Inpatient-based suicide risk early warning method and early warning system

Abstract

The invention relates to a suicide risk early warning method based on an inpatient. The method comprises the following steps: acquiring basic data, behavior characteristic data and vital sign data of the patient by using a data acquisition unit; integrating and analyzing the data acquired by the data acquisition unit through a risk assessment unit, and judging a risk level; the risk early warning unit sends a corresponding early warning notice to the mobile terminal based on the risk level, or starts the emergency intervention unit to make a corresponding intervention behavior; and data acquired by the data acquisition unit, the risk level generated by the risk assessment unit and an intervention record of the emergency intervention unit are archived, managed and stored through the data management unit. According to the method, the basic data, the behavior characteristic data and the vital sign data of the patient are dynamically monitored and collected, whether the patient has the suicide tendency or not is judged in real time according to the collected data, risk early warning and intervention are correspondingly carried out according to division of risk levels, and the suicide rate of the patient is greatly reduced.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and specifically to a suicide risk early warning method and system based on hospitalized patients. Background Technology

[0002] Suicide is a major public health problem worldwide. Hospitalized patients frequently commit suicide, with a suicide rate 4-5 times higher than the general population. As the primary treatment center for various patients, healthcare institutions face the critical challenge of identifying and preventing suicide risks. Traditional methods for assessing patient suicide risk rely heavily on the clinical experience and subjective judgment of healthcare professionals, leading to problems such as untimely, inaccurate, and incomplete assessments, making it difficult to effectively and accurately identify high-risk patients. Furthermore, the lack of systematic and standardized prevention and intervention measures results in poor intervention outcomes. Although suicide is a low-probability event, its consequences are severe. Suicide can lead to disability or even death, causing immense distress to patients' families and healthcare workers, and may even trigger serious medical disputes.

[0003] Our research group is dedicated to developing a scientific and effective system for assessing and preventing suicide risks among hospitalized patients, with the aim of reducing the suicide rate and gradually achieving the goal of "zero suicides" among patients. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a suicide risk early warning method and system based on hospitalized patients, so as to overcome the shortcomings of the prior art.

[0005] The technical solution of this invention to solve the above-mentioned technical problems is as follows: A suicide risk early warning method based on hospitalized patients, comprising the following steps:

[0006] Step S01: Collect the patient's basic data, behavioral characteristics data, and vital signs data using the data acquisition unit;

[0007] Step S02: The risk assessment unit integrates and analyzes the data collected by the data acquisition unit to determine the risk level;

[0008] Step S03: Based on the risk level, the risk warning unit sends a corresponding warning notification to the mobile terminal, or activates the emergency intervention unit to take corresponding intervention actions;

[0009] Step S04: The data management unit archives, manages, and stores the data collected by the data acquisition unit, the risk level generated by the risk assessment unit, and the intervention records of the emergency intervention unit.

[0010] The present application has the beneficial effects that: the present application dynamically monitors and collects basic data, behavior characteristic data and vital sign data of the patient, judges whether the patient has a suicide tendency in real time according to the collected data, carries out risk early warning and intervention according to the division of risk levels, and greatly reduces the suicide rate of the patient.

[0011] Based on the above technical solution, the present application can be further improved as follows.

[0012] Further, the data collected by the data collection unit in step S01 specifically includes:

[0013] The basic data of the patient is derived from demographic data, disease diagnosis data and historical assessment data of the patient, and is used to judge whether the patient has a potential suicide reason;

[0014] The behavior characteristic data is derived from a visual recognition camera in a risk area and a sound pickup device in a ward, and is used to monitor whether the patient has a suicide action and tendency, including climbing windows and balconies, self-injury with knives, micro-expressions and negative language;

[0015] The vital sign data is derived from a smart wearable device worn by the patient, and is used to collect data including heart rate, pulse and blood pressure of the patient.

[0016] Further, step 02 specifically includes:

[0017] Step S21: classifying the basic data, behavior characteristic data and vital sign monitoring data into text type data, audio type data and video type data;

[0018] Step S22: taking historical text type data, audio type data and video type data as samples, and constructing and training a risk assessment large model based on a YOLOv7 target detection algorithm;

[0019] Step S23: analyzing the data collected by the data collection unit in real time by using the risk assessment large model, and judging the risk level according to the risk assessment standard.

