CN115312152B - Medicine early warning system based on clinical test platform - Google Patents
Medicine early warning system based on clinical test platform Download PDFInfo
- Publication number
- CN115312152B CN115312152B CN202211074626.8A CN202211074626A CN115312152B CN 115312152 B CN115312152 B CN 115312152B CN 202211074626 A CN202211074626 A CN 202211074626A CN 115312152 B CN115312152 B CN 115312152B
- Authority
- CN
- China
- Prior art keywords
- reaction
- test
- body data
- thread
- component
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
Abstract
The invention provides a drug early warning system based on a clinical test platform, which comprises: the direct analysis end is used for determining direct influence components contained in the effective components in the test drugs based on the test items; the personality determination end is used for determining personality influence components in the test medicines based on the special body data of the test patients; the reaction prediction end is used for predicting a test reaction thread of a corresponding test patient based on the direct influence component, the individual influence component and the drug reaction mechanism library; the clinical record end is used for carrying out clinical tests on corresponding test patients based on the test items, recording the clinical response of the corresponding test patients in real time, and obtaining a clinical response record thread; the medicine early warning end is used for judging whether to send out an alarm or not based on the test reaction thread and the clinical reaction thread; to ensure the safety of test patients to a greater extent without labor cost and experience.
Description
Technical Field
The invention relates to the technical field of fusion of clinical tests and drug early warning, in particular to a drug early warning system based on a clinical test platform.
Background
Currently, all countries require pharmaceutical companies to perform clinical trials with human testing before new drugs are marketed. Pharmaceutical factories or their agents are required to conduct clinical trials for newly designed drugs to ensure the efficacy and side effects of the drugs, etc.
However, since new medicines are adopted in clinical tests and physiological differences exist among patients, new medicine reactions or human body reactions may be generated in the test process, and further, machine early warning cannot be performed on the reaction of the tested patients to the medicines comprehensively and effectively based on manual experience.
Therefore, the invention provides a drug early warning system based on a clinical test platform.
Disclosure of Invention
The invention provides a medicine early warning system based on a clinical test platform, which is used for predicting a predicted reaction thread of a corresponding test patient to the test medicine by analyzing and mining the effective components of the test medicine and the body data of the test patient, and realizing effective early warning of the reaction of the test patient to the test medicine by combining the clinical reaction record thread of the test patient in the clinical test process, so that the safety of the test patient is ensured to a greater extent under the condition of no labor cost and no manual experience.
The invention provides a drug early warning system based on a clinical test platform, which comprises:
the direct analysis end is used for determining direct influence components contained in the effective components in the test drugs based on the test items;
the personality determination end is used for determining personality influence components in the test medicines based on the special body data of the test patients;
the reaction prediction end is used for predicting a test reaction thread of a corresponding test patient based on the direct influence component, the individual influence component and the drug reaction mechanism library;
the clinical record end is used for carrying out clinical tests on corresponding test patients based on the test items, recording the clinical response of the corresponding test patients in real time, and obtaining a clinical response record thread;
and the medicine early warning end is used for judging whether to send out an alarm or not based on the test reaction thread and the clinical reaction thread.
Preferably, the direct analysis end comprises:
the effective determination module is used for determining effective components in the test medicines based on the test items;
and the direct determination module is used for determining a corresponding predicted drug response mechanism based on the test item, and taking the components participating in the predicted drug response mechanism in the effective components as direct influence components.
Preferably, the personality determination terminal includes:
the special determining module is used for determining special body data of the test patient based on the standard body data range and the historical medical data;
and the personality determination module is used for taking the components which have influence on the special body data in the effective components of the test medicines as personality influence components.
Preferably, the special determination module includes:
a first determination unit configured to take sub-body data exceeding a standard body data range among current body data of a test patient as first special body data;
a second determining unit for determining second special body data of the trial patient based on the historical body data and the historical medication response data and the medical history data included in the historical hospitalization data of the trial patient;
and the deduplication summarizing unit is used for performing deduplication summarization on the first special body data and the second special body data to obtain the special body data of the test patient.
Preferably, the second determining unit includes:
a first determination subunit operable to determine, as first sub-specific body data, sub-body data exceeding a standard body data range among historic body data included in historic medical data of the trial patient;
A second determination subunit operable to take, as second sub-specific body data, response body data corresponding to excessive response data and insufficient response data in the historical medication response data of the trial patient;
a third determination subunit for taking as third sub-specific body data sub-body data affected by the medical history data of the trial patient;
and the deduplication summarizing subunit is used for performing deduplication summarization on the first sub-special body data, the second sub-special body data and the third sub-special body data to obtain second special body data of the test patient.
Preferably, the reaction prediction end comprises:
the first prediction module is used for predicting a first test response of a corresponding test patient to the direct influence component based on a direct influence mechanism of the direct influence component;
the second prediction module is used for predicting a second test response of the corresponding test patient to the individual influence component based on the individual influence component and the individual influence mechanism;
the third prediction module is used for predicting a third test response of the corresponding test patient to the effective component based on the drug response mechanism library;
and the time sequence recording module is used for sequencing and superposing the first test reaction, the second test reaction and the third test reaction based on the predicted occurrence time to obtain test reaction threads of corresponding test patients.
