Inpatient area falling risk assessment and early warning method, system and terminal

Abstract

The invention discloses an inpatient area falling risk assessment and early warning method, system and terminal, and the method comprises the steps: building a risk early warning model in advance, training the risk early warning model through historical data, and obtaining a target model; performing multi-dimensional fall risk assessment on the inpatient to obtain assessment data, and inputting the assessment data into the target model for calculation to obtain a fall risk level; according to the falling risk level, multi-point risk warning is provided for the inpatient, risk early warning measures are provided for the inpatient, and the risk early warning measures comprise pushing of intelligent propaganda and education and starting of intelligent identification equipment; real-time data sent by the intelligent identification equipment is collected, the field condition of the inpatient is obtained according to the real-time data, and if the field condition has the possibility of falling down, a message is sent to medical staff to intervene and process the field condition. According to the invention, targeted prevention and control measures are provided for accidental tumble of the patient during hospitalization, and the tumble risk of the patient can be accurately identified.

Description

Technical Field

[0001] The present invention relates to the technical field of risk early warning, and particularly to a method, system, terminal and computer-readable storage medium for evaluating and warning the fall risk in an inpatient ward area. Background Art

[0002] An accidental fall during hospitalization refers to a fall accident of a patient in the hospital due to various reasons. Such accidental events not only pose a threat to the physical health of the patient, but also may lead to an extension of the patient's hospitalization time and an increase in medical expenses. Therefore, analyzing the causes of accidental fall events during hospitalization and proposing corresponding corrective measures are of great significance for improving the safety of patients and the quality of medical care.

[0003] Currently, the prevention methods for accidental falls during hospitalization in hospitals usually use identification cards to warn of risks and implement the requirements of hierarchical nursing rounds by nursing staff to conduct rounds on time. There are lack of targeted prevention and control measures, or use clinical medical equipment for early warning. However, each device operates independently, lacking an effective integrated risk early warning mechanism, resulting in the inability to accurately identify the fall risks existing in patients.

[0004] Therefore, the existing technology still needs to be improved and developed. Summary of the Invention

[0005] The main purpose of the present invention is to provide a method, system, terminal and computer-readable storage medium for evaluating and warning the fall risk in an inpatient ward area, aiming to solve the problems in the existing technology that there are lack of targeted prevention and control measures for accidental falls during hospitalization, each device operates independently, lacking an effective integrated risk early warning mechanism, resulting in the inability to accurately identify the fall risks existing in patients and thus unable to give early warnings in a timely manner.

[0006] To achieve the above purpose, the present invention provides a method for evaluating and warning the fall risk in an inpatient ward area. The method for evaluating and warning the fall risk in an inpatient ward area includes the following steps:

[0007] Pre-construct a risk early warning model, and use historical data to train the risk early warning model to obtain a target model;

[0008] Conduct a multi-dimensional fall risk assessment on inpatients to obtain assessment data, preprocess the assessment data and input it into the target model for calculation to obtain the fall risk level of the inpatients;

[0009] According to the fall risk level, provide multi-point risk warnings for the inpatients and provide risk early warning measures for the inpatients. Among them, the risk early warning measures include pushing intelligent education and opening intelligent identification devices;

[0010] Collect the real-time data sent by the intelligent recognition device, obtain the on-site situation of the in-patient based on the real-time data, and if there is a possibility of falling in the on-site situation, send a message to the medical staff to intervene in and handle the on-site situation.

[0011] Optionally, for the method for evaluating and warning of the risk of falling in the in-patient ward area, wherein the multi-dimensional risk of falling of the in-patient is evaluated to obtain evaluation data, and the evaluation data is pre-processed and then input into the target model for calculation to obtain the risk level of falling of the patient, specifically including:

[0012] Use a fall risk assessment scale, a muscle strength assessment scale, and a balance assessment scale to conduct a multi-dimensional fall risk assessment of the in-patient to obtain the fall risk assessment data, muscle strength assessment data, and balance assessment data of the in-patient;

[0013] Input the fall risk assessment data, the muscle strength assessment data, and the balance assessment data into the target model for prediction to obtain the fall risk level of the patient.

[0014] Optionally, for the method for evaluating and warning of the risk of falling in the in-patient ward area, wherein providing multi-point risk warnings for the in-patient according to the fall risk level specifically includes:

[0015] If the fall risk level is a low level, set the color of the bedside electronic screen of the in-patient to green to indicate a low fall risk;

[0016] If the fall risk level is a medium level, set the color of the bedside electronic screen of the in-patient to yellow to indicate a medium fall risk;

[0017] If the fall risk level is a high level, set the color of the bedside electronic screen of the in-patient to red to indicate a high fall risk;

[0018] Display the information of the in-patient on multi-point devices, and the multi-point devices include a hospital information management system, a nursing information management system, a medical staff interaction large screen, a ward entrance display screen, and a bedside electronic screen.

