CN117292807B - Clinical blood sugar management quality control system - Google Patents
Clinical blood sugar management quality control system Download PDFInfo
- Publication number
- CN117292807B CN117292807B CN202311577574.0A CN202311577574A CN117292807B CN 117292807 B CN117292807 B CN 117292807B CN 202311577574 A CN202311577574 A CN 202311577574A CN 117292807 B CN117292807 B CN 117292807B
- Authority
- CN
- China
- Prior art keywords
- data
- medical
- hospital
- patient
- server
- 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
- 238000003908 quality control method Methods 0.000 title claims abstract description 15
- 239000008280 blood Substances 0.000 title claims abstract description 14
- 210000004369 blood Anatomy 0.000 title claims abstract description 14
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 15
- 230000000474 nursing effect Effects 0.000 claims abstract description 10
- 238000013480 data collection Methods 0.000 claims abstract description 9
- 238000000034 method Methods 0.000 claims abstract description 8
- 239000003814 drug Substances 0.000 claims description 60
- 229940079593 drug Drugs 0.000 claims description 24
- 238000003556 assay Methods 0.000 claims description 19
- 238000010295 mobile communication Methods 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 238000007689 inspection Methods 0.000 claims description 8
- 230000002641 glycemic effect Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000004806 packaging method and process Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- 238000011158 quantitative evaluation Methods 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000004080 punching Methods 0.000 claims description 2
- 238000012217 deletion Methods 0.000 claims 6
- 230000037430 deletion Effects 0.000 claims 6
- 238000007599 discharging Methods 0.000 description 5
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000008103 glucose Substances 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000000059 patterning Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 239000012567 medical material Substances 0.000 description 2
- 230000007721 medicinal effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 206010048909 Boredom Diseases 0.000 description 1
- 229920001872 Spider silk Polymers 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000001647 drug administration Methods 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/40—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades
Abstract
The invention relates to a clinical blood sugar management quality control system, which comprises a hospital system, a server and a client, wherein the hospital system collects medical and/or nursing data in a hospital so as to transmit the medical and/or nursing data to the server for data collection, the server determines whether the data is missing according to the collected data, so that a reminding signal is sent to the client to remind the client of timely recording of the data, and the server continues to perform artificial intelligent recognition based on the collected complete data after the data collection is complete, so that problem data with deviated scheme is further recognized. The method realizes the patterned management of medical data, the macroscopic recognition of timely deviation schemes of artificial intelligence and the microscopic positioning of problem data.
Description
Technical Field
The invention relates to a clinical blood sugar management quality control system, in particular to a clinical blood sugar management quality control system based on artificial intelligence scheme deviation semi-quantitative evaluation, and belongs to the field of clinical medical quality control.
Background
Deviations from clinical medical protocols refer to the phenomenon that clinical medical (including related clinical trials) does not, or not all, meet prescribed criteria for some reason, require clinical medical activity. In each large medical institution system, various data resources cannot be integrated to carry out overall analysis, so that illegal phenomena are difficult to identify in daily mass clinical data, and a spider silk horse trace which generates problems is searched in a mass data center when the problems occur. However, some data records still stay on the operation records of attendance, large operation equipment and laboratory equipment, and case records are macroscopic data, and although the data is massive, details are not yet reflected, particularly details of nursing stages of hospitalization, such as administration time, dining rules, whether medical administration is in compliance, whether a doctor has excessive treatment, and whether an off-site patient performs administration according to regulations and observation of work and rest time.
The essence of the deviation monitoring of the clinical blood sugar management scheme is the identification of violations in clinical data and the judgment of the comparison result of blood sugar monitoring data and standard data. How to collect these data, how to organize these data, so as to make the judgment result efficiently and accurately, and locate suspicious data are urgent problems to be solved.
In addition, most of the existing surgical equipment and test equipment depend on import, and the supported systems are camping respectively, and a unified data recording system does not exist, so that how to integrate the data recording systems of all the surgical equipment and test equipment is urgent.