Preferably, the third prediction module includes:
a combination determination unit configured to determine a combination of components that can undergo secondary reactions among the effective components based on the component reaction mechanisms contained in the drug reaction mechanism library;
the first generation unit is used for judging whether repeated components exist in the component combination, if so, determining a corresponding first reaction speed based on a component reaction mechanism corresponding to the repeated component combination with the repeated components, and generating a first reaction thread corresponding to the repeated component combination in real time based on the first reaction speed and the real-time component content in the corresponding repeated component combination;
the second generation unit is used for determining a corresponding second reaction speed based on a component reaction mechanism corresponding to the component combination without repeated components, and generating a second reaction thread corresponding to the component combination in real time based on the second reaction speed and the real-time component content in the corresponding component combination;
the first alignment unit is used for aligning all the first reaction threads with all the second reaction threads to obtain simultaneous reaction threads;
the third generation unit is used for determining a corresponding third reaction speed based on the component reaction mechanisms corresponding to all the component combinations and generating a third reaction thread corresponding to the component combinations in real time based on the third reaction speed and the real-time component content in the corresponding component combinations when the fact that the repeated components do not exist in the component combinations is judged;
The second alignment unit is used for aligning all the third reaction threads to obtain simultaneous reaction threads;
the latest determining unit is used for determining the real-time component content of the new component and the effective component generated by component reaction based on the simultaneous reaction thread, and determining a new component combination which can be reacted again from the current residual effective components based on the new component and the real-time component content and the component reaction mechanism contained in the drug reaction mechanism library;
and the latest generation unit is used for generating a new simultaneous reaction thread based on the new component combination and the simultaneous reaction thread, and predicting a third test reaction of the corresponding test patient on the active components based on the current residual active components when the components which can react and correspond to the component reaction mechanisms contained in the drug reaction mechanism library are no longer present in the current residual active components.
Preferably, the timing recording module includes:
the reaction sequencing unit is used for sequencing the first test reaction, the second test reaction and the third test reaction based on the predicted occurrence time to obtain a reaction record thread;
and the reaction superposition unit is used for sequentially carrying out reaction superposition on the first test reaction, the second test reaction and the third test reaction based on the reaction record thread and the reaction superposition mechanism, so as to obtain the test reaction thread of the corresponding test patient.
Preferably, the clinical record end comprises:
the plan determining module is used for determining a corresponding test plan based on the test items;
and the clinical recording module is used for carrying out clinical tests on corresponding test patients based on the test plan, recording clinical response body data of the corresponding test patients in real time and obtaining a clinical response record thread.
Preferably, the medicine early warning end includes:
the thread dividing module is used for dividing the test reaction thread into a reaction presentation time period thread and a non-reaction presentation time period thread, and carrying out secondary division on the reaction presentation time period thread based on the predicted occurrence time to obtain a final dividing thread comprising a plurality of sub-reaction presentation time period threads;
the alignment marking module is used for generating a body data change curve of a corresponding item based on each item of body data in clinical response body data, marking out a sudden change point in each body data change curve, and carrying out time sequence alignment on all the marked body data change curves to obtain an alignment marking curve;
the alignment determining module is used for carrying out head-end alignment on the final dividing thread and the alignment mark curve to obtain an alignment result, judging whether the test patient is currently in the reaction display time period or not based on the alignment result, if so, determining the sub-reaction display time period thread currently corresponding to the test patient and the lasting time of the thread in the corresponding sub-reaction display time period based on the alignment result;
The first judging module is used for determining the total duration of the threads corresponding to the sub-reaction appearing time period, determining a corresponding starting judging time threshold value based on the total duration, judging whether the corresponding lasting time is not smaller than the corresponding starting judging time threshold value, if yes, determining a first alignment mark curve segment corresponding to the corresponding sub-reaction appearing time period in the alignment mark curve, and if not, reserving a corresponding judging result;
the second judging module is used for judging whether the body data types corresponding to the body data change curves of the abrupt change points contained in the first alignment mark curve section are consistent with the corresponding body data types of the threads of the corresponding sub-reaction display time periods, if so, determining the abrupt change body data corresponding to the abrupt change points, determining a standard reaction data range based on the predicted reaction data of the threads of the corresponding sub-reaction display time periods, judging whether the abrupt change body data is in the corresponding standard reaction data range, and if so, reserving the corresponding judging result;
the third judging module is used for sending out an alarm when judging that the body data types corresponding to the body data change curves of the abrupt change points contained in the first alignment mark curve section are inconsistent with the response body data types corresponding to the sub-response presentation time period threads or the abrupt change body data are not in the corresponding standard response data range;
A fourth judging module, configured to determine, when it is determined that the current time period belongs to the non-response presentation time period, a standard response data range of the non-response presentation time period based on body data of the test patient, determine a second alignment mark curve segment corresponding to the non-response presentation time period in the alignment mark curve, and judge whether each body data corresponding to the second alignment mark curve segment is within the corresponding standard response data range, if yes, determine to retain the corresponding judging result, otherwise, send an alarm;
the method for determining the corresponding starting judgment time threshold based on the total duration comprises the following steps:
wherein t is y In order to start judging the time threshold value, alpha is the preset duty ratio of the start judging time threshold value, t all For a total duration t safe The maximum safe reaction time is preset;
wherein determining a standard reaction data range based on predicted reaction data corresponding to the sub-reaction presentation time period thread comprises:
determining a fluctuation coefficient of predicted reaction data corresponding to the sub-reaction presentation time period thread, and determining a corresponding standard reaction data range based on the fluctuation coefficient and the predicted reaction data:
g 0 ＝[(1+β)g y ,(1-β)g y ]
in the formula g 0 For the standard reaction data range, beta is the fluctuation coefficient of the predicted reaction data corresponding to the sub-reaction presentation time period thread, g y Predicted reaction data for threads corresponding to sub-reaction presentation time periods.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of a drug early warning system based on a clinical test platform in an embodiment of the invention;
FIG. 2 is a schematic diagram of a direct analysis end in an embodiment of the present invention;
FIG. 3 is a schematic diagram of a personality determination terminal according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a special determination module according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a second determining unit according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a reaction prediction end according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a third prediction module according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of a timing recording module according to an embodiment of the present invention;
FIG. 9 is a schematic diagram of a clinical record end according to an embodiment of the present invention;
fig. 10 is a schematic diagram of a drug early warning end in an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
Example 1:
the invention provides a drug early warning system based on a clinical test platform, referring to fig. 1, comprising:
the direct analysis end is used for determining direct influence components contained in the effective components in the test drugs based on the test items;
the personality determination end is used for determining personality influence components in the test medicines based on the special body data of the test patients;
the reaction prediction end is used for predicting a test reaction thread of a corresponding test patient based on the direct influence component, the individual influence component and the drug reaction mechanism library;
the clinical record end is used for carrying out clinical tests on corresponding test patients based on the test items, recording the clinical response of the corresponding test patients in real time, and obtaining a clinical response record thread;
And the medicine early warning end is used for judging whether to send out an alarm or not based on the test reaction thread and the clinical reaction thread.
