A method and system for nurse shift handover records

Abstract

The present application discloses a nurse handover record method and system, which relates to the field of medical management. The method includes obtaining the original handover record of a target patient by a target handover staff; matching standard feature tags according to the current physiological characteristics of the target patient; the standard feature tags include structural information feature items and unstructured information feature items of the patient type corresponding to the target patient; obtaining the record completion degree according to the matching results of all the standard feature tags and the original handover record; if the record completion degree is not greater than the completion degree threshold, generating a first feedback message, and returning to the step of obtaining the original handover record of the target patient by the target handover staff until the record completion degree is greater than the completion degree threshold, and obtaining a target handover record according to all the original handover records, so as to realize the integrity verification of the original handover record provided by the target handover staff.

Description

Technical Field

[0001] This application relates to the field of medical management, and particularly to a nurse handover record method and system. Background Art

[0002] Nurse handover refers to the activity in which the handing-over nurse introduces and communicates the patient's condition, treatment, nursing, etc. to the taking-over nurse orally or in writing when the nurse's work shifts alternate, so as to ensure that the patient receives continuous and timely treatment and nursing. Traditional handovers rely on oral transmission and paper records, and time constraints, heavy workload, lack of nursing experience, etc. will all affect the integrity of the handover record.

[0003] With the rapid development of medical informatization, hospital information management systems and electronic medical record systems have been widely applied to clinical nursing work. For example, a method, device and terminal equipment for handover between medical staff with the application number CN201811042431.9 queries patient data generated during the working period of the handing-over staff through an electronic system, and then automatically generates a handover report. Although this method can efficiently and comprehensively obtain structured information such as the test and examination results of patients, it is difficult for the electronic system to directly obtain unstructured information such as the subjective feelings and personalized demands of patients in a timely, accurate and comprehensive manner. The lack of unstructured information in the handover record will lead to a high risk of missing important information in the handover record. Summary of the Invention

[0004] The purpose of the present invention is to solve the technical problem of how to reduce the omission of important information during the nurse handover process, and provides a nurse handover record method and system, which uses the physiological characteristics of the patient to match the necessary characteristic items during the handover process, and checks the integrity of the handover record provided by the handing-over staff according to the matching result, so as to achieve the purpose of reducing the risk of missing important information during the handover process.

[0005] According to the first aspect of the present invention, the present invention claims protection for a nurse handover record method, including:

[0006] Obtain the original handover record of the target patient by the target handing-over staff;

[0007] Match the standard characteristic tags according to the current physiological characteristics of the target patient; the standard characteristic tags include the structural information characteristic items and non-structural information characteristic items corresponding to the patient type of the target patient;

[0008] Obtain the record completion degree according to the matching result of all the standard characteristic tags and the original handover record;

[0009] If the record completion degree is not greater than the completion degree threshold, generate first feedback information, and return to the step of obtaining the original handover record of the target patient by the target handover personnel until the record completion degree is greater than the completion degree threshold, and obtain the target handover record according to all the original handover records; the first feedback information is used to remind the corresponding target handover personnel to supplement the original handover record.

[0010] In an embodiment of the present application, in the step of matching the standard feature label according to the current physiological characteristics of the target patient, it further includes:

[0011] Obtain the candidate handover record and the corresponding integrity evaluation according to the historical handover record;

[0012] Obtain the feature similarity between the physiological characteristics of the patient corresponding to each candidate handover record and the current physiological characteristics of the target patient;

[0013] Obtain candidate feature items according to all the candidate handover records;

[0014] Respectively obtain the necessity components of the candidate feature items existing in the corresponding candidate handover record according to the feature similarity and the integrity evaluation of each candidate handover record;

[0015] Calculate the corresponding necessity degree according to all the necessity degree components of each candidate feature item;

[0016] Use the candidate feature items with the necessity degree greater than the necessity degree threshold as the standard feature items.

[0017] In an embodiment of the present application, the integrity evaluation includes high integrity and low integrity, and the necessity components of the candidate feature items further include:

[0018] ;

[0019] Where N i，j represents the necessity component of the candidate feature item c i in the candidate handover record r j , I represents the indicator function, S j represents the feature similarity of the candidate handover record r j , and E j represents the integrity evaluation of the candidate handover record r j .

[0020] In an embodiment of the present application, the integrity evaluation is obtained according to the comparison result between the number of medical events caused by handover abnormalities in the next shift corresponding to the candidate handover record and the accident number threshold.

[0021] In an embodiment of the present application, in the step of obtaining candidate handover records based on historical handover records, the following steps are further included:

[0022] Query historical handover records according to the original handover record to obtain reference handover records; the record similarity between the reference handover record and the original handover record is not less than the first similarity threshold;

[0023] If the number of the reference handover records is equal to 0, generate second feedback information, and the second feedback information is used to remind the target handover personnel that the handover behavior is abnormal;

[0024] If the number of the reference handover records is greater than 0, screen out candidate handover records from all the reference handover records, and the similarity between the patient physiological characteristics corresponding to the candidate handover records and the current physiological characteristics of the target patient is not less than the second similarity threshold;

[0025] If the number of the candidate handover records is equal to 0, generate the second feedback information.

[0026] In an embodiment of the present application, before the step of querying historical handover records according to the original handover record, the following steps are further included:

[0027] Obtain rejection characteristics according to the current physiological characteristics of the target patient;

[0028] Screen out historical handover records with the rejection characteristics from all the historical handover records.

