A risk management method and system for gynecological drugs

Abstract

The present invention discloses a risk control method and system for gynecological drugs, which relates to the field of drug supervision technology, and realizes real-time modification of drug formulas according to the real-time physical condition data of patients. The present invention generates a characteristic change data set and a one-dimensional time axis of corresponding disease names according to a number of drug use records, and then integrates the characteristic change data set and the one-dimensional time axis of each disease name to obtain a drug risk detection network, collects the real-time physical condition data of gynecological patients, inputs the real-time physical condition data into the drug risk detection network, and then matches the corresponding one-dimensional time axis, and inputs the real-time physical condition data of gynecological patients into the one-dimensional time axis, and then generates and executes drug formulas in each time interval.

Description

Technical Field

[0001] The present invention relates to the technical field of drug supervision, and in particular to a risk management method and system for gynecological drugs. Background Art

[0002] With the continuous advancement of medical technology, gynecological drugs play an increasingly important role in treating women's health problems. However, with this comes concern about the safety and effectiveness of these drugs. The drug instructions contain information such as the use of the drug and side effects, while the warning information reminds doctors and patients to pay attention to possible risks. It is impossible to modify the drug formula in real time based on the patient's real-time physical condition data. Therefore, a risk management method and system for gynecological drugs is provided. Summary of the invention

[0003] In order to solve the above technical problems, the object of the present invention is to provide a risk management method and system for gynecological drugs.

[0004] In order to achieve the above object, the present invention provides the following technical solutions:

[0005] A risk management system for gynecological drugs, comprising a cloud computing platform, wherein the cloud computing platform is communicatively connected to a drug data management module, a patient information analysis module, and a prescription supervision module;

[0006] The drug data management module is used to extract several disease names from several pre-stored drug use records, and generate corresponding feature change data sets and one-dimensional time axes, and then integrate the feature change data sets and one-dimensional time axes of each disease name to obtain a drug risk detection network;

[0007] The patient information analysis module is used to collect real-time physical condition data of gynecological patients, input the real-time physical condition data into the drug risk detection network, match the corresponding one-dimensional time axis, and send the matching results to the prescription supervision module;

[0008] The prescription monitoring module is used to input the real-time physical condition data of gynecological patients into a one-dimensional time axis, thereby generating and executing drug prescriptions in various time intervals, and generating corresponding drug use records after execution.

[0009] Furthermore, the drug use record includes the name of the disease, the patient's physical condition data before and after drug use, the drug formula, the drug sequence and the time node of use, wherein the drug formula consists of multiple drug names and corresponding dosages.

[0010] Furthermore, the process of establishing the feature change data set includes:

[0011] The physical condition data in the drug use record is composed of several types of change curves. N two-dimensional coordinate systems are established according to the number of types of change curves contained in the physical condition data, and the change curves of the same type in different drug use records are mapped to the same two-dimensional coordinate system. At the same time, a normal change curve corresponding to the type of change curve is set on each two-dimensional coordinate system, where N is a natural number greater than 0;

[0012] Several time segments of equal length are divided on the two-dimensional coordinate system, and the values ​​of the change curves of each type at time 0 are compared with the values ​​on the corresponding normal change curves, so as to obtain the abnormal change curves under each disease name, and integrate the abnormal change curves to generate the characteristic change data set of the corresponding disease name.

[0013] Furthermore, the establishment of the one-dimensional time axis includes:

[0014] A multi-dimensional time axis is set, and all physical condition data in multiple drug use records of drug formulas of the same drug type are simultaneously mapped on the multi-dimensional time axis, and corresponding time nodes are divided on the multi-dimensional time axis according to the use time nodes of each drug in the drug use record;

[0015] According to the rising or suppressing trend of each type of change curve in each time segment, the corresponding event time nodes are marked on the multi-dimensional time axis. At the same time, according to the use time nodes of each drug in the drug formula, the use dosage of the corresponding type of drug is marked under the corresponding time node;

[0016] Set a normal change range for each type of change curve, record the coordinate point on the change curve associated with each drug at the use time node as the starting state value, and record the coordinate point on the change curve associated with the drug at the next time node as the end state value;

[0017] Obtain the endpoint state value reached by each starting state value at different dosages of the corresponding drug, and determine whether the endpoint state value at each dosage is within the normal variation range, and generate a corresponding dosage, starting state value, and endpoint state value combination according to the determination result;

[0018] Establish K one-dimensional time axes according to the number of disease names, and then mark the corresponding drug time nodes on the one-dimensional time axis according to the use time nodes of each drug in each disease name, and mark the corresponding drug name for each drug time node, where K is a natural number greater than 0;

[0019] According to the number of change curve types in the characteristic change data set corresponding to the disease name, the same number of state starting nodes are set, and each state starting node is labeled with the corresponding change curve name. Then, according to the type of change curve associated with each drug, each state starting node is mapped to the drug time node corresponding to the one-dimensional time axis.

