, and is represented by a number.

Some common chemotherapy regimens are as follows:

MOPP chemotherapy regimen (indicated with "1"): HN2 (nitrogen mustard) + VCR (vincristine) + PCE (procarbazine) + PDN (prednisone).

ABVD chemotherapy regimen (indicated with "2"): ADM (doxorubicin) + PYM (pingyangmycin) + VLB (vinblastine) + DTIC (dacarbazine).

CVP chemotherapy regimen (indicated with "3"): CTX (cyclophosphamide) + VCR (vincristine) + PDN (prednisone).

CMF chemotherapy regimen (indicated with "4"): CTX (cyclophosphamide) + MTX (methotrexate).

PCMF chemotherapy regimen (indicated with "5"): DDP (cisplatin) + CTX (cyclophosphamide) + MTX (methotrexate).

CAP chemotherapy regimen (indicated with "6"): CTX (cyclophosphamide) + ADM (doxorubicin) + DDP (cisplatin).

The corresponding chemotherapeutic drugs are indicated as: HN2 ("1"), VCR ("2"), PCE ("3"), etc.

6) The heart rate of a patient is acquired through the electrocardiogram monitoring equipment, and is quantified into simple numbers according to the division of the heart rate range, such as the heart rate 98 represented by '1', the heart rate 99 represented by '2', and the like.

7) The underarm temperature characteristic, i.e., the underarm temperature, may be in degrees fahrenheit, with commonly used temperatures quantified as simple numbers, such as "35 degrees celsius" by "1," 35.5 degrees celsius "by" 2, "and so forth.

In the above embodiments, the medical parameters of one patient are as follows, for example.

Scalp temperature: 20 ℃;

the speed of medicine infusion: (4 to 8) drops/10 s;

patient information: male, 41 years old, oily hair;

tumor types: liver cancer;

the types of drugs are: adopting CVP chemotherapy scheme, the name of the current infusion drug is vincristine;

patient heart rate: 98;

axillary temperature: 35 degrees celsius.

The process of characterizing medical parameters in the above embodiment yields: the characteristic values of the medical parameters { scalp temperature characteristic value, characteristic value of the infusion rate of the medicine, characteristic value of the patient information, characteristic value of the tumor type, characteristic value of the medicine type, characteristic value of the heart rate of the patient, and characteristic value of the axillary temperature } = {1,2, [2,7,1],2, [3,2], 1}, it is understood that the present embodiment is only an example of the characterization, and does not represent a limitation thereto, and a person skilled in the art may characterize the medical parameters in any suitable manner.

Step S120: and obtaining a prediction classification result of the drug dose by using the drug parameter characteristic value.

In an embodiment, the obtained characteristic values of the drug parameters are input into a trained drug dose control model, so as to obtain a prediction classification result of the drug dose.

In one embodiment, predicting the classification result includes: proper and improper drug dosage. In the embodiment, under which predicted drug infusion dosage, the corresponding scalp absorbed dosage does not cause alopecia of the patient. Therefore, the drug dosage is suitable for representing that the absorbed dosage of the chemotherapy infusion drug on the scalp does not cause alopecia, and the drug dosage is not suitable for representing that the absorbed dosage of the chemotherapy infusion drug on the scalp causes alopecia of a patient.

Step S130: the adjustment process is repeated until the classification result is predicted to be that the drug dosage is appropriate.

In one embodiment, the amount of chemotherapy infusion absorbed into the scalp can be adjusted by the scalp temperature. When skin is cold, subcutaneous blood vessels shrink, so that the temperature of the scalp of a patient is reduced during chemotherapy of a tumor patient, the blood supply of the scalp can be greatly reduced, the anti-tumor medicine flowing along with the blood flow can less enter cells at the scalp and hair follicle part along with the reduction of the blood flow, namely the absorbed dose of the tumor medicine on the scalp is reduced, the damage to the cells can be greatly reduced, and the alopecia can be correspondingly reduced or slowed down. The whole drug amount can be reduced by adjusting the drug infusion speed, so that the absorbed dose of the chemotherapy infusion drug on the scalp is reduced.

In an embodiment, referring to fig. 6, step S130 includes step S131 and step S132.

Step S131: and regulating the scalp temperature characteristic value.

In an embodiment, if the predicted classification result is that the drug dose is not appropriate, the scalp temperature characteristic value is adjusted within a first preset threshold range to update the drug parameter characteristic value, and the drug parameter characteristic value is input into the drug dose control model again to obtain the predicted classification result of the drug dose. The scalp temperature characteristic value in the medicine parameter characteristic values is only changed, the medicine parameter characteristic values are updated, then the medicine parameter characteristic values are input into the medicine dose control model, and after the scalp temperature characteristic values are modified, the corresponding medicine dose prediction classification results are obtained.

In this embodiment, the local scalp temperature can correspond to the local vasodilation diameter and the drug concentration in the blood flow, that is, the scalp temperature can influence the drug concentration in the blood flow, thereby influencing the absorption dose of the chemotherapy infusion drug on the scalp. In the embodiment, on the basis of ensuring the curative effect of chemotherapy, the absorption dose of chemotherapy infusion drugs on the scalp needs to be reduced, the speed and concentration of systemic intravenous administration are ensured, and the local drug concentration in local blood flow is controlled to reduce the toxicity of hair follicles.

