PICC Home Maintenance Evaluation Method, System, Storage Medium and Electronic Device

Abstract

The present invention discloses a PICC home maintenance evaluation method, system, storage medium and electronic device. The PICC home maintenance evaluation method includes the following steps: S1. Collect catheter position data in a three-dimensional coordinate system within a predetermined time period, obtain a catheter position data set and a reference position data set, and obtain a first difference set; S2. Obtain a standard position data set, obtain a second difference set, compare the magnitude relationship between the first difference and the second difference within a predetermined time period, and obtain a third difference set; S3. Obtain a long short-term memory network method model; S4. Predict the future value of the third difference; S5. According to the prediction result and the relevance of catheter maintenance requirements, divide the training set into a first maintenance requirement classification data set and a second maintenance requirement classification data set; S6. Obtain a plurality of fine classification data sets; S7. Obtain a training model. According to the PICC home maintenance evaluation method of the embodiment of the present invention, it has the effect of being beneficial to the maintenance of the catheter.

Description

Technical Field

[0001] The present invention belongs to the technical fields of software engineering, big data, distributed storage and computing, etc., and particularly relates to a PICC home maintenance evaluation method, system, computer storage medium and electronic device. Background Art

[0002] Peripherally inserted central catheter (PICC) is a central venous access with a low complication rate, which can provide a medium- and long-term chemotherapy venous access for cancer patients. During the intermittent period of chemotherapy, patients need to be discharged with the catheter, and the current main maintenance method is to return to the hospital for maintenance. Discharging with a PICC is a routine operation for long-term chemotherapy cancer patients; the PICC needs to be maintained every 7 days when not in use, and the catheter can be retained for up to one year at most. When patients are at home, they need to make an appointment to register at the PICC maintenance clinic of a nearby tertiary hospital and go to the hospital for maintenance and dressing change.

[0003] Surveys show that the compliance of patients with catheter maintenance after discharge decreases. And the following problems occur clinically: (1) After the patient is discharged, the complication assessment of the PICC loses professional management and timely detection and treatment; (2) The patient can receive professional treatment only when returning to the hospital to maintain the PICC catheter; (3) Due to the lack of awareness of catheter complication assessment and prevention among patients, many PICC catheter complications are delayed due to cognitive biases; (3) The catheters with complications that have occurred need to be evaluated daily, and there is a problem of interruption in the home catheter evaluation and maintenance of patients. Summary of the Invention

[0004] In view of this, the present invention provides a PICC home maintenance evaluation method, system, computer storage medium and device, which can enable patients to conveniently perform PICC home maintenance and solve at least one problem in the background art.

[0005] To solve the above technical problems, on the one hand, the present invention provides a PICC home maintenance evaluation method, including the following steps: S1. Collect catheter position data in a three-dimensional coordinate system within a predetermined time period to obtain a catheter position data set, collect reference position data in the three-dimensional coordinate system within the predetermined time period to obtain a reference position data set, compare the magnitude between each data in the catheter position data set and the corresponding reference position data within the predetermined time period to obtain a first difference, and obtain a first difference set; S2. Collect the standard position of the catheter in the three-dimensional coordinate system within the predetermined time period to obtain a standard position data set, compare the magnitude between each standard position data and the corresponding reference position data within the predetermined time period to obtain a second difference, obtain a second difference set, compare the magnitude relationship between the first difference and the second difference within the predetermined time period to obtain a third difference, and obtain a third difference set; S3. Process the third difference within the predetermined time period to obtain a data network set, use the data network set as a sample set, and divide the sample set into a training set and a test set, test the long short-term memory network method through the test set to obtain a long short-term memory network method model; S4. Collect real-time data of the training set, input the real-time data into the long short-term memory network method model to predict the future value of the third difference; S5. According to the prediction result and the relevance of catheter maintenance requirements, divide the training set into a first maintenance requirement classification data set and a second maintenance requirement classification data set, one of the first maintenance requirement classification data set and the second maintenance requirement classification data set is a no-maintenance classification data set, and the other of the first maintenance requirement classification data set and the second maintenance requirement classification data set is a to-be-maintained classification data set; S6. Classify the first maintenance requirement classification data set and the second maintenance requirement classification data set according to identity information, geographical information, motion information, time information, and indwelling catheter duration information respectively to obtain multiple refined classification data sets; S7. Place the multiple refined classification data sets of the first maintenance requirement classification data set and the second maintenance requirement classification data set in a network for training respectively to obtain a training model.