[0019] Optionally, for the method for evaluating and warning of the risk of falling in the in-patient ward area, wherein the intelligent education promotion includes: regularly pushing a fall prevention education and promotion video, and automatically broadcasting education and promotion voices during high-risk periods;

[0020] The activation of the intelligent recognition device includes: using a non-contact mattress to monitor the first in-bed state of the in-patient, activating a video monitoring system to remotely monitor the second in-bed state of the in-patient, and using a robot to patrol the ward to detect environmental risks and abnormal situations.

[0021] Optionally, in the method for evaluating and warning of fall risks in the inpatient ward area, the real-time data includes: the first in-bed status, the second in-bed status, the environmental risk, and the abnormal condition;

[0022] Before collecting the real-time data sent by the intelligent recognition device, it further includes:

[0023] Use a general interface adaptation module to establish a connection with the intelligent recognition devices of different interface types in the inpatient ward area, and through the general interface adaptation module, collect the real-time data from the intelligent recognition devices of different interface types according to different data collection frequencies;

[0024] Optionally, in the method for evaluating and warning of fall risks in the inpatient ward area, where if there is a possibility of falling in the on-site situation, sending a message to the medical staff to intervene and handle the on-site situation specifically includes:

[0025] If there is a possibility of falling in the on-site situation, generate a fall warning and send the fall warning to the hospital information management system, the nursing information management system, the medical staff interaction large screen, and the ward entrance display screen for display;

[0026] When the medical staff receives or sees the fall warning, intervene and handle the on-site situation.

[0027] Optionally, in the method for evaluating and warning of fall risks in the inpatient ward area, where using historical data to train the risk warning model to obtain a target model specifically includes:

[0028] Obtain historical evaluation data and the corresponding historical fall risk levels of the historical evaluation data, use the historical evaluation data and the historical fall risk levels as a data set, and divide the data set into a training set, a test set, and a validation set according to a preset ratio;

[0029] Use the training set to train the risk warning model, use the test set to evaluate the risk warning model after each round of training to obtain a trained model, and use the validation set to evaluate the trained model to obtain a target model.

[0030] In addition, to achieve the above object, the present invention also provides a system for evaluating and warning of fall risks in the inpatient ward area, where the system for evaluating and warning of fall risks in the inpatient ward area includes:

[0031] A risk warning model construction module, configured to pre-construct a risk warning model, and use historical data to train the risk warning model to obtain a target model;

[0032] A multi - dimensional risk assessment module, which is used to conduct a multi - dimensional fall risk assessment on in - patients, obtain assessment data, pre - process the assessment data and then input it into the target model for calculation to obtain the fall risk level of the in - patients;

[0033] A multi - point risk warning module, which is used to provide multi - point risk warnings for the in - patients according to the fall risk level, and provide risk warning measures for the in - patients. Among them, the risk warning measures include pushing intelligent education and opening intelligent identification devices;

[0034] A risk reporting and intervention module, which is used to collect the real - time data sent by the intelligent identification device, obtain the on - site situation of the in - patients according to the real - time data. If there is a possibility of falling in the on - site situation, a message is sent to the medical staff to intervene and handle the on - site situation.

[0035] In addition, to achieve the above - mentioned purpose, the present invention also provides a terminal. Among them, the terminal includes: a memory, a processor, and an assessment and warning program for in - patient area fall risk stored on the memory and operable on the processor. When the assessment and warning program for in - patient area fall risk is executed by the processor, the steps of the above - mentioned assessment and warning method for in - patient area fall risk are implemented.

[0036] In addition, to achieve the above - mentioned purpose, the present invention also provides a computer - readable storage medium. Among them, the computer - readable storage medium stores an assessment and warning program for in - patient area fall risk. When the assessment and warning program for in - patient area fall risk is executed by a processor, the steps of the above - mentioned assessment and warning method for in - patient area fall risk are implemented.