In this example, the test item is an item for clinical testing of the test drug.
In this example, the test drug is the drug administered to the test patient in the clinical trial of the present invention, and is also the drug to be tested in the clinical trial of the present invention.
In this example, the active ingredient is the drug ingredient of the test drug that participates in the drug reaction process.
In this example, the test patient is the patient who is being tested in the clinical trial.
In this example, the directly influencing component is the drug component that directly exerts the drug effect in the test drug.
In this embodiment, the specific body data is the body data of the patient exceeding the range of the body data of the patient corresponding to the ideal state (i.e., the ideal state corresponding to the clinical trial) in the body data of the test patient.
In this embodiment, the individual influencing component is a pharmaceutical component in the test drug that exerts an individual drug effect (due to physiological differences in the test patient) on the corresponding test patient.
In this embodiment, the drug response mechanism library is a pre-prepared database containing all drug response mechanisms (i.e., the response relationships between the drug components) that have now been discovered.
In this embodiment, the test reaction thread is a recording thread of the physical reaction of the test patient to the test drug predicted based on the direct influence component and the individual influence component, and the drug reaction mechanism library.
In this example, the clinical response is the response of the test patient to the test drug during the clinical test (as represented by the physical data of the test patient).
In this embodiment, the clinical response recording thread is a thread for recording the response process (body data change process) of the test patient to the clinical test process.
In this embodiment, the alarm is an early warning signal for alerting the healthcare worker to an unexpected physical response of the test patient to the test medication.
The beneficial effects of the technology are as follows: the method has the advantages that the effective components of the test drugs and the body data of the test patients are analyzed and mined, the prediction reaction thread of the corresponding test patients to the test drugs is predicted, and the clinical reaction record thread of the test patients in the clinical test process is combined, so that the effective early warning of the reaction of the test patients to the test drugs is realized, and the safety of the test patients is ensured to a greater extent under the condition that labor cost and labor experience are not required.
Example 2:
on the basis of example 1, the direct analysis end, referring to fig. 2, comprises:
the effective determination module is used for determining effective components in the test medicines based on the test items;
and the direct determination module is used for determining a corresponding predicted drug response mechanism based on the test item, and taking the components participating in the predicted drug response mechanism in the effective components as direct influence components.
In this embodiment, the predicted drug response mechanism is a drug response mechanism (drug component response relationship) that should be performed in a theoretical state in the test drug determined based on the test item.
The beneficial effects of the technology are as follows: the direct influence component under the theoretical state can be obtained based on the predicted drug reaction mechanism of the test drug in the test item, so that the preliminary determination and analysis of the effective components of the test drug are realized.
Example 3:
on the basis of embodiment 1, the personality determination terminal, referring to fig. 3, includes:
the special determining module is used for determining special body data of the test patient based on the standard body data range and the historical medical data;
and the personality determination module is used for taking the components which have influence on the special body data in the effective components of the test medicines as personality influence components.
In this embodiment, the standard body data range is the patient body data range corresponding to the ideal state (i.e., the ideal state corresponding to the clinical trial).
In this embodiment, the historical medical data is data stored in a historical medical record of a corresponding test patient, for example, including historical body data, historical drug response data, and medical history data.
The beneficial effects of the technology are as follows: based on the standard body data range and the historical medical data, the personalized response possibly caused by the test drug in the test patient is determined, and personalized analysis of the body data of the patient and prediction of the personalized response of the test drug are realized.
Example 4:
on the basis of embodiment 3, the special determination module, referring to fig. 4, includes:
a first determination unit configured to take sub-body data exceeding a standard body data range among current body data of a test patient as first special body data;
a second determining unit for determining second special body data of the trial patient based on the historical body data and the historical medication response data and the medical history data included in the historical hospitalization data of the trial patient;
and the deduplication summarizing unit is used for performing deduplication summarization on the first special body data and the second special body data to obtain the special body data of the test patient.
In this embodiment, the sub-body data is a single body data included in the current body data, such as a blood pressure value.
In this embodiment, the first specific body data is sub-body data exceeding the standard body data range among the current body data of the test patient.
In this embodiment, the historical business data is body data obtained by once detecting a test patient included in the historical medical data.
In this embodiment, the historical medication response data is response data to medications in a historical medication record of the test patient included in the historical medical data.
In this embodiment, the medical history data is data related to the medical history of the test patient contained in the historical medical data.
In this embodiment, the second specific body data is specific body data related to the historical body data and the historical medication response data and medical history data contained in the historical hospitalization data of the trial patient, which are determined from the current body data of the trial patient.
In this embodiment, the special body data is obtained by performing deduplication and summarization on the first special body data and the second special body data.
The beneficial effects of the technology are as follows: the method is used for comparing the current body data of the test patient with the standard body data range, and combining the historical body data, the historical drug response data and the medical history data contained in the historical medical treatment data of the test patient to realize personalized mining of the body data of the test patient and comprehensive prediction of the possible personalized reaction of the test drug.
Example 5:
on the basis of embodiment 4, the second determination unit, referring to fig. 5, includes:
a first determination subunit operable to determine, as first sub-specific body data, sub-body data exceeding a standard body data range among historic body data included in historic medical data of the trial patient;
a second determination subunit operable to take, as second sub-specific body data, response body data corresponding to excessive response data and insufficient response data in the historical medication response data of the trial patient;
a third determination subunit for taking as third sub-specific body data sub-body data affected by the medical history data of the trial patient;
and the deduplication summarizing subunit is used for performing deduplication summarization on the first sub-special body data, the second sub-special body data and the third sub-special body data to obtain second special body data of the test patient.
In this embodiment, the first sub-specific body data is sub-body data exceeding the standard body data range in the historical body data included in the historical medical data of the test patient.
In this embodiment, the excessive response data is body data corresponding to the case where the test patient included in the historical drug response data is excessively responsive to the drug.
In this embodiment, the insufficient response data is body data corresponding to the test patient contained in the historical medication response data when responding to medication deficiency.
In this embodiment, the response body data is historical body data corresponding to the excessive response data and the insufficient response data.