[0006] According to the PICC home maintenance evaluation method of the embodiment of the present invention, after the patient has the catheter inserted, information can be automatically uploaded and it can be judged in real time whether the catheter needs to be maintained within a certain period of time in the future, so that the patient does not need to be in a state of worrying about catheter maintenance for a long time, relieving the patient's anxiety and timely maintaining the catheter. In addition, the PICC home maintenance evaluation method of the embodiment of the present application can also make targeted judgments according to different scenarios, such as making separate judgments for scenarios such as the patient resting, exercising, lying down, etc., improving the prediction accuracy.

[0007] According to an embodiment of the present invention, step S5 includes: if the predicted result is greater than the first threshold, dividing the training set into the classification data set to be maintained; if the predicted result is less than or equal to the first threshold, dividing the training set into the classification data set that does not need to be maintained.

[0008] According to an embodiment of the present invention, step S7 includes: setting up a hypothetical patient module, which is built-in with random identity information, geographical information, movement information, time information, and intubation duration information; obtaining the identity information, geographical information, movement information, time information, and intubation duration information of the hypothetical patient module; respectively matching the hypothetical patient module with the fine classification data set of one of the first maintenance requirement classification data set and the second maintenance requirement classification data set according to the obtained information at the first time and the second time; when the matching results at the first time and the second time are inconsistent, then matching the hypothetical patient module with the fine classification data set of the other one of the first maintenance requirement classification data set and the second maintenance requirement classification data set according to the obtained information at the second time, ending the training, and obtaining the training model; when the matching results at the first time and the second time are consistent, ending the training, and obtaining the training model.

[0009] According to an embodiment of the present invention, the hypothetical patient module is built-in with reply information for the matching result, and the hypothetical patient module can receive and send interaction information; when the hypothetical patient module replies with consent to the matching result information or does not reply with confirmation information, the training ends; when the hypothetical patient module replies with disagreement to the matching result information, the training model is associated with a third party to obtain the training model.

[0010] 5 According to an embodiment of the present invention, if the predicted result is greater than the first threshold and according to the difference between the predicted result and the first threshold, the classification data set to be maintained is divided into a self-maintenance classification data set and a professional maintenance classification data set; wherein, when the difference between the predicted result and the first threshold is within the first range, the classification data set to be maintained is the self-maintenance classification data set, and when the difference between the predicted result and the first threshold is within the second range, the classification data set to be maintained is the professional maintenance classification data set, and the first range is smaller than the second range.

[0011] According to an embodiment of the present invention, step S5 includes: obtaining the user identifiers of each vertex in the training set; obtaining the numerical ranges of the first range and the second range; comparing the user identifiers with the numerical ranges of the first range and the second range, and if the user identifier is within the numerical range of the first range, classifying the user identifier into the classification data set to be maintained, and if the user identifier is within the numerical range of the second range, classifying the user identifier into the classification data set that does not need to be maintained.

[0012] According to an embodiment of the present invention, the reference position data is obtained through a wearable device, and the wearable device includes at least one of a watch, a bracelet, a necklace, glasses, etc.

[0013] According to an embodiment of the present invention, the identity information includes gender and age group, the geographical information includes region, the exercise information includes exercise time and exercise type, the time information includes date and real-time moment, and the intubation duration information includes the already intubated duration, the last maintenance time, and the predicted next maintenance time.

[0014] In a second aspect, an embodiment of the present invention provides a PICC home maintenance evaluation system, including: a data monitoring module for collecting catheter position data and reference position data; a cloud platform module for receiving the data information obtained by the data monitoring module, and analyzing and processing the catheter position data and the reference position data with the catheter standard position data to obtain the catheter position information within a future time and obtain a decision result on whether the catheter needs to be maintained.

[0015] In a third aspect, an embodiment of the present invention provides a computer storage medium, including one or more computer instructions, and the one or more computer instructions implement the method described in any one of the above when executed.

[0016] In a fourth aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, the memory is used to store one or more computer instructions, and the processor is used to call and execute the one or more computer instructions to implement the method described in any one of the above.

[0017] The additional aspects and advantages of the present invention will be partly given in the following description, partly will become obvious from the following description, or will be understood through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and / or additional aspects and advantages of the present invention will become obvious and easy to understand from the description of the embodiments in conjunction with the following drawings, where:

[0019] Figure 1It is a schematic flowchart of the PICC home maintenance assessment method according to an embodiment of the present invention;

[0020] Figure 2 It is a schematic diagram of an electronic device according to an embodiment of the present invention.

[0021] Reference numerals:

[0022] Electronic device 300;

[0023] Memory 310; Operating system 311; Application program 312;

[0024] Processor 320; Network interface 330; Input device 340; Hard disk 350; Display device 360. Detailed implementation manners

[0025] The embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals indicate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention and should not be construed as a limitation of the present invention.

[0026] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation of the present invention. In addition, features defined as "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise stated, the meaning of "a plurality" is two or more.