[0037] In the present invention, a risk warning model is pre - constructed, and the risk warning model is trained using historical data to obtain a target model; a multi - dimensional fall risk assessment is conducted on in - patients to obtain assessment data, the assessment data is pre - processed and then input into the target model for calculation to obtain the fall risk level of the in - patients; according to the fall risk level, multi - point risk warnings are provided for the in - patients, and risk warning measures are provided for the in - patients. Among them, the risk warning measures include pushing intelligent education and opening intelligent identification devices; the real - time data sent by the intelligent identification device is collected, the on - site situation of the in - patients is obtained according to the real - time data. If there is a possibility of falling in the on - site situation, a message is sent to the medical staff to intervene and handle the on - site situation. The present invention provides targeted prevention and control measures for accidental falls during patients' hospitalization and can accurately identify the fall risks existing in patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 is a flowchart of a preferred embodiment of the method for assessing and warning of fall risks in the inpatient ward of the present invention;

[0039] Figure 2 is an overall architecture diagram of the method for assessing and warning of fall risks in the inpatient ward of the present invention;

[0040] Figure 3 is a structural diagram of a preferred embodiment of the system for assessing and warning of fall risks in the inpatient ward of the present invention;

[0041] Figure 4 is a structural diagram of a preferred embodiment of the terminal of the present invention. Detailed implementation manners

[0042] The present application provides a method, a system and a terminal for assessing and warning of fall risks in the inpatient ward. To make the purpose, technical solutions and effects of the present application clearer and more definite, the following further describes the present application in detail with reference to the accompanying drawings and by way of examples. It should be understood that the specific examples described herein are only used to explain the present application and are not used to limit the present application.

[0043] Those skilled in the art of the present technology can understand that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as the general understanding of those of ordinary skill in the field to which the present application belongs. It should also be understood that terms such as those defined in a general dictionary should be understood to have a meaning consistent with the meaning in the context of the prior art, and will not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0044] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, such descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, features defined with "first", "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between various embodiments may be combined with each other, but it must be based on the fact that those of ordinary skill in the art can implement them. When the combination of technical solutions appears to be contradictory or unable to be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0045] The method for assessing and warning of fall risks in the inpatient ward according to a preferred embodiment of the present invention, as Figure 1 and Figure 2 shown, the method for assessing and warning of fall risks in the inpatient ward includes the following steps:

[0046] Step S10: Pre-construct a risk warning model, and use historical data to train the risk warning model to obtain a target model.

[0047] Specifically, pre-construct a risk warning model, which includes: an input layer, a feature fusion layer, a dynamic incremental learning module, and a classification output layer. Among them, the input layer uses a Transformer-based model (such as BERT or GPT) to extract text features and supports context-aware semantic understanding; the feature fusion layer designs a cross-modal attention module to dynamically adjust the weights of text, image, and sound features to achieve deep fusion of multi-modal information. For example, the Self-Attention mechanism is used to capture the correlation between different modalities, and feature selection techniques (such as chi-square test or mutual information) are introduced to screen out the most representative features and reduce the interference of redundant information. The dynamic incremental learning module designs an incremental training module that can dynamically update the model according to new data, avoid the overhead of re-training, and introduce feedback data to optimize the model parameters in real time to improve the adaptability of the model in practical applications. Finally, the classification output layer supports multi-task classification output and can dynamically adjust the classification threshold according to task requirements to improve the flexibility and robustness of the model.

[0048] Further, obtain historical evaluation data and the corresponding historical fall risk level of the historical evaluation data, use the historical evaluation data and the historical fall risk level as a data set, and divide the data set into a training set, a test set, and a validation set according to a preset ratio. Use the training set to train the risk warning model, use the test set to evaluate the risk warning model for each round of training to obtain a trained model, and use the validation set to evaluate the trained model to obtain a target model.

[0049] Step S20: Conduct a multi-dimensional fall risk assessment on inpatients to obtain assessment data, preprocess the assessment data, and input it into the target model for calculation to obtain the fall risk level of the inpatients.

[0050] Specifically, use a fall risk assessment scale, a muscle strength assessment scale, and a balance assessment scale to conduct a multi-dimensional fall risk assessment on inpatients to obtain the fall risk assessment data, muscle strength assessment data, and balance assessment data of the inpatients.

[0051] It can be understood that the fall risk assessment scale is the MORSE assessment form, which is used to assess the fall risk of patients. In addition, this application also combines the muscle strength assessment scale and the balance assessment scale to assess the muscle strength and balance of patients. Through these three pieces of data, the fall level of patients is obtained from multiple aspects.

[0052] Further, input the fall risk assessment data, the muscle strength assessment data, and the balance ability assessment data into the target model for prediction to obtain the fall risk level of the patient.

[0053] In this embodiment, input the fall risk assessment data, the muscle strength assessment data, and the balance ability assessment data into the target model for feature extraction, and finally obtain the fall risk level of the patient through the classification output layer.

[0054] Step S30: Provide multi-point risk warnings for the in-patient according to the fall risk level, and provide risk warning measures for the in-patient, where the risk warning measures include pushing intelligent education and activating intelligent identification devices.

