Patient compliance nursing management method based on intelligent wristband monitoring

Abstract

The invention provides a patient compliance nursing management method based on intelligent wrist strap monitoring. State data are monitored in combination with an intelligent wrist strap worn by a patient and uploaded to a background. A compliance nursing strategy recommendation model is trained and constructed on a background based on a historical nursing file data set of a patient by using a big data technology, data features in patient state data can be identified, and compliance nursing strategies corresponding to the patient state data features are output in a matching manner according to the identified features. Therefore, the background can dynamically recommend a corresponding compliance nursing scheme according to the state data of the patient. And subsequently, corresponding medical personnel execute the nursing scheme recommended by the system to carry out dynamic compliance nursing on the patient. An administrator does not need to carry out continuous state analysis on each patient, and does not need to supervise and regulate a nursing strategy at any time, so that the manual adjustment link of compliance nursing is reduced, nursing resources are saved, and intelligent nursing is realized.

Description

Technical Field

[0001] The present invention relates to the technical field, and in particular to a patient compliance nursing management method based on smart wristband monitoring, a patient compliance nursing management device based on smart wristband monitoring, an electronic device and a computer-readable storage medium. Background Art

[0002] Patient compliance nursing management mainly refers to letting clinical patients comply with medical staff to know clinical care, and medical staff need to provide compliance nursing guidance in a timely manner. For example, the following compliance nursing contents: ‌1. Management of medical prescription medication‌ ‌Take medication as directed by the doctor‌: Patients must strictly use the medications prescribed by the doctor on time and in the prescribed dosage, such as eye drops or oral medications, and must not increase or decrease the dosage or stop taking the medication at will‌.

[0003] Correct use of medication: Wash your hands when applying eye drops, drop the drops correctly into the conjunctival sac, and avoid contamination of the bottle mouth. When using multiple eye drops, a certain amount of time should be allowed between each use.

[0004] ‌2. Life and eye care‌ ‌Pay attention to rest‌: ensure adequate sleep and avoid using electronic products for long periods of time to reduce eye fatigue‌.

[0005] Eye hygiene: Keep your eyes and surrounding skin clean, avoid rubbing your eyes directly with your hands, and pay special attention to avoid dirty water splashing into your eyes when washing your face or taking a bath.

[0006] Eye protection: Avoid strenuous exercise and heavy physical labor for a period of time after the operation, and wear sunglasses or protective glasses when going out to prevent external stimulation.

[0007] ‌3. Diet adjustment‌ Balanced diet: Eat more foods rich in vitamins A, C, E and trace elements such as zinc and selenium, such as carrots, spinach, citrus fruits, etc., to promote the repair and regeneration of eye tissues.

[0008] Avoid spicy food: Keep a light diet and avoid spicy and irritating food to avoid aggravating eye discomfort.

[0009] ‌Four. Follow-up and communication‌ Regular follow-up: Go back to the hospital for follow-up as scheduled according to the doctor's instructions, and report any discomfort or abnormalities in a timely manner.

[0010] Good communication: Maintain good communication with the doctor, pay attention to postoperative recovery together, and adjust the treatment plan in time.

[0011] However, the above-mentioned compliance care management is mainly for patients with a certain degree of independent activity ability. But for some bedridden patients or patients in the rehabilitation stage, compliance care needs to be implemented more actively, and medical staff should supervise these patients' implementation of compliance care measures, because these compliance care measures are related to their physical health and rehabilitation recovery. For example, patients who have been bedridden for a long time need to be supervised to carry out regular and quantitative activities to avoid muscle atrophy; for patients in the rehabilitation stage, their activities need to be supervised to avoid excessive rehabilitation exercises that cause physical burden and affect the progress of rehabilitation. The existing patient compliance care management is mainly traditional, that is, offline tracking and management by clinical medical staff, which takes up too much time for accompanying.

[0012] In addition, although there are some smart devices such as smart wristbands and smart bracelets that can monitor patients' motion data such as electrocardiogram, heart rate, blood oxygen, etc., the background can only view and monitor these motion data of patients. Their specific compliance care plans still require the background administrator to check the files, generate or adjust the compliance care plan for the patient according to the patient's condition, and hand it over to the medical staff responsible for the patient for execution. Therefore, the existing compliance care management still relies mainly on manual regulation and is still not intelligent enough. Summary of the invention

[0013] In order to solve the technical problems existing in the prior art, the present invention provides the following technical solutions: On the one hand, a patient compliance nursing management method based on smart wristband monitoring is provided, which is implemented by an electronic device and includes: S1. Collect the historical nursing archive data of several compliant nursing patients, build the corresponding compliance nursing strategy recommendation model based on big data technology and deploy it in the background of the nurse station; S2. Monitoring and collecting the status data of the compliant nursing patient through the smart wristband worn by the compliant nursing patient, and reporting it to the backend of the nurse station at regular intervals; S3, importing the state data into the compliance nursing strategy recommendation model, identifying data features in the state data through the compliance nursing strategy recommendation model, and matching and outputting compliance nursing strategies corresponding to the data features; S4. Recommend the compliance nursing strategy to the corresponding nurse's PDA terminal and remind the nurse to execute it.