[0020] Further, the risk assessment standard in step S23 adopts the Columbia Suicide Severity Rating Scale (C-SSRS) for suicide risk.

[0021] Further, step S03 specifically includes:

[0022] When the risk level is low: no warning notification and intervention behavior is made;

[0023] When the risk level is medium: a warning notification is made, and information and pop-up window reminders are sent to the mobile terminal;

[0024] When judging as high risk: making early warning and intervention behavior, sending information and pop-up window reminders to the mobile terminal, starting the sound and light alarm of the nurse station, and enabling the emergency intervention unit to make corresponding intervention behavior.

[0025] Further, the emergency intervention unit in step S03 comprises:

[0026] Electrically operated opening and closing windows arranged in high-risk areas in the hospital;

[0027] Electrically operated extension blocking nets arranged outside the window and outside the balcony.

[0028] Further, the behavior characteristic data is also derived from the thermal imager arranged in the bathroom.

[0029] Further, the method further comprises the following steps:

[0030] Step S05: The doctor marks and corrects the correctness of the historical evaluation record, the historical warning record and the historical intervention record in the data management unit, and optimizes and upgrades through the dynamic learning unit.

[0031] The application also discloses a suicide risk early warning system based on the above-mentioned suicide risk early warning method for risk early warning, comprising a mobile terminal, and a data acquisition unit, a risk assessment unit, a risk early warning unit, an emergency intervention unit and a data management unit connected in sequence by signals, wherein the risk early warning unit is wirelessly connected with the mobile terminal.

[0032] The data acquisition unit is used for acquiring basic data, behavior characteristic data and vital sign data of the patient.

[0033] The risk assessment unit is used for integrating and analyzing the data acquired by the data acquisition unit, and judging the risk level.

[0034] The risk early warning unit is used for sending corresponding early warning notifications to the mobile terminal or enabling the emergency intervention unit to make corresponding intervention behavior based on the risk level.

[0035] The data management unit is used for archiving and managing and storing the data acquired by the data acquisition unit, the risk level generated by the risk assessment unit and the intervention record of the emergency intervention unit.

[0036] The application has the beneficial effects that the application greatly reduces the suicide rate of the patient by real-time risk monitoring and automatically making corresponding early warning notifications and intervention behavior according to the risk level.

[0037] Further, the emergency intervention unit comprises:

[0038] The electrically operated opening and closing windows arranged in the high-risk areas in the hospital are used for closing the windows according to the risk level to prevent the patient from falling from the building.

[0039] The electrically-driven stretching barrier net arranged outside the window and the balcony is used for stretching the barrier net according to the risk level, so as to prevent the patient from falling from the building;

[0040] The data acquisition unit comprises:

[0041] The visual recognition camera arranged in the risk area and the sound pickup arranged in the ward are used for monitoring whether the patient has suicidal behaviors and suicidal tendencies including climbing the window and the balcony, self-injury with a knife, micro-expression and negative language;

[0042] The smart wearable device worn by the patient is used for collecting data including the heart rate, pulse and blood pressure of the patient;

[0043] The thermal imager arranged in the bathroom is used for monitoring whether the patient produces suicidal behaviors in the bathroom;

[0044] The risk warning unit comprises:

[0045] The audible and visual alarm arranged in the nurse station is used for audible and visual alarm according to the risk level evaluated by the risk evaluation unit. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 The structure diagram of the present application is shown. DETAILED DESCRIPTION

[0047] The principles and characteristics of the present application are described below in combination with the drawings, and the examples are only used to explain the present application, and are not used to limit the scope of the present application.