[0029] In an embodiment of the present application, before the step of querying historical handover records according to the original handover record, the following steps are further included:

[0030] Screen out abnormal physiological characteristics from the current physiological characteristics of the target patient;

[0031] Match the historical handover records according to the abnormal physiological characteristics to obtain abnormal handover records;

[0032] Before the preset handover time, update the historical handover records according to the abnormal handover records, and continue to execute the step of querying the updated historical handover records according to the original handover record until the first target handover record is obtained, and send the first target handover record to the target successor;

[0033] After the preset handover time, obtain a second target handover record according to the first target handover record and the supplementary record of the target successor, update the original handover record according to the second target handover record, and continue to execute the step of querying all the historical handover records according to the updated original handover record to obtain the second target handover record.

[0034] According to a second aspect of the present invention, the present invention claims protection for a nurse handover record system, comprising:

[0035] A record acquisition module, which is used to acquire the original handover record of a target patient by a target handover person;

[0036] A standard matching module, which is used to match standard feature tags according to the current physiological characteristics of the target patient; wherein, the standard feature tags include structural information feature items and non-structural information feature items of the patient type corresponding to the target patient;

[0037] A completion degree calculation module, which is used to obtain the record completion degree according to the matching results of all the standard feature tags and the original handover record;

[0038] A record processing module, which is used to compare the record completion degree with a completion degree threshold. If the record completion degree is not greater than the completion degree threshold, it generates a first feedback message and returns it to the record acquisition module until the record completion degree is greater than the completion degree threshold, and obtains a target handover record according to all the original handover records; the first feedback message is used to remind the corresponding target handover person to supplement the original handover record.

[0039] The present application has the following beneficial effects:

[0040] 1. The pre-acquired original handover record is an original detailed description of the individual characteristics of the target patient based on the professional knowledge and clinical experience of the target handover person. The corresponding handover feature items are matched according to the current physiological characteristics of the target patient, and the handover feature items are matched with the original handover record provided by the target handover person. According to the matching results, the record completion degree of the original handover record is calculated. If the record completion degree is not greater than the completion degree threshold, the current original handover record is regarded as having important information omitted, and the target handover person is reminded to supplement it until the record completion degree is greater than the completion degree threshold. This not only realizes the integrity verification of the original handover record provided by the target handover person, reduces the risk of important information omission in the handover record, but also retains the individual characteristic description based on professional knowledge and clinical experience, reduces the phenomenon that the special characteristics of the target patient are ignored, and further reduces the risk of important information omission in the handover record.

[0041] 2. According to the reference degree of the candidate handover record to the handover information of the target patient, the necessity of the candidate feature items existing in the candidate handover record is obtained, and the important information required for the handover of the target patient is accurately identified individually according to the historical handover record and the historical handover evaluation result, improving the adaptability of the handover information to the target patient and further reducing the risk of important information omission in the nurse handover.

[0042] 3. The degree of necessity obtained from statistics of multiple candidate handover records is not only conducive to extracting common necessary handover feature items from high-completeness historical handover records, but also conducive to extracting necessary handover feature items omitted from low-completeness historical handover records based on the comparison results of low-completeness historical handover records and high-completeness historical handover records, thereby improving the matching completeness of standard feature labels and reducing the risk of missing important information.

[0043] 4. The completeness evaluation is obtained based on the number of medical events caused by abnormal handover in the next shift corresponding to the candidate handover record, so as to reduce the inaccurate completeness evaluation of historical handover records caused by human subjectivity.

[0044] 5. Candidate handover records are obtained by screening from historical handover records based on record similarity and feature similarity. On the one hand, the influence of handover records with little correlation with the target patient on the standard feature label is reduced, and the degree of adaptability of the standard feature label to the target patient is improved. On the other hand, the second feedback information can be used to capture the abnormal handover behavior of the target handover personnel and reduce the risk of missing information of the target patient caused by abnormal handover behavior. For example, when uploading the handover record, only a small number of patient feature descriptions are uploaded for integrity verification results to obtain the first feedback information containing feature items that do not meet the preset matching rules, so that the content of the first feedback information is used as a template to improve the handover record, ignoring the personalized characteristics of the target patient.

[0045] 6. The historical handover records are screened in advance by using the exclusion feature. The historical handover records with the exclusion feature will no longer participate in the matching of the standard feature labels of the target patient, so as to reduce the amount of calculation inside the computer.

[0046] 7. Before the preset handover time, all historical handover records are screened according to abnormal physiological characteristics, so as to ensure that the standard feature tags corresponding to the abnormal physiological characteristics can be matched before the preset handover time, while reducing the computational complexity of a single handover record verification task before the preset handover time and increasing the maximum number of concurrent requests of the computer. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0048] Figure 1 A flowchart of an implementation method of a nurse shift handover recording method involved in an embodiment of the present application;

[0049] Figure 2 A flowchart for obtaining standard feature items involved in the embodiments of the present application;

[0050] Figure 3 This is a flowchart for screening candidate handover records involved in the embodiments of this application;

[0051] Figure 4 This is a flowchart of another implementation manner of a nurse handover record method involved in the embodiments of this application;

[0052] Figure 5 This is a schematic structural diagram of a nurse handover record system involved in the embodiments of this application;

[0053] Figure 6 This is a schematic structural diagram of an electronic device involved in the embodiments of this application. Detailed implementation manners

[0054] The present invention provides a nurse handover record method and system. To make the above objects, features, and advantages of this application more obvious and understandable, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Usually, the components of the embodiments of this application described and shown in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, with reference to terms such as "one embodiment", "some embodiments", "implementation manners", "embodiments", "schematic embodiments", "examples", "specific examples", or "some examples", etc., the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of this application that is required to be protected, but only represents that the specific features, structures, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. Moreover, the specific features, structures, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of this application.