[0027] In the description of the present invention, it should be noted that, unless otherwise clearly defined and limited, the terms "mounted", "connected", and "connected" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the internal communication of two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0028] First, the PICC home maintenance assessment method according to an embodiment of the present invention will be specifically described below with reference to the accompanying drawings.

[0029] The PICC home maintenance assessment method according to an embodiment of the present application includes the following steps:

[0030] S1. Collect the catheter position data in a three-dimensional coordinate system within a predetermined time period to obtain a catheter position data set. Collect the reference position data in the three-dimensional coordinate system within the predetermined time period to obtain a reference position data set. Compare the magnitude between each data in the catheter position data set and the corresponding reference position data within the predetermined time period to obtain a first difference, and obtain a first difference set.

[0031] The three-dimensional coordinate system may be a three-dimensional coordinate system composed of an X-axis, a Y-axis, and a Z-axis. When collecting the predetermined time period, the predetermined time period may be a set time period, such as 0:00 - 5:00 in the early morning, 5:00 - 8:00 in the early morning, 8:00 - 12:00 in the morning, 12:00 - 13:00 at noon, 13:00 - 17:30 in the afternoon, 17:30 - 18:00 in the evening, 18:00 - 0:00 at night. It should be noted that the predetermined time period includes but is not limited to the above time period embodiments, and the predetermined time period can also be freely defined according to requirements.

[0032] The following takes the time period of 0:00 - 1:00 as an example for illustration.

[0033] During this time period, the person is usually in a deep sleep mode, or occasionally gets up, or is not sleeping, etc. If the person is in a deep sleep mode, at multiple moments within this time period, the position of the catheter in the three-dimensional coordinate system is collected respectively to obtain a catheter position data set, and the data of the reference position is collected to obtain a reference position data set. For example, at a certain moment to, the position of the catheter is (x 1 , y 1 , z 1 ), at this moment, the reference position is (x 01 , y 01 , z 01 ), the magnitude relationship between the position of the catheter and the reference position at this moment, that is, the first difference is (x 1 - x 01 , y 1 - y 01 , z 1 - z 01 ). At the next moment t1, the position of the catheter is (x 2 , y 2 , z 2 ), at this moment, the reference position is (x 02 , y 02 , z 02 ), the magnitude relationship between the position of the catheter and the reference position at this moment, that is, the first difference is (x2 -x 01 ,y 1 -y 01 ,z 1 -z 01 )。 Similarly, when the person is in the motion mode, the first difference can also be obtained through the above steps, which will not be elaborated here. It should be noted that the three-dimensional coordinate system can be obtained through existing GPS positioning and measuring coordinates. The motion state and rest state of the patient can be judged by using existing features such as acceleration signals, which will not be elaborated here. The catheter position refers to the position of a certain point or a certain part of the catheter, such as the central position or the center of gravity position, in the three-dimensional coordinate system, which can include the insertion position and the depth position. The reference position refers to the position of the reference point, which can be the position of an actual object, such as the position of a matching wearable device, or a virtual set position. The catheter position and the reference position share a three-dimensional coordinate system, which is convenient for obtaining the first difference. In addition, when collecting the catheter position, a catheter position collection module can be installed on the catheter-related instrument. When obtaining the reference position, a reference position collection module different from the catheter position collection module can be installed on the catheter-related instrument, or a reference position collection module can be installed on a wearable device different from the catheter-related instrument. For example, a reference position collection module can be designed on the elastic bandage that binds the catheter.

[0034] S2. Collect the standard positions of the catheter in the three-dimensional coordinate system within a predetermined time period, obtain a set of standard position data, compare the magnitudes of each standard position data and the corresponding reference position data within the predetermined time period to obtain a second difference, obtain a set of second differences, compare the magnitude relationship between the first difference and the second difference within the predetermined time period to obtain a third difference, and obtain a set of third differences. It should be noted that the standard positions of the catheter at two adjacent moments can be different. For example, when the arm is stretched downward, the standard position of the catheter is the first position, and when the arm is raised, the standard position of the catheter is the second position. That is, in the same coordinate system, the first position can be different from the second position. For different people, different postures, etc., when comparing in the same coordinate system, the first positions at the same moment can also be different. That is, the positions of the catheter, the reference position, and the standard position can all change in real time. To improve the accuracy, the first difference and the second difference are compared to obtain the third difference.