Disclosure of Invention
The present invention contemplates a solution to the problems described above in that: firstly, consider the data acquisition system of the patient at the hospital and outside the hospital, secondly, consider the classification patterning of the blood sugar management related data, and thirdly, consider the artificial intelligence recognition based on patterning and the pulling out of the problem data. All references to systems of the present invention refer to hardware systems (e.g., computers) and non-transitory storage media that can be run on the hardware systems, including computers, in which programs that can perform medical data and care data acquisition, recording, transmission are stored. And so that the above problems are solved in large part satisfactorily.
In view of the above, the present invention provides a clinical blood glucose management quality control system based on semi-quantitative assessment of a scheme deviation of artificial intelligence, which comprises a hospital system in the form of a computer, a server and a client, wherein the hospital system performs data collection on medical data and/or nursing data related to blood glucose management of a patient in the hospital and transmits the data to the server, the server determines whether the data is missing according to the collected data, so as to send a reminding signal to the client to remind the client of timely recording of the data, and the server continues to perform artificial intelligence identification based on the collected complete data after the data collection is complete, so as to further identify problem data of the scheme deviation.
The medical equipment comprises an attendance system, an operation equipment operation recording system, an assay equipment operation recording system and a medical equipment recording system, wherein the attendance system comprises an attendance system, an operation equipment operation recording system, a medical equipment recording system and a medicine recording system, wherein the medical equipment operation recording system is used for recording data of medical equipment in-out of a hospital and in-hospital allocation and use, and the medicine recording system is used for recording data of medicine in-out of the hospital and in-hospital allocation and use, and the medical equipment and medicine use condition recording system.
The attendance system records attendance data through card punching and/or face recognition, the operation recording system of the operation equipment carries out first data recording through operation history on the operation equipment and information of a patient, the operation recording system of the test equipment carries out second data recording through test data on the test equipment and information of the patient, the medical instrument recording system carries out recognition of hospital entering quantity through a medical instrument packaging inspection channel and recognition of hospital discharging quantity through a medical instrument discharging channel, the inspection channel and the image acquisition device arranged above a conveying belt carries out recognition of hospital entering quantity through the medical instrument discharging channel (for example, a recognition algorithm is obtained through a pre-trained intelligent model, the acquisition of a training set is carried out while the initial daily entering channel is used, and an algorithm model with high recognition rate is obtained continuously during a period of use).
The attendance data, the first data record, the second data record, the number of medical instruments and medicines entering and exiting as the medical data, the data allocated and used and the manually recorded data as the nursing data are all uploaded to a server, when the medical instruments and medicines are used, a manual entry missing signal and an electronic tag scanning missing signal are sent to a client through the server to remind the supplementary recording, and the data scanning is carried out according to the medical instruments and medicines and the specified time outside the medical order time to identify the manual entry missing and the electronic tag scanning missing.
It can be understood that the medical material distribution and the use condition of the main links in the medical activity can be detected through the system record or the manual record of the data, so that the classified physical storage of the medical data is realized, the manual recorder is used for standardizing the specifications of the equipment and the medicine, the real-time monitoring of the deviation of the scheme is ensured, and the medical staff is checked to work through the electronic tag scanning and the manual record missing record frequency, so that the medical staff is urged to form professional habit in the standardized direction of the scheme.
The client comprises a hospital client and an off-hospital client, wherein the hospital client comprises a computer system for recording medical records, medical scheme records, medical instruments and medicine distribution records of other medical staff, the off-hospital client comprises a mobile communication device for the doctors and the other medical staff and patients or medical attendees, the server sends a reminding short message to the mobile communication device of the other medical staff within the specified time except the specified order time and the order time of the prescribed administration and/or the medical advice according to the use order requirements of the medical instruments and the medicine of the patients or medical attendees, and intermittently sends the reminding short message to the mobile communication device of the patients or medical attendees, so that the use reminding of the instruments and/or the medicine is carried out between the medical staff and the patient staff, and the patients or the medical attendees eliminate the reminding short message by confirming on the mobile communication device and send the eliminated operation information to the server so as to make the server know the normal use of the medical instruments and/or the medicine outside the hospital.