[0055] It should be noted that: similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, relational terms such as "first", "second", etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0056] According to the first aspect of the present invention, the present invention claims protection for a nurse handover record method. Referring to the attached Figure 1 as shown, it includes:

[0057] S1: Obtain the original handover record of the target patient by the target handover personnel.

[0058] It should be noted that the target handover personnel include the medical staff who hand over information such as the work situation of the current shift and the condition of the target patient to the next shift during the handover process. For example, the nurse of the current shift responsible for the target patient and the auxiliary nurse who assists the nurse of the current shift to complete the nursing tasks, etc. There can be 1 target handover personnel, or more than 1. This application does not further limit the number of target handover personnel for the target patient. When there are more than 1 target handover personnel, the original handover records of each target handover personnel for the target patient are obtained respectively.

[0059] It should be noted that the original handover record includes at least one of the basic information of the target patient, the change of the condition, the information of the executed doctor's orders, and the information of precautions, and of course it can be more than this. The basic information includes at least one of the patient's identity identifier, gender, age, and admission time, and of course it can be more than this. The identity identifier includes the identifier for identifying the patient's unique identity information to verify the patient's information, such as the patient number, hospital stay number, and bed number, etc. The change of the condition includes at least one of the vital signs and symptoms. The vital signs include heart rate, blood pressure, body temperature, blood oxygen saturation, etc. The symptoms include pain, bleeding, swelling, conscious, drowsy, coma, etc. The information of the executed doctor's orders includes at least one of the completed doctor's order information, the doctor's orders to be executed in the next shift, and the information of the changed doctor's orders, and of course it can be more than this. The doctor's order information includes at least one of the main diagnosis, the overview of the condition, the information of the treatment items, and the information of the nursing operations. For example, the drug name, dosage, and administration time of the medication, the operation method of sputum suction, the equipment used, and the operation time, etc. The information of precautions includes at least one of the special needs of the patient and the family, the unexpected situations during the treatment process, and the special doctor's orders.

[0060] S2: Match the standard feature tags according to the current physiological characteristics of the target patient. Among them, the standard feature tags include the handover feature items of the patient type corresponding to the target patient, and the handover feature items include the structural information feature items and the unstructured information feature items, and of course it can be more than this. The structural information feature items include the feature items with clear predefined data models and formats that can be directly obtained by querying electronic systems such as the medical information management system, such as biochemical examination results, vital signs, etc., and the unstructured information feature items include the feature items that cannot be directly obtained by querying electronic systems such as the medical information management system and have no predefined features, such as the subjective feelings of the patient, etc.

[0061] It should be noted that the physiological characteristics include all treatment information stored in electronic systems such as the information management system and / or the electronic medical record system of the medical institution. For example, basic information, vital signs, examination results, test results, etc.

[0062] It should be noted that the handover characteristic items of patient types are obtained according to the handover specifications of the corresponding medical institutions. The specific patient types and the corresponding handover characteristic items can be stored in the type characteristic database in a preset manner; when in use, the target patient is classified according to the current physiological characteristics of the target patient, and the type characteristic database is queried according to the corresponding patient type to obtain the corresponding standard characteristic label. It is also possible to set preset standard characteristic labels for the physiological characteristics of historical patients in medical institutions, train a neural network model according to the physiological characteristics of the corresponding historical patients and the preset standard characteristic labels, and optimize the neural network model according to the difference between the predicted standard characteristic label output by the neural network model and the preset standard characteristic label. When in use, the current physiological characteristics of the target patient are input into the trained neural network model to obtain the standard characteristic label.

[0063] S3: Obtain the record completion degree according to the matching results of all the standard characteristic labels and the original handover record.

[0064] It should be noted that the matching result can be a classification result, such as a binary classification result (such as successful matching or failed matching), a multi-classification result (such as high matching degree, medium matching degree, and low matching degree), etc., or a regression result, such as a correlation degree, etc.

[0065] In this embodiment, step S3 further includes the following sub-steps: S31. Match each of the standard characteristic labels with the original handover record respectively. S32. Screen out the standard characteristic labels that meet the preset matching rules from all the standard characteristic labels; S33. Calculate the proportion of the standard characteristic labels that meet the preset matching rules in all the standard characteristic labels to obtain the record completion degree.

[0066] In this embodiment, taking "whether the matching is successful" as the matching result and "the standard feature label with the matching result being successful" as the preset matching rule as an example, a detailed description is given. In step S31, each of the standard feature labels and corresponding synonyms can be retrieved in the original handover record. If the retrieval is successful, the matching result corresponding to the standard feature label is set to successful. If the retrieval is unsuccessful, the matching result corresponding to the standard feature label is set to failed. It is also possible to extract the keywords of the original handover record; convert all keywords into corresponding word vectors; convert all the standard feature labels into corresponding word vectors; calculate the cosine similarity between the word vector of each keyword and the word vector of each standard feature label respectively; if there is a cosine similarity greater than the similarity threshold among all the cosine similarities corresponding to each standard feature label, the matching result corresponding to the standard feature label is set to successful. If all the cosine similarities corresponding to each standard feature label are not greater than the similarity threshold, the matching result corresponding to the standard feature label is set to failed. It is also possible to choose to pre-train a machine learning model and train the machine learning model through supervised learning, and the matching result is obtained from the output of the original handover record and each of the standard feature labels in the machine learning model.

[0067] S4: Compare the record completeness with the completeness threshold. If the record completeness is greater than the completeness threshold, generate a target handover record based on the original handover record and send the target handover record to the target successor. If the record completeness is not greater than the completeness threshold, generate a first feedback message and return to step S1 for execution until the record completeness of the corresponding original handover record is greater than the completeness threshold, and obtain the target handover record based on all the original handover records.

[0068] It should be noted that the completeness threshold can be obtained by means of pre-setting.

[0069] It should be noted that the original handover record can be directly used as the first handover record, or the first handover record can be obtained after preprocessing the original handover record. The preprocessing is, for example, removing duplicates from the content of multiple original handover records.

[0070] It should be noted that the target successor includes medical staff who take over the care work of the target patient in the next shift. For example, the nurse in the next shift responsible for the target patient and the auxiliary nurse who assists the nurse in the next shift to complete the care task, etc. There can be 1 target successor, or more than 1. This application does not further limit the number of target successors of the target patient. When there are more than 1 target successors, the first handover record is sent to each of the target successors respectively.

[0071] In this embodiment, the first feedback information is used to remind the corresponding target handover personnel to supplement the original handover record. The first feedback information includes the standard feature tags that do not conform to the preset matching rules. When the number of the target handover personnel is more than one, the first feedback information can be sent to each of the target handover personnel simultaneously; or the first feedback information can be sent to a designated target handover personnel, such as a responsible nurse, etc.; or according to the standard feature tags that do not conform to the preset matching rules, the corresponding nursing executor can be matched, and the first feedback information can be sent to the nursing executor.

[0072] It should be noted that the pre-obtained original handover record is an original detailed description of the individual characteristics of the target patient based on the professional knowledge and clinical experience of the target handover personnel. The corresponding handover feature items are matched according to the current physiological characteristics of the target patient, and the handover feature items are matched with the original handover record provided by the target handover personnel. According to the matching result, the record completion degree of the original handover record is calculated. If the record completion degree is not greater than the completion degree threshold, the current original handover record is regarded as having important information omitted, and the target handover personnel are reminded to supplement it until the record completion degree is greater than the completion degree threshold. This not only realizes the integrity verification of the original handover record provided by the target handover personnel, reduces the risk of important information omission in the handover record, but also retains the individual characteristic description based on professional knowledge and clinical experience, reduces the phenomenon that the special characteristics of the target patient are ignored, and further reduces the risk of important information omission in the handover record.

[0073] In a feasible embodiment, referring to the appendix Figure 2 as shown, step S2 further includes the following sub-steps:

[0074] S21: Obtain the candidate handover record and the corresponding integrity evaluation according to the historical handover record.

[0075] It should be noted that the candidate handover record is screened from the historical handover record. The screening strategy can be no screening, or screening according to the similarity between the physiological characteristics of the patient corresponding to the historical handover record and the current physiological characteristics of the target patient, or other feasible embodiments. Denote the candidate handover record as R, R = {r 1 , r 2 , …, r j , …, r m}. Wherein, r j represents the j-th candidate handover record, and m represents the number of all candidate handover records.

[0076] It should be noted that the integrity evaluation can be obtained according to the evaluation results of the nursing staff in the next shift corresponding to the candidate handover records, or according to the evaluation results of the head nurse, etc., or other feasible methods. The integrity can be a scoring result, such as a scoring result on a 10-point scale or a 100-point scale, etc., or a grading result, such as a three-category grading result of high integrity evaluation, medium integrity evaluation, and low integrity evaluation, etc.

[0077] S22. Obtain the feature similarity between the physiological characteristics of each patient corresponding to the candidate handover record and the current physiological characteristics of the target patient.

[0078] It should be noted that the feature vectors of the current physiological characteristics of the target patient and the physiological characteristics of the historical patients corresponding to all the candidate handover records can be extracted respectively through the first neural network model. Calculate the cosine similarity between the feature vector of the current physiological characteristics of the target patient and the feature vector of the physiological characteristics of the historical patient corresponding to each candidate handover record, and obtain the feature similarity between the physiological characteristics of the historical patient corresponding to the candidate handover record and the current physiological characteristics of the target patient.

[0079] S23: Obtain candidate feature items according to all the candidate handover records.

[0080] It should be noted that all the feature items existing in all the candidate handover records can be statistically integrated to obtain the candidate feature items. Denote the candidate feature items as C, C = {c 1 , c 2 , …, c i , …, c n}. Among them, c i represents the i-th candidate feature item, and n represents the number of all candidate feature items.

[0081] S24: Respectively obtain the necessity components of the candidate feature items existing in the corresponding candidate handover record according to the feature similarity and the integrity evaluation of each candidate handover record. Calculate the corresponding degree of necessity according to all the necessity degree components of each candidate feature item.

[0082] It should be noted that the feature similarity and the integrity evaluation of each candidate handover record can be linearly weighted and calculated by setting weight coefficients to obtain the necessity components of all the candidate feature items existing in the candidate handover record.

[0083] It should be noted that the corresponding degree of necessity of the candidate feature item can be linearly weighted and calculated by setting weight coefficients for each necessity component corresponding to the candidate feature item.

[0084] S25: Use the candidate feature items with a necessity degree greater than the necessity threshold as the standard feature items. The specific value of the necessity threshold can be set in advance.

[0085] It should be noted that for candidate handover records with the same integrity evaluation, the greater the feature similarity of the candidate handover record, the greater the referenceability of the handover information corresponding to the target patient, and the smaller the feature similarity of the candidate handover record, the smaller the referenceability of the handover information corresponding to the target patient. For candidate handover records with the same feature similarity, the greater the integrity evaluation of the candidate handover record, the greater the referenceability of the handover information corresponding to the target patient, and the smaller the integrity evaluation of the candidate handover record, the smaller the referenceability of the handover information corresponding to the target patient. The necessity degree of the candidate feature items existing in the candidate handover record is obtained according to the reference degree of the candidate handover record to the handover information of the target patient, and the important information required for the handover of the target patient is accurately identified personalized according to the historical handover record and the historical handover evaluation result, improving the adaptability of the handover information to the target patient and further reducing the risk of omission of important information in the nurse handover.

[0086] In a feasible implementation manner, the integrity evaluation includes high integrity and low integrity. The necessity degree N i corresponding to the candidate feature item c i is calculated as follows:

[0087] ;

[0088] ;

[0089] where m represents the number of the candidate handover records, N i，j represents the necessity component of the i-th candidate feature item in the candidate handover record r j , Sj represents the feature similarity of the candidate handover record r j , and E j represents the integrity evaluation of the candidate handover record r j .

[0090] It should be noted that I represents the indicator function. When the "condition" holds, the value of I(condition) is 1, and when the "condition" does not hold, the value of I(condition) is 0.

[0091] It should be noted that taking the candidate handover record shown in Table 1 below as an example for detailed description. When the candidate feature item belongs to the candidate handover record, the corresponding cell value is 1, otherwise the value is 0. For example, the values corresponding to c 7 and r 2 in Table 1 are 1, indicating that the candidate feature item c 7 belongs to the candidate handover record r2 The patient characteristics recorded in 7 and r 1 The corresponding value is 0, indicating that the candidate feature item c 7 does not belong to the candidate handover record r 1 The patient characteristics recorded in.

[0092] Table 1 Statistical table of candidate handover record information

[0093]

[0094] It should be noted that the candidate feature item c 7 In the candidate handover record r 1 The necessity component N 7，1 Is 1 * 0.9 = 0.9, and the candidate feature item c 7 In the candidate handover record r 2 The necessity component N 7，2 Is 1 * 0.8 = 0.8, and the candidate feature item c 7 In the candidate handover record r 3 The necessity component N 7，3 Is 0 * 0.7 = 0. Thus, the calculated necessary degree N 7 Corresponding to the candidate feature item c 7 The value of is 0.9 + 0.8 + 0 = 1.7. Similarly, the necessary degree corresponding to c 1 -c 7 Is as shown in Table 2 below:

[0095] Table 2 Example table of the necessary degree of candidate feature items

[0096]

[0097] It should be noted that when the integrity evaluation of the candidate handover record is a high integrity, it indicates that when evaluating the integrity of the candidate handover record, the characteristic items existing in the candidate handover record play a greater role in the high integrity evaluation than the characteristic items that do not exist in improving the integrity evaluation. That is, the handover necessity degree of the characteristic items existing in the candidate handover record with high integrity is greater than that of the characteristic items that do not exist. When the integrity evaluation of the candidate handover record is a low integrity, it indicates that when evaluating the integrity of the candidate handover record, the characteristic items that do not exist in the candidate handover record play a greater role in improving the integrity evaluation than the existing characteristic items. That is, there are characteristic items with a high handover necessity degree in the candidate handover record with low integrity. The necessity degree statistically obtained from multiple candidate handover records is not only beneficial to extracting the common necessary handover characteristic items from the historical handover records with high integrity, but also beneficial to extracting the necessary handover characteristic items missed in the historical handover records with low integrity according to the comparison results between the historical handover records with low integrity and the historical handover records with high integrity. For example, the candidate characteristic item c in Table 2 5 , so as to improve the matching integrity of the standard characteristic label and reduce the risk of missing important information.

[0098] In a feasible implementation manner, the integrity evaluation is obtained according to the comparison result between the number of medical events caused by handover anomalies in the next shift corresponding to the candidate handover record and the accident number threshold. When the number of medical events that occur to the historical patient due to handover anomalies in the next shift is greater than the accident number threshold, the integrity evaluation corresponding to the candidate handover record is the high integrity. When the number of medical events that occur to the historical patient due to handover anomalies in the next shift is not greater than the accident number threshold, the integrity evaluation corresponding to the candidate handover record is the low integrity, so as to reduce the adverse impact of human subjective factors on the integrity evaluation of historical handover records.

[0099] It should be noted that the evaluation criteria for the handover anomalies are preset according to the norms of the medical institution. The specific value of the accident number threshold can be obtained by a preset method.

[0100] In a feasible implementation manner, as shown in the attached Figure 3 figure, step S21 further includes the following sub-steps:

[0101] S210. Obtain rejection characteristics according to the current physiological characteristics of the target patient. Obtain all historical handover records, and screen out the historical handover records with the rejection characteristics from all the historical handover records.

[0102] It should be noted that the exclusion features include features that are contradictory to the current physiological features of the target patient. For example, if the gender of the target patient is female, the corresponding exclusion feature includes the feature of male gender. By screening the historical handover records in advance with the exclusion features, the historical handover records with the exclusion features no longer participate in the matching of the standard feature tags of the target patient, so as to reduce the computational workload inside the computer.

[0103] S211. Query historical handover records according to the original handover record to obtain reference handover records; the record similarity between the reference handover record and the original handover record is not less than the first similarity threshold. Among them, the specific value of the first similarity threshold can be obtained by a pre-set method.

[0104] It should be noted that the feature vectors of the original handover record and all the historical handover records can be extracted respectively by the second neural network model. Calculate the cosine similarity between the feature vector of the original handover record and the feature vector of each historical handover record respectively to obtain the corresponding record similarity. Obtain the reference handover record according to the comparison result between all the record similarities and the first similarity threshold; use the historical handover record with the record similarity greater than the first similarity threshold as the reference handover record.

[0105] In this embodiment, if there is no historical handover record with the record similarity greater than the first similarity threshold, second feedback information is generated. The second feedback information is used to remind the target handover personnel that the handover behavior is abnormal, and return to step 1; if the number of the reference handover records is greater than 0, continue to execute step S212.

[0106] S212. Obtain the reference physiological features of the historical patients corresponding to each reference handover record; calculate the feature similarity between the target patient and each reference physiological feature respectively, and use the reference handover record corresponding to the feature similarity greater than the second similarity threshold as the candidate handover record. Among them, the specific value of the second similarity threshold can be obtained by a pre-set method.

[0107] It should be noted that the feature vectors of the current physiological characteristics of the target patient and the physiological characteristics of the historical patients corresponding to all the reference handover records can be extracted respectively by the second neural network model. The cosine similarity between the feature vector of the current physiological characteristics of the target patient and the feature vector of the physiological characteristics of the historical patient corresponding to each reference handover record is calculated respectively to obtain the corresponding feature similarity. The candidate handover records are obtained according to the comparison results of all the feature similarities and the second similarity threshold; the reference handover records corresponding to the feature similarities greater than the second similarity threshold are used as the candidate handover records.

[0108] In this embodiment, if there is no reference handover record with a feature similarity greater than the second similarity threshold, the second feedback information is generated and the process returns to step S1 for execution.

[0109] It should be noted that the candidate handover records are screened from the historical handover records according to the record similarity and the feature similarity. On the one hand, it reduces the influence of handover records with too low correlation with the target patient on the screening of standard feature labels, and improves the adaptation degree of the standard feature labels to the target patient. On the other hand, the second feedback information can be used to capture the abnormal handover record behavior of the target handover personnel, reducing the risk of information omission of the target patient caused by abnormal handover behavior. For example, when uploading the handover record, only a small number of patient feature descriptions are uploaded for the integrity verification result to obtain the first feedback information containing feature items that do not conform to the preset matching rules, so as to use the first feedback information as a template to improve the handover record and ignore the personalized features of the target patient.

[0110] In a feasible embodiment, referring to the appendix Figure 4 as shown, step S21 further includes the following sub-steps:

[0111] S210: Abnormal physiological characteristics are screened out from the current physiological characteristics of the target patient. The historical handover records are matched according to the abnormal physiological characteristics to obtain abnormal handover records. The values of the physiological characteristics corresponding to the abnormal handover records do not fall within the normal value range of the abnormal physiological characteristics.

[0112] Before the preset handover time, the historical handover records are updated according to the abnormal handover records; from step S211, the updated historical handover records are queried according to the original handover records and the process continues until the first target handover record is obtained. The record completion degree corresponding to the first target handover record is greater than the completion degree threshold.

[0113] After the preset handover time, obtain the supplementary record of the first target handover record by the target successor, obtain the second target handover record according to the first target handover record and the supplementary record of the target successor, use the second target handover record as the updated original handover record, and continue to execute from step S211 to query all the historical handover records according to the updated original handover record until the target handover record is obtained.

[0114] It should be noted that there are multiple pairs of nurses on shift at the same preset handover time. At the same time, to ensure high continuity of patient care, the patient conditions in the handover record are as similar as possible to those observed by the successor nurses. Therefore, the time for nurses with the same preset handover time to upload and verify the integrity of the handover record is concentrated. Inevitably, the computer needs to concurrently verify the handover records of all target patients. Before the preset handover time, all historical handover records are preferentially screened according to abnormal physiological characteristics, so as to ensure that the standard feature tags corresponding to the abnormal physiological characteristics can be matched before the preset handover time, while reducing the computational workload of a single handover record verification task before the preset handover time and increasing the maximum concurrent request number of the computer.

[0115] According to the second aspect of the present invention, the present invention claims protection for a nurse handover record system, as shown in the attached Figure 5 It includes:

[0116] A record acquisition module, which is used to acquire the original handover record of the target patient by the target handover personnel;

[0117] A standard matching module, which is used to match and obtain standard feature tags according to the current physiological characteristics of the target patient; wherein, the standard feature tags include the structural information feature items and non-structural information feature items of the patient type corresponding to the target patient;

[0118] A completion degree calculation module, which is used to obtain the record completion degree according to the matching results of all the standard feature tags and the original handover record;

[0119] A record processing module, which is used to compare the record completion degree with the completion degree threshold. If the record completion degree is not greater than the completion degree threshold, generate a first feedback message and return it to the record acquisition module until the record completion degree is greater than the completion degree threshold, and obtain the target handover record according to all the original handover records; the first feedback message is used to remind the corresponding target handover personnel to supplement the original handover record.