[0014] Preferably, the S1 collects historical nursing archive data of several compliant nursing patients, and constructs a corresponding compliance nursing strategy recommendation model based on big data technology and deploys it in the background of the nurse station: construct keywords and archive search logic related to adherence care; Combining the keywords and the archive retrieval logic, constructing a large language model prompt word and inputting a preset LLM large language model; Traversing the backend database through the LLM large language model, retrieving the historical nursing archive data of several compliant nursing patients from the backend database based on the large language model prompt words, wherein the historical nursing archive data includes the compliance nursing strategies historically implemented for the compliant nursing patients and their historical status data and patient clinical examination data, and the historical status data is collected through the smart wristband worn by the compliant nursing patients and recorded and stored in the backend database; Preprocessing the retrieved historical nursing archive data of the plurality of compliant nursing patients to generate a data set consisting of the historical nursing archive data of the plurality of compliant nursing patients; Performing feature engineering on the data set to extract corresponding data features, including: extracting corresponding status data features from the historical status data, extracting corresponding clinical symptom data features from the patient clinical examination data, and extracting corresponding strategy keywords from the compliance nursing strategy and performing feature association binding; Constructing a feature set consisting of several of the data features, and dividing it into corresponding training sets and validation sets according to a preset ratio; Inputting the training set into a preset random forest model to perform feature training and learning to generate the compliance nursing strategy recommendation model; The recognition performance of the compliance nursing strategy recommendation model is verified using the verification set: If the verification is passed, the compliance nursing strategy recommendation model is deployed in the background of the nurse station and put into clinical compliance nursing management; Otherwise, repeat the above steps.

[0015] Preferably, after performing feature engineering on the data set and extracting corresponding data features, the method further includes: The state data feature in the data feature is marked with a feature, wherein the marking information includes: The disease type, symptom stage and / or relevant compliance medication of the compliance care patient corresponding to the data characteristics.

[0016] Preferably, the step S2, monitoring and collecting the status data of the compliant nursing patient through the smart wristband worn by the compliant nursing patient, and reporting the data to the nurse station backend at regular intervals, includes: Establish data communication between the smart wristband worn by the compliant nursing patient and the nurse station backend, and the nurse station backend records the device number of the smart wristband worn by the compliant nursing patient and binds it with the identity / visit ID of the compliant nursing patient; The nurse station backend issues corresponding sampling instructions to the smart wristband according to the preset sampling frequency; Responding to the sampling instruction through the smart wristband and reporting the status data of the compliant nursing patient to the backend of the nurse station; wherein the status data includes the heart rate data, body temperature data, posture sensor data and / or electromyography data of the compliant nursing patient; The nurse station background receives and saves the status data of the compliant nursing patient into the electronic medical record nursing file in the HIS system.

[0017] Preferably, the step S3, importing the status data into the compliance nursing strategy recommendation model, identifying data features in the status data through the compliance nursing strategy recommendation model, and matching and outputting compliance nursing strategies corresponding to the data features, includes: Regularly reading the status data of the compliance nursing patient and importing it into the compliance nursing strategy recommendation model; Identifying and extracting status data features in the status data of the compliance nursing patient through the compliance nursing strategy recommendation model, and outputting the strategy keywords associated with the status data features and annotation information annotated on the status data features; Generate corresponding search instructions according to the strategy keywords and the annotation information and send them to the backend database; The backend database responds to the search instruction, retrieves and outputs the policy data matching the policy keywords and the annotation information from the pre-stored compliance care policy set; The retrieved policy data is bound to the identity / visit ID of the compliant care patient to generate the compliant care policy for the compliant care patient.

[0018] On the other hand, a patient compliance nursing management device based on smart wristband monitoring is provided, and the patient compliance nursing management device based on smart wristband monitoring is used to implement the patient compliance nursing management method based on smart wristband monitoring, and the device includes: A smart wristband is used to monitor and collect the status data of the compliant nursing patients and report it to the nurse station backend at regular intervals; The nurse station backend is used to import the status data into the compliance nursing strategy recommendation model, identify the data features in the status data through the compliance nursing strategy recommendation model, and match and output the compliance nursing strategy corresponding to the data features; and recommend the compliance nursing strategy to the PDA terminal of the corresponding nurse and remind the nurse to execute it; A PDA terminal, used for receiving and displaying the compliance care strategy of the compliance care patient; The smart wristband and the PDA terminal are respectively connected to the backend of the nurse station for communication.