[0020] Furthermore, the characteristic change data sets of each disease name are bound to the corresponding one-dimensional time axis, and then the one-dimensional time axis of each disease name is integrated to obtain a drug risk detection network.

[0021] Furthermore, the process of matching the real-time physical condition data with the one-dimensional time axis includes:

[0022] The patient information analysis module collects real-time physical condition data of gynecological patients, including real-time body temperature value, real-time blood sugar value, etc.

[0023] Compare each real-time value in the real-time physical condition data with the corresponding preset normal condition range, and obtain the abnormal real-time value according to the comparison result;

[0024] The patient information analysis module collects statistics on abnormal real-time numerical names, retrieves the characteristic change data set of each disease name from the drug risk detection network, and matches the abnormal real-time numerical names with the characteristic change data set;

[0025] If the real-time numerical name of the abnormality is the same as the data name corresponding to the abnormal change curve in the feature change data set, the drug risk detection network will send the one-dimensional time axis and the real-time physical condition data of the gynecological patient to the prescription supervision module based on the one-dimensional time axis corresponding to the feature change data set. Otherwise, it is judged that the feature change data set does not match the patient.

[0026] Furthermore, if there is no abnormal real-time numerical name and the same feature change data set, a prompt is sent to the consulting doctor, who plans the corresponding drug prescription and generates a drug usage record after the drug prescription is executed and sends it to the drug data management module. The drug data management module then generates a corresponding one-dimensional time axis and feature change data set and inputs it into the drug risk detection network.

[0027] Furthermore, the generation and execution process of the drug formula includes:

[0028] The prescription supervision module matches the dosage usage nodes in the one-dimensional coordinate axis according to the real-time physical condition data of the gynecological patient, and then generates a corresponding drug formula according to the matched starting state value, wherein the drug formula includes the drug and the dosage;

[0029] According to the time interval between each drug time node on the one-dimensional time axis, whenever the corresponding time interval ends, the prescription supervision module obtains the real-time physical condition data of the gynecological patient, and generates the drug formula used in the next interval according to the real-time physical condition data corresponding to each starting state value in the new drug time node, and repeats the above operation of generating the drug formula until the real-time physical condition data of the gynecological patient has no abnormal real-time value or the corresponding one-dimensional time axis ends, and at the end, generates the corresponding drug usage record and sends it to the drug data management module.

[0030] A risk control method for a risk control system of gynecological drugs, comprising the following steps:

[0031] Step S1, generating a characteristic change data set and a one-dimensional time axis of a corresponding disease name according to a number of drug use records, and then integrating the characteristic change data sets and the one-dimensional time axis of each disease name to obtain a drug risk detection network;

[0032] Step S2, collecting real-time physical condition data of gynecological patients, inputting the real-time physical condition data into the drug risk detection network, and then matching the corresponding one-dimensional time axis;

[0033] Step S3: input the real-time physical condition data of the gynecological patient into the one-dimensional time axis, and then generate and execute the drug prescriptions in each time interval, and generate corresponding drug use records after the execution is completed.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] The present invention generates a characteristic change data set and a one-dimensional time axis of corresponding disease names based on a number of drug use records, and then integrates the characteristic change data set and the one-dimensional time axis of each disease name to obtain a drug risk detection network, collects real-time physical condition data of gynecological patients, inputs the real-time physical condition data into the drug risk detection network, and then matches the corresponding one-dimensional time axis, inputs the real-time physical condition data of gynecological patients into the one-dimensional time axis, and then generates and executes drug prescriptions in each time interval, thereby realizing real-time modification of drug prescriptions according to the real-time physical condition data of patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention.

[0037] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0038] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0039] like Figure 1 As shown, a risk management system for gynecological drugs includes a cloud computing platform, wherein the cloud computing platform is communicatively connected to a drug data management module, a patient information analysis module, and a prescription supervision module;

[0040] The drug data management module is used to extract several disease names from several pre-stored drug use records, and generate corresponding feature change data sets and one-dimensional time axes, and then integrate the feature change data sets and one-dimensional time axes of each disease name to obtain a drug risk detection network, and send the drug risk detection network to the patient information analysis module and the patient information analysis module;

[0041] The patient information analysis module is used to collect real-time physical condition data of gynecological patients, input the real-time physical condition data into the drug risk detection network, match the corresponding one-dimensional time axis, and send the matching results to the prescription supervision module;

[0042] The prescription monitoring module is used to input the real-time physical condition data of gynecological patients into a one-dimensional time axis, thereby generating and executing drug prescriptions in various time intervals, and generating corresponding drug use records after execution.