[0035] For example, at a certain moment to, the actual position of the catheter is (x 1 ,y 1 ,z 1 ), at this moment, the reference position is (x 01 ,y 01 ,z 01 ), and the standard position of the catheter is (x 01’ ,y01’ , z 01’ ), at this moment, the second difference is (x 01’ - x 01 , y 01’ - y 01 , z 01’ - z 01 ), the first difference is (x 1 - x 01 , y 1 - y 01 , z 1 - z 01 ), the third difference is ([(x 01’ - x 01 ) - (x 1 - x 01 ), [(y 01’ - y 01 ) - (y 1 - y 0 ), [(z 01’ - z 01 ) - (z 1 - z 01) )].

[0036] S3. Process the third differences within a predetermined time period to obtain a data network set, use the data network set as a sample set, and divide the sample set into a training set and a test set. Test the long short - term memory network method through the test set to obtain a long short - term memory network method model. That is to say, through the server, the obtained third difference set can be processed to obtain a data network set. The long short - term memory network method can be called the LSTM method, and the LSTM method is applicable to the time - series field.

[0037] S4. Collect the real - time data of the training set, input the real - time data into the long short - term memory network method model to predict the future values of the third differences. That is to say, the third differences in the future time can be predicted.

[0038] S5. According to the prediction result and the relevance of the catheter maintenance requirements, divide the training set into a first maintenance requirement classification data set and a second maintenance requirement classification data set. One of the first maintenance requirement classification data set and the second maintenance requirement classification data set is a no-maintenance classification data set, and the other is a to-be-maintained classification data set. For example, when the first maintenance requirement classification data set is the no-maintenance classification data set, the second maintenance requirement classification data set is the to-be-maintained classification data set. For example, when it is predicted that the deviation of the third difference in a future period is small, the data of the corresponding training set can be divided into the no-maintenance classification data set, that is, the catheter does not need to be maintained. If it is predicted that the deviation of the third difference is large, the data of the corresponding training set can be divided into the to-be-maintained classification data set, that is, the catheter needs to be maintained.

[0039] It should be noted that different information related to the patient will affect the change of the third difference in the future. For example, for hyperactive children, patients who have exercised for a certain period of time, during the day when they are not resting, patients who wear too much clothing in a cold environment, etc., the third difference will change greatly in a future period. For those in a resting state, with a gentle exercise mode, and wearing less clothing in a hot environment, the third difference will change less in a future period. Therefore, in this embodiment, when judging the relevance between the prediction result and the catheter maintenance requirements, it can be judged by the change value of the third difference, which can be applied to different user information characteristics, without the need to specifically set judgment methods for different characteristics, and has the advantages of batch data processing and strong versatility.

[0040] S6. Classify the first maintenance requirement classification dataset and the second maintenance requirement classification dataset according to identity information, geographical information, movement information, time information, and intubation duration information respectively to obtain multiple refined classification datasets. For example, the server can further classify the obtained first maintenance requirement classification dataset and the second maintenance requirement classification dataset according to different restricted information, such as the patient's identity information, geographical information, movement information, time information, intubation duration information, etc. The identity information can include the patient's gender, age, medical history information, family medical history information, information on the same type of disease in the user's location, etc. The geographical information can include the external geographical location information related to the patient, regional natural environment information, etc. The movement information can include the types and durations of movements that the patient is engaged in, has engaged in, and may engage in in the future. The intubation duration information can include the intubation duration, intubation history information, etc. It should be noted that from the start of catheter insertion, information such as its brand, model, insertion site, depth, exposure, arm circumference, catheter tip positioning chest radiograph, and information on each subsequent maintenance use are recorded and can be used as the basis for classifying the refined classification dataset.

[0041] S7. Place the multiple refined classification datasets of the first maintenance requirement classification dataset and the second maintenance requirement classification dataset in the network for training respectively to obtain a training model. When specifically analyzing the intubation maintenance situation of a specific patient, the patient's identity information, geographical information, movement information, time information, intubation duration information, etc. can be input into the training model. Subsequently, the training model can obtain feedback information based on the input information and prompt whether the catheter needs to be maintained within a certain period in the future.

[0042] It should be noted that establishing an association between the patient's identity information, geographical information, movement information, time information, intubation duration information, etc. and the intubation maintenance information is beneficial for personalized analysis of the causes of complications. An association can also be established between the movement information and the intubation maintenance information to obtain the rehabilitation movement methods of different patients. For example, when it is monitored that the exercise amount or activity range exceeds the limit and the probability of catheter maintenance increases, a warning reminder can be sent to the user.

[0043] Thus, according to the PICC home maintenance assessment method of the embodiment of the present application, after the patient is intubated, the information can be automatically uploaded and it can be determined in real time whether the catheter needs to be maintained within a certain period in the future, enabling the patient not to be in a state of worrying about catheter maintenance for a long time, relieving the patient's anxiety, and timely maintaining the catheter. In addition, the PICC home maintenance assessment method of the embodiment of the present application can also make targeted judgments according to different scenarios, such as making separate judgments for scenarios where the patient is resting, exercising, lying down, etc., improving the prediction accuracy.