In one embodiment, the scalp temperature is 22-29 ℃ through statistics and research, and the patient can tolerate the temperature, so that the treatment time/infusion speed required by the systemic chemotherapy treatment can be not influenced, the local follicular toxicity can be reduced, and the alopecia can be reduced. And further, the scalp temperature is at a more comfortable temperature between 25 degrees celsius and 26 degrees celsius.

Fig. 7 is a schematic diagram illustrating a first preset threshold range according to an embodiment of the present application.

As can be seen in FIG. 7, the first preset threshold range includes a comfort temperature threshold range (T1 in FIG. 7), a tolerance temperature threshold range (T2 in FIG. 7), wherein the comfort temperature threshold range T1 includes a lower comfort temperature limit T1 _min And upper comfortable temperature limit T1 _max The tolerance temperature threshold range T2 includes a tolerance temperature lower limit T2 _min And upper temperature limit of tolerance T2 _max It can be seen that the comfort temperature threshold range T1 is actually a subset of the tolerance temperature threshold range T2, and therefore the lower comfort temperature limit T1 _min Is greater than the lower limit T2 of the tolerant temperature _min Upper limit of comfort temperature T1 _max Less than upper limit of tolerance temperature T2 _max . For example, in the above embodiment, the comfort temperature threshold range T1 is [25 °,26 ° ]]Wherein the lower comfortable temperature limit T1 _min Is 25 DEG, comfortable temperature upper limit T1 _max Is 26 degrees, and the tolerance temperature threshold range T2 is [22 degrees, 29 degrees ]]Lower limit of temperature tolerance T2 _min Is 22 degrees and has the upper limit of tolerance temperature T2 _max Is 29 deg..

In an embodiment, referring to fig. 8, step S131 specifically includes step S1311 to step S1312.

Step S1311: the scalp temperature characteristic value is adjusted within the comfort temperature threshold range.

In this embodiment, the characteristic value of the drug parameter is updated within the comfortable temperature threshold range, and then the characteristic value of the drug parameter is input into the drug dose control model again to obtain the prediction classification result of the drug dose. Aims to ensure that the scalp temperature of a patient is in a comfortable interval and reduce the possibility of alopecia on the premise of ensuring the curative effect.

Step S1312: and adjusting the scalp temperature characteristic value within the tolerance temperature threshold range outside the comfortable temperature threshold range.

In this embodiment, if the scalp temperature of the patient is in the comfortable interval on the premise that the prediction classification result of the drug dose obtained by adjusting the scalp temperature characteristic value within the comfortable temperature threshold range is that the drug dose is not appropriate, that is, the therapeutic effect cannot be guaranteed, the scalp temperature characteristic value is adjusted within the tolerable temperature threshold range outside the comfortable temperature threshold range to update the drug parameter characteristic value. Namely, on the premise of ensuring the curative effect, the temperature-controlled hair loss treatment device is adjusted within the range which can be tolerated by a patient, and the patient can tolerate the temperature even if the temperature is not comfortable, so that the aim of reducing hair loss is fulfilled.

In an embodiment, even if the appropriate scalp temperature cannot be found within the whole tolerance temperature threshold range, the drug infusion speed may be adjusted to reduce the whole drug amount, thereby reducing the absorbed dose of the chemotherapy infusion drug on the scalp, but since the drug infusion speed has a certain influence on the duration of the treatment, it can be understood that, in order to find the optimal implementation effect, the drug infusion speed is adjusted on the premise that the appropriate scalp temperature cannot be found within the tolerance temperature threshold range. If the medicine infusion speed is simply adjusted, the aim of reducing the alopecia can be achieved to a certain extent.

Step S132: and regulating the characteristic value of the medicine infusion speed.

In an embodiment, if the scalp temperature characteristic value is adjusted to exceed the first preset threshold range, and the obtained predicted classification result of the drug dosage is that the drug dosage is not appropriate, the drug infusion speed characteristic value is adjusted within the second preset threshold range to update the drug parameter characteristic value, and the drug parameter characteristic value is input into the drug dosage control model again to obtain the predicted classification result of the drug dosage.

In one embodiment, the dosage of the medication and the infusion rate may be determined from instructions for different medications. For example, the following is described in the drug insert for doxorubicin: the injection is dissolved by adding 0.9% sodium chloride injection or prepared water for injection before use, the concentration is generally 2mg/ml, and the injection is slowly injected into veins or arteries. The dosage commonly used by adults is as follows: 40-60 mg/m2 (or 50-60 mg for 1 time), 1 time every 3 weeks; or 20-30 mg per week for 3 weeks. When the composition is used in combination, 2/3 of the single dosage can be used. The use of the medicine for several times every week is less in myocardial toxicity, bone marrow suppression and gastrointestinal reactions (including oral ulcer) than the use of the medicine for 1 time every three weeks, and the gastrointestinal reactions of continuous administration for three days are greater, so that the medicine is not suitable for use. Children take about half as much as adults. It is currently believed that the cumulative total dose of ADM should not exceed 450-500 mg/m2. 30-40 mg can be used in the bladder or the chest every time.