In this embodiment, the second sub-specific body data is response body data corresponding to excessive response data and insufficient response data in the historical drug response data of the test patient.
In this embodiment, the third sub-specific body data is the sub-body data affected by the medical history data of the test patient.
In this embodiment, the second specific body data is the specific body data that is active after the first sub-specific body data and the second sub-specific body data are deduplicated and aggregated.
The beneficial effects of the technology are as follows: by respectively analyzing the historical medical treatment data, the historical drug response data and the medical history data of the test patient, the personalized excavation of the physical data of the test patient and the comprehensive prediction of the personalized reaction possibly occurring to the test drug are realized.
Example 6:
on the basis of example 1, the reaction prediction end, referring to fig. 6, includes:
The first prediction module is used for predicting a first test response of a corresponding test patient to the direct influence component based on a direct influence mechanism of the direct influence component;
the second prediction module is used for predicting a second test response of the corresponding test patient to the individual influence component based on the individual influence component and the individual influence mechanism;
the third prediction module is used for predicting a third test response of the corresponding test patient to the effective component based on the drug response mechanism library;
and the time sequence recording module is used for sequencing and superposing the first test reaction, the second test reaction and the third test reaction based on the predicted occurrence time to obtain test reaction threads of corresponding test patients.
In this embodiment, the direct influence mechanism is the mechanism of action when the efficacy of the direct influence component is exerted.
In this embodiment, the first test response is the predicted response (expressed as the change in the physical data) of the corresponding test patient to the direct-influencing component based on the direct-influencing mechanism of the direct-influencing component.
In this embodiment, the individual influencing mechanism is the mechanism of action when the efficacy of the individual influencing component is exerted.
In this embodiment, the second test reaction is a reaction result (represented by a change condition of the body data) of the corresponding test patient to the personality influence component, which is predicted based on the personality influence mechanism of the personality influence component.
In this example, the third test reaction is the result of the reaction (expressed by the change of the physical data) of the new component obtained after the secondary reaction of the corresponding test patient to the active component predicted based on the drug reaction mechanism library.
In this embodiment, the predicted occurrence time is the predicted occurrence time of each of the first test reaction, the second test reaction, and the third test reaction.
In this embodiment, the test reaction thread is a predicted thread representing a reaction process of the test drug corresponding to the test patient after the first test reaction, the second test reaction and the third test reaction are sequentially stacked based on the predicted occurrence time.
The beneficial effects of the technology are as follows: based on the respective corresponding influence mechanisms of the components obtained after the analysis of the effective components of the test drugs, different test reactions are predicted, and the comprehensive prediction of the reaction results of the test patients on the test drugs is realized.
Example 7:
on the basis of embodiment 6, a third prediction module, referring to fig. 7, includes:
a combination determination unit configured to determine a combination of components that can undergo secondary reactions among the effective components based on the component reaction mechanisms contained in the drug reaction mechanism library;
The first generation unit is used for judging whether repeated components exist in the component combination, if so, determining a corresponding first reaction speed based on a component reaction mechanism corresponding to the repeated component combination with the repeated components, and generating a first reaction thread corresponding to the repeated component combination in real time based on the first reaction speed and the real-time component content in the corresponding repeated component combination;
the second generation unit is used for determining a corresponding second reaction speed based on a component reaction mechanism corresponding to the component combination without repeated components, and generating a second reaction thread corresponding to the component combination in real time based on the second reaction speed and the real-time component content in the corresponding component combination;
the first alignment unit is used for aligning all the first reaction threads with all the second reaction threads to obtain simultaneous reaction threads;
the third generation unit is used for determining a corresponding third reaction speed based on the component reaction mechanisms corresponding to all the component combinations and generating a third reaction thread corresponding to the component combinations in real time based on the third reaction speed and the real-time component content in the corresponding component combinations when the fact that the repeated components do not exist in the component combinations is judged;
the second alignment unit is used for aligning all the third reaction threads to obtain simultaneous reaction threads;
The latest determining unit is used for determining the real-time component content of the new component and the effective component generated by component reaction based on the simultaneous reaction thread, and determining a new component combination which can be reacted again from the current residual effective components based on the new component and the real-time component content and the component reaction mechanism contained in the drug reaction mechanism library;
and the latest generation unit is used for generating a new simultaneous reaction thread based on the new component combination and the simultaneous reaction thread, and predicting a third test reaction of the corresponding test patient on the active components based on the current residual active components when the components which can react and correspond to the component reaction mechanisms contained in the drug reaction mechanism library are no longer present in the current residual active components.
In this embodiment, the component response mechanism is the reaction relationship between the drug components contained in the drug response mechanism library.
In this embodiment, the composition of the components is a composition of at least two components which can undergo secondary reactions among the active ingredients based on the component reaction mechanisms contained in the drug reaction mechanism library.
In this embodiment, the duplicate component is a pharmaceutical component contained in both component combinations.
In this embodiment, the repeating component combination is a component combination in which a repeating component exists.
In this embodiment, the first reaction rate is a reaction rate (i.e., a component consumption rate) of the corresponding repeating component combination determined based on the component reaction mechanism corresponding to the repeating component combination.
In this embodiment, the real-time component content is the real-time residual content of each component contained in the repeating component combination.
In this embodiment, the first reaction thread is a thread generated in real time based on the first reaction speed and the real-time component content in the corresponding repeated component combination, and used for representing the process of the corresponding repeated component combination reacting according to the corresponding component reaction mechanism.
In this embodiment, the second reaction rate is a reaction rate (i.e., component consumption rate) of the corresponding component combination determined based on the component reaction mechanism corresponding to the component combination in which the repeated component is not present.
In this embodiment, the second reaction thread is a thread generated in real time based on the second reaction speed and the real-time component content in the corresponding component combination, and used for representing the process of the corresponding component combination reacting according to the corresponding component reaction mechanism.
In this embodiment, the simultaneous reaction thread is a thread that characterizes the simultaneous reaction process in the active ingredients in the test drug.
In this embodiment, the third reaction rate is the reaction rate (i.e., component consumption rate) of the corresponding component combination determined based on the component reaction mechanism corresponding to each component combination when it is determined that there is no duplicate component in the component combination.