[0044] According to an embodiment of the present application, step S5 includes the following steps: If the predicted result is greater than the first threshold, the training set is divided into a classification data set to be maintained; if the predicted result is less than or equal to the first threshold, the training set is divided into a classification data set that does not need to be maintained. That is to say, if the third difference deviation is too large and greater than the first threshold range, it indicates that the catheter needs to be maintained at a certain time in the future. On the contrary, if the third difference deviation is not large, that is, less than the first threshold range, it indicates that the catheter will not need to be maintained at a certain time in the future. Among them, when the predicted result is equal to the first threshold, maintenance can be carried out or not at this time. It can be judged whether the catheter needs to be maintained according to the patient's independent evaluation or external evaluation. Further, if the predicted result is greater than the first threshold, the interval duration of the next prediction is shortened to further improve the prediction accuracy and precision.

[0045] In some specific embodiments of the present application, step S7 includes the following steps:

[0046] Set up a hypothetical patient module, which is built-in with random identity information, geographical information, movement information, time information, and intubation duration information. For example, the patient is a 6-year-old child, the time is July, located in the Northeast region, and the intubation duration is 1 day.

[0047] Obtain the identity information, geographical information, movement information, time information, and intubation duration information of the hypothetical patient module.

[0048] At the first time and the second time respectively, match the hypothetical patient module with a fine classification data set of one of the first maintenance requirement classification data set and the second maintenance requirement classification data set according to the obtained information. For example, match the hypothetical patient module with the fine classification data set of the classification data set that does not need to be maintained.

[0049] When the matching results at the first time and the second time are inconsistent, then match the hypothetical patient module with a fine classification data set of the other of the first maintenance requirement classification data set and the second maintenance requirement classification data set according to the information obtained at the second time, end the training, and obtain a training model. For example, if the matching result of the previous step is inconsistent, then match the hypothetical patient module with the fine classification data set of the classification data set to be maintained.

[0050] When the matching results at the first time and the second time are consistent, end the training and obtain a training model.

[0051] In this embodiment, by comparing the matching results at the first time and the second time for training, it has the advantage of saving training time.

[0052] According to an embodiment of the present application, the imaginary patient module is built-in with reply information for the matching result. The imaginary patient module can receive and send interaction information. For example, the imaginary patient module can receive suggestions sent by medical staff and can also consult medical staff.

[0053] When the imaginary patient module replies with an agreement to the matching result information or does not reply with a confirmation message, the training ends.

[0054] When the imaginary patient module replies with a disagreement to the matching result information, the training model is associated with a third party to obtain a training model. For example, although it is judged that the catheter does not need to be maintained in the next period of time and the patient disagrees with this judgment, the patient can also consult a third party. The third party can be medical staff or a hospital. The medical staff can judge whether the catheter needs to be maintained or apply to the hospital for a maintenance appointment.

[0055] When it is judged that the catheter needs to be maintained in the next period of time, the third party can actively send information to the patient module, and the patient module can receive this information. Through the active service of medical staff, the communication with the patient can be strengthened, the patient's anxiety and fear can be alleviated, the patient's confidence in overcoming the disease can be helped, and the patient can be prompted to regularly and actively perform pipeline maintenance.

[0056] When a complication of PICC occurs, the patient can ask a third party through interaction information. The third party can also investigate various information of the patient recently and evaluate the complication of PICC after the patient is discharged from the hospital, so that the complication evaluation of PICC after the patient is discharged from the hospital can be professionally managed and timely discovered and treated.

[0057] In addition, the patient can conduct self-evaluation. Once an abnormality occurs, the patient can take a photo and upload it, and the expert will give suggestions after preliminary evaluation. It has the advantages of strongly reminding the patient to return for a follow-up visit, increasing the probability of discovering complications at home, early discovery, early follow-up visit, and early treatment. For the complications that have already occurred, the function of taking a photo of the previous time can also be used for tracking observation, and the professional in the third party will guide the nursing.

[0058] According to an embodiment of the present application, if the predicted result is greater than the first threshold and based on the difference between the predicted result and the first threshold, the to-be-maintained classification data set is divided into a self-maintenance classification data set and a professional-maintenance classification data set.

[0059] Among them, when the difference between the predicted result and the first threshold is within the first range, the classification data to be maintained is the self-maintenance classification data set; when the difference between the predicted result and the first threshold is within the second range, the classification data to be maintained is the professional maintenance classification data set, and the first range is smaller than the second range. That is to say, when the predicted result is greater than the first threshold by a certain range, it is determined that the catheter can be maintained by oneself or with the assistance of relatives and friends, and the maintenance personnel here can be those with less experience and professional knowledge. When the predicted result is greater than the first threshold by a larger range, it is determined that professional maintenance is required, and the professionals here can be medical staff or those who have received specific training and have certificates.