[0055] The providing multi-point risk warnings for the in-patient according to the fall risk level specifically includes:

[0056] If the fall risk level is a low level, set the color of the bedside electronic screen of the in-patient to green to indicate a low fall risk; if the fall risk level is a medium level, set the color of the bedside electronic screen of the in-patient to yellow to indicate a medium fall risk; if the fall risk level is a high level, set the color of the bedside electronic screen of the in-patient to red to indicate a high fall risk;

[0057] It can be understood that green generally symbolizes safety and normality and is suitable for indicating low risks. Yellow generally represents warning and attention and is suitable for indicating medium risks. Red generally represents danger and emergency and is suitable for indicating high risks, and green, yellow, and red are significantly distributed in the spectrum and are easy to distinguish and suitable for quick identification. Therefore, in this embodiment, the fall risk levels of the patients are represented as green, yellow, and red in sequence from low to high, and the corresponding colors are set as the colors of the bedside electronic screens of the patients, which can help medical staff quickly and effectively obtain the fall risk levels of the patients.

[0058] Further, display the information of the in-patient on multi-point devices, where the multi-point devices include a hospital information management system, a nursing information management system, a medical staff interaction large screen, a ward door display screen, and a bedside electronic screen.

[0059] In this embodiment, display the information of the in-patient on multi-point devices to achieve multi-point risk warnings, where the multi-point devices cover most of the interaction devices in the inpatient area, including a hospital information management system (HIS system), a nursing information management system (NIS system), a medical staff interaction large screen, a ward door display screen, and a bedside electronic screen, etc. Through such multi-point risk warnings, the protection of patients prone to falling can be strengthened, and medical staff can also timely grasp the real-time situation of patients prone to falling.

[0060] Furthermore, when the information of the in-patient is displayed on the multi-point device, it can be selectively displayed according to the fall risk level of the in-patient. For example, if the fall risk level is high, when the patient suddenly gets out of bed, warning information will be sent to the hospital information management system and the nursing information management system, and at the same time, a strong sound and light alarm will be issued; if the fall risk level is medium, the warning information will be displayed through the nursing information management system and the medical staff interaction large screen; if the fall risk level is low, it will only be prompted on the medical staff interaction large screen, the display screen at the ward entrance and the bedside electronic screen for the convenience of medical staff to check and handle in daily life.

[0061] Even further, the push of intelligent education includes: regularly pushing prevention of fall education videos and automatically broadcasting education voices during high-risk periods; the activation of intelligent identification devices includes: using a non-contact mattress to monitor the first in-bed state of the in-patient, activating the video monitoring system to remotely monitor the second in-bed state of the in-patient, and using a robot to patrol the ward to detect environmental risks and abnormal situations.

[0062] It can be understood that intelligent education refers to using modern information technologies such as artificial intelligence, the Internet of Things, and big data to provide personalized and precise health education and medical information services for patients and medical staff. According to the characteristics of the patient's condition, age, educational level, etc., it intelligently matches and regularly pushes content related to fall prevention. The content displays the education content in various forms such as text, pictures, videos, and audio, making the information more intuitive and easy to understand, providing scientific guidance for patients, and strengthening the patients' awareness of prevention. And when a high fall risk situation is detected, the education voice will be automatically broadcast.

[0063] The activation of the intelligent identification device includes: using a non-contact mattress to monitor the first in-bed state of the in-patient, activating the video monitoring system to remotely monitor the second in-bed state of the in-patient, and using a robot to patrol the ward to detect environmental risks and abnormal situations.

[0064] It is understandable that two devices are used to obtain the in-bed status of the in-patient, namely, using a non-contact mattress to monitor the first in-bed status of the in-patient and turning on the video surveillance system to remotely monitor the second in-bed status of the in-patient. Among them, the non-contact mattress is an intelligent mattress that uses advanced sensing technology to achieve non-contact vital sign monitoring. It can collect real-time vital sign data of patients such as breathing, heart rate, and body movement through built-in sensors (such as radar waves, fiber optic sensors, etc.), without direct contact with the skin, avoiding the sense of restraint and discomfort of traditional monitoring devices. The first in-bed status of the in-patient can be obtained through the non-contact mattress, and the second in-bed status of the in-patient can be returned through the video surveillance system. When both the first in-bed status and the second in-bed status indicate not in bed, it can be determined that the user may have fallen.

[0065] The robot is a patrol robot, and the work of the patrol robot mainly includes three aspects: patrol, warning, and reporting. First, the patrol robot continuously patrols in the in-hospital ward area and the in-hospital ward corridor according to a fixed route to obtain environmental image information that may have potential hazards; then, the patrol robot uses its own recognition model to recognize the environmental image information that may have potential hazards, judge environmental risks and abnormal situations, and report the environmental risks and abnormal situations to notify the nurses to deal with them in time to block the occurrence of risks. In addition, the patrol robot can also be equipped with sensors to obtain environmental parameters. For example, it can monitor the environmental parameters in areas such as hospital wards, operating rooms, and outpatient clinics, such as floor humidity, air quality, etc. When the floor humidity is too high, the floor is slippery and it is also easy to have a risk of falling.

[0066] Step S40: Collect the real-time data sent by the intelligent recognition device, obtain the on-site situation of the in-patient according to the real-time data. If there is a possibility of falling in the on-site situation, send a message to the medical staff to intervene and handle the on-site situation.

[0067] Specifically, the first in-bed status, the second in-bed status, the environmental risk, and the abnormal situation; before collecting the real-time data sent by the intelligent recognition device, it also includes:

[0068] Use a general interface adaptation module to establish a connection with the intelligent recognition devices of different interface types in the in-hospital ward area, and through the general interface adaptation module, collect the real-time data from the intelligent recognition devices of different interface types according to different data collection frequencies.

[0069] It can be understood that for the intelligent recognition devices of the above-mentioned different interface types, the present application has developed a general interface adaptation module, which can automatically identify and establish a stable connection with the early warning system. The general interface adaptation module can be an interface adapter, which is specially designed according to the interface types of various devices in the hospital. The interface adapter is the signal hub between the test device and the device to be detected, gathering a large number of signals to be detected. Its function is to send the signals of each interface of the device to be detected to the measuring instrument through different conditioning modules. By using the general interface adapter, the user can control the matrix switch to automatically switch through the measurement and control computer to adapt to different test objects, so as to achieve the purpose of one test system corresponding to multiple test objects and solve the problem of repeated development of the interface adapter.

[0070] It can be understood that the data acquisition frequency is set according to the importance of the device and the risk sensitivity, and different data acquisition frequencies are set for each device. For example, the non-contact mattress collects key parameters every 20 seconds, and the patrol robot device collects data every 40 seconds. Then, through the general interface adaptation module, the sensing data of each device is converted to obtain unified real-time data, solving the problem that the existing system cannot uniformly access and manage clinical devices of different brands and different interface standards, resulting in poor device compatibility.

[0071] Furthermore, the first in-bed state, the second in-bed state, the environmental risk, and the abnormal situation sent by the intelligent recognition device are collected, and the on-site situation of the in-patient is obtained according to the real-time data. For example, when both the first in-bed state and the second in-bed state are out of bed, it is determined that there may be a risk of falling in the on-site situation.

[0072] Furthermore, if there may be a risk of falling in the on-site situation, a message is sent to the medical staff to intervene and handle the on-site situation, specifically including:

[0073] If there may be a risk of falling in the on-site situation, a fall warning is generated and sent to the hospital information management system, the nursing information management system, the medical staff interaction large screen, and the ward door display screen for display;

[0074] When the medical staff receives or sees the fall warning, they intervene and handle the on-site situation.

[0075] It is understandable that when there is a possibility of falling in the on-site situation, a fall warning is automatically generated and sent to the hospital information management system, the nursing information management system, the medical staff interaction large screen, and the ward entrance display screen for display. The nurse can directly call back the bed arm screen or the bedside card where the mattress is located through the call or video operation button under the message received by the terminal device equipped with the nursing information management system, inquire about the details, and then take corresponding medical measures.

[0076] The following further elaborates on the method of the present invention through specific application embodiments. The method for evaluating and warning of the fall risk in the inpatient ward area specifically includes the following steps:

[0077] S101. Deploy a data processing server and storage device in the hospital network center, and install an operating system and relevant software environments. Then install perception layer devices and connect terminals in each clinical department, and configure corresponding interface parameters according to different device types to ensure stable connection with medical devices.

[0078] S102. Initialize the risk warning model, import historical data for training, and obtain the target model.

[0079] S103. Use the fall risk assessment scale, muscle strength assessment scale, and balance assessment scale to conduct multi-dimensional fall risk assessments on inpatients, and obtain the fall risk assessment data, muscle strength assessment data, and balance assessment data of the inpatients.

[0080] S104. Input the fall risk assessment data, the muscle strength assessment data, and the balance assessment data into the target model for prediction, and obtain the fall risk level of the patient.

[0081] S105. Provide multi-point risk warnings for the inpatients according to the fall risk level, and provide risk warning measures for the inpatients.

[0082] S106. After receiving the warning message, medical staff can further view the detailed data according to the prompt, select to call or video the bedside device of the patient to confirm the details, and take corresponding medical measures.