[0043] Further, the working principle of the present invention is described below by way of examples:

[0044] The drug data management module pre-stores Num drug usage records of a number of gynecological drugs, where Num is a natural number greater than 0;

[0045] The drug use record includes the name of the disease, the patient's physical condition data before and after drug use, the drug formula, the drug sequence and the time node of use, wherein the drug formula consists of multiple drug names and corresponding dosages;

[0046] The process of generating a drug risk detection network based on the drug use records:

[0047] The physical condition data in the drug use record includes body temperature change curve, blood sugar change curve, hormone concentration change curve, etc.;

[0048] According to the number of types of change curves contained in the physical condition data, N two-dimensional coordinate systems are established, and the change curves of the same type in the different drug use records are mapped to the same two-dimensional coordinate system, and at the same time, a normal change curve corresponding to the type of change curve is set on each two-dimensional coordinate system, where N is a natural number greater than 0;

[0049] A number of time segments of equal length are divided on a two-dimensional coordinate system, and then the gap area value between each change curve and its corresponding normal change curve in each time segment is obtained. Depending on whether the change curve is above or below its corresponding normal change curve, the corresponding gap area value has a positive or negative sign;

[0050] If the gap area value has a positive sign, it is judged that the patient's corresponding type of physical condition data has an upward trend in the corresponding time period;

[0051] If the gap area has a negative sign, it is judged that within the corresponding time period, the patient's corresponding type of physical condition data has a suppression trend;

[0052] At the same time, the values ​​of each type of change curve at time 0 are compared with the values ​​on the corresponding normal change curve, so as to obtain the abnormal change curve under each disease name, and integrate the abnormal change curve to generate the characteristic change data set of the corresponding disease name;

[0053] A multi-dimensional time axis is set, and all physical condition data in multiple drug use records of drug formulas of the same drug type are simultaneously mapped on the multi-dimensional time axis, and corresponding time nodes are divided on the multi-dimensional time axis according to the use time nodes of each drug in the drug use record;

[0054] According to the rising or suppressing trend of each type of change curve in each time segment, the corresponding event time nodes are marked on the multi-dimensional time axis. At the same time, according to the use time nodes of each drug in the drug formula, the use dosage of the corresponding type of drug is marked under the corresponding time node;

[0055] A normal change range interval is set for each type of change curve. It should be noted that the center position value of the normal change range interval is the value of the corresponding normal change curve;

[0056] The coordinate point on the change curve associated with each drug at the use time node is recorded as the starting state value, and the coordinate point on the change curve associated with the drug at the next time node is recorded as the end state value;

[0057] It should be noted that for drug formulations with different dosages, each corresponding drug has multiple starting state values ​​at the same time node on the multidimensional time axis;

[0058] Then, the endpoint state values ​​reached by each starting state value at different dosages of the corresponding drug are obtained, and it is determined whether the endpoint state values ​​at each dosage are within the normal variation range;

[0059] If not, it is judged that the corresponding combination of dosage, starting state value and end state value has risk;

[0060] If not, there is a risk in retaining the corresponding combination of dosage, starting state value, and endpoint state value.

[0061] Furthermore, K one-dimensional time axes are established according to the number of disease names, and then the corresponding drug time nodes are marked on the one-dimensional time axis according to the use time nodes of each drug in each disease name, and the corresponding drug name is marked for each drug time node, where K is a natural number greater than 0;

[0062] According to the number of change curve types in the characteristic change data set corresponding to the disease name, the same number of state start nodes are set, and the corresponding change curve name is marked on each state start node, and then according to the type of change curve associated with each drug, each state start node is mapped to the drug time node corresponding to the one-dimensional time axis;

[0063] According to the dosage of each drug, the starting state value and the end state value combination, a corresponding number of dosage use nodes are set in each state starting node;

[0064] The characteristic change data sets of each disease name are bound to the corresponding one-dimensional time axis, and then the one-dimensional time axis of each disease name is integrated to obtain a drug risk detection network.