And the transfusion speed of different medicines is limited, such as dopamine, adrenaline, dobutamine, noradrenaline, nitroglycerin, sodium nitroprusside and the like, and the specifications and dosage ranges of various vasoactive medicines are different, for example, the dosage range of the dopamine is 1-20 ug/kg/min, and the dosage range of the adrenaline is 0.01-0.2 ug/kg/min.

In one embodiment, the rate of infusion of the medication is related to the therapeutic effect of the patient, since the rate of infusion of the medication is related to the input dosage of the medication, which has a different effect on the therapeutic effect. According to the specification of the medicine, a group of medicine infusion speed ranges with better curative effect can be determined and defined as a strong curative effect speed threshold range, and a medicine infusion speed range which can only produce curative effect is defined as a critical curative effect speed threshold range.

In an embodiment, referring to fig. 9, a schematic diagram of a second predetermined threshold range in an embodiment of the present application is shown.

As can be seen in fig. 9, the second predetermined threshold range includes a strong efficacy rate threshold range (C1 in fig. 9), a critical efficacy rate threshold range (C2 in fig. 9), wherein the strong efficacy rate threshold range C1 includes a lower limit C1 of the strong efficacy rate _min And the upper limit of the rate of strong therapeutic effect C1 _max The threshold range C2 includes a lower threshold C2 _min And critical upper limit of therapeutic effect rate C2 _max It can be seen that the high efficacy rate threshold range C1 is actually a subset of the critical efficacy rate threshold range C2, and thus the lower high efficacy rate limit C1 _min Greater than the lower limit of the critical curative effect speed C2 _min The upper limit of the therapeutic effect rate C1 _max Less than the upper limit of the critical curative effect rate C2 _max 。

In an embodiment, referring to fig. 10, the step S132 specifically includes steps S1321 to S1322.

Step S1321: the characteristic value of the medicine infusion speed is adjusted within the range of the speed threshold value with strong curative effect.

In this embodiment, the characteristic value of the drug parameter is first updated within the threshold range of the high efficacy speed, and then the characteristic value of the drug parameter is input into the drug dose control model again to obtain the result of predictive classification of the drug dose. The aim is to firstly ensure better curative effect and reduce the possibility of alopecia.

Step S1322: the characteristic value of the medicine infusion speed is adjusted within the range of the critical curative effect speed threshold outside the range of the strong curative effect speed threshold.

In this embodiment, if the predicted classification result of the medication dose obtained by adjusting the medication infusion speed characteristic value within the high-efficacy speed threshold range is that the medication dose is not appropriate, that is, the curative effect cannot be ensured well, the medication infusion speed characteristic value is adjusted within the critical-efficacy speed threshold range outside the high-efficacy speed threshold range to update the medication parameter characteristic value. On the premise of ensuring the curative effect to the maximum extent, the speed of medicine infusion is adjusted, and the whole medicine quantity is reduced, so that the absorbed dose of chemotherapy infusion medicines on the scalp is reduced, and the aim of reducing alopecia is fulfilled.

In an embodiment, referring to fig. 11, the training step for training the drug dose control model in the present embodiment includes steps S1110 to S1140.

In step S1110, a training sample set is obtained.

In one embodiment, the samples of the training sample set include a medical parameter feature sequence and a dose classification label. Wherein, the medical parameter characteristic value in the medical parameter characteristic sequence comprises: including scalp temperature eigenvalue, medicine infusion speed eigenvalue, patient information eigenvalue, tumour kind eigenvalue, medicine kind eigenvalue, patient heart rate eigenvalue, armpit temperature eigenvalue, corresponding dose classification label includes: a drug dose appropriateness label and a drug dose improper label.

The appropriate drug dose label is that the absorbed dose of the chemotherapy infusion drugs corresponding to the sample medical parameter characteristic sequence on the scalp does not cause alopecia or causes little alopecia, and the inappropriate drug dose label is that the absorbed dose of the chemotherapy infusion drugs corresponding to the sample medical parameter characteristic sequence on the scalp causes alopecia of a patient.

The following is an example of a drug dose configuration for intravenous administration.

If: the weight (kg) of A (mg) is prepared into 50mL solution, bmL is needed to be taken out every hour, and the dosage of the medicine is A x B/3 (ug/kg/min).

For example: a50 kg patient was prepared with a dopamine solution of 50 ANG 3 (A) =150mg,150mg dopamine 15mL, and 35mL water was added to prepare a 50mL solution, 3mL (B) was dispensed per hour, and the dose of dopamine A was 3 (A) × 3 (B)/3 =3ug/kg/min. It can be calculated that 150mg dopamine is prepared into 50mL solution, which is equivalent to 3mg dopamine in each mL solution, 3mL solution in each hour, and 9mg dopamine in each hour, and converted into ug/kg/min, namely (9 ANG 1000) ug/(50kg 60min) =3ug/kg/min.