[0083] It can be seen that the present invention can achieve unified risk early warning management for multiple risk projects, realize a closed-loop management integrating risk assessment - risk early warning - risk reporting - risk intervention, and improve the effectiveness of risk control by nursing staff; through advanced risk analysis technology, real-time extraction of data for dynamic risk analysis improves the accuracy of risk identification; the real-time transmission security of data ensures the integrity of medical data and realizes the sharing of medical data; through risk reporting and effective intervention, full-ward coverage of risk identification is achieved, and the clinical application effect of the intelligent risk prevention and control system is remarkable. Through data statistics, the incidence rate of fall events has decreased from 0.29% to 0.03%, realizing risk pre-position management, reducing the occurrence of fall events, and improving the quality of medical services.

[0084] Furthermore, as Figure 3 shown, based on the above-mentioned method for assessing and warning of fall risks in the inpatient ward area, the present invention also correspondingly provides a system for assessing and warning of fall risks in the inpatient ward area, wherein the system for assessing and warning of fall risks in the inpatient ward area includes:

[0085] A risk early warning model construction module 51, configured to pre-construct a risk early warning model, and use historical data to train the risk early warning model to obtain a target model;

[0086] A multi-dimensional risk assessment module 52, configured to perform multi-dimensional fall risk assessment on inpatients to obtain assessment data, preprocess the assessment data and input it into the target model for calculation to obtain the fall risk level of the inpatients;

[0087] A multi-point risk early warning module 53, configured to provide multi-point risk warnings for the inpatients according to the fall risk level, and provide risk early warning measures for the inpatients, wherein the risk early warning measures include pushing intelligent education and activating intelligent identification devices;

[0088] A risk reporting and intervention module 54, configured to collect real-time data sent by the intelligent identification device, obtain the on-site situation of the inpatients according to the real-time data, and if there is a possibility of falling in the on-site situation, send a message to the medical staff to intervene and handle the on-site situation.

[0089] Furthermore, as Figure 4 shown, based on the above-mentioned method and system for assessing and warning of fall risks in the inpatient ward area, the present invention also correspondingly provides a terminal, which includes a processor 10, a memory 20, and a display 30. Figure 4 Only some components of the terminal are shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented.

[0090] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as the hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk equipped on the terminal, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 20 may also include both the internal storage unit of the terminal and the external storage device. The memory 20 is used to store application software installed on the terminal and various types of data, such as program codes for installing the terminal. The memory 20 may also be used to temporarily store data that has been output or will be output. In one embodiment, an evaluation and early warning program 40 for the fall risk in the inpatient ward area is stored on the memory 20, and the evaluation and early warning program 40 for the fall risk in the inpatient ward area can be executed by the processor 10, so as to implement the evaluation and early warning method for the fall risk in the inpatient ward area in this application.

[0091] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other data processing chips, and is used to run the program codes stored in the memory 20 or process data, such as executing the evaluation and early warning method for the fall risk in the inpatient ward area, etc.

[0092] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) toucher, etc. The display 30 is used to display information on the terminal and to display a visual user interface. The components of the terminal communicate with each other through a system bus.

[0093] In one embodiment, when the processor 10 executes the evaluation and early warning program 40 for the fall risk in the inpatient ward area stored in the memory 20, the following steps are implemented:

[0094] Pre-construct a risk early warning model, and use historical data to train the risk early warning model to obtain a target model;

[0095] Conduct a multi-dimensional fall risk assessment on inpatients to obtain assessment data, preprocess the assessment data and input it into the target model for calculation to obtain the fall risk level of the inpatients;

[0096] According to the fall risk level, provide multi-point risk warnings for the inpatients and provide risk early warning measures for the inpatients, where the risk early warning measures include pushing intelligent education and opening intelligent identification devices;

[0097] Collect the real-time data sent by the intelligent recognition device, obtain the on-site situation of the in-patient based on the real-time data, and if there is a possibility of falling in the on-site situation, send a message to the medical staff to intervene in and handle the on-site situation.

[0098] Among them, the multi-dimensional fall risk assessment of the in-patient is carried out to obtain assessment data, and after preprocessing the assessment data, it is input into the target model for calculation to obtain the fall risk level of the patient, which specifically includes:

[0099] Use a fall risk assessment scale, a muscle strength assessment scale, and a balance assessment scale to conduct a multi-dimensional fall risk assessment on the in-patient to obtain the fall risk assessment data, muscle strength assessment data, and balance assessment data of the in-patient;

[0100] Input the fall risk assessment data, the muscle strength assessment data, and the balance assessment data into the target model for prediction to obtain the fall risk level of the patient.