[0120] In a feasible implementation manner, the standard matching module further includes:

[0121] A candidate record acquisition sub-module, which is used to obtain candidate handover records and corresponding integrity evaluations according to historical handover records;

[0122] A feature similarity acquisition sub-module, which is used to obtain the feature similarity between the physiological characteristics of each candidate handover record and the current physiological characteristics of the target patient;

[0123] A feature necessity calculation sub-module, which is used to obtain candidate feature items according to all the candidate handover records; respectively obtain the necessity components of the candidate feature items existing in the corresponding candidate handover record according to the feature similarity and the integrity evaluation of each candidate handover record; calculate the corresponding degree of necessity according to all the degree of necessity components of each candidate feature item;

[0124] A feature screening sub-module, which is used to use the candidate feature items with the degree of necessity greater than the necessity degree threshold as the standard feature items.

[0125] In a feasible implementation manner, the integrity evaluation includes high integrity and low integrity, and the necessity component of the candidate feature item further includes:

[0126] ;

[0127] where N i，j represents the necessity component of the candidate feature item c i in the candidate handover record r j , I represents the indicator function, S j represents the feature similarity of the candidate handover record r j , and E j represents the integrity evaluation of the candidate handover record r j .

[0128] In a feasible implementation manner, the integrity evaluation is obtained according to the comparison result between the number of medical events caused by handover anomalies in the next shift corresponding to the candidate handover record and the accident number threshold.

[0129] In a feasible implementation manner, the candidate record acquisition sub-module further includes:

[0130] A record similarity screening grandchild module, which is used to query historical handover records according to the original handover record to obtain reference handover records; the record similarity between the reference handover record and the original handover record is not less than the first similarity threshold;

[0131] The first information feedback sub-module is used to determine whether the number of the reference handover records is 0. If the number of the reference handover records is equal to 0, it generates a second feedback message for reminding the target handover personnel that the handover behavior is abnormal. If the number of the reference handover records is greater than 0, it sends all the reference handover records to the feature similarity screening sub-module.

[0132] The feature similarity screening sub-module is used to screen out candidate handover records from all the reference handover records, and the similarity between the patient physiological features corresponding to the candidate handover records and the current physiological features of the target patient is not less than a second similarity threshold.

[0133] The second information feedback sub-module is used to determine whether the number of the candidate handover records is 0. If the number of the candidate handover records is equal to 0, it generates the second feedback message.

[0134] In a feasible implementation manner, the candidate record acquisition sub-module further includes a rejection screening sub-module, which is used to obtain rejection features according to the current physiological features of the target patient, and screen out the historical handover records with the rejection features from all the historical handover records.

[0135] In a feasible implementation manner, the candidate record acquisition sub-module further includes an abnormal feature screening sub-module, which is used to screen out abnormal physiological features from the current physiological features of the target patient, and match the historical handover records according to the abnormal physiological features to obtain abnormal handover records.

[0136] Before the preset handover time, the abnormal feature screening sub-module sends the abnormal handover records as the historical handover records to the record similarity screening sub-module, and the record similarity screening sub-module continues to query the updated historical handover records according to the original handover records until the first target handover record is obtained, and then sends the first target handover record to the target successor.

[0137] After the preset handover time, the record processing module is further used to obtain a second target handover record according to the first target handover record and the supplementary record of the target successor. The record processing module sends the second target handover record to the record similarity screening sub-module, and the record similarity screening sub-module continues to query all the historical handover records according to the updated original handover record to obtain the second target handover record.

[0138] Refer to the appendix Figure 6As shown, an embodiment of the present application provides an electronic device, including: a processor and a memory. The processor and the memory are interconnected and communicate with each other through a communication bus and / or other forms of connection mechanisms (not shown), and the memory stores a computer program executable by the processor. When the computing device runs, the processor executes the computer program to execute the system in any optional implementation manner of the above embodiment.

[0139] An embodiment of the present application provides a storage medium. When the computer program is executed by the processor, it executes the system in any optional implementation manner of the above embodiment. Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (abbreviated as SRAM), electrically erasable programmable read-only memory (abbreviated as EEPROM), erasable programmable read-only memory (abbreviated as EPROM), programmable read-only memory (abbreviated as PROM), read-only memory (abbreviated as ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0140] In the embodiments provided by the present application, it should be understood that the disclosed system can be implemented in other ways. The system embodiments described above are only illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For another example, multiple modules 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 between each other can be through some communication interfaces. The indirect coupling or communication connection of the system or unit can be in an electrical, mechanical or other form.

[0141] In addition, the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0142] Furthermore, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.

[0143] Flowcharts are used in this document to illustrate the steps of the methods of the embodiments of the present disclosure. It should be understood that the steps before or after do not necessarily have to be carried out precisely in order. On the contrary, various steps can be evaluated in reverse order or simultaneously. Also, other operations can be added to these processes.