For another example: a 60kg patient required a pump of noradrenaline solution, 60 x 0.03mg (a) =1.8mg, equivalent to 0.9mL noradrenaline, plus 49.1mL water, formulated into 50mL solution, 6mL (B) per hour, equivalent to 0.03 (a) × 6 (B)/3 =0.06ug/kg/min.

According to the medicine dose configuration mode, the concentration of the medicine in blood, namely the medicine dose, at normal scalp temperature can be calculated, in the embodiment, the concentration of the medicine in blood is changed by adjusting the scalp temperature or the medicine infusion speed, if the concentration is within a reasonable range, the medicine dose is proper under the changed parameter, otherwise, the medicine dose is not proper, and the reasonable range is judged by a professional doctor according to experience and knowledge.

In one embodiment, a plurality of patient chemotherapy-related medical data and short, medium and long-term hair loss states are collected with informed consent, and corresponding samples are generated from the collected data, the samples including medical parameter signature sequences and dose classification tags. The blood drug concentration corresponding to the collected medical parameter characteristic sequence is firstly evaluated by a professional doctor whether the medical effect is ensured, and then a dose classification label of a sample corresponding to the medical parameter characteristic sequence is generated according to the alopecia state. The label may be manually labeled or labeled by machine learning, and is not specifically limited herein.

In one embodiment, the medical parameter signature sequence and dose classification label are represented as samples [ x, y ]]Wherein x represents the characteristic sequence of the medical parameter, y represents the label corresponding to x, and a large amount of collected data is generated into a corresponding sample. The sample set may be represented as (x) ₁ ，y ₁ )，(x ₂ ，y ₂ )......(x _N ，y _N ) N represents the total number of samples, where x ∈ R is an N-dimensional vector representing the characteristic value of the drug parameter, x _i The value of the ith sample on the n characteristics is represented, the n characteristics can be { scalp temperature characteristic value, medicine transfusion speed characteristic value, patient information characteristic value, tumor type characteristic value, medicine type characteristic value, patient heart rate characteristic value and axillary temperature characteristic value }, and the y characteristic can be { scalp temperature characteristic value, medicine transfusion speed characteristic value, patient information characteristic value, tumor type characteristic value, medicine type characteristic value, patient heart rate characteristic value and axillary temperature characteristic value }, respectively _i E { -1,1} represents whether the sample is a positive sample or a negative sample, wherein the positive sample, i.e. y =1, indicates that the absorbed dose of the chemotherapy infusion drug on the scalp does not cause alopecia, and the negative sample, i.e. y = -1, indicates that the absorbed dose of the chemotherapy infusion drug on the scalp will cause alopecia of the patient, and in the present embodiment, the positive sample can be used to represent a general search.

In addition, in one embodiment, a professional doctor can perform primary screening and denoising on data in the acquisition process or the sample generation process, and remove obviously unqualified samples, so that the accuracy of training a drug dosage control model by using the sample set is improved.

Step S1120, inputting the sample into the drug dose control model for logistic regression.

In this embodiment, the sample is input into the drug dose control model to perform logistic regression, and the feature weights corresponding to the influencing factors in the sample are combined to calculate to obtain the prediction classification result.

Referring to fig. 12, in an embodiment, step S1120 includes step S1121 and step S1122.

Step S1121: and inputting the sample into a drug dose control model for logistic regression, and calculating by combining the characteristic weight corresponding to the influence factors in the sample to obtain the predicted classification probability value.

In this embodiment, the input variable of the drug dose control model is an independent variable in the sample data, i.e. the above-mentioned drug parameter characteristic value x, corresponding to dendrites in neurons, and then the input variable is received as a linear model corresponding to cell bodies of the neurons, and the output of the linear model in the neurons is expressed as:

wherein, the first and the second end of the pipe are connected with each other,

representing the weights corresponding to the characteristic values of different drug parameters in the sample, b representing the intercept,

representing a linear function.

In addition, the linear function can also be expressed as:

the function parameters to be solved, namely the weights corresponding to the characteristic values of the different drug parameters,

expressing the intercept, i.e. b above, assuming the characteristic value of the independent variable drug parameter is expressed as a matrix X, expressing a linear equation coefficient matrix

Then the function is simplified by:

the predicted classification probability value indicating that the predicted classification result is the appropriate drug dose, i.e. the probability that the result takes 1.

Step S1122: and inputting the prediction classification probability value into a nonlinear activation function to obtain a prediction classification result.

In this embodiment, the nonlinear activation function is used to control whether signals are sent externally, corresponding to axons in neurons. The activation function joins the various parts of the drug dose control model to yield the final output, which is passed on to the next neuron model. The activation function definition is very intuitive and equals 1 when the prediction classification probability value is larger than a certain threshold, and equals 0 otherwise. The activation function in this embodiment is a perceptron, and in particular a sigmoid activation function.

And obtaining a prediction classification result after an activation function, wherein the prediction classification results (probability forms) corresponding to two different dose classification labels are represented as follows:

when the predicted classification probability value is greater than 50%, which is a suitable drug dosage, the predicted classification result is 1, and it is understood that 50% of the predicted classification probability value can be adjusted as required.