[0019] On the other hand, an electronic device is provided, comprising: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the above-mentioned patient compliance care management methods based on smart wristband monitoring is implemented.

[0020] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction is stored in the storage medium, and the at least one instruction is loaded and executed by a processor to implement any one of the above-mentioned patient compliance care management methods based on smart wristband monitoring.

[0021] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: The present invention combines the smart wristband worn by the patient to monitor the status data and upload it to the background. In the background, based on the patient's historical nursing file data set and trained using big data technology, a compliance nursing strategy recommendation model is constructed. The recommendation model can identify the data features in the patient's status data, and output the compliance nursing strategy corresponding to the patient's status data features based on the identified feature matching, so that the background can dynamically recommend the corresponding compliance nursing plan based on the patient's status data. Subsequently, the corresponding medical staff will execute the nursing plan recommended by the system to provide dynamic compliance nursing care for the patient.

[0022] Therefore, based on the existing application of smart wristbands, AI technology can be used in the background to manage and recommend smart compliance care for patients. The background can automatically recommend corresponding compliance care strategies based on patient status data. There is no need for administrators to conduct continuous status analysis on each patient, nor is there a need to monitor and adjust care strategies at any time, which can reduce the manual adjustment of compliance care, save nursing resources, and achieve smart care. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 This is a flow chart of a patient compliance nursing management method based on smart wristband monitoring provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of using the LLM large language model to perform data assisted retrieval according to an embodiment of the present invention; Figure 3 is a model training flow chart provided by an embodiment of the present invention; Figure 4 This is a block diagram of a patient compliance nursing management device based on smart wristband monitoring provided by an embodiment of the present invention; Figure 5 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0026] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0027] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0028] In the embodiments of the present invention, sometimes the subscripts such as W 1 It may be mistakenly written as a non-subscript form such as W1. When the difference is not emphasized, the meanings they express are the same.

[0029] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0030] In this embodiment, the data communication between the PDA terminal (or EDA) used by medical staff and the backend of the nurse station (server, referred to as the backend), as well as the smart wristband distributed and worn by the patient through the hospital (it can also be a wearable terminal device such as a smart bracelet that communicates with the backend), can be understood by referring to the existing technologies implemented in existing hospitals, and will not be elaborated in this embodiment.

[0031] The data communication between the smart wristband device and the background server can be wired or wireless, and Bluetooth modules or 5G communication modules are preferably used for wireless communication. The logic, application and communication configuration of data communication are established between the background and the administrator can implement the binding management and registration of each smart wristband in the background.

[0032] Corresponding smart wristband device management and file management such as HIS system and push system can be set up in the background, which can realize device management, patient management and patient care file management, etc.

[0033] The embodiment of the present invention provides a patient compliance nursing management method based on smart wristband monitoring, which can be implemented by an electronic device, which can be a terminal or a server. Figure 1 The flowchart of the patient compliance nursing management method based on smart wristband monitoring is shown, and the processing flow of the method may include the following steps: S1. Collect the historical nursing archive data of several compliant nursing patients, build the corresponding compliance nursing strategy recommendation model based on big data technology and deploy it in the background of the nurse station; S2. Monitoring and collecting the status data of the compliant nursing patient through the smart wristband worn by the compliant nursing patient, and reporting it to the backend of the nurse station at regular intervals; S3, importing the state data into the compliance nursing strategy recommendation model, identifying data features in the state data through the compliance nursing strategy recommendation model, and matching and outputting compliance nursing strategies corresponding to the data features; S4. Recommend the compliance nursing strategy to the corresponding nurse's PDA terminal and remind the nurse to execute it.

[0034] Compliance care patients, as described in the background art, are mainly patients who require active care management by medical staff, such as patients with cerebral palsy or mobility impairment who are undergoing rehabilitation training.

[0035] In the past, the background nurses and others designated historical nursing archive data for compliance nursing patients, including, for example, the time when the nurse intervened in the patient's compliance nursing, the patient's status data at that time (such as ECG heart rate, posture, body temperature, etc.), the data characteristics that triggered the intervention nursing (such as body temperature exceeding 39 degrees Celsius, heart rate rising to the alarm value or falling to the warning value, and the appearance of bed-falling posture, etc.) and the compliance nursing strategies implemented by the background for patients (such as nursing patients to take corresponding heart rate-lowering drugs when the heart rate soared, and using cooling patches and ice compresses issued to the accompanying nurses when fever occurred). These nursing logs will be recorded and saved in the background database of the background, forming compliance nursing strategy big data (that is, historical nursing archive data of compliance nursing patients), which contains a lot of compliance nursing knowledge, and can provide clinical compliance nursing guidance and management based on its big data characteristics.