[0144] Unless otherwise defined, all terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present disclosure pertains. It should also be understood that terms such as those defined in a common dictionary should be interpreted as having a meaning consistent with their meaning in the context of the relevant art, and should not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0145] The above has introduced in detail a method and system for nurse shift handover records. Specific examples are used in this document to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only for the embodiments of the present application, and is only used to help understand a method and system for nurse shift handover records of the present application, and is not used to limit the protection scope of the present application; at the same time, for those skilled in the art, various changes and modifications can be made to the present application. Any modification and equivalent replacement made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A method for recording nurse shift handover, characterized in that: include: Obtain the original handover record of the target patient by the target handover personnel; Obtain standard feature labels based on the current physiological features of the target patient; The standard feature label includes structural information feature items and non-structural information feature items corresponding to the patient type of the target patient; Obtaining the record completion degree according to the matching results of all the standard feature tags and the original handover record; If the completion degree of the record is not greater than the completion degree threshold, a first feedback message is generated, and the process returns to the step of obtaining the original handover record of the target patient by the target handover personnel, until the completion degree of the record is greater than the completion degree threshold, and the target handover record is obtained according to all the original handover records; the first feedback message is used to remind the corresponding target handover personnel to supplement the original handover record; The step of obtaining a standard feature label according to the current physiological feature matching of the target patient also includes: Obtain candidate handover records and corresponding completeness evaluations based on historical handover records; Obtaining the feature similarity between the patient physiological feature corresponding to each of the candidate handover records and the current physiological feature of the target patient; Obtaining candidate feature items according to all the candidate handover records; Obtaining the necessity component of the candidate feature item existing in the corresponding candidate handover record according to the feature similarity and the completeness evaluation of each candidate handover record; Calculating the corresponding necessity degree according to all the necessity degree components of each of the candidate feature items; The candidate feature item whose necessity degree is greater than a necessity degree threshold is used as the standard feature item.

2. A nurse shift handover recording method according to claim 1, characterized in that: The completeness evaluation includes high completeness and low completeness, and the necessity component of the candidate feature item also includes: ； Among them, N i，j Represents the candidate feature item c i In the candidate handover record j The necessity component, I represents the indicator function, S j Represents the candidate handover record r j The feature similarity, E j Represents the candidate handover record r j The completeness evaluation of .

3. A nurse shift handover recording method according to claim 1, characterized in that: The completeness evaluation is obtained based on a comparison result between the number of medical events caused by abnormal handover in the next shift corresponding to the candidate handover record and a threshold value of the number of accidents.

4. A nurse shift handover recording method according to any one of claims 1 to 3, characterized in that: The step of obtaining candidate handover records according to historical handover records also includes: querying historical handover records according to the original handover record to obtain a reference handover record; the record similarity between the reference handover record and the original handover record is not less than a first similarity threshold; If the number of the reference handover records is equal to 0, second feedback information is generated, and the second feedback information is used to remind the target handover personnel that the handover behavior is abnormal; If the number of the reference handover records is greater than 0, a candidate handover record is selected from all the reference handover records, and the similarity between the patient physiological characteristics corresponding to the candidate handover record and the current physiological characteristics of the target patient is not less than a second similarity threshold; If the number of the candidate handover records is equal to 0, the second feedback information is generated.

5. A nurse shift handover recording method according to claim 4, characterized in that: Before the step of querying the historical handover record according to the original handover record, the method further includes: obtaining a rejection feature according to a current physiological feature of the target patient; The historical handover records having the exclusion feature are screened out from all the historical handover records.

6. A nurse shift handover recording method according to claim 4, characterized in that: Before the step of querying the historical handover record according to the original handover record, the method further includes: Screening out abnormal physiological characteristics from the current physiological characteristics of the target patient; Matching the historical handover record according to the abnormal physiological characteristics to obtain an abnormal handover record; Before the preset handover time, the historical handover record is updated according to the abnormal handover record, and the step of querying the updated historical handover record according to the original handover record is continued until a first target handover record is obtained, and the first target handover record is sent to a target successor; After the preset handover time, a second target handover record is obtained based on the first target handover record and the supplementary record of the target successor, the original handover record is updated based on the second target handover record, and all the historical handover records are continued to be queried based on the updated original handover record to obtain the second target handover record.

7. A nurse shift record system, characterized in that: include: A record acquisition module, the record acquisition module is used to obtain the original handover record of the target patient by the target handover personnel; A standard matching module, the standard matching module is used to obtain a standard feature label according to the current physiological feature matching of the target patient; wherein the standard feature label includes a structural information feature item and a non-structural information feature item of the patient type corresponding to the target patient; A completion degree calculation module, the completion degree calculation module is used to obtain the record completion degree according to the matching results of all the standard feature tags and the original handover record; A record processing module, the record processing module is used to compare the record completion degree with the completion degree threshold, and if the record completion degree is not greater than the completion degree threshold, generate first feedback information, and return to the record acquisition module until the record completion degree is greater than the completion degree threshold, and obtain the target handover record according to all the original handover records; the first feedback information is used to remind the corresponding target handover personnel to supplement the original handover record; The standard matching module also includes: A candidate record acquisition submodule, the candidate record acquisition submodule is used to obtain candidate handover records and corresponding completeness evaluations based on historical handover records; A feature similarity acquisition submodule, the feature similarity acquisition submodule is used to acquire the feature similarity between the patient physiological feature corresponding to each candidate handover record and the current physiological feature of the target patient; A feature necessity calculation submodule, the feature necessity calculation submodule is used to obtain candidate feature items based on all the candidate handover records; obtain the necessity components of the candidate feature items existing in the corresponding candidate handover records based on the feature similarity and the completeness evaluation of each candidate handover record; calculate the corresponding necessity degree based on all the necessity degree components of each candidate feature item; A feature screening submodule is used to use the candidate feature items whose necessity degree is greater than a necessity degree threshold as the standard feature items.

Images