[0101] Among them, providing multi-point risk warnings for the in-patient according to the fall risk level specifically includes:

[0102] If the fall risk level is low, set the color of the bedside electronic screen of the in-patient to green to indicate a low fall risk;

[0103] If the fall risk level is medium, set the color of the bedside electronic screen of the in-patient to yellow to indicate a medium fall risk;

[0104] If the fall risk level is high, set the color of the bedside electronic screen of the in-patient to red to indicate a high fall risk;

[0105] Display the information of the in-patient on multi-point devices, and the multi-point devices include a hospital information management system, a nursing information management system, a medical staff interaction large screen, a ward door display screen, and a bedside electronic screen.

[0106] Among them, the push of intelligent education includes: regularly pushing prevention of fall education videos and automatically playing education voices during high-risk periods;

[0107] The activation of the intelligent recognition device includes: using a non-contact mattress to monitor the first in-bed state of the in-patient, activating the video monitoring system to remotely monitor the second in-bed state of the in-patient, and using a robot to patrol the ward to monitor environmental risks and abnormal situations.

[0108] Among them, the real-time data includes: the first in-bed state, the second in-bed state, the environmental risk, and the abnormal situation;

[0109] Before collecting the real-time data sent by the intelligent identification device, it further includes:

[0110] Use a general interface adaptation module to establish a connection with the intelligent identification devices of different interface types in the hospital ward area, and through the general interface adaptation module, collect the real-time data from the intelligent identification devices of different interface types according to different data collection frequencies;

[0111] Among them, if there is a possibility of falling in the on-site situation, send a message to the medical staff to intervene in and handle the on-site situation, specifically including:

[0112] If there is a possibility of falling in the on-site situation, generate a fall warning and send the fall warning to the hospital information management system, the nursing information management system, the medical staff interaction large screen, and the ward door display screen for display;

[0113] When the medical staff receives or sees the fall warning, intervene in and handle the on-site situation.

[0114] Among them, using the historical data to train the risk warning model to obtain a target model specifically includes:

[0115] Obtain historical evaluation data and the corresponding historical fall risk level of the historical evaluation data, use the historical evaluation data and the historical fall risk level as a data set, and divide the data set into a training set, a test set, and a validation set according to a preset ratio;

[0116] Use the training set to train the risk warning model, use the test set to evaluate the risk warning model after each round of training to obtain a trained model, and use the validation set to evaluate the trained model to obtain a target model.

[0117] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores an evaluation and warning program for the fall risk in the inpatient ward area, and when the evaluation and warning program for the fall risk in the inpatient ward area is executed by a processor, the steps of the above-mentioned method for evaluating and warning the fall risk in the inpatient ward area are realized.

[0118] In summary, the present invention provides a method, a system and a terminal for evaluating and warning of the fall risk in an inpatient ward area. The method includes: pre-constructing a risk warning model, training the risk warning model with historical data to obtain a target model; performing a multi-dimensional fall risk assessment on inpatients to obtain assessment data, preprocessing the assessment data and inputting the preprocessed data into the target model for calculation to obtain the fall risk level of the inpatients; providing multi-point risk warnings for the inpatients according to the fall risk level, and providing risk warning measures for the inpatients, where the risk warning measures include pushing intelligent education and activating intelligent identification devices; collecting real-time data sent by the intelligent identification devices, obtaining the on-site situation of the inpatients according to the real-time data, and if there is a possibility of falling in the on-site situation, sending a message to medical staff to intervene in and handle the on-site situation. The present invention provides targeted prevention and control measures for accidental falls during the hospitalization of patients, and can accurately identify the fall risks existing in patients.

[0119] It should be noted that in this article, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or terminal including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or terminal. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or terminal including that element.

[0120] Of course, those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided by the present invention can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0121] It should be understood that the application of the present invention is not limited to the above examples. For those of ordinary skill in the art, improvements or transformations can be made according to the above description. All such improvements and transformations should fall within the protection scope of the appended claims of the present invention.

Claims

1. A method for assessing and warning the risk of falling in an inpatient ward, characterized in that: The method for assessing and warning the risk of falls in the inpatient ward includes: Pre-constructing a risk warning model, and using historical data to train the risk warning model to obtain a target model; Performing a multi-dimensional fall risk assessment on hospitalized patients to obtain assessment data, pre-processing the assessment data and inputting the data into the target model for calculation to obtain the fall risk level of the hospitalized patients; According to the fall risk level, provide the inpatient with multi-point risk warnings and provide risk warning measures for the inpatient, wherein the risk warning measures include pushing intelligent education and turning on intelligent identification equipment; The real-time data sent by the intelligent identification device is collected, and the on-site situation of the hospitalized patient is obtained according to the real-time data. If there is a possibility of a fall in the on-site situation, a message is sent to medical staff to intervene and handle the on-site situation.