[0048] As shown in Figure 1 Embodiment 1, a suicide risk warning method based on inpatient, comprising the following steps:

[0049] Step S01: collecting basic data, behavior characteristic data and vital sign data of the patient by using the data acquisition unit;

[0050] Step S02: integrating and analyzing the data collected by the data acquisition unit by using the risk evaluation unit, and judging the risk level;

[0051] Step S03: the risk warning unit sends corresponding warning notification to the mobile terminal based on the risk level, or enables the emergency intervention unit to make corresponding intervention behavior;

[0052] Step S04: archiving and managing and storing the data collected by the data acquisition unit, the risk level generated by the risk evaluation unit, and the intervention record of the emergency intervention unit by using the data management unit.

[0053] The application greatly reduces the suicide rate of patients by dynamically monitoring and collecting basic data, behavior characteristic data and vital sign data of the patient, judging whether the patient has a suicide tendency in real time according to the collected data, and performing risk warning and intervention according to the division of risk levels.

[0054] Embodiment 2 is a further improvement based on embodiment 1, which is specifically as follows:

[0055] The data collected by the data collection unit in step S01 specifically includes:

[0056] The basic data of the patient is derived from demographic data, disease diagnosis data and historical assessment data of the patient, and is used to judge whether the patient has a potential suicide reason; in a specific implementation, the demographic data includes psychological state, family support, social environment and economic status of the patient.

[0057] The behavior characteristic data is derived from a visual recognition camera in a risk area and a sound pickup device in a ward, and is used to monitor whether the patient has a suicide action and tendency, including climbing windows and balconies, self-injury with knives, micro-expression and negative language.

[0058] The vital sign data is derived from a smart wearable device worn by the patient, and is used to collect data including heart rate, pulse and blood pressure of the patient.

[0059] Embodiment 3 is a further improvement based on embodiment 2, which is specifically as follows:

[0060] Step 02 specifically includes:

[0061] Step S21: classifying the basic data, behavior characteristic data and vital sign monitoring data into text type data, audio type data and video type data;

[0062] Step S22: taking historical text type data, audio type data and video type data as samples, and constructing and training a risk assessment large model based on a YOLOv7 target detection algorithm;

[0063] Step S23: analyzing the data collected by the data collection unit in real time by using the risk assessment large model, and judging the risk level according to the risk assessment standard.

[0064] Embodiment 4 is a further improvement based on embodiment 3, which is specifically as follows:

[0065] The risk assessment standard in step S23 adopts a suicide risk Columbia Suicide Severity Rating Scale (C-SSRS).

[0066] Embodiment 5, this embodiment is a further improvement made on the basis of Embodiment 1, which is specifically as follows:

[0067] Step S03 specifically includes:

[0068] When it is judged as low risk: no pre-warning notification and intervention behavior; normal state is low risk;

[0069] When it is judged as medium risk: pre-warning notification is made, information and pop-up window reminder are sent to the mobile terminal; at this time, it indicates that the patient may have a suicide risk, which is specifically embodied in that negative emotions have been generated, negative language expression is made, but no specific action is taken at this time, and through the pre-warning notification of medical staff, psychological counseling can be effectively reduced to develop into a high risk hidden danger;

[0070] When it is judged as high risk: pre-warning notification and intervention behavior are made, information and pop-up window reminder are sent to the mobile terminal, the sound and light alarm of the nurse station is started, and the emergency intervention unit is enabled to make corresponding intervention behavior.

[0071] When the patient produces sudden impulsive behavior, the emergency intervention unit can be automatically triggered to make emergency intervention before the medical staff arrive on the scene, which can effectively avoid injury and death caused by jumping from the building.

[0072] Embodiment 6, this embodiment is a further improvement made on the basis of Embodiment 1, which is specifically as follows:

[0073] The emergency intervention unit in step S03 includes:

[0074] Electrically operated opening and closing windows arranged in high-risk areas in the hospital;

[0075] Electrically operated extension blocking nets arranged outside the windows and outside the balcony.

[0076] In specific implementation, the intervention behavior of jumping from the window for suicide adopts automatic adjustment of the opening angle of the window, only a gap of 10-15 cm is reserved, and at the same time, the electrically operated extension blocking net is extended, which has the effect of secondary protection; balcony jumping: the electrically operated extension blocking net is extended.

