A respiratory data alerting system for a critically ill patient

Abstract

The application discloses a kind of respiratory data reminding system of respiratory critical illness patient, belongs to respiratory critical illness technical field, comprising: respiratory acquisition module, for collecting the real-time respiratory data of respiratory critical illness patient;Data processing module is handled and is stored for the real-time respiratory data of respiratory critical illness patient;Respiratory analysis module is analyzed for the real-time respiratory data of respiratory critical illness patient;Reminding intervention module is for the abnormal behavior of respiratory critical illness patient's respiratory warning and reminding and intervention control.The application solves the problem that existing cannot be monitored and early warning reminded in real time to the respiratory condition of respiratory critical illness patient.The application can be monitored and early warning reminded in real time to the respiratory condition of respiratory critical illness patient, can find abnormal behavior in time, and can be intervened and controlled in time to respiratory critical illness patient, to a certain extent, improve the survival rate of patient.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of respiratory critical illness, in particular to a respiratory data reminding system for respiratory critical illness patients. BACKGROUND

[0002] Respiratory critical illness is a disease caused by lung infection, which refers to a clinical sign of severe, variable and life-threatening critical condition, which may be accompanied by dyspnea and low blood oxygen saturation, and may be accompanied by respiratory failure or multiple organ failure, which may endanger life. With the progress of modern medical technology, the monitoring and treatment of respiratory critical illness patients are becoming more and more precise.

[0003] The existing respiratory critical illness patients cannot monitor and early warn the respiratory condition of the respiratory critical illness patients in real time when being treated, cannot timely find abnormal respiratory behavior, and cannot timely intervene and control the respiratory critical illness patients, thereby reducing the survival rate of patients. SUMMARY

[0004] The present application aims to provide a respiratory data reminding system for respiratory critical illness patients, which can monitor and early warn the respiratory condition of the respiratory critical illness patients in real time, can timely find abnormal respiratory behavior, and can timely intervene and control the respiratory critical illness patients, thereby improving the survival rate of patients to a certain extent and solving the problems in the above background.

[0005] To achieve the above-mentioned purpose, the present application provides the following technical scheme:

[0006] A respiratory data reminding system for respiratory critical illness patients, comprising:

[0007] A respiration collecting module for collecting the respiratory condition of the respiratory critical illness patients in real time by using an intelligent sensor, and determining real-time respiratory data of the respiratory critical illness patients based on the intelligent sensor;

[0008] A data processing module for cleaning the real-time respiratory data of the respiratory critical illness patients, removing inconsistent data, invalid values and missing values in the real-time respiratory data of the respiratory critical illness patients, and storing the cleaned real-time respiratory data of the respiratory critical illness patients;

[0009] A respiration analyzing module for analyzing the real-time respiratory data of the respiratory critical illness patients, judging whether the respiratory critical illness patients have abnormal respiratory behavior, and determining the respiration analysis result of the respiratory critical illness patients;

[0010] A reminding and intervening module for early warning and intervening the abnormal respiratory behavior of the respiratory critical illness patients, so as to make the respiratory critical illness patients breathe normally.

[0011] Preferably, the respiratory acquisition module comprises:

[0012] a frequency monitoring unit for monitoring and continuously acquiring the respiratory frequency of the respiratory critical patient in real time based on the intelligent sensor, and obtaining the respiratory frequency parameter of the respiratory critical patient;

[0013] a depth monitoring unit for monitoring and continuously acquiring the respiratory depth of the respiratory critical patient in real time based on the intelligent sensor, and obtaining the respiratory depth parameter of the respiratory critical patient;

[0014] an oxygen monitoring unit for monitoring and continuously acquiring the oxygen saturation of the respiratory critical patient in real time based on the intelligent sensor, and obtaining the oxygen saturation parameter of the respiratory critical patient;

[0015] an arterial blood gas monitoring unit for monitoring and continuously acquiring the arterial blood gas of the respiratory critical patient in real time based on the intelligent sensor, and obtaining the arterial blood gas parameter of the respiratory critical patient;

[0016] wherein, based on the respiratory frequency parameter, the respiratory depth parameter, the oxygen saturation parameter and the arterial blood gas parameter, the real-time respiratory data of the respiratory critical patient based on the intelligent sensor is determined.