In this embodiment, the third reaction thread is a thread generated in real time for characterizing a process in which each component combination reacts according to the corresponding component reaction mechanism when it is determined that there is no repetitive component in the component combination, based on the third reaction speed and the real-time component content in the corresponding component combination.
In this example, the new component is the component produced after the secondary reaction of the active ingredient contained in the test drug.
In this example, the real-time component content is the real-time component content of the active ingredient contained in the test drug during the secondary reaction.
In this embodiment, the new component combination is a component combination that can be reacted again, which is determined from the currently remaining active components, based on the new component and the real-time component content and the component reaction mechanism contained in the drug reaction mechanism library.
In this embodiment, the simultaneous reaction thread is a thread obtained by time-aligning a fourth reaction thread generated based on a new component combination with the simultaneous reaction thread.
In this example, the third test reaction is the reaction that occurs when the active ingredient remaining at present directly exerts its efficacy on the test patient.
The beneficial effects of the technology are as follows: based on the staged analysis of the self-reaction process between the active ingredients in the test medicine, the complete self-reaction process in the test medicine is reduced, so that other ingredients generated in the self-reaction process of the test medicine are predicted, the accurate determination of the ingredients which directly exert the efficacy in the test medicine is realized, and the comprehensive and accurate prediction of the reaction of the test medicine of a test patient is realized.
Example 8:
on the basis of embodiment 6, the timing recording module, referring to fig. 8, includes:
the reaction sequencing unit is used for sequencing the first test reaction, the second test reaction and the third test reaction based on the predicted occurrence time to obtain a reaction record thread;
and the reaction superposition unit is used for sequentially carrying out reaction superposition on the first test reaction, the second test reaction and the third test reaction based on the reaction record thread and the reaction superposition mechanism, so as to obtain the test reaction thread of the corresponding test patient.
In this embodiment, the reaction recording thread is a recording thread for characterizing an occurrence sequence of the test reactions obtained after sequencing the first test reaction, the second test reaction and the third test reaction based on the predicted occurrence time.
In this embodiment, the reaction superposition mechanism is that when the adjacent test reactions will affect the same body data, the influence of the test reaction that occurs later on the corresponding body data is superposed on the influence of the test influence that occurs earlier on the corresponding body data, for example, the former test reaction causes the blood glucose level to rise by 0.3 mmol/l, the latter test reaction causes the blood glucose level to rise by 0.6 mmol/l, and when the test reaction time reaches the latter test reaction, the blood glucose level rises by 0.6 mmol/l based on the initial blood glucose level value.
In this embodiment, the test reaction thread is a thread corresponding to a reaction process of a test patient to a test drug, which is predicted by a characterization obtained by sequentially performing reaction superposition on the first test reaction, the second test reaction and the third test reaction based on the reaction recording thread and the reaction superposition mechanism.
The beneficial effects of the technology are as follows: and sequencing and superposing test reactions in different stages based on the predicted occurrence time and a reaction superposition mechanism, wherein the predicted complete reaction process of the corresponding test patient to the test drug is performed.
Example 9:
on the basis of example 1, the clinical record side, referring to fig. 9, includes:
The plan determining module is used for determining a corresponding test plan based on the test items;
and the clinical recording module is used for carrying out clinical tests on corresponding test patients based on the test plan, recording clinical response body data of the corresponding test patients in real time and obtaining a clinical response record thread.
In this embodiment, the test plan is a clinical test plan corresponding to the test item.
In this example, the clinical response body data is the body data characterizing the change in response to the test drug in the corresponding test patient when the clinical test plan is executed.
In this embodiment, the clinical response record thread is a record thread obtained after recording clinical response physical data of a corresponding test patient in real time when the corresponding test patient is subjected to a clinical test based on a test plan.
The beneficial effects of the technology are as follows: clinical tests are carried out based on test plans corresponding to test items, body data representing the response of patients to test drugs are recorded, and real-time monitoring of the clinical test data of the patients is achieved.
Example 10:
on the basis of embodiment 7, the drug early warning end, referring to fig. 10, includes:
the thread dividing module is used for dividing the test reaction thread into a reaction presentation time period thread and a non-reaction presentation time period thread, and carrying out secondary division on the reaction presentation time period thread based on the predicted occurrence time to obtain a final dividing thread comprising a plurality of sub-reaction presentation time period threads;
The alignment marking module is used for generating a body data change curve of a corresponding item based on each item of body data in clinical response body data, marking out a sudden change point in each body data change curve, and carrying out time sequence alignment on all the marked body data change curves to obtain an alignment marking curve;
the alignment determining module is used for carrying out head-end alignment on the final dividing thread and the alignment mark curve to obtain an alignment result, judging whether the test patient is currently in the reaction display time period or not based on the alignment result, if so, determining the sub-reaction display time period thread currently corresponding to the test patient and the lasting time of the thread in the corresponding sub-reaction display time period based on the alignment result;
the first judging module is used for determining the total duration of the threads corresponding to the sub-reaction appearing time period, determining a corresponding starting judging time threshold value based on the total duration, judging whether the corresponding lasting time is not smaller than the corresponding starting judging time threshold value, if yes, determining a first alignment mark curve segment corresponding to the corresponding sub-reaction appearing time period in the alignment mark curve, and if not, reserving a corresponding judging result;
The second judging module is used for judging whether the body data types corresponding to the body data change curves of the abrupt change points contained in the first alignment mark curve section are consistent with the corresponding body data types of the threads of the corresponding sub-reaction display time periods, if so, determining the abrupt change body data corresponding to the abrupt change points, determining a standard reaction data range based on the predicted reaction data of the threads of the corresponding sub-reaction display time periods, judging whether the abrupt change body data is in the corresponding standard reaction data range, and if so, reserving the corresponding judging result;
the third judging module is used for sending out an alarm when judging that the body data types corresponding to the body data change curves of the abrupt change points contained in the first alignment mark curve section are inconsistent with the response body data types corresponding to the sub-response presentation time period threads or the abrupt change body data are not in the corresponding standard response data range;
a fourth judging module, configured to determine, when it is determined that the current time period belongs to the non-response presentation time period, a standard response data range of the non-response presentation time period based on body data of the test patient, determine a second alignment mark curve segment corresponding to the non-response presentation time period in the alignment mark curve, and judge whether each body data corresponding to the second alignment mark curve segment is within the corresponding standard response data range, if yes, determine to retain the corresponding judging result, otherwise, send an alarm;
The method for determining the corresponding starting judgment time threshold based on the total duration comprises the following steps:
wherein t is y For the threshold of the start judgment time, α is a preset threshold duty ratio of the start judgment time (determined according to the importance degree of the corresponding body data, when the importance degree is higher, α is smaller, and vice versa), t all For a total duration t safe The maximum safe reaction time is preset;
wherein determining a standard reaction data range based on predicted reaction data corresponding to the sub-reaction presentation time period thread comprises:
determining a fluctuation coefficient of predicted reaction data corresponding to the sub-reaction presentation time period thread, and determining a corresponding standard reaction data range based on the fluctuation coefficient and the predicted reaction data:
g 0 ＝[(1+β)g y ,(1-β)g y ]
in the formula g 0 For the standard response data range, β is the fluctuation coefficient of the predicted response data (related to the fluctuation range of the corresponding body data in the safety condition) corresponding to the sub-response presentation period thread, g y Predicted reaction data for threads corresponding to sub-reaction presentation time periods.