Preferably, the prescribed time other than the order time is 0.5 hours to 6 hours.
The total duration of intermittently sending the reminding short message is 1-2min, and the intermittent frequency is that reminding is carried out every 20-30 seconds.
Preferably, the mobile communication device comprises a smart phone, a notebook computer and a tablet computer.
Therefore, the electronic tag scanning and manual recording missing information can also be reported to the hospital client side, so that doctors can conveniently check and prompt other medical staff to conduct relevant records in time if necessary, and the dispensing and the use of instruments and medicines are facilitated. Thereby realizing the communication of the material flow and the data flow of the three parties of the medical party, the patient party and the medical object party, realizing the supervision of the medical treatment and further identifying the problem data which is used for the server to find the possible scheme deviation by artificial intelligence, thereby semi-quantitatively giving out the quality control scheme. Semi-quantitative refers to the problem of finding out the data of problems possibly causing deviation of a scheme, and is not the condition of reagents focusing on the data, including whether the quantity, the dosage, the frequency, the parameter index and the like are scientifically configured with the type, the quantity, the administration time and the like of a specific medicament; on the other hand, the abnormal number of medical instruments for medicines can also realize semi-quantitative possible overdose medical conditions, such as abuse of cardiovascular stents, qualitative auxiliary judgment of improper small-disease large-medical conditions of a certain type of medicines and the like.
It should be emphasized that the setting of the total duration of the intermittent sending of the reminding short message is not suitable to be too long or too short, and if too long, the taking operation can be carried out in a large probability due to the boredom of the patient outside the hospital, and the taking operation can also be carried out, so that the effect of taking the medicine in a large probability can be realized, but on one hand, the bad experience of the patient system is caused, and on the other hand, the situation of whether the patient has the habit of forgetting to take the medicine can not be detected. This is because the proper duration reminder will make the patient notice the medication, but if the patient forgets to take the medication habitually, the operation will not be eliminated with a certain probability, so that the server will not receive the eliminated operation information, and the possibility of forgetting to take the medication is monitored. And if the time is too short (within the interval of several seconds to tens of seconds), a certain probability cannot play a reminding effect. Thus, long-term observation confirms that 1-2min is a suitable total reminding duration.
The method for identifying the artificial intelligence comprises the following steps:
s1, collecting the medical data of different periods, and the names, the numbers, the administration amounts and the frequency of instruments, medicines, operations and assays under the information of each patient and/or doctor, and whether the usage amount and the frequency are normal or not, wherein whether the usage amount and the frequency are normal or not is identified by three items of data of operation information scanned by the electronic tag, manually recorded and eliminated, and any item is not considered to be abnormal; dividing the medical data, the names, the number, the use number and the frequency of instruments, medicines, operations and assays under the information of each patient and/or doctor, and whether the use number and the frequency are normal or not, wherein the ratio of the two is 6-2:1; the patient and/or patient information comprises patient and/or patient name, age, department of registration, and doctor name;
s2, sorting according to the time sequence of the patient and/or the doctor, and collecting information of the patient and the doctor, names, quantity, use quantity and frequency of instruments, medicines, operations and assays under the information, and whether the use quantity and frequency are normal or not, and collecting medical data to form a data set; pseudo-colorization processing of giving color values to data in the data set is carried out according to a rule to form a pixel set which is sequenced according to time sequence after the pixel set corresponding to the medical data set, so as to form an aggregate image;
s3, refilling color values corresponding to standard data predicted by a quality control system according to the set image to form a standard set image, wherein the standard set image refers to pixel values corresponding to each data in the image in a normal state;
it will be appreciated that the determination of the standard data should be determined by highly qualified specialist physicians or authoritative physicians within the industry based on patient medical records and/or test report data, and that after a long-term determination of the patient's instrument drug administration and usage, the quality control system will learn the standard data based on the medical records and/or test report data to make predictions of the standard data.