[0060] According to an embodiment of the present application, step S5 includes the following steps:

[0061] Obtain the user identifiers of each vertex in the training set. The user identifier can be the patient's identity information, geographical information, etc.

[0062] Obtain the numerical ranges of the first range and the second range.

[0063] Compare the user identifier with the numerical ranges of the first range and the second range. If the user identifier is within the numerical range of the first range, classify the user identifier into the classification data set to be maintained; if the user identifier is within the numerical range of the second range, classify the user identifier into the classification data set that does not require maintenance.

[0064] In this embodiment, by comparing the user identifier with the first range and the second range, it is beneficial to shorten the classification time required for the fine classification data set and improve the prediction accuracy.

[0065] In some specific embodiments of the present application, the reference position data is obtained through a wearable device, and the wearable device includes at least one of a watch, a bracelet, a necklace, glasses, etc. It should be noted that when obtaining the reference position data, it can be judged in combination with the user's status and mode. For example, targeted judgments can be made according to different scenarios, such as judging separately for scenarios such as the patient resting, exercising, lying down, etc., to improve the prediction accuracy.

[0066] According to an embodiment of the present application, the identity information includes gender and age group, the geographical information includes region, the exercise information includes exercise time and exercise type, the time information includes date and real-time moment, and the intubation duration information includes the already intubated duration, the last maintenance time, and the predicted next maintenance time. By refining the patient's information, the accuracy of judging whether the catheter needs to be maintained in the future period can be improved.

[0067] The present application also discloses a PICC home maintenance evaluation system. The PICC home maintenance evaluation system includes: a data monitoring module and a cloud platform module. The data monitoring module is used to collect catheter position data and reference position data. The cloud platform module is used to receive the data information obtained by the data monitoring module, and analyze and process the catheter position data, reference position data and catheter standard position data to obtain the catheter position information within a future time and obtain a decision result on whether the catheter needs to be maintained. By adopting the cloud platform module, not only can the data of the brand, model, insertion site, depth, exposure, arm circumference, catheter tip positioning chest radiograph, and every subsequent maintenance use of the catheter from the time of insertion be integrated and managed through the system, but also no matter which hospital the patient goes to for maintenance, the catheter maintenance use data in the cloud platform module can be used to understand the whole process of PICC insertion, use and maintenance of the patient.

[0068] At the same time, the cloud platform module is also provided with a maintenance reminder function to remind the patient to perform regular maintenance, standardize regular maintenance to extend the service life of the catheter and reduce the probability of complications, and at the same time detect the occurrence of warning complications as early as possible. In addition, the PICC home maintenance evaluation system can be installed in an electronic device and used in conjunction with software. The software can directly make an appointment for a maintenance clinic, which is convenient and fast. At the same time, a health education section is provided in the software to continuously educate the patient by pushing videos or texts. The patient can obtain points to exchange for gifts by clicking to watch and learn the video for the cumulative learning duration. By adopting the software, the self-management ability of the patient can be helped to improve. Specifically, it includes the following advantages: the patient enters the personal homepage and can select the corresponding functions according to needs; the basic information in the software covers all information of the catheter, including the X-ray positioning imaging data after successful catheterization; no matter which hospital the patient goes to for treatment or maintenance, the previous catheterization and maintenance records can be viewed; directly make an appointment for the PICC maintenance clinic through the software.

[0069] That is to say, the system can include a data monitoring module and a cloud platform module. Among them, the catheter position and reference position can be collected through the data monitoring module. For example, the data monitoring module includes a wireless sensor, a GPS locator, etc. The cloud platform module can judge and predict future data information to obtain a conclusion on whether the catheter needs to be maintained. The cloud platform module can include a data storage and processing module. Through the data storage and processing module, the obtained data information, etc. can be processed and analyzed to obtain a decision result, and the decision result is sent to the information receiving module where the user can obtain the decision result.

[0070] All in all, according to the PICC home maintenance evaluation method and system of the embodiments of the present application, the whole process of PICC can be controlled, the maintenance of PICC catheterization can be realized, and difficult complications can be monitored, which can provide work guidance for medical staff.

[0071] In addition, an embodiment of the present invention further provides a computer storage medium, which includes one or more computer instructions. When the one or more computer instructions are executed, the above-mentioned PICC home maintenance assessment method is implemented.

[0072] That is to say, the computer storage medium stores a computer program. When the computer program is run by a processor, the processor is caused to execute the above-mentioned PICC home maintenance assessment method.