[0065] Further, the drug data management module sends the drug risk detection network to the patient information analysis module and the prescription supervision module;

[0066] The patient information analysis module collects real-time physical condition data of gynecological patients, including real-time body temperature value, real-time blood sugar value, etc.

[0067] Compare each real-time value in the real-time physical condition data with the corresponding preset normal condition range;

[0068] If the real-time value is not within the normal range, it is judged that the corresponding real-time value is abnormal; if the real-time value is within the normal range, it is judged that the corresponding real-time value is normal;

[0069] The patient information analysis module collects statistics on abnormal real-time numerical names, retrieves the characteristic change data set of each disease name from the drug risk detection network, and matches the abnormal real-time numerical names with the characteristic change data set;

[0070] If the name of the abnormal real-time numerical value is the same as the data name corresponding to the abnormal change curve in the feature change data set, the drug risk detection network sends the one-dimensional time axis and the real-time physical condition data of the gynecological patient to the prescription supervision module according to the one-dimensional time axis corresponding to the feature change data set;

[0071] Otherwise, it is judged that the feature change dataset does not match the patient;

[0072] It should be noted that if there is no abnormal real-time numerical name and the same feature change data set, a prompt will be sent to the consulting doctor, who will plan the corresponding drug prescription and generate a drug usage record after the drug prescription is executed and send it to the drug data management module. The drug data management module then generates the corresponding one-dimensional time axis and feature change data set and inputs it into the drug risk detection network.

[0073] Furthermore, the prescription supervision module matches the dosage usage node in the one-dimensional coordinate axis according to the real-time physical condition data of the gynecological patient, and then generates a corresponding drug formula according to the matched starting state value, wherein the drug formula includes the drug and the dosage;

[0074] According to the time interval between each drug time node on the one-dimensional time axis, whenever the corresponding time interval ends, the prescription supervision module obtains the real-time physical condition data of the gynecological patient, and generates the drug formula used in the next interval according to the real-time physical condition data corresponding to each starting state value in the new drug time node, and repeats the above operation of generating the drug formula until the real-time physical condition data of the gynecological patient has no abnormal real-time value or the corresponding one-dimensional time axis ends, and at the end, generates the corresponding drug usage record and sends it to the drug data management module.

[0075] The present invention also discloses a risk control method for a risk control system of gynecological drugs, comprising the following steps:

[0076] Step S1, generating a characteristic change data set and a one-dimensional time axis of a corresponding disease name according to a number of drug use records, and then integrating the characteristic change data sets and the one-dimensional time axis of each disease name to obtain a drug risk detection network;

[0077] Step S2, collecting real-time physical condition data of gynecological patients, inputting the real-time physical condition data into the drug risk detection network, and then matching the corresponding one-dimensional time axis;

[0078] Step S3: input the real-time physical condition data of the gynecological patient into the one-dimensional time axis, and then generate and execute the drug prescriptions in each time interval, and generate corresponding drug use records after the execution is completed.

[0079] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A risk management system for gynecological drugs, comprising a cloud computing platform, characterized in that: The cloud computing platform is communicatively connected to a drug data management module, a patient information analysis module, and a prescription supervision module; The drug data management module is used to extract several disease names from several pre-stored drug use records, and generate corresponding feature change data sets and one-dimensional time axes, and then integrate the feature change data sets and one-dimensional time axes of each disease name to obtain a drug risk detection network; The drug use record includes the name of the disease, the patient's physical condition data before and after drug use, the drug formula, the drug sequence and the time node of use, wherein the drug formula consists of multiple drug names and corresponding dosages; The process of establishing the feature change data set includes: The physical condition data in the drug use record is composed of several types of change curves. N two-dimensional coordinate systems are established according to the number of types of change curves contained in the physical condition data, and the change curves of the same type in different drug use records are mapped to the same two-dimensional coordinate system. At the same time, a normal change curve corresponding to the type of change curve is set on each two-dimensional coordinate system, where N is a natural number greater than 0; Divide a number of time segments of equal length on the two-dimensional coordinate system, compare the values ​​of each type of change curve at time 0 with the values ​​on its corresponding normal change curve, and then obtain the abnormal change curve under each disease name, and integrate the abnormal change curves to generate the characteristic change data set corresponding to the disease name; The establishment of the one-dimensional time axis includes: A multi-dimensional time axis is set, and all physical condition data in multiple drug use records of drug formulas of the same drug type are simultaneously mapped on the multi-dimensional time axis, and corresponding time nodes are divided on the multi-dimensional time axis according to the use time nodes of each drug in the drug use record; According to the use time nodes of each drug in the drug formula, the use dosage of the corresponding type of drug is marked at the corresponding time node, and the normal change range interval is set for each type of change curve. The coordinate point on the change curve associated with the corresponding drug at the use time node of each drug is recorded as the starting state value, and the coordinate point on the change curve associated with the corresponding drug at the next time node is recorded as the end state value; Obtain the endpoint state value reached by each starting state value at different dosages of the corresponding drug, and determine whether the endpoint state value at each dosage is within the normal variation range, and generate a corresponding dosage, starting state value, and endpoint state value combination according to the determination result; Establish K one-dimensional time axes according to the number of disease names, and then mark the corresponding drug time nodes on the one-dimensional time axis according to the use time nodes of each drug in each disease name, and mark the corresponding drug name for each drug time node, where K is a natural number greater than 0; According to the number of change curve types in the characteristic change data set corresponding to the disease name, the same number of state start nodes are set, and the corresponding change curve name is marked on each state start node, and then according to the type of change curve associated with each drug, each state start node is mapped to the drug time node corresponding to the one-dimensional time axis; The patient information analysis module is used to collect real-time physical condition data of gynecological patients, input the real-time physical condition data into the drug risk detection network, and then match the corresponding one-dimensional time axis, and send the matching results to the prescription supervision module; The prescription monitoring module is used to input the real-time physical condition data of gynecological patients into a one-dimensional time axis, thereby generating and executing drug prescriptions in various time intervals, and generating corresponding drug use records after execution.