And step S1130, obtaining a cost function according to the prediction classification result and the dose classification label of the sample.

In this embodiment, in order to represent the deviation between the prediction classification result and the dose classification label, a cost function is constructed as an error evaluation index.

According to the dose classification labels of the samples, a likelihood estimation function of a prediction classification result is calculated, firstly, prediction classification results corresponding to two different dose classification labels are combined, and are expressed as follows:

expressed as:

a likelihood estimation function is then calculated for the predicted classification result, expressed as:

logarithm is taken to the likelihood estimation function, and a cost function is obtained according to the result after logarithm taking, and the cost function is expressed as:

wherein p represents probability, y represents dose classification label, x represents characteristic value of drug parameter in sample,

representing the weight matrix corresponding to the characteristic values of different drug parameters,

the prediction classification probability value indicating that the prediction classification result is the proper drug dosage, N indicates the type of the characteristic value of the drug parameter,

a function representing the likelihood estimation is performed,

representing a cost function.

And step S1140, adjusting the characteristic weight of the drug dose control model according to the value of the cost function until the cost function converges, so as to obtain the trained drug dose control model.

In this embodiment, a gradient descent method is used to calculate the minimum value of the cost function, and the characteristic weight of the drug dose control model is adjusted. If the dose classification label of the sample is 1, the closer the predicted classification result is to 1, the smaller the cost is paid, and vice versa, and if the dose classification label of the sample is 0, the closer the predicted classification result is to 0, the smaller the cost is paid, and vice versa.

Firstly, the negative sign of the cost function is averaged to be expressed as:

then, the parameters for minimizing the J function are calculated

Because the negative direction of the gradient is the fastest descending direction of the cost function, the method continuously iterates to solve the partial derivative by using the gradient descending method and gradually approaches to the method

The J function is enabled to obtain a minimum value, so that the characteristic weight of the drug dose control model is optimized until the cost function is converged, and the trained drug dose control model is obtained.

In one embodiment, referring to fig. 13, the method for controlling the dosage of the chemotherapy infusion solution further includes steps S1310 to S1330.

In step S1310, a verification information set is acquired.

In step S1320, the verification information set is input into the drug dosage control model to obtain a verification result.

Step S1330, updating the feature weight of the drug dose control model according to the verification result.

In this embodiment, after the trained drug dose control model is obtained, a new sample is generated in the process of applying the drug dose control model, the new sample can be used as verification data to verify the model, and the precision and recall rate of the drug dose control model are calculated according to the verification result, so that the prediction accuracy of the drug dose control model is represented. Meanwhile, the verification sample can expand a training sample set for iterative training of the drug dose control model.

In one embodiment, the external cooling device is used to adjust the scalp temperature to a scalp temperature corresponding to the scalp temperature characteristic value. The external cooling device includes: a scalp temperature sensor, a temperature control unit and a cooling unit, wherein a cooling liquid is present in the cooling unit. The temperature control unit controls the scalp temperature sensor to acquire the scalp temperature at the current moment according to the temperature control instruction, calculates the temperature difference between the scalp temperature at the current moment and the scalp temperature corresponding to the scalp temperature characteristic value, and then adjusts the temperature of the cooling liquid in the cooling unit according to the temperature difference, so that the cooling unit adjusts the scalp temperature through heat exchange with the scalp.

In one embodiment, the cooling liquid may be water, and the cooling unit controls the temperature of the cooling liquid by heating or cooling, wherein the correspondence between the temperature control of the cooling liquid and the temperature of the scalp may be determined by a priori knowledge obtained by experimental statistics.

In one embodiment, the external cooling device is a wearable helmet, and the specific structure of the external cooling device is not limited in the scheme.

Referring to fig. 14, the step of adjusting the scalp temperature for the external cooling device of the present embodiment includes steps S1410 to S1430.

In step S1410, the scalp temperature at the current time is acquired by the temperature sensor.

Step S1420, a temperature difference between the scalp temperature at the current time and the scalp temperature corresponding to the scalp temperature characteristic value is calculated.

In step S1430, the temperature of the cooling liquid in the cooling unit is adjusted by the temperature control unit according to the temperature difference, so that the cooling unit can adjust the scalp temperature by heat exchange between the cooling liquid and the scalp.

In this embodiment, the temperature control unit adjusts the temperature of the cooling liquid in the cooling unit according to the temperature difference, and according to the priori knowledge, the temperature of the cooling liquid can be adjusted in a heating or cooling manner, so that the scalp temperature reaches the scalp temperature corresponding to the scalp temperature characteristic value to be adjusted.

The method for controlling the dosage of the chemotherapy infusion drugs comprises the steps of obtaining the drug parameter characteristic value of a patient, inputting the drug parameter characteristic value into a trained drug dosage control model to obtain a prediction classification result of the drug dosage, if the prediction classification result indicates that the drug dosage is not appropriate, firstly adjusting the scalp temperature characteristic value within a first preset threshold range, if the expected effect cannot be achieved, adjusting the drug infusion speed characteristic value within a second preset threshold range, and repeatedly executing until the prediction classification result indicates that the drug dosage is appropriate. According to the embodiment, the scalp temperature control and the medicine infusion speed are guided and adjusted according to the prediction classification result of the medicine dose, so that the chemotherapy infusion medicine can not cause alopecia of a patient in the absorbed dose on the scalp, the chemotherapy curative effect, the scalp comfort and the alopecia reduction effect can be considered, the treatment experience of the patient is improved, and the treatment effect is improved in the psychology.