2. The method for assessing and warning the risk of falling in an inpatient ward according to claim 1, characterized in that: The multi-dimensional fall risk assessment of hospitalized patients is performed to obtain assessment data, and the assessment data is pre-processed and then input into the target model for calculation to obtain the patient's fall risk level, specifically including: Use the fall risk assessment scale, muscle strength assessment scale and balance assessment scale to conduct multi-dimensional fall risk assessment on hospitalized patients, and obtain the fall risk assessment data, muscle strength assessment data and balance assessment data of hospitalized patients; The fall risk assessment data, the muscle strength assessment data and the balance assessment data are input into the target model for prediction to obtain the patient's fall risk level.

3. The method for assessing and warning the risk of falling in an inpatient ward according to claim 1, characterized in that: The providing of multi-point risk warnings for the inpatient according to the fall risk level specifically includes: If the fall risk level is low, the color of the bedside electronic screen of the inpatient is set to green to indicate low fall risk; If the fall risk level is medium, the color of the bedside electronic screen of the inpatient is set to yellow to indicate medium fall risk; If the fall risk level is high, the color of the bedside electronic screen of the inpatient is set to red to indicate a high fall risk; The information of the hospitalized patients is displayed on multi-point devices, which include a hospital information management system, a nursing information management system, a large medical and nursing interaction screen, a display screen at the door of the ward, and an electronic screen at the bedside.

4. The method for assessing and warning the risk of falling in an inpatient ward according to claim 1, characterized in that: The push of intelligent education includes: regularly pushing fall prevention education videos and automatically broadcasting education voice during high-risk periods; The activation of the intelligent identification device includes: using a non-contact mattress to monitor the first bed state of the inpatient, activating a video monitoring system to remotely monitor the second bed state of the inpatient, and using a robot to patrol the ward to monitor environmental risks and abnormal conditions.

5. The method for assessing and warning the risk of falling in an inpatient ward according to claim 4, characterized in that: The real-time data includes: the first bed state, the second bed state, the environmental risk and the abnormal situation; The collecting of real-time data sent by the intelligent identification device also includes: A universal interface adapter module is used to establish a connection with the intelligent identification devices of different interface types in the hospital wards, and through the universal interface adapter module, real-time data from the intelligent identification devices of different interface types are collected according to different data collection frequencies.

6. The method for assessing and warning the risk of falling in an inpatient ward according to claim 3, characterized in that: If there is a possibility of falling in the on-site situation, a message is sent to medical personnel to intervene and handle the on-site situation, specifically including: If there is a possibility of falling in the on-site situation, a fall warning is generated, and the fall warning is sent to the hospital information management system, the nursing information management system, the medical and nursing interaction large screen and the display screen at the ward entrance for display; When the medical staff receives or sees the fall warning, they intervene and handle the on-site situation.

7. The method for assessing and warning the risk of falling in an inpatient ward according to claim 1, characterized in that: The use of historical data to train the risk warning model to obtain a target model specifically includes: Acquire historical assessment data and historical fall risk levels corresponding to the historical assessment data, use the historical assessment data and the historical fall risk levels as a data set, and divide the data set into a training set, a test set, and a validation set according to a preset ratio; The risk warning model is trained using the training set, and the risk warning model of each round of training is evaluated using the test set to obtain a trained model, and the trained model is evaluated using the validation set to obtain a target model.

8. A fall risk assessment and early warning system for inpatient wards, characterized in that: The inpatient ward fall risk assessment and early warning system includes: A risk warning model building module is used to pre-build a risk warning model and train the risk warning model using historical data to obtain a target model; A multi-dimensional risk assessment module is used to perform a multi-dimensional fall risk assessment on an inpatient to obtain assessment data, and the assessment data is pre-processed and then input into the target model for calculation to obtain the fall risk level of the inpatient; A multi-point risk warning module, used to provide multi-point risk warnings for the inpatients according to the fall risk level, and provide risk warning measures for the inpatients, wherein the risk warning measures include pushing intelligent education and turning on intelligent identification equipment; The risk reporting and intervention module is used to collect the real-time data sent by the intelligent identification device, obtain the on-site situation of the hospitalized patient based on the real-time data, and if there is a possibility of falling in the on-site situation, send a message to medical staff to intervene and handle the on-site situation.

9. A terminal, characterized in that: The terminal includes: a memory, a processor, and an inpatient ward fall risk assessment and early warning program stored in the memory and executable on the processor. When the inpatient ward fall risk assessment and early warning program is executed by the processor, the steps of the inpatient ward fall risk assessment and early warning method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an inpatient ward fall risk assessment and early warning program, and when the inpatient ward fall risk assessment and early warning program is executed by a processor, the steps of the inpatient ward fall risk assessment and early warning method as described in any one of claims 1-7 are implemented.

Images