[0036] Therefore, the present invention combines the smart wristband worn by the patient to monitor the status data and upload it to the background. In the background, based on the patient's historical nursing file data set and trained using big data technology, a compliance nursing strategy recommendation model is constructed. The recommendation model can identify the data features in the patient's status data, and output the compliance nursing strategy corresponding to the patient's status data features based on the identified feature matching, so that the background can dynamically recommend the corresponding compliance nursing plan based on the patient's status data. Subsequently, the corresponding medical staff will execute the nursing plan recommended by the system to provide dynamic compliance care for the patient.

[0037] Based on the existing application of smart wristbands, AI technology is used in the background to manage and recommend smart compliance care for patients. The background can automatically recommend corresponding compliance care strategies based on patient status data. Administrators do not need to conduct continuous status analysis on each patient, nor do they need to monitor and adjust care strategies at any time, which can reduce the manual adjustment of compliance care, save nursing resources, and achieve smart care.

[0038] The application principle will be described in detail below.

[0039] Preferably, the S1 collects historical nursing archive data of several compliant nursing patients, and constructs a corresponding compliance nursing strategy recommendation model based on big data technology and deploys it in the background of the nurse station: construct keywords and archive search logic related to adherence care; Combining the keywords and the archive retrieval logic, constructing a large language model prompt word and inputting a preset LLM large language model; Traversing the backend database through the LLM large language model, retrieving the historical nursing archive data of several compliant nursing patients from the backend database based on the large language model prompt words, wherein the historical nursing archive data includes the compliance nursing strategies historically implemented for the compliant nursing patients and their historical status data and patient clinical examination data, and the historical status data is collected through the smart wristband worn by the compliant nursing patients and recorded and stored in the backend database; Preprocessing the retrieved historical nursing archive data of the plurality of compliant nursing patients to generate a data set consisting of the historical nursing archive data of the plurality of compliant nursing patients; Performing feature engineering on the data set to extract corresponding data features, including: extracting corresponding status data features from the historical status data, extracting corresponding clinical symptom data features from the patient clinical examination data, and extracting corresponding strategy keywords from the compliance nursing strategy and performing feature association binding; Constructing a feature set consisting of several of the data features, and dividing it into corresponding training sets and validation sets according to a preset ratio; Inputting the training set into a preset random forest model to perform feature training and learning to generate the compliance nursing strategy recommendation model; The recognition performance of the compliance nursing strategy recommendation model is verified using the verification set: If the verification is passed, the compliance nursing strategy recommendation model is deployed in the background of the nurse station and put into clinical compliance nursing management; Otherwise, repeat the above steps.

[0040] like Figure 2 As shown, when building the model, it is necessary to retrieve the corresponding big data from the database, that is, the historical nursing file data of several compliant nursing patients. If the administrator is asked to search the database, the workload is huge and the efficiency is low. The present invention utilizes the LLM large language model (LLM large language model API interface is deployed on the background, and you can log in and request a third-party large language model platform to request to call its model, such as Baidu's Wenxin Yiyan) to assist in automatic database search, thereby greatly improving the efficiency of model building.

[0041] The steps for letting the LLM large language model perform data retrieval based on prompt words can refer to the following application steps: ‌Construct prompt words‌: According to the retrieval requirements, carefully write prompt words containing keywords and contextual information to stimulate the LLM model to generate relevant responses‌. In this embodiment, it is necessary to construct keywords and archive retrieval logic related to compliance care; combine the keywords and the archive retrieval logic to construct large language model prompt words and input the preset LLM large language model. Specifically, the keywords for compliance care can be constructed based on the type, age, symptom type, degree of care, etc. of compliance patients managed by the hospital; and the archive retrieval logic, that is, the logic of what format of archive data is required, the retrieval time range and population range, and data classification conditions. These keywords and logic can be determined by the administrator.

[0042] ‌Data decomposition and embedding‌: Divide large amounts of unstructured data into blocks and embed each block into the high-dimensional space of a vector database, using natural language processing technology to understand its context and semantic meaning‌.

[0043] Retrieval and matching: The LLM model uses a retrieval algorithm to quickly identify and match based on the semantic similarity between the prompt word and the data block, rather than simple keyword matching.

[0044] ‌Generate Response‌: Based on the most relevant chunk of data retrieved, the LLM model generates a precise, contextually appropriate response‌.

[0045] The LLM large language model is used to traverse the background database (SQL instructions containing keywords and the file retrieval logic can be generated, etc.), and the LLM large language model retrieves the historical nursing file data of several compliant nursing patients from the background database based on the large language model prompt words, wherein the historical nursing file data includes the compliance nursing strategies implemented for the compliant nursing patients in history (specifically determined according to historical logs, such as compliance nursing plans, compliance medication, etc.) and their historical status data (status data collected and recorded by a smart wristband, such as temperature values ​​monitored by a temperature sensor in the smart wristband, pressure values ​​monitored by a pressure sensor (mainly to prevent pressure injuries), posture and body position data monitored by an acceleration sensor, etc.) and patient clinical examination data (clinical CT image data of patients examined during intervention, blood routine examination data, etc.), and the historical status data is collected by the smart wristband worn by the compliant nursing patients and recorded and stored in the background database.

[0046] advantage: ‌Efficient retrieval‌: Significantly reduce the time and computing resources required to process large amounts of data‌.

[0047] ‌Real-time updates‌: As data changes, the corresponding data blocks in the vector database can be easily updated to ensure the latest information‌.

[0048] ‌Precise response‌: By focusing on semantically related data blocks, the LLM model can provide more precise responses that fit user needs‌.

[0049] like Figure 3 As shown, after the data set is collected, the historical nursing archive data of the retrieved several compliant nursing patients are preprocessed to generate a data set consisting of the historical nursing archive data of the several compliant nursing patients. Preprocessing, for example, divides the data into groups according to the department to which the patient belongs, the symptom stage or the disease type, etc.; data cleaning can also be performed to remove data that does not meet the requirements. After preprocessing, a data set is obtained.

[0050] Feature engineering is performed on the data set to extract corresponding data features, including: extracting corresponding status data features from the historical status data, extracting corresponding clinical symptom data features from the patient clinical examination data, and extracting corresponding strategy keywords from the compliance care strategy and performing feature association binding.

[0051] It is necessary to use data feature extraction methods to extract corresponding data features from each group of data, including status data features, clinical symptom data features and strategy keywords, and bind them with the corresponding data features, so that the subsequent model can recognize the corresponding data features (mainly status data features), and then output the corresponding strategy keywords according to the binding relationship and use them to search the database for various strategies containing strategy keywords, so as to form the patient's compliance nursing strategy, record it in the electronic medical record and save it.

[0052] The corresponding data feature extraction method can refer to the following steps: 1. Extract state data features: ‌Collect historical data‌: First, collect the patient's historical status data from the hospital information system, including but not limited to medical records, diagnosis results, patient posture, body position, temperature, heart rate and other data‌.

[0053] ‌Data preprocessing‌: Clean and organize the collected data, remove invalid or erroneous data, and ensure the accuracy and completeness of the data.

[0054] Feature extraction: Using data analysis technology, features related to the patient’s condition are extracted from historical data, such as disease type, disease course, treatment effect, etc.

[0055] 2. Extract clinical symptom data features: ‌Obtain clinical examination data‌: Obtain relevant data from the patient's clinical examination report, including laboratory test results, imaging examinations, etc.‌

[0056] ‌Data standardization‌: Standardize clinical examination data to ensure that data from different sources and formats can be analyzed and compared uniformly.

[0057] Feature analysis: Analyze outliers and trends in clinical examination data using statistical and machine learning algorithms, and extract features related to clinical symptoms, such as abnormal indicators and lesion sites.

[0058] The above features are mainly the characteristic values ​​of the data corresponding to intervention compliance care, such as the maximum temperature value during high fever and the maximum heart rate value during tension (if a lesion occurs, the corresponding lesion morphology image features can be obtained from the lesion CT image, and CNN can be used for image feature extraction. Subsequently, the model can be allowed to match strategies based on the lesion image features), etc.

[0059] 3. Extract the keywords of compliance care strategy: ‌Organize nursing strategy documentation‌: Collect and organize documents containing compliance nursing strategies, such as nursing plans, doctor's order records, etc. ‌ Text Analysis: Use natural language processing technology to perform text analysis on nursing strategy documents to identify and extract keywords related to compliance care, such as medication reminders, dietary recommendations, regular check-ups, etc.

[0060] ‌Keyword screening‌: The extracted keywords are screened and sorted according to the importance and relevance of the nursing strategies so that personalized nursing plans can be formulated later.

[0061] Through feature engineering, a feature set is constructed.

[0062] Preferably, after performing feature engineering on the data set and extracting corresponding data features, the method further includes: The state data feature in the data feature is marked with a feature, wherein the marking information includes: The disease type, symptom stage and / or relevant compliance medication of the compliance care patient corresponding to the data characteristics.

[0063] like Figure 3 As shown, the present invention performs feature training and learning based on the random deep forest model to construct a model.

[0064] The training process of the general random forest model can be described as follows: Using the random forest model for feature training and learning, the steps to build the corresponding model usually include the following key stages: 1. Data Preparation ‌Data Collection‌: Collect datasets from reliable sources, ensuring the quality and integrity of the data.

[0065] ‌Data cleaning‌: Process missing values ​​and outliers, and standardize or normalize the data to ensure the stability and accuracy of model training.

[0066] Feature selection: Based on business understanding and data analysis, select feature variables that have an impact on the target variable.

[0067] 2. Data Partitioning ‌Training set and validation set division‌: Randomly divide the dataset into training set and test set, usually with a ratio of 70% training set and 30% validation set, or adjust according to specific circumstances.

[0068] 3. Random Forest Model Construction ‌Initialization‌: Set the parameters of the random forest, such as the number of trees, maximum depth, minimum number of sample splits, etc.

[0069] ‌Train Model‌: Train the Random Forest model using the training set data. The model builds multiple decision trees, each of which is independently trained on a random subset of the training data.

[0070] ‌Feature Importance Assessment‌: The random forest model can automatically calculate the importance of each feature, helping to understand which features have a greater impact on the prediction results.

[0071] 4. Model evaluation and tuning ‌Performance evaluation‌: Evaluate the performance of the model on the validation set. Common evaluation indicators include accuracy, recall, F1 score, ROC curve, and AUC value. The administrator can evaluate the model performance.

[0072] Parameter Tuning: Based on the model evaluation results, adjust the parameters of the random forest, such as increasing or decreasing the number of trees, adjusting the depth of the trees, etc., to optimize the model performance.

[0073] ‌Cross-validation (optional)‌: Use cross-validation techniques to further verify the stability and generalization ability of the model.

[0074] 5. Model deployment and monitoring ‌Model deployment‌: Deploy the trained random forest model to a production environment for prediction or classification tasks on actual data.

[0075] ‌Performance Monitoring‌: Continuously monitor the performance of the model in actual applications to promptly detect and address problems caused by model degradation or changes in data distribution.

[0076] 6. Continuous learning and updating (optional) ‌Data collection and update‌: Regularly collect new data for continuous learning and updating of the model.

[0077] ‌Model iteration‌: Retrain or incrementally learn the model based on new data to maintain the accuracy and timeliness of the model.

[0078] Through the above steps, a stable and accurate compliance nursing strategy recommendation model can be built to solve machine learning problems such as classification and regression. The model file can be loaded and installed on the background for compliance nursing strategy recommendation.

[0079] Preferably, the step S2, monitoring and collecting the status data of the compliant nursing patient through the smart wristband worn by the compliant nursing patient, and reporting the data to the nurse station backend at regular intervals, includes: Establish data communication between the smart wristband worn by the compliant nursing patient and the nurse station backend, and the nurse station backend records the device number of the smart wristband worn by the compliant nursing patient and binds it with the identity / visit ID of the compliant nursing patient; The nurse station backend issues corresponding sampling instructions to the smart wristband according to the preset sampling frequency; Responding to the sampling instruction through the smart wristband and reporting the status data of the compliant nursing patient to the backend of the nurse station; wherein the status data includes the heart rate data, body temperature data, posture sensor data and / or electromyography data of the compliant nursing patient; The nurse station background receives and saves the status data of the compliant nursing patient into the electronic medical record nursing file in the HIS system.

[0080] After the patient wears the smart wristband device distributed by the hospital, the administrator, such as the accompanying nurse, can activate it and establish data communication between the wristband and the background. The background can send sampling instructions to the smart wristband worn by the patient according to the sampling frequency set for each patient, and the wristband responds and collects the patient's status data to the background. Various sensors in the wristband can monitor the patient's various status data and upload it to the background. After receiving it, the background can write and save the patient's status data into the medical record file of HIS according to the binding relationship between the device and the patient.

[0081] Preferably, the step S3, importing the status data into the compliance nursing strategy recommendation model, identifying data features in the status data through the compliance nursing strategy recommendation model, and matching and outputting compliance nursing strategies corresponding to the data features, includes: Regularly reading the status data of the compliance nursing patient and importing it into the compliance nursing strategy recommendation model; Identifying and extracting status data features in the status data of the compliance nursing patient through the compliance nursing strategy recommendation model, and outputting the strategy keywords associated with the status data features and annotation information annotated on the status data features; Generate corresponding search instructions according to the strategy keywords and the annotation information and send them to the backend database; The backend database responds to the search instruction, retrieves and outputs the policy data matching the policy keywords and the annotation information from the pre-stored compliance care policy set; The retrieved policy data is bound to the identity / visit ID of the compliant care patient to generate the compliant care policy for the compliant care patient.

[0082] When the model is used in the background to monitor and identify the patient's status data in real time and recommend the corresponding compliance nursing strategy, the model can read the written patient status data and input it into the model while writing the status data into the HIS electronic medical record file. The model identifies the status data features therein, and matches the identified status data features with the associated binding relationship learned by the model for the feature, so as to output the strategy keywords associated with the feature and the annotation information on the feature (optionally output). Therefore, the model can be used to output the nursing strategy keywords and corresponding annotation information that match the current patient status features, and the model can identify the disease type, symptom stage or compliance medication suitable for treating the feature that matches the current feature. The model output results are then saved in the electronic medical record file.

[0083] Subsequently, the backend will combine the policy keywords and various information in the annotation information (constructing SQL instructions) to form corresponding search instructions, and send them to the backend database, which will execute the search instructions, retrieve the policy data that matches the policy keywords, etc., and output them. The backend will automatically write the retrieved policy data into the patient's medical record, generate the current state of compliance nursing strategy for the current patient in the HIS system, and send it to the nurse's handheld PDA terminal responsible for the patient. Nurses can view the current state of compliance nursing strategy of the current patient through the PDA terminal to achieve dynamic nursing.

[0084] During the implementation of the above, the system can also construct corresponding search instructions only according to the strategy keywords, and retrieve and output various policy data related to or containing the strategy keywords (there may be multiple groups of strategies). Subsequently, the various policy data can be matched for relevance in combination with the annotation information on the feature. For example, the LLM large language model can be used to find the compliance care strategy that is most relevant to the annotated data, and the top three strategies can be taken as the patient's compliance care strategy according to the size of the correlation and output, or the strategy data that best matches the annotated information can be found as the compliance care strategy. When calculating the correlation between the annotated information and the policy data, for example, text similarity can be used, and the cosine theorem can be used to calculate text similarity to find the most similar and related strategies. The specific cosine theorem will not be described here.

[0085] Figure 4 The block diagram of a patient compliance nursing management device based on smart wristband monitoring according to an exemplary embodiment is shown. The device is used in a patient compliance nursing management method based on smart wristband monitoring. Figure 4 The device includes a smart wristband, a PDA terminal and a nurse station backend. A smart wristband is used to monitor and collect the status data of the compliant nursing patients and report it to the nurse station backend at regular intervals; The nurse station backend is used to import the status data into the compliance nursing strategy recommendation model, identify the data features in the status data through the compliance nursing strategy recommendation model, and match and output the compliance nursing strategy corresponding to the data features; and recommend the compliance nursing strategy to the PDA terminal of the corresponding nurse and remind the nurse to execute it; A PDA terminal, used for receiving and displaying the compliance care strategy of the compliance care patient; The smart wristband and the PDA terminal are respectively connected to the backend of the nurse station for communication.

[0086] The interaction of the above-mentioned devices may be understood in conjunction with the above-mentioned method steps, and will not be described in detail in this embodiment.

[0087] Figure 5 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 5 As shown, the electronic device 410 may include a first processor 2001 .

[0088] Optionally, the electronic device 410 may further include a memory 2002 and a transceiver 2003 .

[0089] The first processor 2001, the memory 2002 and the transceiver 2003 may be connected via a communication bus.

[0090] Combine the following Figure 5 The components of the electronic device 410 are described in detail: The first processor 2001 is the control center of the electronic device 410, and may be a processor or a general term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or may be application specific integrated circuits (ASICs), or may be one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (field programmable gate arrays, FPGAs).

[0091] Optionally, the first processor 2001 can execute various functions of the electronic device 410 by running or executing a software program stored in the memory 2002 and calling data stored in the memory 2002 .

[0092] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Figure 5 CPU0 and CPU1 are shown in FIG.

[0093] In a specific implementation, as an embodiment, the electronic device 410 may also include multiple processors, such as Figure 5 The first processor 2001 and the second processor 2004 are shown in FIG. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0094] The memory 2002 is used to store the software program for executing the solution of the present invention, and is controlled to be executed by the first processor 2001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0095] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001, or may exist independently and access the first processor 2001 through the interface circuit ( Figure 5 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0096] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0097] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 5 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0098] Optionally, the transceiver 2003 may be integrated with the first processor 2001, or may exist independently and communicate with the first processor 2001 through the interface circuit ( Figure 5 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0099] It should be noted that Figure 5 The structure of the electronic device 410 shown in the figure does not constitute a limitation on the router, and the actual knowledge structure recognition device may include more or fewer components than those shown in the figure, or combine certain components, or arrange the components differently.

[0100] In addition, the technical effects of the electronic device 410 can refer to the technical effects of the patient compliance care management method based on smart wristband monitoring described in the above method embodiment, which will not be repeated here.

[0101] It should be understood that the first processor 2001 in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0102] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may 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 may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0103] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0104] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0105] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0106] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0107] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0108] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0109] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0110] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0111] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0112] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0113] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A patient compliance nursing management method based on smart wristband monitoring, characterized in that: The method comprises: S1. Collect the historical nursing archive data of several compliance nursing patients, build the corresponding compliance nursing strategy recommendation model based on big data technology and deploy it in the background of the nurse station; S2. Monitoring and collecting the status data of the compliant nursing patient through the smart wristband worn by the compliant nursing patient, and reporting it to the backend of the nurse station at regular intervals; S3, importing the state data into the compliance nursing strategy recommendation model, identifying data features in the state data through the compliance nursing strategy recommendation model, and matching and outputting compliance nursing strategies corresponding to the data features; S4. Recommend the compliance nursing strategy to the corresponding nurse's PDA terminal and remind the nurse to execute it.

2. The patient compliance nursing management method based on intelligent wristband monitoring according to claim 1 is characterized in that: S1, collects historical nursing archive data of several compliant nursing patients, and builds a corresponding compliance nursing strategy recommendation model based on big data technology and deploys it in the background of the nurse station: construct keywords and archive search logic related to adherence care; Combining the keywords and the archive retrieval logic, constructing a large language model prompt word and inputting a preset LLM large language model; Traversing the backend database through the LLM large language model, retrieving the historical nursing archive data of several compliant nursing patients from the backend database based on the large language model prompt words, wherein the historical nursing archive data includes the compliance nursing strategies historically implemented for the compliant nursing patients and their historical status data and patient clinical examination data, and the historical status data is collected through the smart wristband worn by the compliant nursing patients and recorded and stored in the backend database; Preprocessing the retrieved historical nursing archive data of the plurality of compliant nursing patients to generate a data set consisting of the historical nursing archive data of the plurality of compliant nursing patients; Performing feature engineering on the data set to extract corresponding data features, including: extracting corresponding status data features from the historical status data, extracting corresponding clinical symptom data features from the patient clinical examination data, and extracting corresponding strategy keywords from the compliance nursing strategy and performing feature association binding; Constructing a feature set consisting of several of the data features, and dividing it into corresponding training sets and validation sets according to a preset ratio; Inputting the training set into a preset random forest model to perform feature training and learning to generate the compliance nursing strategy recommendation model; The recognition performance of the compliance nursing strategy recommendation model is verified using the verification set: If the verification is passed, the compliance nursing strategy recommendation model is deployed in the background of the nurse station and put into clinical compliance nursing management; Otherwise, repeat the above steps.

3. The patient compliance nursing management method based on intelligent wristband monitoring according to claim 2 is characterized in that: After performing feature engineering on the data set and extracting corresponding data features, the following steps are also included: The state data feature in the data feature is marked with a feature, wherein the marking information includes: The disease type, symptom stage and / or relevant compliance medication of the compliance care patient corresponding to the data characteristics.

4. The patient compliance nursing management method based on intelligent wristband monitoring according to claim 2 is characterized in that: S2, monitoring and collecting the status data of the compliant nursing patient through the smart wristband worn by the compliant nursing patient, and reporting it to the backend of the nurse station at regular intervals, includes: Establish data communication between the smart wristband worn by the compliant nursing patient and the nurse station backend, and the nurse station backend records the device number of the smart wristband worn by the compliant nursing patient and binds it with the identity / visit ID of the compliant nursing patient; The nurse station backend issues corresponding sampling instructions to the smart wristband according to the preset sampling frequency; Responding to the sampling instruction through the smart wristband and reporting the status data of the compliant nursing patient to the backend of the nurse station; wherein the status data includes the heart rate data, body temperature data, posture sensor data and / or electromyography data of the compliant nursing patient; The nurse station background receives and saves the status data of the compliant nursing patient into the electronic medical record nursing file in the HIS system.

5. The patient compliance nursing management method based on intelligent wristband monitoring according to claim 4 is characterized in that: The step S3, importing the state data into the compliance nursing strategy recommendation model, identifying data features in the state data through the compliance nursing strategy recommendation model, and matching and outputting compliance nursing strategies corresponding to the data features, includes: Regularly reading the status data of the compliance nursing patient and importing it into the compliance nursing strategy recommendation model; Identifying and extracting status data features in the status data of the compliance nursing patient through the compliance nursing strategy recommendation model, and outputting the strategy keywords associated with the status data features and annotation information annotated on the status data features; Generate corresponding search instructions according to the strategy keywords and the annotation information and send them to the backend database; The backend database responds to the search instruction, retrieves and outputs the policy data matching the policy keywords and the annotation information from the pre-stored compliance care policy set; The retrieved policy data is bound to the identity / visit ID of the compliant care patient to generate the compliant care policy for the compliant care patient.

6. A patient compliance nursing management device based on smart wristband monitoring, the patient compliance nursing management device based on smart wristband monitoring is used to implement the patient compliance nursing management method based on smart wristband monitoring as described in any one of claims 1 to 5, characterized in that: The device comprises: A smart wristband is used to monitor and collect the status data of the compliant nursing patients and report it to the nurse station backend at regular intervals; The nurse station backend is used to import the status data into the compliance nursing strategy recommendation model, identify the data features in the status data through the compliance nursing strategy recommendation model, and match and output the compliance nursing strategy corresponding to the data features; and recommend the compliance nursing strategy to the PDA terminal of the corresponding nurse and remind the nurse to execute it; A PDA terminal, used for receiving and displaying the compliance care strategy of the compliance care patient; The smart wristband and the PDA terminal are respectively connected to the backend of the nurse station for communication.

7. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 5.

Images