[0077] Embodiment 7, this embodiment is a further improvement made on the basis of Embodiment 2, which is specifically as follows:

[0078] The behavior characteristic data is also derived from the thermal imager arranged in the bathroom, which serves the purpose of protecting the privacy of the patient.

[0079] Embodiment 8, this embodiment is a further improvement made on the basis of Embodiment 1, which is specifically as follows:

[0080] Further including the following steps:

[0081] Step S05: The doctor marks and corrects the correctness of the historical evaluation record, the historical warning record and the historical intervention record in the data management unit, and optimizes and upgrades through the dynamic learning unit. Through correction and learning, the risk assessment unit can be continuously improved, and the accuracy of the risk assessment unit can be improved.

[0082] Embodiment 9, a suicide risk warning system, based on the suicide risk warning method of any one of embodiments 1 to 8, comprising a mobile terminal, and a data acquisition unit, a risk assessment unit, a risk warning unit, an emergency intervention unit and a data management unit connected in turn by signals, the risk warning unit is wirelessly connected with the mobile terminal;

[0083] The data acquisition unit is used for collecting basic data, behavior characteristic data and vital sign data of the patient.

[0084] The risk assessment unit is used for integrating and analyzing the data collected by the data acquisition unit, and judging the risk level.

[0085] The risk warning unit is used for issuing corresponding warning notifications to the mobile terminal or enabling the emergency intervention unit to make corresponding intervention behaviors based on the risk level.

[0086] The data management unit is used for archiving and storing the data collected by the data acquisition unit, the risk level generated by the risk assessment unit, and the intervention record of the emergency intervention unit.

[0087] Embodiment 10, this embodiment is a further improvement based on embodiment 9, and the specific embodiments are as follows:

[0088] The emergency intervention unit comprises:

[0089] The electrically operated opening and closing window arranged in the high-risk area of the hospital is used for closing the window according to the risk level to prevent the patient from falling from the building;

[0090] The electrically operated stretching barrier net arranged outside the window and outside the balcony is used for stretching the barrier net according to the risk level to prevent the patient from falling from the building;

[0091] The data acquisition unit comprises:

[0092] The visual recognition camera arranged in the risk area and the sound pickup device arranged in the ward are used for monitoring whether the patient has suicidal behavior and suicidal tendency including climbing the window and the balcony, self-injury with a knife, micro-expression and negative language;

[0093] The smart wearable device worn by the patient is used for collecting the heart rate, pulse and blood pressure data of the patient.

[0094] The thermal imager arranged in the bathroom is used for monitoring whether the patient produces a suicide action in the bathroom;

[0095] The risk early warning unit comprises:

[0096] The sound and light alarm arranged in the nurse station is used for sound and light alarm according to the risk level evaluated by the risk evaluation unit.

[0097] In the specific implementation, the data acquisition unit further comprises a metal detection security door arranged at the entrance and exit of the hospital and the ward door, and is used for detecting whether the patient or the patient's family member carries a knife.

[0098] Although the embodiments of the present application have been shown and described above, it should be understood that the above-mentioned embodiments are exemplary and cannot be understood as limiting the present application, and those skilled in the art can make changes, modifications, replacements and modifications to the above-mentioned embodiments within the scope of the present application.

Claims

1. A suicide risk early warning method based on hospitalized patients, characterized in that, Includes the following steps: Step S01: Collect the patient's basic data, behavioral characteristics data, and vital signs data using the data acquisition unit; Step S02: The risk assessment unit integrates and analyzes the data collected by the data acquisition unit to determine the risk level; Step S03: Based on the risk level, the risk warning unit sends a corresponding warning notification to the mobile terminal, or activates the emergency intervention unit to take corresponding intervention actions; Step S04: The data management unit archives, manages, and stores the data collected by the data acquisition unit, the risk level generated by the risk assessment unit, and the intervention records of the emergency intervention unit.