2. A risk management system for gynecological drugs according to claim 1, characterized in that: The characteristic change data sets of each disease name are bound to the corresponding one-dimensional time axis, and then the one-dimensional time axis of each disease name is integrated to obtain a drug risk detection network.

3. A risk management system for gynecological drugs according to claim 2, characterized in that: The process of matching the real-time physical condition data with the one-dimensional time axis includes: The patient information analysis module collects the real-time physical condition data of gynecological patients, compares each real-time value in the real-time physical condition data with the corresponding preset normal condition range, and obtains the real-time value with abnormalities according to the comparison results; The patient information analysis module collects statistics on abnormal real-time numerical names, retrieves the characteristic change data set of each disease name from the drug risk detection network, and matches the abnormal real-time numerical names with the characteristic change data set; If the real-time numerical name of the abnormality is the same as the data name corresponding to the abnormal change curve in the feature change data set, the drug risk detection network will send the one-dimensional time axis and the real-time physical condition data of the gynecological patient to the prescription supervision module based on the one-dimensional time axis corresponding to the feature change data set. Otherwise, it is judged that the feature change data set does not match the patient.

4. A risk management system for gynecological drugs according to claim 3, characterized in that: If there is no abnormal real-time numerical name and the same feature change data set, a prompt will be sent to the consulting doctor, who will plan the corresponding drug prescription and generate a drug usage record after the drug prescription is executed and send it to the drug data management module. The drug data management module will then generate the corresponding one-dimensional time axis and feature change data set and input it into the drug risk detection network.

5. A risk management system for gynecological drugs according to claim 4, characterized in that: The generation and execution process of the drug formula includes: The prescription supervision module matches the dosage usage nodes in the one-dimensional coordinate axis according to the real-time physical condition data of the gynecological patient, and then generates a corresponding drug formula according to the matched starting state value, wherein the drug formula includes the drug and the dosage; According to the time interval between each drug time node on the one-dimensional time axis, whenever the corresponding time interval ends, the prescription supervision module obtains the real-time physical condition data of the gynecological patient, and generates the drug formula used in the next interval according to the real-time physical condition data corresponding to each starting state value in the new drug time node, and repeats the above operation of generating the drug formula until the real-time physical condition data of the gynecological patient has no abnormal real-time value or the corresponding one-dimensional time axis ends, and at the end, generates the corresponding drug usage record and sends it to the drug data management module.

6. A risk control method for a risk control system for gynecological drugs according to any one of claims 1 to 5, characterized in that: The following steps are involved: Step S1, generating a characteristic change data set and a one-dimensional time axis of a corresponding disease name according to a number of drug use records, and then integrating the characteristic change data sets and the one-dimensional time axis of each disease name to obtain a drug risk detection network; Step S2, collecting real-time physical condition data of gynecological patients, inputting the real-time physical condition data into the drug risk detection network, and then matching the corresponding one-dimensional time axis; Step S3: input the real-time physical condition data of the gynecological patient into the one-dimensional time axis, and then generate and execute the drug prescriptions in each time interval, and generate corresponding drug use records after the execution is completed.

Images