S4, inputting the medical data corresponding to the medical data in the aggregate image, the names, the quantity, the use quantity and the frequency of instruments, medicines, operations and assays under the information of each patient and/or patient, and the image parts corresponding to the data of whether the use quantity and the frequency are normal or not into a medical data CNN model and a patient and/or patient CNN model respectively, wherein the output ends of the two CNN models are respectively output through the binary classification of the normal or not through a softmax function, and are compared with the actual classification, so that the accuracy is calculated according to a verification set and a loss function is calculated, and CNN network parameters are adjusted until the accuracy and the loss function are stable and stop training;
the further identifying problem data for a deviation of the scheme further comprises:
s5, inputting the set image to be predicted into the CNN model in the trained S4, when the judging result is abnormal, differentiating the set image to be predicted with the corresponding standard set image formed according to the S3, obtaining a differential result, knowing the patient and/or responsible doctor corresponding to the problem data, and finally transmitting the judging and problem data to the hospital system by the server.
Preferably, the CNN model is a residual mechanism based reset.
It should be understood that, the sizes of all the pixels in the aggregate image are consistent, and the image needs to be divided regionally due to different types and data amounts of the data, so that a phenomenon that the image is not equally divided may exist in the dividing process, for example, left-right or upper-lower adjacent data items in the later embodiment are many-to-one, for example, two items of administration number and administration frequency are left of an assay name, the pixels are still arranged in the three items of data in a consistent size, and a plurality of pixels are used for representing one assay name for the assay name.
According to the present invention, there are at least three significant advantages over the prior art:
1. medical supplies are discharged and the distribution is recorded through the recording system of each data.
2. The medical material use is normally supervised and career good habit cultivation is realized through the electronic tag and the manual record, and the fixed-point and mobile double-reminding mode is realized through the medical instrument and medicine use condition recording system and the server.
3. The patient and/or responsible doctor corresponding to the problematic data are identified through artificial intelligent prediction and the difference of the standard set images, so that a patterning quality control scheme of macroscopic and microscopic data is realized, massive data are organized into one set image, and the organization and the processing of the data are facilitated.
Drawings
FIG. 1 is a schematic structural diagram of a clinical blood glucose management quality control system based on artificial intelligence-based protocol deviation semi-quantitative evaluation in embodiment 1 of the present invention.
Fig. 2 is a schematic diagram showing the internal constitution of the aggregate image in embodiment 2 of the present invention.
Fig. 3 is a schematic flow chart of the training process of the CNN model in the internal structures of the image part 1 and the image part 2 in the aggregate image in the embodiment 2 of the present invention.
Fig. 4 is a schematic diagram of a differential image method of problem data discovery.
Wherein reference numerals 1 are used for image portions corresponding to medical data of different periods and 2 are used for image portions corresponding to patients/caregivers.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Example 1
This embodiment will describe a clinical glycemic control system based on semi-quantitative evaluation of a schema deviation of artificial intelligence, as shown in fig. 1, which includes a hospital system, a server, and a client, wherein the hospital system performs data collection on medical data and nursing data related to glycemic control in the hospital and transmits the data to the server, the server determines whether the data is missing according to the collected data, so as to send a reminding signal to the client to remind the client to record the data in time, and when the data collection is complete, the server continues to perform artificial intelligence recognition based on the collected complete data, so as to further identify problem data of schema deviation, and sends a judgment result and the problem data to the hospital system to display reminding in a corresponding recording system in the hospital system.
The recording system of the hospital system comprises an attendance system, an operation equipment operation recording system, an assay equipment operation recording system and a medical instrument recording system, wherein the medical instrument recording system is used for recording data of medical instrument in and out of a hospital and in-hospital allocation and use, and the medical instrument recording system is used for recording data of medicine in and out of the hospital and in-hospital allocation and use and a medical instrument and medicine use condition recording system.