In this embodiment, the reaction presentation time period thread is a thread of physical data included in the test reaction thread that characterizes the time period in which the test patient reacts to the test drug.
In this embodiment, the non-response presentation time period thread is a thread of physical data included in the test response thread that characterizes a time period in which the test patient does not respond to the test drug.
In this embodiment, the sub-reaction presentation time period thread is a plurality of thread segments obtained by dividing the reaction presentation time period thread twice based on the predicted occurrence time.
In this embodiment, the final dividing thread is a thread including a plurality of sub-reaction presentation time period threads obtained by performing secondary division on the reaction presentation time period threads based on the predicted occurrence time.
In this embodiment, the body data change curve is a curve of a change process of the corresponding item of body data generated based on each item of body data in the clinical response body data.
In this embodiment, the alignment mark curve is a curve obtained by time-aligning all the body data change curves marked with the abrupt change points.
In this embodiment, the alignment result is a result obtained after head-end alignment is performed on the final divided thread and the alignment mark curve.
In this embodiment, the thread of the sub-reaction presentation time period currently corresponding to the test patient is determined based on the alignment result, which is:
And determining a sub-reaction presentation time period thread corresponding to the current time of the test patient in the final dividing thread based on the alignment result.
In this embodiment, the duration is the time interval between the current time determined based on the alignment result and the start time in the corresponding sub-reaction presentation time period thread.
In this embodiment, the total duration is the duration of the thread in the final partition thread corresponding to the sub-reaction presentation time period.
In this embodiment, the start judgment time threshold is the fastest time for starting early warning judgment on the alignment mark curve when the test patient is currently in the corresponding sub-reaction presentation time period thread in the reaction presentation time period.
In this embodiment, the first alignment mark curve segment is an alignment curve segment in the corresponding sub-reaction appearance time period in the alignment mark curve determined based on the alignment result.
In this embodiment, the type of body data is the type of body data represented by the body data change curve, such as blood glucose level, blood pressure value, and the like.
In this embodiment, the reactive body data type is the body data type that changes (i.e., reacts to the test drug) in the sub-reaction presentation period thread.
In this embodiment, the abrupt body data is the body data corresponding to the abrupt point in the corresponding body data change curve.
In this embodiment, the standard response data range is a body data change range corresponding to the test patient when the response of the test patient to the test drug is normal is determined based on the predicted response data corresponding to the thread of the sub-response presentation time period when the current time period belongs to the response presentation time period, for example, the predicted response data is that the blood glucose content increases by 0.5 mmol/l, and the corresponding standard response data range may be that the blood glucose content increases by 0.3 to 0.7 mmol/l;
alternatively, the patient's safe range of body data fluctuation is tested when the current time period belongs to the non-response manifestation time period.
In this embodiment, the second alignment mark curve segment is an alignment curve segment in the corresponding non-sub-reaction appearance time period in the alignment mark curve determined based on the alignment result.
The beneficial effects of the technology are as follows: the final dividing thread after the stage division of the test reaction thread and the alignment mark curve corresponding to the clinical reaction body data are subjected to real-time alignment analysis, so that the current reaction time period of the test patient can be determined, the alignment mark curve is divided, the corresponding alignment mark curve segment is obtained, the type and the data range of the changed body data contained in the alignment mark curve segment are judged based on the standard reaction data range corresponding to the reaction time period, and the comprehensive judgment and early warning of the reaction of the test patient to the test medicine in the clinical test are realized.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (7)
1. A clinical trial platform based drug early warning system, comprising:
the direct analysis end is used for determining direct influence components contained in the effective components in the test drugs based on the test items;
the personality determination end is used for determining personality influence components in the test medicines based on the special body data of the test patients;
the reaction prediction end is used for predicting a test reaction thread of a corresponding test patient based on the direct influence component, the individual influence component and the drug reaction mechanism library;
the clinical record end is used for carrying out clinical tests on corresponding test patients based on the test items, recording the clinical response of the corresponding test patients in real time, and obtaining a clinical response record thread;
the medicine early warning end is used for judging whether to send out an alarm or not based on the test reaction thread and the clinical reaction thread;
a reaction prediction end comprising:
The first prediction module is used for predicting a first test response of a corresponding test patient to the direct influence component based on a direct influence mechanism of the direct influence component;
the second prediction module is used for predicting a second test response of the corresponding test patient to the individual influence component based on the individual influence component and the individual influence mechanism;
the third prediction module is used for predicting a third test response of the corresponding test patient to the effective component based on the drug response mechanism library;
the time sequence recording module is used for sequencing and superposing the first test reaction, the second test reaction and the third test reaction based on the predicted occurrence time to obtain test reaction threads of corresponding test patients;
a third prediction module comprising:
a combination determination unit configured to determine a combination of components that can undergo secondary reactions among the effective components based on the component reaction mechanisms contained in the drug reaction mechanism library;
the first generation unit is used for judging whether repeated components exist in the component combination, if so, determining a corresponding first reaction speed based on a component reaction mechanism corresponding to the repeated component combination with the repeated components, and generating a first reaction thread corresponding to the repeated component combination in real time based on the first reaction speed and the real-time component content in the corresponding repeated component combination;
The second generation unit is used for determining a corresponding second reaction speed based on a component reaction mechanism corresponding to the component combination without repeated components, and generating a second reaction thread corresponding to the component combination in real time based on the second reaction speed and the real-time component content in the corresponding component combination;
the first alignment unit is used for aligning all the first reaction threads with all the second reaction threads to obtain simultaneous reaction threads;