An embodiment of the present invention further provides a chemotherapy infusion drug dosage control apparatus, which can implement the above-mentioned chemotherapy infusion drug dosage control method, and with reference to fig. 15, the apparatus includes:

a characteristic value obtaining module 1510, configured to obtain a characteristic value of a medication parameter of a patient, where the characteristic value of the medication parameter includes: a scalp temperature characteristic value and a medicine infusion speed characteristic value;

an input module 1520, configured to input the characteristic value of the drug parameter into the trained drug dose control model to obtain a predicted classification result of the drug dose, where the predicted classification result includes: proper and improper drug dosage; the dosage of the medicine is suitable for representing that the absorbed dosage of the chemotherapy infusion medicine on the scalp does not cause alopecia, and the dosage of the medicine is not suitable for representing that the absorbed dosage of the chemotherapy infusion medicine on the scalp causes alopecia of a patient;

an adjusting module 1530 for repeatedly performing the following steps until the classification result is predicted to be the proper dosage of the drug:

if the predicted classification result is that the medicine dose is not appropriate, regulating the scalp temperature characteristic value within a first preset threshold value range to update the medicine parameter characteristic value, and inputting the medicine parameter characteristic value into the medicine dose control model again to obtain the predicted classification result of the medicine dose;

The specific implementation of the chemotherapy infusion drug dosage control device of this embodiment is substantially the same as the specific implementation of the chemotherapy infusion drug dosage control method, and is not repeated herein.

The embodiment of the invention also provides a chemotherapy infusion medicine dosage control system, which comprises:

and the processor unit is respectively connected with the external cooling device and the liquid pump flow control device and is used for executing the chemotherapy infusion drug dosage control method in any one of the embodiments to control the external cooling device and the liquid pump flow control device so as to realize chemotherapy infusion drug dosage control.

In some embodiments, the process and related description of the method for controlling the dosage of chemotherapeutic infusion drugs are as described above and will not be repeated herein. That is, the chemotherapy infusion drug dosage control process of the chemotherapy infusion drug dosage control system provided by the present invention can be executed in the processor unit of the chemotherapy infusion drug dosage control system, that is, the chemotherapy infusion drug dosage control process in the present embodiment and the chemotherapy infusion drug dosage control process in the embodiments shown in fig. 4 and the like belong to the same inventive concept, so that the embodiments have the same implementation principle and technical effect, and are not described in detail herein.

According to the chemotherapy infusion drug dose control system, the external cooling device and the liquid pump flow control device are guided to adjust scalp temperature control and drug infusion speed according to the prediction classification result of the drug dose output by the processor unit, so that the chemotherapy infusion drug does not cause alopecia of a patient in the absorbed dose of the scalp, the chemotherapy treatment effect, the scalp comfort and the alopecia reduction effect can be considered, the treatment experience of the patient is improved, and the treatment effect is improved in the psychology.

The embodiment of the invention also provides a storage medium which is a computer-readable storage medium, and the computer-readable storage medium stores computer-executable instructions for causing a computer to execute the chemotherapy infusion drug dosage control method.

According to the method for controlling the dose of the chemotherapy infusion drug, the device for controlling the dose of the chemotherapy infusion drug, the electronic equipment and the storage medium provided by the embodiment of the invention, the drug parameter characteristic value of a patient is obtained, and the drug parameter characteristic value is input into a trained drug dose control model, so that a predicted classification result of the drug dose is obtained, if the predicted classification result is that the drug dose is not appropriate, the scalp temperature characteristic value is firstly adjusted within a first preset threshold range, and if the expected effect cannot be achieved, the drug infusion speed characteristic value is adjusted within a second preset threshold range, and the operation is repeatedly performed until the predicted classification result is that the drug dose is appropriate. According to the embodiment, the scalp temperature control and the medicine infusion speed are guided and adjusted according to the prediction classification result of the medicine dose, so that the chemotherapy infusion medicine can not cause alopecia of a patient in the absorbed dose on the scalp, the chemotherapy curative effect, the scalp comfort and the alopecia reduction effect can be considered, the treatment experience of the patient is improved, and the treatment effect is improved in the psychology.

The memory, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs as well as non-transitory computer executable programs. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory located remotely from the processor, and these remote memories may be connected to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The embodiment described in the embodiment of the present invention is for more clearly illustrating the technical solution of the embodiment of the present invention, and does not constitute a limitation to the technical solution provided in the embodiment of the present invention, and it can be known by those skilled in the art that the technical solution provided in the embodiment of the present invention is also applicable to similar technical problems with the evolution of technology and the occurrence of new application scenarios.

It will be appreciated by those skilled in the art that the solutions shown in fig. 1-15 are not meant to limit embodiments of the present invention, and may include more or fewer steps than those shown, or some of the steps may be combined, or different steps may be included.

The above described embodiments of the apparatus are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

One of ordinary skill in the art will appreciate that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof.

The terms "first," "second," "third," "fourth," and the like in the description of the invention and in the drawings described above, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in other sequences than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It is to be understood that, in the present invention, "at least one" means one or more, "a plurality" means two or more. "and/or" is used to describe the association relationship of the associated object, indicating that there may be three relationships, for example, "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of the singular or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one type of logical functional division, and other divisions may be realized in practice, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may substantially or partially contribute to the prior art, or all or part of the technical solution may be embodied in the form of a software product, which is stored in a storage medium and includes multiple instructions for enabling an electronic device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing programs, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

The preferred embodiments of the present invention have been described above with reference to the accompanying drawings, and are not intended to limit the scope of the embodiments of the invention. Any modifications, equivalents and improvements that may occur to those skilled in the art without departing from the scope and spirit of the embodiments of the present invention are intended to be within the scope of the claims of the embodiments of the present invention.

Claims

1. A method for controlling the dosage of a chemotherapy infusion solution is characterized by comprising the following steps:

inputting the characteristic values of the drug parameters into a trained drug dose control model to obtain a prediction classification result of the drug dose, wherein the prediction classification result comprises: proper and improper drug dosage; wherein the drug dose is suitable for representing that the absorbed dose of the chemotherapy infusion drug on the scalp does not cause alopecia, and the drug dose is not suitable for representing that the absorbed dose of the chemotherapy infusion drug on the scalp causes alopecia of a patient;

repeatedly executing the following steps until the predicted classification result is that the drug dose is proper:

if the predicted classification result is that the medicine dose is not appropriate, adjusting the scalp temperature characteristic value within a first preset threshold value range to update the medicine parameter characteristic value, and inputting the medicine parameter characteristic value into the medicine dose control model again to obtain a predicted classification result of the medicine dose;

if the scalp temperature characteristic value is adjusted to exceed the first preset threshold range, and the obtained prediction classification result of the medicine dosage is that the medicine dosage is not appropriate, the medicine infusion speed characteristic value is adjusted within the second preset threshold range to update the medicine parameter characteristic value, and the medicine parameter characteristic value is input into the medicine dosage control model again to obtain the prediction classification result of the medicine dosage.

2. The method for controlling dosage of chemotherapeutic infusion drugs as claimed in claim 1, wherein said obtaining characteristic values of drug parameters of the patient comprises:

acquiring medical parameters of a patient, the medical parameters including: scalp temperature, drug infusion rate, and at least one of: patient information, tumor type, drug type, patient heart rate, underarm temperature;

the medical parameters are subjected to data preprocessing to obtain the medicine parameter characteristic values, and the medicine parameter characteristic values comprise a scalp temperature characteristic value, a medicine infusion speed characteristic value and at least one of the following values: patient information characteristic value, tumor type characteristic value, medicine type characteristic value, patient heart rate characteristic value and armpit temperature characteristic value.

3. The method for controlling the dosage of a chemotherapeutic infusion drug as in claim 1, wherein the first predetermined threshold range comprises a comfortable temperature threshold range, a tolerable temperature threshold range; the comfort temperature threshold range comprises a lower comfort temperature limit and an upper comfort temperature limit, and the tolerance temperature threshold range comprises a lower tolerance temperature limit and an upper tolerance temperature limit, wherein the lower comfort temperature limit is greater than the lower tolerance temperature limit, and the upper comfort temperature limit is less than the upper tolerance temperature limit;

the adjusting the scalp temperature characteristic value within the first preset threshold range to update the medicine parameter characteristic value comprises the following steps:

regulating the scalp temperature characteristic value within the comfortable temperature threshold value range to update the medicine parameter characteristic value, and re-inputting the medicine dose control model to obtain a medicine dose prediction classification result;

if the predicted classification result of the medicine dose obtained by adjusting the scalp temperature characteristic value within the comfortable temperature threshold range is that the medicine dose is not appropriate, adjusting the scalp temperature characteristic value within the tolerance temperature threshold range to update the medicine parameter characteristic value outside the comfortable temperature threshold range.

4. The method for controlling the dosage of a chemotherapeutic infusion drug as in claim 1, wherein said second predetermined threshold range comprises: a strong efficacy speed threshold range and a critical efficacy speed threshold range; the high curative effect speed threshold range comprises a low curative effect speed limit and a high curative effect speed limit, and the critical curative effect speed threshold range comprises a lower critical curative effect speed limit and an upper critical curative effect speed limit, wherein the lower high curative effect speed limit is greater than the lower critical curative effect speed limit, and the upper high curative effect speed limit is smaller than the upper critical curative effect speed limit;

the adjusting the medicine infusion speed characteristic value within a second preset threshold range to update the medicine parameter characteristic value comprises the following steps:

adjusting the drug infusion speed characteristic value within the range of the high curative effect speed threshold value to update the drug parameter characteristic value, and re-inputting the drug dose control model to obtain a prediction classification result of the drug dose;

if the predicted classification result of the medicine dosage obtained by adjusting the medicine infusion speed characteristic value within the high curative effect speed threshold range is that the medicine dosage is not appropriate, adjusting the medicine infusion speed characteristic value within the critical curative effect speed threshold range outside the high curative effect speed threshold range to update the medicine parameter characteristic value.