[0073] As Figure 2 shown, an embodiment of the present invention provides an electronic device 300, which includes a memory 310 and a processor 320. The memory 310 is used to store one or more computer instructions, and the processor 320 is used to call and execute the one or more computer instructions, so as to implement the above-mentioned method.

[0074] That is to say, the electronic device 300 includes: a processor 320 and a memory 310. Computer program instructions are stored in the memory 310. When the computer program instructions are run by the processor, the processor 320 is caused to execute the above-mentioned method.

[0075] Further, as Figure 2 shown, the electronic device 300 further includes a network interface 330, an input device 340, a hard disk 350, and a display device 360.

[0076] The above-mentioned various interfaces and devices can be interconnected through a bus architecture. The bus architecture can include any number of interconnected buses and bridges. Specifically, one or more central processing units (CPUs) represented by the processor 320 and various circuits of one or more memories represented by the memory 310 are connected together. The bus architecture can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits. It can be understood that the bus architecture is used to realize the connection and communication between these components. In addition to the data bus, the bus architecture also includes a power bus, a control bus, and a status signal bus, which are well known in the art and will not be described in detail herein.

[0077] The network interface 330 can be connected to a network (such as the Internet, a local area network, etc.), obtain relevant data from the network, and can be stored in the hard disk 350.

[0078] The input device 340 can receive various instructions input by an operator and send them to the processor 320 for execution. The input device 340 can include a keyboard or a pointing device (for example, a mouse, a trackball, a touchpad, or a touch screen, etc.).

[0079] The display device 360 can display the results obtained by the processor 320 executing instructions.

[0080] The memory 310 is used to store the programs and data necessary for the operation of the operating system, as well as data such as intermediate results during the calculation process of the processor 320.

[0081] It can be understood that the memory 310 in the embodiments of the present invention can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. The memory 310 of the devices and methods described herein is intended to include, but is not limited to, these and any other suitable types of memories.

[0082] In some embodiments, the memory 310 stores the following elements, executable modules, or data structures, or subsets thereof, or extended sets thereof: the operating system 311 and the application program 312.

[0083] Among them, the operating system 311 includes various system programs, such as the framework layer, the core library layer, the driver layer, etc., and is used to implement various basic services and process hardware-based tasks. The application program 312 includes various application programs, such as a browser (Browser), etc., and is used to implement various application services. The program for implementing the method of the embodiments of the present invention can be included in the application program 312.

[0084] When the above-mentioned processor 320 calls and executes the application programs and data stored in the memory 310, specifically, when it is the programs or instructions stored in the application program 312, it dispersedly sends one of the first set and the second set to the nodes where the other of the first set and the second set is distributed, where the other is dispersedly stored in at least two nodes; and performs intersection processing node by node according to the node distribution of the first set and the node distribution of the second set.

[0085] The method disclosed in the above embodiments of the present invention can be applied to or implemented by the processor 320. The processor 320 may be an integrated circuit chip with signal processing capabilities. In the implementation process, the steps of the above method can be completed by the integrated logic circuit in hardware or instructions in software form in the processor 320. The above-mentioned processor 320 may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 310, and the processor 320 reads the information in the memory 310 and combines its hardware to complete the steps of the above method.

[0086] It can be understood that these embodiments described herein can be implemented using hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described in this application, or a combination thereof.

[0087] For software implementation, the techniques described herein can be implemented by modules (e.g., procedures, functions, etc.) that execute the functions described herein. The software code can be stored in a memory and executed by a processor. The memory can be implemented within the processor or external to the processor.

[0088] Specifically, the processor 320 is further configured to read the computer program and execute any one of the above methods.

[0089] In several embodiments provided by the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in electrical, mechanical or other forms.

[0090] In addition, each functional unit in various embodiments of the present invention can be integrated in a processing unit, or each unit can be physically included separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a combination of hardware and software functional units.

[0091] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit stored in a storage medium includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute some steps of the transceiver method described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM for short), random access memories (RAM for short), magnetic disks, or optical discs that can store program codes.

[0092] The above is the preferred implementation manner of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for evaluating home maintenance of PICC, characterized in that, it includes the following steps: S1. Collect catheter position data in a three-dimensional coordinate system within a predetermined time period to obtain a set of catheter position data, collect reference position data in the three-dimensional coordinate system within the predetermined time period to obtain a set of reference position data, compare the magnitude between each data in the set of catheter position data and the corresponding reference position data within the predetermined time period to obtain a first difference, and obtain a set of first differences; S2. Collect the standard positions of the catheter in the three-dimensional coordinate system within the predetermined time period to obtain a set of standard position data, compare the magnitude between each of the standard position data and the corresponding reference position data within the predetermined time period to obtain a second difference, obtain a set of second differences, compare the magnitude relationship between the first difference and the second difference within the predetermined time period to obtain a third difference, and obtain a set of third differences; S3. Process the third differences within the predetermined time period to obtain a data network set, use the data network set as a sample set, and divide the sample set into a training set and a test set, test the long short-term memory network method through the test set to obtain a long short-term memory network method model; S4. Collect real-time data of the training set, input the real-time data into the long short-term memory network method model to predict the future value of the third difference; S5. According to the prediction result and the relevance of catheter maintenance requirements, divide the training set into a first maintenance requirement classification data set and a second maintenance requirement classification data set; One of the first maintenance requirement classification data set and the second maintenance requirement classification data set is a no-maintenance classification data set, and the other of the first maintenance requirement classification data set and the second maintenance requirement classification data set is a to-be-maintained classification data set; If the prediction result is greater than a first threshold, divide the training set into the to-be-maintained classification data set, and if the prediction result is less than or equal to the first threshold, divide the training set into the no-maintenance classification data set; S6. Classify the first maintenance requirement classification data set and the second maintenance requirement classification data set according to identity information, geographical information, movement information, time information, and indwelling catheter duration information respectively to obtain multiple refined classification data sets; S7. Place the multiple refined classification data sets of the first maintenance requirement classification data set and the second maintenance requirement classification data set in a network for training respectively to obtain a training model; Set up a hypothetical patient module, and the hypothetical patient module is built-in with random identity information, geographical information, movement information, time information, and indwelling catheter duration information; Obtain the identity information, geographical information, movement information, time information, and indwelling catheter duration information of the hypothetical patient module; Match the hypothetical patient module with a refined classification data set of one of the first maintenance requirement classification data set and the second maintenance requirement classification data set according to the obtained information at a first time and a second time respectively; When the matching results at the first time and the second time are inconsistent, the imaginary patient module is matched with the refined classification dataset of the other one of the first maintenance requirement classification dataset and the second maintenance requirement classification dataset according to the information obtained at the second time, and the training is ended to obtain the training model; When the matching results at the first time and the second time are consistent, the training is ended to obtain the training model; The imaginary patient module is built with reply information for the matching result, and the imaginary patient module can receive and send interaction information; When the imaginary patient module replies with consent to the matching result information or does not reply with confirmation information, the training is ended; When the imaginary patient module replies with disagreement to the matching result information, the training model is associated with a third party to obtain the training model.

2. The PICC home maintenance evaluation method according to claim 1, wherein, If the predicted result is greater than the first threshold and according to the difference between the predicted result and the first threshold, the to-be-maintained classification dataset is divided into a self-maintenance classification dataset and a professional maintenance classification dataset; Among them, when the difference between the predicted result and the first threshold is within the first range, the to-be-maintained classification data is the self-maintenance classification dataset, and when the difference between the predicted result and the first threshold is within the second range, the to-be-maintained classification data is the professional maintenance classification dataset, and the first range is smaller than the second range.

3. The PICC home maintenance evaluation method according to claim 2, wherein, Step S5 includes: Obtaining the user identifiers of each vertex in the training set; Obtaining the numerical ranges of the first range and the second range; Comparing the user identifier with the numerical ranges of the first range and the second range. If the user identifier is within the numerical range of the first range, the user identifier is classified into the to-be-maintained classification dataset. If the user identifier is within the numerical range of the second range, the user identifier is classified into the non-maintenance required classification dataset.

4. The PICC home maintenance evaluation method according to claim 1, wherein, The identity information includes gender and age group, the geographical information includes region, the exercise information includes exercise time and exercise type, the time information includes date and real-time moment, and the indwelling duration information includes the indwelling duration, the last maintenance time, and the predicted next maintenance time.

5. A PICC home maintenance evaluation system, wherein, The PICC home maintenance evaluation system uses the PICC home maintenance evaluation method described in any one of claims 1-4 to maintain the PICC. The PICC home maintenance evaluation system includes: A data monitoring module, which is used to collect catheter position data and reference position data; A cloud platform module, which is used to receive the data information obtained by the data monitoring module, and analyze and process the catheter position data, the reference position data and the catheter standard position data to obtain the catheter position information in the future time and obtain a decision result on whether the catheter needs to be maintained.

6. A computer storage medium, characterized in that it includes one or more computer instructions, and when the one or more computer instructions are executed, the method described in any one of claims 1-4 is implemented.

7. An electronic device, comprising a memory and a processor, characterized in that the memory is used to store one or more computer instructions; the processor is used to call and execute the one or more computer instructions, so as to implement the method described in any one of claims 1-4.

Images