the third generation unit is used for determining a corresponding third reaction speed based on the component reaction mechanisms corresponding to all the component combinations and generating a third reaction thread corresponding to the component combinations in real time based on the third reaction speed and the real-time component content in the corresponding component combinations when the fact that the repeated components do not exist in the component combinations is judged;
the second alignment unit is used for aligning all the third reaction threads to obtain simultaneous reaction threads;
the latest determining unit is used for determining the real-time component content of the new component and the effective component generated by component reaction based on the simultaneous reaction thread, and determining a new component combination which can be reacted again from the current residual effective components based on the new component and the real-time component content and the component reaction mechanism contained in the drug reaction mechanism library;
The latest generation unit is used for generating a new simultaneous reaction thread based on the new component combination and the simultaneous reaction thread until the components which can react and correspond to the component reaction mechanisms contained in the drug reaction mechanism library do not exist in the current residual active components any more, and predicting a third test reaction of the corresponding test patients on the active components based on the current residual active components;
a medication early warning terminal comprising:
the thread dividing module is used for dividing the test reaction thread into a reaction presentation time period thread and a non-reaction presentation time period thread, and carrying out secondary division on the reaction presentation time period thread based on the predicted occurrence time to obtain a final dividing thread comprising a plurality of sub-reaction presentation time period threads;
the alignment marking module is used for generating a body data change curve of a corresponding item based on each item of body data in clinical response body data, marking out a sudden change point in each body data change curve, and carrying out time sequence alignment on all the marked body data change curves to obtain an alignment marking curve;
the alignment determining module is used for carrying out head-end alignment on the final dividing thread and the alignment mark curve to obtain an alignment result, judging whether the test patient is currently in the reaction display time period or not based on the alignment result, if so, determining the sub-reaction display time period thread currently corresponding to the test patient and the lasting time of the thread in the corresponding sub-reaction display time period based on the alignment result;
The first judging module is used for determining the total duration of the threads corresponding to the sub-reaction appearing time period, determining a corresponding starting judging time threshold value based on the total duration, judging whether the corresponding lasting time is not smaller than the corresponding starting judging time threshold value, if yes, determining a first alignment mark curve segment corresponding to the corresponding sub-reaction appearing time period in the alignment mark curve, and if not, reserving a corresponding judging result;
the second judging module is used for judging whether the body data types corresponding to the body data change curves of the abrupt change points contained in the first alignment mark curve section are consistent with the corresponding body data types of the threads of the corresponding sub-reaction display time periods, if so, determining the abrupt change body data corresponding to the abrupt change points, determining a standard reaction data range based on the predicted reaction data of the threads of the corresponding sub-reaction display time periods, judging whether the abrupt change body data is in the corresponding standard reaction data range, and if so, reserving the corresponding judging result;
the third judging module is used for sending out an alarm when judging that the body data types corresponding to the body data change curves of the abrupt change points contained in the first alignment mark curve section are inconsistent with the response body data types corresponding to the sub-response presentation time period threads or the abrupt change body data are not in the corresponding standard response data range;
A fourth judging module, configured to determine, when it is determined that the current time period belongs to the non-response presentation time period, a standard response data range of the non-response presentation time period based on body data of the test patient, determine a second alignment mark curve segment corresponding to the non-response presentation time period in the alignment mark curve, and judge whether each body data corresponding to the second alignment mark curve segment is within the corresponding standard response data range, if yes, determine to retain the corresponding judging result, otherwise, send an alarm;
the method for determining the corresponding starting judgment time threshold based on the total duration comprises the following steps:
wherein t is y In order to start judging the time threshold value, alpha is the preset duty ratio of the start judging time threshold value, t all For a total duration t safe The maximum safe reaction time is preset;
wherein determining a standard reaction data range based on predicted reaction data corresponding to the sub-reaction presentation time period thread comprises:
determining a fluctuation coefficient of predicted reaction data corresponding to the sub-reaction presentation time period thread, and determining a corresponding standard reaction data range based on the fluctuation coefficient and the predicted reaction data:
g 0 ＝[(1+β)g y ,(1-β)g y ]
in the formula g 0 Is the standard reaction number According to the range, beta is the fluctuation coefficient of the predicted reaction data corresponding to the sub-reaction presentation time period thread, g y Predicted reaction data for threads corresponding to sub-reaction presentation time periods.
2. The clinical trial platform based drug pre-warning system of claim 1, wherein the direct analysis end comprises:
the effective determination module is used for determining effective components in the test medicines based on the test items;
and the direct determination module is used for determining a corresponding predicted drug response mechanism based on the test item, and taking the components participating in the predicted drug response mechanism in the effective components as direct influence components.
3. The clinical trial platform based medication early warning system of claim 1, wherein the personality determination terminal comprises:
the special determining module is used for determining special body data of the test patient based on the standard body data range and the historical medical data;
and the personality determination module is used for taking the components which have influence on the special body data in the effective components of the test medicines as personality influence components.
4. A clinical trial platform based medication early warning system according to claim 3, wherein the special determination module comprises:
A first determination unit configured to take sub-body data exceeding a standard body data range among current body data of a test patient as first special body data;
a second determining unit for determining second special body data of the trial patient based on the historical body data and the historical medication response data and the medical history data included in the historical hospitalization data of the trial patient;
and the deduplication summarizing unit is used for performing deduplication summarization on the first special body data and the second special body data to obtain the special body data of the test patient.