5. The method for controlling the dosage of a chemotherapeutic infusion solution drug according to any one of claims 1 to 4, wherein before inputting the characteristic value of the drug parameter into the trained drug dosage control model, the training of the drug dosage control model comprises:

acquiring a training sample set, wherein samples of the training sample set comprise a medical parameter feature sequence and a dose classification label; the medical parameter characteristic value in the medical parameter characteristic sequence comprises: a scalp temperature characteristic value, a drug infusion rate characteristic value, and at least one of: the patient information characteristic value, the tumor type characteristic value, the medicine type characteristic value, the patient heart rate characteristic value and the armpit temperature characteristic value, wherein the dose classification label comprises a medicine dose appropriate label and a medicine dose inappropriate label;

inputting the sample into the drug dose control model to carry out logistic regression, and calculating by combining with the feature weight corresponding to the influence factors in the sample to obtain a prediction classification result;

obtaining a cost function according to the prediction classification result and the dose classification label of the sample;

and adjusting the characteristic weight of the drug dose control model according to the value of the cost function until the cost function is converged to obtain the trained drug dose control model.

6. The method for controlling dosage of chemotherapeutic infusion drugs according to claim 5, wherein the step of inputting the sample into the drug dosage control model for logistic regression and calculating the predicted classification result by combining the feature weights corresponding to the influencing factors in the sample comprises:

inputting the sample into the drug dose control model to carry out logistic regression, and calculating by combining with the characteristic weight corresponding to the influence factors in the sample to obtain a prediction classification probability value;

and inputting the prediction classification probability value into a nonlinear activation function to obtain a prediction classification result.

7. The method of claim 6, wherein said deriving a cost function from said predicted classification result and said sample dose classification label comprises:

calculating a likelihood estimation function of the prediction classification result according to the dose classification label of the sample;

logarithm is taken for the likelihood estimation function, and a cost function is obtained according to the result after logarithm taking;

expressed as:

wherein p represents a probability, y represents a dose classification label, x represents a drug parameter characteristic value in the sample,

a function representing the likelihood estimation is performed,

representing a cost function.

8. The method for controlling the dose of a chemotherapeutic infusion fluid according to claim 7, wherein the adjusting the characteristic weights of the drug dose control model according to the value of the cost function comprises:

and calculating the minimum value of the cost function by using a gradient descent method, and adjusting the characteristic weight of the drug dose control model.

9. The method for controlling dosage of chemotherapeutic infusion drugs as claimed in claim 5, further comprising, after training the model for controlling dosage of drugs:

acquiring a verification information set;

inputting the verification information set into the drug dose control model to obtain a verification result;

and updating the characteristic weight of the drug dose control model according to the verification result.

10. The method for controlling the dosage of chemotherapeutic infusion drug as claimed in claim 5, wherein an external cooling device is used to adjust the scalp temperature to the scalp temperature corresponding to the scalp temperature characteristic value.

11. The method for controlling the dosage of chemotherapy infusion drugs according to claim 10, wherein the adjusting the scalp temperature to the scalp temperature corresponding to the scalp temperature characteristic value by using the external cooling device comprises:

acquiring the scalp temperature at the current moment by using a temperature sensor;

calculating the temperature difference value of the scalp temperature at the current moment and the scalp temperature corresponding to the scalp temperature characteristic value;

and adjusting the temperature of the cooling liquid in the cooling unit by using a temperature control unit according to the temperature difference value, so that the cooling unit can adjust the scalp temperature by using the cooling liquid to exchange heat with the scalp.

12. A chemotherapy infusion drug dosage control device, comprising:

a characteristic value obtaining module, configured to obtain a drug parameter characteristic value of a patient, where the drug parameter characteristic value includes: scalp temperature characteristic value and medicine infusion speed characteristic value;

an input module, configured to input the drug parameter feature value into a trained drug dose control model to obtain a prediction classification result of a drug dose, where the prediction classification result includes: proper and improper drug dosage; wherein the drug dose is suitable for representing that the absorbed dose of the chemotherapy infusion drug on the scalp does not cause alopecia, and the drug dose is not suitable for representing that the absorbed dose of the chemotherapy infusion drug on the scalp causes alopecia of a patient;

an adjustment module, configured to repeatedly perform the following steps until the predicted classification result indicates that the drug dosage is appropriate:

13. A chemotherapy infusion drug dosage control system, comprising:

a processor unit connected to the external cooling device and the liquid pump flow control device, respectively, for executing the method for controlling the dosage of the chemotherapeutic infusion drug according to any of claims 1 to 11, so as to control the external cooling device and the liquid pump flow control device, thereby realizing the dosage control of the chemotherapeutic infusion drug.

14. A computer-readable storage medium storing computer-executable instructions for performing the method of chemotherapeutic infusion drug dosage control of any of claims 1-11.