The attendance system records attendance data through face recognition, the operation equipment operation recording system records first data through operation history on operation equipment and receiver information, the assay equipment operation recording system records second data through test data on assay equipment and receiver information, the medical instrument recording system identifies the number of hospital entries through a medical instrument packaging inspection channel and the number of hospital exits through a medical instrument discharging channel, the inspection channel and the number of hospital exits through an image acquisition device arranged above a conveyor belt on the discharge channel, the data once allocated and used in hospital is recorded through electronic tag scanning on the medical instrument or packaging of the medical instrument, the medical recording system identifies the number of hospital entries through a medicine packaging inspection channel and the number of hospital exits through a medicine discharging channel, the medical instrument and the medicine use condition recording system records the data allocated and used in hospital through electronic tag scanning on a medicine package, and the medical instrument and the medicine use condition recording system carries out manual recording through medical staff.
The attendance data, the first data record, the second data record, the number of medical instruments and medicines entering and exiting as the medical data, the data allocated and used and the manually recorded data as the nursing data are all uploaded to a server, when the medical instruments and medicines are used, a manual entry missing signal and an electronic tag scanning missing signal are sent to a client through the server to remind the supplementary recording, and the data scanning is carried out according to the medical instruments and medicines and the specified time outside the medical order time to identify the manual entry missing and the electronic tag scanning missing.
The client comprises a hospital client and an off-hospital client, wherein the hospital client comprises a computer system for recording medical records, medical scheme records, medical instruments and medicine distribution records of other medical staff, the off-hospital client comprises a mobile communication device for the doctors and the other medical staff and patients or medical attendees, the server sends a reminding short message to the mobile communication device of the other medical staff within the specified time except the specified order time and the order time of the prescribed administration and/or the medical advice according to the use order requirements of the medical instruments and the medicine of the patients or medical attendees, and intermittently sends the reminding short message to the mobile communication device of the patients or medical attendees, so that the use reminding of the instruments and/or the medicine is carried out between the medical staff and the patient staff, and the patients or the medical attendees eliminate the reminding short message by confirming on the mobile communication device and send the eliminated operation information to the server so as to make the server know the normal use of the medical instruments and/or the medicine outside the hospital.
In another preferred embodiment, the predetermined time other than the order time is 0.5 hours to 6 hours, and in another preferred embodiment, the predetermined time other than the order time is 1 hour. The total duration of intermittently sending the reminding short message is 1-2min, and the intermittent frequency is that reminding is carried out every 20-30 seconds. In another preferred embodiment, the alert short message is sent intermittently for a total duration of 1min, with the intermittent frequency being once every 25 seconds. The mobile communication equipment comprises a smart phone, a notebook computer and a tablet personal computer. In another preferred embodiment, the mobile communication device comprises a smart phone.
Example 2
This example will illustrate the method of artificial intelligence identification using the clinical glycemic control system of example 1 above, and the steps of further identifying issue data for deviations from the protocol: the method for describing the identification of the artificial intelligence comprises the following steps:
s1, collecting the medical data (medical data related to blood sugar management of patients) in different periods, and the names, the number, the administration quantity and the frequency of instruments, medicines, operations and assays under the information of each patient and/or patient, and whether the use quantity and the frequency are normal or not, wherein whether the use quantity and the frequency are normal or not is identified by three items of data of operation information of electronic tag scanning, manual recording and elimination, and the lack of any item is regarded as abnormal; dividing the medical data, the names, the number, the use number and the frequency of instruments, medicines, operations and assays under the information of each patient and/or doctor, and whether the use number and the frequency are normal or not into a training set and a verification set, wherein the ratio of the training set to the verification set is 3:1; the patient and/or patient information includes patient and/or patient name, age, department of registration, and physician name.
S2, as shown in FIG. 2, sorting the information of the patient and/or the patient according to the time sequence of the patient and/or the patient, namely, the arrow direction, carrying out data collection on the information, the names, the number, the use number and the frequency of the instruments, the medicines, the operations and the assays under the information, and whether the data of the number and the frequency are normal or not to form an image part 2 (comprising a plurality of image parts sorted according to the arrow time sequence), and carrying out medical data collection to form an image part 1 to form a data set; pseudo-colorization processing of giving color values to data in the data set is carried out according to a rule, and after an image part 1 is formed, pixel sets which are ordered according to time sequence are formed, so that an aggregate image is formed; fig. 3 shows the internal configuration of the image portion 1 and the image portion 2.
And S3, refilling the color values corresponding to the standard data predicted by the quality control system according to the set image to form a standard set image.
S4, as shown in fig. 3, the image part 1 and the image part 2 corresponding to the medical data in the aggregate image and the data corresponding to the instrument, the medicine, the operation, the test name, the number, the use number and the frequency under the information of each patient and/or the patient are respectively input into a medical data CNN model and the patient and/or the patient CNN model, wherein the data corresponding to the use number and the frequency are normal, the output ends of the two CNN models are respectively output in a normal or abnormal binary classification mode through a softmax function, and are compared with the actual classification mode, so that the accuracy rate is calculated according to a verification set, the loss function is calculated, and CNN network parameters are adjusted until the accuracy rate and the loss function are stable and the training is stopped.
The step of further identifying issue data for a solution deviation includes:
s5, inputting the set image to be predicted into the CNN model in the trained S4, when the judging result is abnormal, as shown in fig. 4, differentiating the set image to be predicted with the corresponding standard set image formed according to the S3 to obtain a differential result, knowing a patient and/or responsible doctor corresponding to the problem data, and finally transmitting the judging and problem data to the hospital system by the server.
The CNN model in fig. 3 is here a residual mechanism based reset.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all technical features thereof can be replaced by others within the spirit and principle of the present invention; such modifications and substitutions do not depart from the scope of the invention.
Claims (5)
1. The clinical blood sugar management quality control system based on the semi-quantitative evaluation of the scheme deviation of artificial intelligence is characterized by comprising a hospital system in the form of a computer, a server and a client, wherein the hospital system collects medical data and/or nursing data related to blood sugar management in a hospital and transmits the medical data and/or nursing data to the server, the server determines whether the data is missing according to the collected data so as to send a reminding signal to the client to remind the client of timely recording of the data, and the server continues to identify the artificial intelligence based on the collected complete data after the data collection is complete so as to further identify problem data of the scheme deviation;
wherein the hospital system comprises an attendance system, an operation equipment operation recording system, an assay equipment operation recording system, a medical equipment recording system, a medicine recording system, a medical equipment and medicine use condition recording system, wherein the medical equipment operation recording system is used for recording data of medical equipment in and out of a hospital and in-hospital allocation and use, the medicine recording system is used for recording data of medicine in and out of the hospital and in-hospital allocation and use,
the attendance checking system records attendance data through card punching and/or face recognition, the operation recording system of the operation equipment records first data through operation history on the operation equipment and information of a patient, the operation recording system of the test equipment records second data through test data on the test equipment and information of the patient, the medical instrument recording system identifies the number of hospital entries through a medical instrument packaging inspection channel and the number of hospital exits through a medical instrument discharge channel, the inspection channel and the number of hospital entries through an image acquisition device arranged above a conveyor belt on the discharge channel, the medical instrument or electronic tag scanning on a package thereof records data of one hospital allocation and use, the medical instrument recording system identifies the number of hospital entries through a medical instrument packaging inspection channel and the number of hospital exits through the medical discharge channel, the medical instrument and medical use condition recording system records data of hospital allocation and use through medical staff;
the attendance data, the first data record, the second data record, the number of medical instruments and medicines entering and exiting as the medical data, the data allocated and used and the manually recorded data as the nursing data are all uploaded to a server, when a medical instrument and medicine use condition recording system identifies manual entry deletion and electronic tag scanning deletion, a manual entry deletion signal and an electronic tag scanning deletion signal are sent to a client through the server so as to remind the supplementary recording, data scanning is carried out according to the medical order time of the medical instrument and the medicine and the specified time outside the medical order time so as to identify the manual entry deletion and the electronic tag scanning deletion,
the client comprises an in-hospital client and an out-of-hospital client, wherein the in-hospital client comprises a computer system for recording medical records, medical scheme records, medical instruments and medicine distribution records of other medical staff, the out-of-hospital client comprises a mobile communication device for the doctors and other medical staff and patients or medical attendees, the server transmits a reminding short message to the mobile communication device of the other medical staff within the specified time except the specified order time and the order time of the prescribed administration and/or medicine according to the use order requirements of the medical instruments and medicine of the patients or medical attendees, and intermittently transmits the reminding short message to the mobile communication device of the patients or medical attendees, so that the use reminding of the instruments and/or medicine is carried out between the medical staff and the patient staff, and the patients or medical attendees eliminate the reminding short message by confirming on the mobile communication device and transmit the eliminated operation information to the server so as to make the server know the normal administration and/or medicine of the out-of-hospital;
the method for identifying the artificial intelligence comprises the following steps:
s1, collecting the medical data of different periods, and the names, the numbers, the administration amounts and the frequency of instruments, medicines, operations and assays under the information of each patient and/or doctor, and whether the usage amount and the frequency are normal or not, wherein whether the usage amount and the frequency are normal or not is identified by three items of data of operation information scanned by the electronic tag, manually recorded and eliminated, and any item is not considered to be abnormal; dividing the medical data, the names, the number, the use number and the frequency of instruments, medicines, operations and assays under the information of each patient and/or doctor, and whether the use number and the frequency are normal or not; the patient and/or patient information comprises patient and/or patient name, age, department of registration, and doctor name;
s2, sorting according to the time sequence of the patient and/or the doctor, and collecting information of the patient and the doctor, names, quantity, use quantity and frequency of instruments, medicines, operations and assays under the information, and whether the use quantity and frequency are normal or not, and collecting medical data to form a data set; pseudo-colorization processing of giving color values to data in the data set is carried out according to a rule to form a pixel set which is sequenced according to time sequence after the pixel set corresponding to the medical data set, so as to form an aggregate image;
s3, refilling color values corresponding to standard data predicted by a quality control system according to the set image to form a standard set image, wherein the standard set image refers to pixel values corresponding to each data in the image in a normal state;
s4, inputting the medical data corresponding to the medical data in the aggregate image, the names, the quantity, the use quantity and the frequency of instruments, medicines, operations and assays under the information of each patient and/or patient, and the image parts corresponding to the data of whether the use quantity and the frequency are normal or not into a medical data CNN model and a patient and/or patient CNN model respectively, wherein the output ends of the two CNN models are respectively output through the binary classification of the normal or not through a softmax function, and are compared with the actual classification, so that the accuracy is calculated according to a verification set and a loss function is calculated, and CNN network parameters are adjusted until the accuracy and the loss function are stable and stop training;
s5, inputting the set image to be predicted into the CNN model in the trained S4, when the judging result is abnormal, differentiating the set image to be predicted with the corresponding standard set image formed according to the S3, obtaining a differential result, knowing the patient and/or responsible doctor corresponding to the problem data, and finally transmitting the judging and problem data to the hospital system by the server.
2. The clinical glycemic control system of claim 1 wherein the prescribed time other than the order time is 0.5 hour to 6 hours.
3. The clinical glycemic control system of claim 1 or 2, wherein the total duration of intermittently sending the reminder short message is 1-2 minutes, and the intermittent frequency is once every 20-30 seconds.
4. The clinical glycemic control system of claim 3 wherein the mobile communication device comprises a smart phone, a notebook computer, a tablet computer.
5. The clinical glycemic control system of claim 1 wherein the CNN model is a residual mechanism based ResNET.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311577574.0A CN117292807B (en) | 2023-11-24 | 2023-11-24 | Clinical blood sugar management quality control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311577574.0A CN117292807B (en) | 2023-11-24 | 2023-11-24 | Clinical blood sugar management quality control system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117292807A CN117292807A (en) | 2023-12-26 |
| CN117292807B true CN117292807B (en) | 2024-02-06 |
Family
ID=89257483
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311577574.0A Active CN117292807B (en) | 2023-11-24 | 2023-11-24 | Clinical blood sugar management quality control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117292807B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1999058050A1 (en) * | 1998-05-13 | 1999-11-18 | Cygnus, Inc. | Signal processing for measurement of physiological analytes |
| CN105361892A (en) * | 2015-12-17 | 2016-03-02 | 无锡桑尼安科技有限公司 | Personnel physiological state recognition platform based on race detection |
| WO2021207016A1 (en) * | 2020-04-05 | 2021-10-14 | Theator inc. | Systems and methods for automating video data management during surgical procedures using artificial intelligence |
| CN115312205A (en) * | 2022-10-11 | 2022-11-08 | 四川省医学科学院·四川省人民医院 | Single-disease clinical path management system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230072368A1 (en) * | 2019-10-03 | 2023-03-09 | Rom Technologies, Inc. | System and method for using an artificial intelligence engine to optimize a treatment plan |
| US20210118559A1 (en) * | 2019-10-22 | 2021-04-22 | Tempus Labs, Inc. | Artificial intelligence assisted precision medicine enhancements to standardized laboratory diagnostic testing |
-
2023
- 2023-11-24 CN CN202311577574.0A patent/CN117292807B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1999058050A1 (en) * | 1998-05-13 | 1999-11-18 | Cygnus, Inc. | Signal processing for measurement of physiological analytes |
| CN105361892A (en) * | 2015-12-17 | 2016-03-02 | 无锡桑尼安科技有限公司 | Personnel physiological state recognition platform based on race detection |
| WO2021207016A1 (en) * | 2020-04-05 | 2021-10-14 | Theator inc. | Systems and methods for automating video data management during surgical procedures using artificial intelligence |
| CN115312205A (en) * | 2022-10-11 | 2022-11-08 | 四川省医学科学院·四川省人民医院 | Single-disease clinical path management system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117292807A (en) | 2023-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200258608A1 (en) | Medical database and system | |
| US20200294642A1 (en) | Methods and systems for a pharmacological tracking and reporting platform | |
| CN111145844B (en) | Comprehensive medical supervision platform | |
| US20200303047A1 (en) | Methods and systems for a pharmacological tracking and representation of health attributes using digital twin | |
| CN105260588B (en) | A kind of health guards robot system and its data processing method | |
| US20160378950A1 (en) | Method and apparatus for tracking a pharmaceutical | |
| US20060173715A1 (en) | Health information system and method | |
| US20070299326A1 (en) | Multiple patient monitoring system for proactive health management | |
| US20120029940A1 (en) | System for Clinical Trial Subject Compliance | |
| WO2007075588A2 (en) | Healthcare management systems and associated methods | |
| US11830585B2 (en) | Time-based resource allocation for long-term integrated health computer system | |
| US20040073459A1 (en) | Bio-surveillance system and method | |
| US20120095780A1 (en) | Assessing consistency of a patient's continuity-of-care records | |
| CN103140854A (en) | Method and apparatus for soliciting an expert opinion from a care provider and managing health management protocols | |
| CN112102956A (en) | Method and system for improving compliance of diabetic patient | |
| CN111161891B (en) | Traditional Chinese medicine information management platform | |
| CN117292807B (en) | Clinical blood sugar management quality control system | |
| US20150106124A1 (en) | Date and time accuracy testing patient data transferred from a remote device | |
| WO2020086465A1 (en) | Relating data to identifiers for variant testing | |
| US11631484B1 (en) | Method and apparatus for predicting, encouraging, and intervening to improve patient medication adherence | |
| CN111180055A (en) | Hospital supervision system and method | |
| US11587682B2 (en) | Method and system to integrate data, analyze and develop improved care plan for a patient at home | |
| CN112309519B (en) | Electronic medical record medication structured processing system based on multiple models | |
| US20210202082A1 (en) | Remote View Playback Tool | |
| CN114974590A (en) | Multi-dimensional monitoring critical patient prediction nursing method and system |
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 |