5. The clinical trial platform-based medication early warning system of claim 4, wherein the second determination unit comprises:
a first determination subunit operable to determine, as first sub-specific body data, sub-body data exceeding a standard body data range among historic body data included in historic medical data of the trial patient;
a second determination subunit operable to take, as second sub-specific body data, response body data corresponding to excessive response data and insufficient response data in the historical medication response data of the trial patient;
a third determination subunit for taking as third sub-specific body data sub-body data affected by the medical history data of the trial patient;
And the deduplication summarizing subunit is used for performing deduplication summarization on the first sub-special body data, the second sub-special body data and the third sub-special body data to obtain second special body data of the test patient.
6. The clinical trial platform based medication early warning system of claim 1, wherein the timing recording module comprises:
the reaction sequencing unit is used for sequencing the first test reaction, the second test reaction and the third test reaction based on the predicted occurrence time to obtain a reaction record thread;
and the reaction superposition unit is used for sequentially carrying out reaction superposition on the first test reaction, the second test reaction and the third test reaction based on the reaction record thread and the reaction superposition mechanism, so as to obtain the test reaction thread of the corresponding test patient.
7. The clinical trial platform based medication early warning system of claim 1, comprising:
the plan determining module is used for determining a corresponding test plan based on the test items;
and the clinical recording module is used for carrying out clinical tests on corresponding test patients based on the test plan, recording clinical response body data of the corresponding test patients in real time and obtaining a clinical response record thread.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211074626.8A CN115312152B (en) | 2022-09-01 | 2022-09-01 | Medicine early warning system based on clinical test platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211074626.8A CN115312152B (en) | 2022-09-01 | 2022-09-01 | Medicine early warning system based on clinical test platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115312152A CN115312152A (en) | 2022-11-08 |
| CN115312152B true CN115312152B (en) | 2023-06-20 |
Family
ID=83866715
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211074626.8A Active CN115312152B (en) | 2022-09-01 | 2022-09-01 | Medicine early warning system based on clinical test platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115312152B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115394386A (en) * | 2022-08-26 | 2022-11-25 | 北京舒曼德医药科技开发有限公司 | Automatic acquisition method and system for clinical test data |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030065669A1 (en) * | 2001-10-03 | 2003-04-03 | Fasttrack Systems, Inc. | Timeline forecasting for clinical trials |
| US20050096311A1 (en) * | 2003-10-30 | 2005-05-05 | Cns Response | Compositions and methods for treatment of nervous system disorders |
| JP7118046B2 (en) * | 2017-03-02 | 2022-08-15 | 第一三共株式会社 | microRNA biomarkers for predicting therapeutic efficacy of opioid drugs |
| CN109559786B (en) * | 2018-11-08 | 2022-04-08 | 三峡大学 | Pilot compound discovery and synthesis method based on quantum group intelligent optimization |
| CN113393946B (en) * | 2021-08-17 | 2021-11-09 | 奥罗科技(天津)有限公司 | Medical clinical test auxiliary system and method based on virtual reality technology |
| CN113823365A (en) * | 2021-09-30 | 2021-12-21 | 北京兴德通医药科技股份有限公司 | Clinical research quality control method, system, electronic device and storage medium |
-
2022
- 2022-09-01 CN CN202211074626.8A patent/CN115312152B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115394386A (en) * | 2022-08-26 | 2022-11-25 | 北京舒曼德医药科技开发有限公司 | Automatic acquisition method and system for clinical test data |
Non-Patent Citations (1)
| Title |
|---|
| 中药注射剂的不良反应及安全性再评价基本思路;胡中慧;吴纯启;廖明阳;王全军;;中南药学;第8卷(第10期);772-774 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115312152A (en) | 2022-11-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tebbi | Treatment compliance in childhood and adolescence | |
| Cullen et al. | Prevention of adverse drug events: a decade of progress in patient safety | |
| Forster et al. | Adverse drug events occurring following hospital discharge | |
| Erickson et al. | Pharmacists' ability to influence outcomes of hypertension therapy | |
| Federico | Preventing harm from high-alert medications | |
| Brown et al. | Development of a conceptual model of adherence to oral anticoagulants to reduce risk of stroke in patients with atrial fibrillation | |
| Blevins | Professional continuous glucose monitoring in clinical practice 2010 | |
| Vogel et al. | Treatment for speech disorder in Friedreich ataxia and other hereditary ataxia syndromes | |
| Li et al. | Automated detection of medication administration errors in neonatal intensive care | |
| CN105335606B (en) | Method and system for determining correlations between clinical events | |
| Koff et al. | Impact of proactive integrated care on chronic obstructive pulmonary disease | |
| CN115312152B (en) | Medicine early warning system based on clinical test platform | |
| Georgiou et al. | The effectiveness of systematic pain assessment on critically ill patient outcomes: a randomised controlled trial | |
| Ju et al. | Interventions for fatigue in people with chronic kidney disease requiring dialysis | |
| CN110086565B (en) | Data transmission and storage method | |
| Draznin | Managing Diabetes and Hyperglycemia in the Hospital Setting: A Clinician's Guide | |
| Blike et al. | Specific elements of a new hemodynamics display improves the performance of anesthesiologists | |
| US20200214644A1 (en) | System for predicting thyrotoxicosis using a wearable device and computer program using the same | |
| Zochodne et al. | Diabetic neurology | |
| Moreno et al. | Prognosis of medically stabilized unstable angina pectoris with a negative exercise test | |
| Kim et al. | The efficacy of the time-scheduled decremental continuous infusion of fentanyl for postoperative patient-controlled analgesia after total intravenous anesthesia | |
| Cacciola et al. | The Addiction Severity Index in clinical efficacy trials of medications for cocaine dependence | |
| Haire et al. | Effect of working consecutive night shifts on sleep time, prior wakefulness, perceived levels of fatigue and performance on a psychometric test in emergency registrars | |
| Stoodley et al. | Problems in the development of a computerized ward monitoring system for a paediatric intensive care unit | |
| Gardner et al. | Computerized alert system use in clinical medicine |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |