Inpatient falling risk early warning method, device and processing system

Abstract

The invention provides a hospitalized patient falling risk early warning method and device and a processing system, which are used for designing a set of specific application scheme for a falling risk early warning target of a hospital patient, and further providing a series of optimization settings from the aspect of details, so that the defects in the prior art are made up, and the early warning effect of the hospitalized patient falling risk is improved. The falling risk reminding can be given in time for the hospitalized patient using the medicine with the falling risk, so that the falling event of the hospitalized patient caused by medicine use is avoided, and the safety of the hospitalized patient is guaranteed. The method comprises the following steps: acquiring medicine data of a current inpatient; inputting the medicine data into a pre-configured tumble risk analysis model, and enabling the tumble risk analysis model to carry out corresponding tumble risk analysis processing; extracting a tumble risk analysis result output by the tumble risk analysis model; and on the basis of the tumble risk analysis result, according to a preset tumble risk early warning strategy, outputting a corresponding early warning to remind and pay attention to prevention of tumble.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a fall risk warning method, device and processing system for hospitalized patients. Background Art

[0002] For patients, about 40% of adverse events are falls. Falls not only harm the physical and mental health of patients, but also bring heavy burdens to their families and society.

[0003] The inventors of the present application have discovered that, with regard to fall risk warning, existing solutions usually focus on certain diseases that may cause patients to fall, such as stroke, osteoporosis, etc., or focus on age or postoperative conditions that may cause patients to fall, but ignore the fact that certain drugs themselves may also cause patients to fall, such as antihypertensive drugs, hypoglycemic drugs, antidepressants, diuretics, analgesics, etc. After taking the drugs, blood pressure, consciousness, vision, balance, etc. will be affected to a certain extent, thus posing a risk of falling.

[0004] For hospitalized patients, considering that they are in the hospital, medical staff can provide rescue to the patients at the first time, so it is easy to ignore the risk of falls caused by certain drugs. In addition, relying on manual notification methods, it is difficult to inform in time or fail to inform in time due to incomplete memory of drug types.

[0005] In other words, when it comes to fall risk warnings for hospitalized patients, there are problems with them being easily overlooked and the notification efficiency being low when relying on manual notification methods. Summary of the invention

[0006] The present application provides a fall risk warning method, device and processing system for hospitalized patients, which is used to design a set of specific application solutions for the fall risk warning target of hospital patients, and also continues to provide a series of optimization settings in terms of details, which makes up for the shortcomings of the existing technology. For hospitalized patients who use drugs with fall risks, fall risk reminders can be given in time, avoiding the occurrence of fall incidents caused by medication in hospitalized patients, thereby ensuring the safety of hospitalized patients.

[0007] In a first aspect, the present application provides a method for early warning of fall risk in hospitalized patients, the method comprising:

[0008] Obtaining drug data of the current inpatient, wherein the drug data specifically refers to data describing at least one of the drugs used by the current inpatient and the drugs involved in the doctor's order;

[0009] Inputting the drug data into a pre-configured fall risk analysis model so that the fall risk analysis model carries out corresponding fall risk analysis processing, wherein the fall risk analysis model is used to analyze the fall risk corresponding to the drug data input into the model, and the fall risk analysis model is a model trained by the labeled sample drug data;

[0010] Extracting the fall risk analysis results output by the fall risk analysis model;

[0011] Based on the fall risk analysis results, the corresponding warning is output according to the preset fall risk warning strategy to remind people to pay attention to fall prevention.

[0012] In a second aspect, the present application provides a fall risk warning device for hospitalized patients, the device comprising:

[0013] An acquisition unit, used to acquire drug data of a current inpatient, wherein the drug data specifically refers to data describing at least one of a drug used by the current inpatient and a drug involved in a doctor's order;

[0014] An analysis unit, used to input the drug data into a pre-configured fall risk analysis model, so that the fall risk analysis model carries out corresponding fall risk analysis processing, wherein the fall risk analysis model is used to analyze the fall risk corresponding to the drug data input into the model, and the fall risk analysis model is a model trained by labeled sample drug data;

[0015] An extraction unit, used for extracting the fall risk analysis result output by the fall risk analysis model;

[0016] The early warning unit is used to output corresponding early warnings based on the fall risk analysis results and in accordance with the preset fall risk early warning strategy to remind people to pay attention to fall prevention.

[0017] In a third aspect, the present application provides a processing system for executing the method provided in the first aspect of the present application.

[0018] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a plurality of instructions suitable for loading by a processor to execute the method provided in the first aspect of the present application.

[0019] From the above content, it can be concluded that the present application has the following beneficial effects:

[0020] Aiming at the goal of fall risk warning for hospital patients, this application, after obtaining the drug data of the current inpatient, inputs the drug data into a pre-configured fall risk analysis model, so that the fall risk analysis model carries out the corresponding fall risk analysis processing, and then extracts the fall risk analysis results output by the fall risk analysis model, and then based on the fall risk analysis results, outputs the corresponding warning in accordance with the preset fall risk warning strategy to remind people to pay attention to fall prevention. In this way, this application designs a set of specific application solutions, and continues to provide a series of optimization settings in details, which makes up for the shortcomings of the existing technology. For inpatients at risk of falling, timely reminders to pay attention to falls can be given, thereby avoiding the occurrence of fall incidents caused by medication in inpatients, and ensuring the experience and safety of inpatients. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 A flowchart of a fall risk warning method for hospitalized patients in this application;

[0023] Figure 2 A schematic diagram of a structure of a fall risk warning device for hospitalized patients in this application;

[0024] Figure 3 A structural diagram of the application processing system. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0026] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. The naming or numbering of steps in this application does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The process steps that have been named or numbered can change the execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved.

[0027] The division of modules in this application is a logical division. There may be other division methods when it is implemented in actual applications. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between modules can be electrical or other similar forms, which are not limited in this application. In addition, the modules or submodules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed in multiple circuit modules, and some or all of the modules may be selected according to actual needs to achieve the purpose of the present application.

[0028] Before introducing the fall risk warning method for hospitalized patients provided by this application, the background content involved in this application is first introduced.

[0029] The inpatient fall risk warning method, device and computer-readable storage medium provided in the present application can be applied to a processing system to design a set of specific application solutions for the fall risk warning target of hospital patients, and further provide a series of optimization settings in terms of details, which make up for the shortcomings of the existing technology. For inpatients who use drugs with fall risks, fall risk reminders can be given in time, avoiding the occurrence of fall incidents caused by medication in hospital patients and ensuring the safety of hospital patients.

[0030] The inpatient fall risk warning method mentioned in this application can be executed by an inpatient fall risk warning device, or a processing system (or warning system) that integrates the inpatient fall risk warning device. Among them, the inpatient fall risk warning device can be implemented in hardware or software. In the specific application of the processing system, the types of equipment involved and the equipment deployment form are relatively flexible. The inpatient fall risk warning method / inpatient fall risk warning method corresponding application service provided by this application can be used to achieve the inpatient fall risk warning target.

[0031] Specifically, the processing system can be different types of devices such as a server, a physical host or a user equipment (UE). The UE can specifically be a terminal device such as a smart phone, a tablet computer, a laptop computer, a desktop computer or a personal digital assistant (PDA). In addition, the processing system can also be set up in the form of a device cluster, involving multiple or multiple devices, which are all possible in actual situations.

[0032] Next, we will introduce the fall risk warning method for hospitalized patients provided by this application.

[0033] First, see Figure 1 , Figure 1 A schematic diagram of a process of the inpatient fall risk warning method of the present application is shown. The inpatient fall risk warning method provided by the present application may specifically include the following steps S101 to S104:

[0034] Step S101, obtaining drug data of the current inpatient, wherein the drug data specifically refers to data describing at least one of the drugs used by the current inpatient and the drugs involved in the doctor's order;

[0035] It can be understood that what the present application aims to predict and issue a warning for is the risk of falls caused by hospitalized patients after taking medication. For this purpose, it is possible to determine the medications already used by the current hospitalized patient (the current treatment object) and / or the medications involved in the doctor's orders (i.e., the medications to be taken), and obtain medication data.

[0036] In specific operations, the drug data is usually ready-made data that can be obtained online. Of course, the possibility of real-time input / scanning is not ruled out, and such special circumstances may exist in actual situations.

[0037] As an exemplary embodiment here, obtaining the drug data of the current inpatient may specifically include:

[0038] Obtain medication data for current inpatients from business systems including nursing management systems, electronic medical record systems, and nursing documentation systems.

[0039] It can be understood that a specific implementation plan is provided here for how to pull the drug data required for this application plan online.

[0040] At the same time, it should be understood that in addition to the nursing management system, electronic medical record system and nursing document system listed in the embodiments here, in actual situations, other types of business systems (data sources) may also be involved. The requirements can be met by storing the drug data of hospitalized patients in the business system, so other types of business systems can continue to be supplemented / replaced.

[0041] Generally speaking, the pulling of drug data involves pre-configured data transmission channels / links to meet the application requirements of the business system automatically pushing drug data, actively pulling drug data from the business system, or triggering the business system to push drug data.

[0042] In addition, drug data may include not only the drugs taken or to be taken, but also the patient's physical fitness (such as age, weight, gender, etc.), living habits (including walking posture habits, sitting habits, standing habits, eating habits, etc.) and diseases, etc., so as to further help improve the analysis accuracy of the risk of falls caused by the drugs taken.

[0043] It can be understood that in the setting here, this application believes that even the same drugs that cause fall risk will have different specific fall risks under different conditions, rather than just comparing the drugs to directly obtain the corresponding fall risk. This can more accurately and comprehensively evaluate and analyze the fall risk and obtain a more precise fall risk analysis effect.

[0044] Step S102, inputting the drug data into a pre-configured fall risk analysis model, so that the fall risk analysis model carries out corresponding fall risk analysis processing, wherein the fall risk analysis model is used to analyze the fall risk corresponding to the drug data input into the model, and the fall risk analysis model is a model trained by the labeled sample drug data;

[0045] It can be understood that this application introduces artificial intelligence (AI) technology to complete the corresponding risk analysis work for the fall risk of hospitalized patients, and is specifically implemented through a machine learning model.

[0046] During the model configuration work before the fall risk analysis model is put into actual use, the real patient data of the hospital after removing personal privacy content can be used to convert into training samples for training the model. Alternatively, the real patient data of the hospital after removing personal privacy content can be processed again to form training samples with a richer sample size. Alternatively, the training samples can be manually / automatically generated. These training samples can all be used in actual situations, so that the required sample drug data can be obtained.

[0047] Before using sample drug data to train the fall risk analysis model, labeling processing may also be involved. By labeling the sample drug data with the corresponding fall risk, it can be used as the true value in the subsequent model training process and combined with the loss function to guide the model training.

[0048] Among them, except for the annotation content, the sample drug data is the model input data after the model is put into actual use, that is, the drug data involved in the previous step S101. In addition, for the sample drug data, its annotation content corresponds to the output result during the actual use of the model, which can be set in a binary way of whether there is a risk of falling or not, such as "0" can be used to indicate no risk of falling, and "1" can be used to indicate a risk of falling, or it can be set with a specific quantitative probability of falling risk.

[0049] In specific operations, annotation processing can be done manually or by corresponding automated annotation tools. For automated annotation tools, the corresponding automated annotation logic / strategy needs to be pre-configured for use in automated annotation processing.

[0050] As an example, on the one hand, all drug data information of clinical patients who have fallen can be collected from different data sources in the hospital to form drug data 1. On the other hand, we can work with the pharmacy department to sort out 269 types of high-risk drugs for falls to form a knowledge base and obtain drug data 2. Then, we can compare the two to obtain drug data 3 corresponding to the patients who have fallen after taking high-risk drugs for falls. This drug data 3 can be used as a training sample.

[0051] In the process of model training, taking neural network as an example, the following processing contents are usually included:

[0052] In each round of model training, a group of training samples are input into the model so that the model can carry out corresponding fall risk analysis processing to realize forward propagation. Then, based on the fall risk analysis results output by the model and the pre-configured annotation results of the training samples, the loss function is calculated. The model parameters are optimized according to the calculation results of the loss function to realize reverse propagation. In this way, when the preset model training requirements such as training duration, number of trainings or prediction accuracy are met, the model training can be completed. At this time, the model is a fall risk analysis model that can be put into practical use.

[0053] The model architecture used by the fall risk analysis model can be an existing model architecture, or it can be further optimized and improved on the basis of the existing model architecture, or it can be a self-developed novel model architecture, which is possible in actual situations. In addition, the model training architecture and loss function used in the model training process also have this feature.

[0054] As an exemplary embodiment, the fall risk analysis model may specifically adopt a random forest model.

[0055] The Random Forest (BF) model can be understood as an integrated learning method that aims to solve the problem of decision trees being prone to overfitting. It improves the overall prediction performance by combining the prediction results of multiple decision trees. Specifically, it is based on the Bagging technology and randomly selects training data subsets and feature subsets to construct multiple decision trees. Finally, they are integrated for prediction. This helps reduce the variance of a single decision tree and improves the generalization ability of the overall model.

[0056] The random forest model has the following advantages, which can well meet the model usage requirements of this application scheme:

[0057] 1. Easy to understand and explain

[0058] The decision-making process of decision trees is intuitive and easy to explain, which can help people understand patterns and regularities in data.

[0059] 2. Ability to handle both numerical and categorical data

[0060] Decision trees can handle mixed data without the need for feature preprocessing.

[0061] 3. Robustness

[0062] It is insensitive to outliers in the data and can handle missing values.

[0063] In addition, it can be understood that, corresponding to the application of the model, the present application may also involve early model configuration / training processing.

[0064] In this regard, as an exemplary embodiment, the inpatient fall risk warning method of the present application may also include:

[0065] Obtain medication data for a sample of hospitalized patients with falls;

[0066] Label the corresponding fall risks for sample drug data;

[0067] Use labeled sample drug data to train a fall risk analysis model.

[0068] It can be understood that the contents involved in the model configuration / training processing in the embodiment here have been explained before and will not be repeated here in detail.

[0069] In addition, to facilitate data sorting and configuration, as an exemplary embodiment, the drug types involved in the training samples, i.e., the sample drug data, can also be classified, specifically including three types: oral drug types, intravenous drug types, and intramuscular drug types.

[0070] Step S103, extracting the fall risk analysis result output by the fall risk analysis model;

[0071] In this way, after the patient data of the current inpatient is input into the fall risk analysis model to carry out the corresponding fall risk analysis processing, the model can output the corresponding fall risk analysis results, and correspondingly, the fall risk analysis results output by the fall risk analysis model can be extracted.

[0072] At this time, the fall risk analysis results can be stored and forwarded, and a prompt for completing the fall risk analysis process can be output, and further data applications can be carried out. These can obviously be configured with corresponding data application strategies according to actual needs. The focus of this application plan is the subsequent early warning processing, which promptly reminds the current inpatients to prevent falls, so as to ensure the personal safety of the current inpatients during hospitalization and for a period of time after discharge.

[0073] Step S104: Based on the fall risk analysis result and in accordance with the preset fall risk warning strategy, a corresponding warning is output to remind the user to pay attention to fall prevention.

[0074] It can be understood that the present application involves the application of an early warning mechanism, so that when the fall risk analysis results output by the fall risk analysis model show that there is / has a fall risk, or there is / has a high fall risk, an early warning is issued to the current inpatient to directly remind the current inpatient to pay attention to fall prevention, or an early warning is issued to medical staff to prompt them to remind the current inpatient to pay attention to fall prevention, thereby playing an indirect reminder role. At the same time, medical staff can also be reminded to pay attention to whether the current patient has fallen, so as to provide rescue as soon as possible in case of a fall.

[0075] Furthermore, in terms of details, regarding how to achieve better reminder effects through direct / indirect reminder methods, this application also provides a series of detailed setting solutions from the perspective of practical applications.

[0076] Specifically, as an exemplary implementation, the fall risk warning strategy involved in this application may include at least one of the following strategy contents:

[0077] 1. In the online business system, a warning sign for preventing falls is output to medical staff to remind them to prevent falls;

[0078] Among them, the online business system here is any system that medical staff can access or view in their specific work, such as the nursing management system, electronic medical record system and nursing document system mentioned above.

[0079] As an example, if the system recognizes that a patient's medical prescription (doctor's order) involves drugs that may cause a fall risk, the system will automatically pop up a warning sign with the word "fall". Specifically, when the nurse is processing the doctor's order and checking the drugs, the row containing the drugs that may cause a fall risk can be displayed in red, and the word "fall" can be displayed next to the drug name. When the nurse double-clicks the drug name on the interface, the system automatically pops up the precautions after taking the medication (or other fall prevention measures related to the drug). The system recognizes that the nurse has checked it, and the content of the row containing the drug automatically changes from red to green, indicating that the nurse has checked the relevant measures. After the nurse knows the measures, she can accurately inform the patient to reduce the patient's risk of falls caused by the drug.

[0080] 2. Outputting the fall prevention attention event to the drug label processing system to prompt the addition of a fall prevention attention label content to the drug label of the current inpatient;

[0081] It is understandable that the medicines distributed to patients usually have corresponding labels affixed to identify information such as the medicine name and time of administration. For the medicine label, label content that reminds people to prevent falls, such as the word "fall", can be added / displayed. This means that the medicine label processing system that prints the medicine label needs to set the content of the medicine label and set the label content that reminds people to prevent falls. In this way, medical staff or patients can clearly see the label content to effectively prevent falls.

[0082] 3. Outputting the fall prevention precaution event to the medication label processing system to prompt the current inpatients to add the fall prevention precaution content to the scanned content of the medication label;

[0083] In addition, in some cases, the labels attached to the drugs may also have settings for scanning to obtain corresponding information (such as medical instructions, etc.), which involves the application of scanning labels such as barcodes and QR codes. For the display content obtained after scanning, that is, the scanned content, you can add / display label content that reminds you to prevent falls, such as the word "fall". This means that the drug label processing system needs to set the display content that can be scanned, and set the label content that reminds you to prevent falls. In this way, medical staff or patients who trigger the scanning operation can clearly see the label content and pay attention to preventing falls.

[0084] The drug label processing system here and the drug label processing system mentioned above may be the same system or different systems, which is possible in actual situations.

[0085] 4. Output precautions for preventing falls to the user terminals of current inpatients or medical staff to remind them to prevent falls.

[0086] In addition, current inpatients or medical staff are usually equipped with user terminals. In this way, precautions for preventing falls can be directly output to the user terminals, and the user terminals can perform specific reminder operations through display interfaces or voice, thereby directly reminding patients to prevent falls, or reminding medical staff to pay attention to patients to prevent falls.

[0087] For patients, the user terminal is usually a mobile phone, and for medical staff, the user terminal is usually a PDA. Of course, the specific user terminal may also change in actual situations.

[0088] In addition, the present application further designs a real-time / dynamic reminder mechanism in terms of specific applications. Specifically, as an exemplary embodiment, the fall risk warning strategy involved in the present application may also include the following strategy content:

[0089] Based on the monitoring bracelets carried by the current inpatients, determine the specific location of the current inpatients in the hospital;

[0090] If the distance between the specific location and the high-risk location for falling is within a preset range, a reminder is output through the monitoring bracelet, or a reminder is output through a pre-configured output device at the specific location or the high-risk location for falling, so as to remind people to pay attention to prevent falls.

[0091] It is easy to see that the embodiment here focuses on some positions in the hospital scene where patients are prone to falls, typically fixed positions such as corners where the environment changes. Alternatively, there may be positions in the hospital that may cause patients to fall temporarily or for a long time due to some special circumstances. Therefore, in some specific scenarios in actual applications, there is a need for fall prevention reminders in this regard. In addition, some patients also have personal fall prevention reminders in this regard.

[0092] In this case, the monitoring bracelet (which can also be understood as an electronic wristband) configured / carried by the patient can be equipped with an indoor positioning module, so that the specific location of the patient carrying / wearing the monitoring bracelet in the hospital can be located for subsequent distance analysis.

[0093] Among them, the indoor positioning module configured by the monitoring bracelet may involve indoor positioning technologies such as RFID, WI-FI, ultrasonic indoor positioning, and Bluetooth indoor positioning. Considering that these positioning technologies can usually adopt existing technologies, they will not be described in detail here. It is worth noting that for some technologies, corresponding modules need to be configured in the hospital venue to work together with the indoor positioning module configured by the monitoring bracelet to achieve indoor positioning goals.

[0094] It can be understood that when the specific location of the patient is at or close to the high-risk fall location predetermined by the system (corresponding to the judgment strategy / rule within the preset range), it means that timely reminders can be given to remind the patient himself to prevent falls, or to remind the surrounding medical staff to pay attention to the patient's falls.

[0095] In this way, under this real-time / dynamic reminder mechanism, it is obviously possible to achieve better reminder effects that are more in line with real-time situations in terms of details in actual situations, thereby further ensuring patient safety.

[0096] In addition, it is understandable that in addition to issuing reminders for the patient's current high-risk fall location, it is also possible to combine the predicted processing of the patient's walking path to achieve a smoother and more delicate reminder effect.

[0097] Specifically, for hospitalized patients, if they walk during their hospitalization, they will go to the toilet, go to the window, go to the nurse's station, and other routine situations. In this regard, it is easy to combine the current walking path of the hospitalized patients to achieve the purpose of predicting the patient's walking path, so that the high-risk positions for falls in the predicted results of the patient's walking path can be learned, so that a more friendly reminder can be given in advance. At the same time, it can also guide the patient's walking path. While reminding, the specific positions ahead, including high-risk positions for falls, can be informed. If the patient's actual walking path is not to the location the patient really wants to go, it is obvious that corrections / adjustments can be made in time, or a clearer grasp of the walking path ahead can be made. In this way, under the setting that combines fall reminders and position guidance, it can further ensure that the patient will not go the wrong way and increase the risk of falling, while also providing a good guidance experience.

[0098] In addition, it can be understood that in addition to bracelets designed to be worn on the wrist, the indoor positioning module set up in the scheme involved in the embodiment here can also be implemented through other types of user terminals. In addition to typical mobile phones, watches, etc., it can also be a device designed to be worn on the waist, arm, neckline, ear (corresponding to ear clip), eye (corresponding to glasses), etc.

[0099] Even more, based on the image recognition technology of the cameras deployed in the hospital, the positioning goal of the patient in the hospital can be achieved. For example, face recognition can be introduced, or attachments with shapes or colors that have significant image features in image recognition can be configured on the patient, or clothes with shapes or colors that have significant image features in image recognition can be directly assigned to the patient. This also has good implementation conditions and is relatively easy to achieve in some specific hospitals.

[0100] Thus, in addition to monitoring the wristband, other methods may also be used to implement the preferred real-time / dynamic reminder mechanism of the embodiment herein.

[0101] Finally, for the above solution contents (including the solution contents of each exemplary embodiment), in general, for the fall risk warning goal of hospital patients, after obtaining the drug data of the current inpatient, this application inputs the drug data into a pre-configured fall risk analysis model, so that the fall risk analysis model carries out the corresponding fall risk analysis processing, and then extracts the fall risk analysis results output by the fall risk analysis model, and then based on the fall risk analysis results, according to the preset fall risk warning strategy, outputs the corresponding warning to remind people to pay attention to prevent falls. In this way, this application designs a set of specific application solutions, and continues to provide a series of optimization settings in details, which makes up for the shortcomings of the existing technology. For inpatients who use drugs with fall risks, fall risk reminders can be given in time to avoid the occurrence of fall incidents caused by medication in hospitalized patients, thereby ensuring the safety of hospitalized patients.

[0102] The above is an introduction to the inpatient fall risk warning method provided by this application. In order to better implement the inpatient fall risk warning method provided by this application, this application also provides an inpatient fall risk warning device from the perspective of functional modules.

[0103] See also Figure 2 , Figure 2 This is a schematic diagram of a structure of a fall risk warning device for hospitalized patients in this application. In this application, the fall risk warning device 200 for hospitalized patients may specifically include the following structure:

[0104] The acquisition unit 201 is used to acquire the drug data of the current inpatient, wherein the drug data specifically refers to data describing at least one of the drugs used by the current inpatient and the drugs involved in the doctor's order;

[0105] An analysis unit 202 is used to input the drug data into a pre-configured fall risk analysis model so that the fall risk analysis model carries out corresponding fall risk analysis processing, wherein the fall risk analysis model is used to analyze the fall risk corresponding to the drug data input into the model, and the fall risk analysis model is a model trained by the labeled sample drug data;

[0106] An extraction unit 203, used to extract the fall risk analysis result output by the fall risk analysis model;

[0107] The warning unit 204 is used to output a corresponding warning based on the fall risk analysis result and in accordance with a preset fall risk warning strategy to remind people to pay attention to fall prevention.

[0108] In an exemplary embodiment, the acquisition unit 201 is specifically configured to:

[0109] Obtain medication data for current inpatients from business systems including nursing management systems, electronic medical record systems, and nursing documentation systems.

[0110] In yet another exemplary embodiment, the sample medication data relates to medication types including oral medication types, intravenous medication types, and intramuscular medication types.

[0111] In yet another exemplary embodiment, the fall risk analysis model specifically adopts a random forest model.

[0112] In yet another exemplary embodiment, the apparatus further includes a training unit 205, configured to:

[0113] Obtain medication data for a sample of hospitalized patients with falls;

[0114] Label the corresponding fall risks for sample drug data;

[0115] Use labeled sample drug data to train a fall risk analysis model.

[0116] In another exemplary embodiment, the fall risk warning strategy includes at least one of the following strategy contents:

[0117] On the online business system, a warning sign for preventing falls is output to medical staff to remind them to prevent falls;

[0118] Outputting a fall prevention attention event to a medication label processing system to prompt the addition of a fall prevention attention label content to the medication label of a current inpatient;

[0119] Outputting a fall prevention precaution event to a medication label processing system to prompt the addition of fall prevention precaution content to the scanned content of medication labels of current inpatients;

[0120] Output precautions for preventing falls to the user terminal of the current inpatient or medical staff to prompt them to pay attention to preventing falls.

[0121] In another exemplary embodiment, the fall risk warning strategy includes the following strategy contents:

[0122] Based on the monitoring bracelets carried by the current inpatients, determine the specific location of the current inpatients in the hospital;

[0123] If the distance between the specific location and the high-risk location for falling is within a preset range, a reminder is output through the monitoring bracelet, or a reminder is output through a pre-configured output device at the specific location or the high-risk location for falling, so as to remind people to pay attention to prevent falls.

[0124] The present application also provides a processing system from the perspective of hardware structure. For the convenience of explanation, it is regarded as a device (including the case of a device cluster). Figure 3 , Figure 3 301, a memory 302, and an input / output device 303. The processor 301 is used to execute the computer program stored in the memory 302 to implement the following Figure 1 The steps of the inpatient fall risk warning method in the corresponding embodiment; or, the processor 301 is used to execute the computer program stored in the memory 302 to implement the following Figure 2 Corresponding to the functions of each unit in the embodiment, the memory 302 is used to store the processor 301 executing the above Figure 1 The computer program required by the inpatient fall risk warning method in the corresponding embodiment.

[0125] Exemplarily, the computer program may be divided into one or more modules / units, one or more modules / units are stored in the memory 302, and executed by the processor 301 to complete the present application. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the computer device.

[0126] The processing system may include, but is not limited to, a processor 301, a memory 302, and an input / output device 303. Those skilled in the art will appreciate that the illustration is merely an example of a processing system and does not constitute a limitation on the processing system, and may include more or fewer components than shown in the illustration, or a combination of certain components, or different components. For example, the processing system may also include a network access device, a bus, etc., and the processor 301, the memory 302, the input / output device 303, etc. are connected via a bus.

[0127] The processor 301 may be a central processing unit (CPU), or 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 any conventional processor, etc. The processor is the control center of the processing system, and uses various interfaces and lines to connect various parts of the entire device.

[0128] The memory 302 can be used to store computer programs and / or modules. The processor 301 implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory 302 and calling the data stored in the memory 302. The memory 302 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the processing system, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0129] When the processor 301 is used to execute the computer program stored in the memory 302, the following functions can be implemented:

[0130] Obtaining drug data of the current inpatient, wherein the drug data specifically refers to data describing at least one of the drugs used by the current inpatient and the drugs involved in the doctor's order;

[0131] Inputting the drug data into a pre-configured fall risk analysis model so that the fall risk analysis model carries out corresponding fall risk analysis processing, wherein the fall risk analysis model is used to analyze the fall risk corresponding to the drug data input into the model, and the fall risk analysis model is a model trained by the labeled sample drug data;

[0132] Extracting the fall risk analysis results output by the fall risk analysis model;

[0133] Based on the fall risk analysis results, the corresponding warning is output according to the preset fall risk warning strategy to remind people to pay attention to fall prevention.

[0134] A person skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described inpatient fall risk warning device, processing system and its corresponding units can refer to the following. Figure 1 The description of the method for early warning of the risk of falling of hospitalized patients in the corresponding embodiment will not be repeated here.

[0135] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0136] To this end, the present application provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the present application as follows: Figure 1 The steps of the inpatient fall risk warning method in the corresponding embodiment, the specific operation can be referred to as follows Figure 1 The description of the fall risk warning method for hospitalized patients in the corresponding embodiment will not be repeated here.

[0137] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0138] Due to the instructions stored in the computer-readable storage medium, the present application can be executed. Figure 1 The steps of the method for early warning of the risk of falling of hospitalized patients in the corresponding embodiment, therefore, the present application can be implemented as follows Figure 1 The beneficial effects that can be achieved by the method for early warning of the risk of falling of hospitalized patients in the corresponding embodiment are detailed in the previous description and will not be repeated here.

[0139] The above is a detailed introduction to the hospitalized patient fall risk warning method, device, processing system and computer-readable storage medium provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for early warning of fall risk of hospitalized patients, characterized in that: The method comprises: Obtaining drug data of the current inpatient, wherein the drug data specifically describes at least one of the drugs used by the current inpatient and the drugs involved in the doctor's order; Inputting the drug data into a pre-configured fall risk analysis model so that the fall risk analysis model carries out corresponding fall risk analysis processing, wherein the fall risk analysis model is used to analyze the fall risk corresponding to the drug data input into the model, and the fall risk analysis model is a model trained by labeled sample drug data; Extracting the fall risk analysis result output by the fall risk analysis model; Based on the fall risk analysis results, a corresponding warning is output according to a preset fall risk warning strategy to remind people to pay attention to fall prevention.

2. The method according to claim 1, characterized in that The obtaining of drug data of the current inpatients includes: The drug data of the current inpatient is obtained from business systems including a nursing management system, an electronic medical record system, and a nursing document system.

3. The method according to claim 1, characterized in that The drug types involved in the sample drug data include oral drug types, intravenous drug types and intramuscular drug types.

4. The method according to claim 1, characterized in that: The fall risk analysis model specifically adopts a random forest model.

5. The method according to claim 1, characterized in that The method further comprises: obtaining medication data for the sample inpatients who have fallen; Annotating the sample drug data with corresponding fall risks; The fall risk analysis model is trained with the labeled sample drug data.

6. The method according to claim 1, characterized in that The fall risk warning strategy includes at least one of the following strategy contents: On the online business system, a warning sign for preventing falls is output to medical staff to remind them to prevent falls; Outputting a fall prevention attention event to a medication label processing system to prompt the addition of a fall prevention attention label content to the medication label of the current inpatient; Outputting a fall prevention precaution event to the medication label processing system to prompt the current inpatient to add a fall prevention precaution content to the scanned content of the medication label; Outputting precautions for preventing falls to the user terminal of the current inpatient or the medical staff to prompt them to pay attention to preventing falls.

7. The method according to claim 1, characterized in that The fall risk warning strategy includes the following strategy contents: Determine the specific location of the current inpatient in the hospital based on the monitoring bracelet carried by the current inpatient; If the distance between the specific location and the high-risk location for falling is within a preset range, a reminder is output through the monitoring bracelet, or a reminder is output through an output device pre-configured for the specific location or the high-risk location for falling, so as to remind people to pay attention to preventing falls.

8. A fall risk warning device for hospitalized patients, characterized in that: The device comprises: An acquisition unit, used to acquire drug data of a current inpatient, wherein the drug data specifically refers to data describing at least one of a drug used by the current inpatient and a drug involved in a doctor's order; an analysis unit, configured to input the drug data into a pre-configured fall risk analysis model, so that the fall risk analysis model carries out corresponding fall risk analysis processing, wherein the fall risk analysis model is used to analyze the fall risk corresponding to the drug data input into the model, and the fall risk analysis model is a model trained by labeled sample drug data; an extraction unit, used for extracting the fall risk analysis result output by the fall risk analysis model; The early warning unit is used to output a corresponding early warning based on the fall risk analysis result and in accordance with a preset fall risk early warning strategy to remind people to pay attention to fall prevention.

9. A processing system, characterized in that: Used to perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the method according to any one of claims 1 to 7.

Images