2. The suicide risk early warning method based on hospitalized patients according to claim 1, characterized in that, The data collected by the data acquisition unit in step S01 specifically includes: The patient's basic data comes from the patient's demographic data, disease diagnosis data, and historical assessment data, and is used to determine whether the patient has potential reasons for suicide. The behavioral data comes from visual recognition cameras in the risk area and microphones in the wards to monitor whether patients have suicidal behaviors and tendencies, including climbing windows and balconies, self-harm with knives, micro-expressions and negative language. The vital signs data are obtained from the smart wearable device worn by the patient, which is used to collect data including the patient's heart rate, pulse, and blood pressure.

3. The suicide risk early warning method based on hospitalized patients according to claim 2, characterized in that, Step 02 specifically includes: Step S21: Classify the basic data, the behavioral feature data, and the vital sign monitoring data into text type data, audio type data, and video type data; Step S22: Using historical text data, audio data, and video data as samples, construct and train a large-scale risk assessment model based on the YOLOv7 object detection algorithm; Step S23: Analyze the data collected in real time by the data acquisition unit using the risk assessment model, and determine the risk level based on the risk assessment criteria.

4. The suicide risk early warning method based on hospitalized patients according to claim 3, characterized in that, The risk assessment criteria in step S23 adopt the Columbia Suicide Severity Rating Scale (C-SSRS).

5. A suicide risk early warning method based on hospitalized patients according to claim 1, characterized in that, Step S03 specifically includes: When the risk level is assessed as low: no early warning or intervention will be issued; When the risk level is determined to be medium: issue an early warning notification, send a message and pop-up reminder to mobile devices; When a high-risk situation is identified: issue early warnings and take intervention measures, send messages and pop-up reminders to mobile devices, activate the sound and light alarm at the nurse station, and activate the emergency intervention unit to take corresponding intervention measures.

6. The suicide risk early warning method based on hospitalized patients according to claim 1, characterized in that, The emergency intervention unit in step S03 includes: Electric windows installed in high-risk areas of the hospital; Motorized extendable barrier nets are installed on the outside of windows and balconies.

7. A suicide risk early warning method based on hospitalized patients according to claim 2, characterized in that, The behavioral data also comes from thermal imaging cameras installed in the bathroom.

8. A suicide risk early warning method based on hospitalized patients according to claim 1, characterized in that, It also includes the following steps: Step S05: Doctors mark and correct the accuracy of historical assessment records, historical warning records, and historical intervention records in the data management unit, and optimize and upgrade them through the dynamic learning unit.

9. A suicide risk early warning system, characterized in that, The suicide risk warning method based on any one of claims 1 to 8 includes a mobile terminal, and a data acquisition unit, a risk assessment unit, a risk warning unit, an emergency intervention unit, and a data management unit connected in sequence by signals, wherein the risk warning unit is wirelessly connected to the mobile terminal. The data acquisition unit is used to collect the patient's basic data, behavioral characteristic data, and vital sign data. The risk assessment unit is used to integrate and analyze the data collected by the data acquisition unit to determine the risk level; The risk warning unit is used to issue a corresponding warning notification to the mobile terminal based on the risk level, or to activate the emergency intervention unit to take corresponding intervention actions. The data management unit is used to archive, manage, and store data including data collected by the data acquisition unit, risk levels generated by the risk assessment unit, and intervention records from the emergency intervention unit.

10. A suicide risk early warning system according to claim 9, characterized in that, The emergency intervention unit includes: Electric windows installed in high-risk areas of the hospital are used to close the windows according to the risk level to prevent patients from falling. The electrically extendable barrier nets installed on the outside of windows and balconies are used to extend the barrier nets according to the risk level to prevent patients from falling. The data acquisition unit includes: Visual recognition cameras installed in high-risk areas and microphones installed in wards are used to monitor whether patients exhibit suicidal behaviors and tendencies, including climbing windows and balconies, self-harm with knives, micro-expressions, and negative language. The smart wearable device worn by the patient is used to collect data including the patient's heart rate, pulse, and blood pressure. Thermal imaging devices installed in bathrooms are used to monitor whether patients engage in suicidal behavior in the bathroom. The risk warning unit includes: The audible and visual alarm installed at the nurses' station is used to trigger an audible and visual alarm based on the risk level assessed by the risk assessment unit.

Images