[0017] Preferably, the data processing module comprises:

[0018] a data cleaning unit for cleaning the real-time respiratory data of the respiratory critical patient;

[0019] obtaining the real-time respiratory data of the respiratory critical patient based on the intelligent sensor;

[0020] performing consistency check on each parameter of the real-time respiratory data of the respiratory critical patient;

[0021] checking whether there is inconsistent data useless for respiratory data warning in the real-time respiratory data of the respiratory critical patient, and if there is inconsistent data, removing the inconsistent data in the real-time respiratory data of the respiratory critical patient;

[0022] performing invalid value and missing value check on each parameter of the real-time respiratory data of the respiratory critical patient;

[0023] checking whether there is invalid value and missing value useless for respiratory data warning in the real-time respiratory data of the respiratory critical patient, and if there is invalid value and missing value, removing the invalid value and missing value in the real-time respiratory data of the respiratory critical patient;

[0024] determining the real-time respiratory data of the respiratory critical patient useful for respiratory data warning.

[0025] Preferably, the data processing module further comprises:

[0026] a data storage unit configured to store real-time respiratory data of the respiratory critical patient;

[0027] obtain real-time respiratory data of the respiratory critical patient useful for respiratory data reminding after cleaning;

[0028] group the real-time respiratory data of the respiratory critical patient useful for respiratory data reminding according to different times, and store the grouped real-time respiratory data of the respiratory critical patient.

[0029] Preferably, the respiratory analysis module comprises:

[0030] a threshold setting unit configured to set threshold respiratory data of the respiratory critical patient;

[0031] pre-set the threshold respiratory data of the respiratory critical patient according to the respiratory data reminding needs of the respiratory critical patient, and store the pre-set threshold respiratory data of the respiratory critical patient;

[0032] a respiratory analysis unit configured to analyze the real-time respiratory data of the respiratory critical patient;

[0033] extract the threshold respiratory data of the respiratory critical patient;

[0034] analyze the real-time respiratory data of the respiratory critical patient according to the threshold respiratory data of the respiratory critical patient, judge whether the respiratory critical patient has respiratory abnormal behavior, and determine the respiratory analysis result of the respiratory critical patient.

[0035] Preferably, judging whether the respiratory critical patient has respiratory abnormal behavior comprises:

[0036] when the real-time respiratory data of the respiratory critical patient is within the threshold respiratory data range of the respiratory critical patient, the respiratory analysis result of the respiratory critical patient is that the respiratory critical patient does not have respiratory abnormal behavior;

[0037] when the real-time respiratory data of the respiratory critical patient is not within the threshold respiratory data range of the respiratory critical patient, the respiratory analysis result of the respiratory critical patient is that the respiratory critical patient has respiratory abnormal behavior.

[0038] Preferably, the reminding intervention module comprises:

[0039] a pre-warning reminding unit configured to immediately issue pre-warning reminding information according to the respiratory analysis result of the respiratory critical patient, pre-warn the respiratory abnormal behavior of the respiratory critical patient, and remind medical staff to timely pay attention to the situation of the respiratory critical patient;

[0040] The intervention control module is configured to intervene and control the abnormal breathing behavior of the respiratory critical patient.

[0041] The device of the respiratory critical patient and the device of the medical staff are connected through the wireless network, and the device of the respiratory critical patient and the device of the medical staff are remotely intervened to control the operation of the breathing machine and help the respiratory critical patient to breathe normally.

[0042] Preferably, the reminding intervention module further comprises:

[0043] The record display unit is configured to record the real-time breathing data and the early warning reminding information of the respiratory critical patient, and visually display the recorded real-time breathing data and the early warning reminding information of the respiratory critical patient, so that the medical staff can view and monitor the condition of the respiratory critical patient in real time.

[0044] Preferably, the respiratory data reminding system of the respiratory critical patient further comprises a supervision module configured to supervise and analyze the behavior of the associated personnel after the early warning reminding;

[0045] The supervision module supervises and analyzes the behavior of the associated personnel, including:

[0046] Obtaining the location of the associated personnel and tracking the location to determine whether the location change conforms to the pre-configured rule, and if not, reminding again;

[0047] And / or,

[0048] Planning a path based on the location of the associated personnel and a pre-configured map;

[0049] Analyzing the planned path based on the historical movement data of the associated personnel to determine a movement path;

[0050] Determining an arrival time based on the movement path and the movement speed;

[0051] If the arrival time is within the threshold time corresponding to the respiratory critical patient, no reminding is performed; otherwise, reminding is performed;

[0052] The arrival time is determined based on the movement path and the movement speed, including:

[0053] Segmenting the movement path based on path parameters and determining the movement speed corresponding to each segment respectively;

[0054] Determining the transition mode between each segment and determining the transition time according to the transition mode and a pre-configured transition time corresponding table;

[0055] According to the length of each segment, the movement speed and the transition time between each segment, the arrival time is calculated, and the calculation formula is as follows:

[0056] ;

[0057] In the formula, denotes the arrival time; denotes the length of the th road section; denotes the moving speed of the th road section; denotes the transition time between the th road section and the th road section, configured when , that is, ; denotes the total number of road sections.

[0058] Preferably, the supervision module is further configured to analyze the states and positions of all the patients associated with each associated personnel, determine a standby area, analyze the standby area, determine an optimal standby position, and output the optimal standby position.

[0059] The supervision module performs the following operations:

[0060] Based on the pre-configured patient analysis library, the state data of the patients is analyzed to determine the threshold radius of standby and the range of standby area;

[0061] The intersection area of the range of standby area of each patient is taken as the standby area;

[0062] The standby area is sampled to obtain a plurality of analysis points;

[0063] According to the distance of each analysis point from each patient and the distance of each analysis point from each pre-configured facility point, the priority of each analysis point is evaluated, and the evaluation formula is as follows:

[0064] ;

[0065] In the formula, denotes the priority; denotes the distance of the analysis point from the th patient; denotes the distance of the analysis point from the th facility point; is a pre-configured conversion coefficient corresponding to the th patient; is a pre-configured conversion coefficient corresponding to the th facility point; is the number of patients associated with the associated personnel; is the total number of facility points;

[0066] The point with the largest priority value is taken as the best standby position and output.

[0067] Compared with the prior art, the present application has the following advantages:

[0068] 1、The present application collects the breathing condition of the respiratory critical patient in real time through the intelligent sensor, determines the real-time breathing data of the respiratory critical patient based on the intelligent sensor, removes the inconsistent data, invalid value and missing value in the real-time breathing data of the respiratory critical patient by cleaning the real-time breathing data of the respiratory critical patient, can improve the analysis accuracy and analysis efficiency of the subsequent real-time breathing data of the respiratory critical patient, and stores the cleaned real-time breathing data of the respiratory critical patient, which is convenient for subsequent checking and analysis.

[0069] 2、The present application analyzes the real-time breathing data of the respiratory critical patient, judges whether the respiratory critical patient has abnormal breathing behavior, determines the breathing analysis result of the respiratory critical patient, and immediately issues a warning reminder information when the respiratory critical patient has abnormal breathing behavior, so as to warn the abnormal breathing behavior of the respiratory critical patient, remind the medical staff to pay attention to the respiratory critical patient in time, connect the equipment of the respiratory critical patient and the medical staff through a wireless network, and remotely intervene the equipment of the respiratory critical patient and the medical staff to control the operation of the breathing machine, help the respiratory critical patient to breathe normally, can monitor and warn the respiratory condition of the respiratory critical patient in real time, can timely find the abnormal breathing behavior, and can timely intervene and control the respiratory critical patient, which improves the survival rate of the patient to a certain extent. BRIEF DESCRIPTION OF DRAWINGS

[0070] FIG. 1 The structural framework diagram of the respiratory data warning system for the respiratory critical patient of the present application is shown in the figure.

[0071] FIG. 2 The algorithm flowchart of the respiratory data warning system for the respiratory critical patient of the present application is shown in the figure. DETAILED DESCRIPTION

[0072] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0073] In order to solve the problem that the existing respiratory critical patient cannot monitor and early warn the respiratory condition of the respiratory critical patient in real time, cannot find abnormal respiratory behavior in time, and cannot intervene and control the respiratory critical patient in time, thereby reducing the survival rate of the patient, please refer to FIGS. 1-2 The embodiment provides the following technical scheme:

[0074] A respiratory data reminding system for a respiratory critical patient, comprising a respiratory acquisition module, a data processing module, a respiratory analysis module and a reminding intervention module.

[0075] It should be noted that the real-time respiratory data of the respiratory critical patient based on the intelligent sensor is acquired through the respiratory acquisition module; the real-time respiratory data of the respiratory critical patient is cleaned and stored through the data processing module; the real-time respiratory data of the respiratory critical patient is analyzed through the respiratory analysis module to determine whether the respiratory critical patient has abnormal respiratory behavior; the abnormal respiratory behavior of the respiratory critical patient is early warned and intervened and controlled through the reminding intervention module, so that the respiratory critical patient can breathe normally, the respiratory condition of the respiratory critical patient can be monitored and early warned in real time, abnormal respiratory behavior can be found in time, and the respiratory critical patient can be intervened and controlled in time, thereby improving the survival rate of the patient to a certain extent.

[0076] The respiratory acquisition module is configured to acquire the respiratory condition of the respiratory critical patient in real time based on the intelligent sensor, and determine the real-time respiratory data of the respiratory critical patient based on the intelligent sensor.

[0077] In the embodiment, the respiratory acquisition module comprises:

[0078] The frequency monitoring unit is configured to monitor and continuously acquire the respiratory frequency of the respiratory critical patient in real time based on the intelligent sensor, and acquire the respiratory frequency parameter of the respiratory critical patient.

[0079] It should be noted that the respiratory frequency is a medical term for describing the number of breaths per minute, and one fluctuation of the chest is one breath, that is, one inhalation and one exhalation, and the number of breaths per minute is called the respiratory frequency.

[0080] The depth monitoring unit is configured to monitor and continuously acquire the respiratory depth of the respiratory critical patient in real time based on the intelligent sensor, and acquire the respiratory depth parameter of the respiratory critical patient.

[0081] It should be noted that the respiratory depth refers to the intensity of breathing, that is, the exchange degree of respiratory gas during quiet breathing, and the respiratory movement is to expand and contract the chest by means of the contraction and relaxation of the diaphragm and intercostal muscles and other respiratory muscles to drive the expansion and contraction of the lung.

[0082] a blood oxygen monitoring unit configured to monitor and continuously collect, based on the intelligent sensor, the blood oxygen saturation of the respiratory critical patient in real time, and obtain a blood oxygen saturation parameter of the respiratory critical patient;

[0083] It should be noted that the blood oxygen saturation is the percentage of the volume of oxygenated hemoglobin combined with oxygen in the blood to the total volume of hemoglobin that can be combined, that is, the concentration of blood oxygen in the blood, which is an important physiological parameter of respiratory circulation. The metabolic process of the human body is a biological oxidation process, and the oxygen required in the metabolic process enters the human body through the respiratory system, combines with hemoglobin in red blood cells to form oxygenated hemoglobin, and is then transported to various tissues and cells in the human body. The ability of blood to carry and transport oxygen is measured by blood oxygen saturation.

[0084] an arterial blood gas monitoring unit configured to monitor and continuously collect, based on the intelligent sensor, the arterial blood gas of the respiratory critical patient in real time, and obtain an arterial blood gas parameter of the respiratory critical patient;

[0085] It should be noted that the arterial blood gas is the dissolved gas component in the arterial blood. For a healthy person, the main components are nitrogen, oxygen, and carbon dioxide, among which the oxygen partial pressure is 80-100 mmHg, and the carbon dioxide partial pressure is 35-45 mmHg. Arterial blood gas analysis refers to the technical process of analyzing various gases, different types of gases, and acidic and basic substances.

[0086] The real-time respiratory data of the respiratory critical patient based on the intelligent sensor is determined based on the respiratory rate parameter, the respiratory depth parameter, the blood oxygen saturation parameter, and the arterial blood gas parameter.

[0087] It should be noted that in this embodiment, the real-time respiratory data of the respiratory critical patient based on the intelligent sensor is the real-time respiratory rate parameter, the respiratory depth parameter, the blood oxygen saturation parameter, and the arterial blood gas parameter of the respiratory critical patient.

[0088] The intelligent sensor is a sensor with information processing function. The intelligent sensor has a microprocessor and has the ability to collect, process, and exchange information. It is a product of the combination of sensor integration and microprocessor. Therefore, the intelligent sensor can monitor and continuously collect the respiratory rate, the respiratory depth, the blood oxygen saturation, and the arterial blood gas of the respiratory critical patient in real time, and further obtain the respiratory rate parameter, the respiratory depth parameter, the blood oxygen saturation parameter, and the arterial blood gas parameter of the respiratory critical patient. This can provide data support for the respiratory data reminder of the respiratory critical patient and facilitate the timely discovery of abnormal respiratory behaviors of the respiratory critical patient.

[0089] The data processing module is configured to clean real-time respiratory data of the respiratory critical patient, remove inconsistent data, invalid values and missing values in the real-time respiratory data of the respiratory critical patient, and store the cleaned real-time respiratory data of the respiratory critical patient.

[0090] In this embodiment, the data processing module comprises:

[0091] The data cleaning unit is configured to clean the real-time respiratory data of the respiratory critical patient.

[0092] The real-time respiratory data of the respiratory critical patient based on the intelligent sensor is acquired.

[0093] Each parameter of the real-time respiratory data of the respiratory critical patient is subjected to consistency checking.

[0094] It is checked whether there is inconsistent data useless for the respiratory data in the real-time respiratory data of the respiratory critical patient, and if there is inconsistent data, the inconsistent data in the real-time respiratory data of the respiratory critical patient is removed.

[0095] Each parameter of the real-time respiratory data of the respiratory critical patient is subjected to invalid value and missing value checking.

[0096] It is checked whether there is invalid value and missing value useless for the respiratory data in the real-time respiratory data of the respiratory critical patient, and if there is invalid value and missing value, the invalid value and missing value in the real-time respiratory data of the respiratory critical patient is removed.

[0097] The real-time respiratory data of the respiratory critical patient useful for the respiratory data is determined.

[0098] It should be noted that data cleaning refers to a process of processing and organizing original data in the data analysis process to improve the quality and availability of data. It is a key step in data preprocessing, and the main purpose is to remove errors, incomplete, inaccurate and irrelevant data to ensure the quality and accuracy of the data, so that it is more suitable for data analysis or data mining.

[0099] Among them, the consistency check is to check whether the data meets the requirements according to the reasonable value range and the mutual relationship of each parameter, and to find the data that exceeds the normal range, is logically unreasonable or contradictory; For example, the variable measured by the 1-7 level scale appears 0 value, and the weight appears negative number, which should be considered as exceeding the normal value range; SPSS, SAS and Excel computer software can automatically identify each variable value exceeding the range according to the defined value range; The answers with logical inconsistency may appear in many forms: for example, many survey objects say they drive to work, but report no car; Or the survey objects report that they are heavy users and users of a certain brand, but at the same time give very low scores on the familiarity scale.

[0100] Therefore, by cleaning the real-time respiratory data of the respiratory critical patient, the inconsistent data, invalid values and missing values in the real-time respiratory data of the respiratory critical patient can be removed, and the real-time respiratory data of the respiratory critical patient useful for respiratory data reminding can be determined, so that the processing accuracy and efficiency of the subsequent real-time respiratory data of the respiratory critical patient can be improved, and the subsequent analysis of the real-time respiratory data of the respiratory critical patient can be facilitated.

[0101] In the embodiment, the data processing module further comprises:

[0102] The data storage unit is configured to store the real-time respiratory data of the respiratory critical patient.

[0103] The real-time respiratory data of the respiratory critical patient useful for respiratory data reminding after cleaning is obtained.

[0104] The real-time respiratory data of the respiratory critical patient useful for respiratory data reminding is grouped according to time, and the grouped real-time respiratory data of the respiratory critical patient is stored.

[0105] The respiratory analysis module is configured to analyze the real-time respiratory data of the respiratory critical patient, judge whether the respiratory critical patient has abnormal respiratory behavior, and determine the respiratory analysis result of the respiratory critical patient.

[0106] In the embodiment, the respiratory analysis module comprises:

[0107] The threshold setting unit is configured to set the threshold respiratory data of the respiratory critical patient.

[0108] The threshold respiratory data of the respiratory critical patient is set in advance according to the respiratory data reminding demand of the respiratory critical patient, and the set threshold respiratory data of the respiratory critical patient is stored.

[0109] The respiratory analysis unit is configured to analyze the real-time respiratory data of the respiratory critical patient.

[0110] extracting threshold respiratory data of the respiratory critically ill patient;

[0111] analyzing real-time respiratory data of the respiratory critically ill patient according to the threshold respiratory data of the respiratory critically ill patient, judging whether the respiratory critically ill patient has respiratory abnormal behavior, and determining a respiratory analysis result of the respiratory critically ill patient.

[0112] In this embodiment, judging whether the respiratory critically ill patient has respiratory abnormal behavior comprises:

[0113] When the real-time respiratory data of the respiratory critically ill patient is within the threshold respiratory data range of the respiratory critically ill patient, the respiratory analysis result of the respiratory critically ill patient is that the respiratory critically ill patient does not have respiratory abnormal behavior.

[0114] When the real-time respiratory data of the respiratory critically ill patient is not within the threshold respiratory data range of the respiratory critically ill patient, the respiratory analysis result of the respiratory critically ill patient is that the respiratory critically ill patient has respiratory abnormal behavior.

[0115] Specifically, according to the threshold respiratory data of the respiratory critically ill patient, the real-time respiratory data of the respiratory critically ill patient is analyzed, wherein the respiratory analysis result of the respiratory critically ill patient is shown in Table 1:

[0116] Table 1: Respiratory analysis result of the respiratory critically ill patient

[0117] analyzing real-time respiratory data of a respiratory critically ill patient against threshold respiratory data of the respiratory critically ill patient respiratory analysis result of the respiratory critically ill patient the real-time respiratory data of the respiratory critically ill patient is within the threshold respiratory data range of the respiratory critically ill patient the respiratory critically ill patient is free of respiratory abnormal behavior the real-time respiratory data of the respiratory critically ill patient is not within the threshold respiratory data range of the respiratory critically ill patient the respiratory critically ill patient is exhibiting respiratory abnormal behavior

[0118] Therefore, according to the threshold respiratory data of the respiratory critically ill patient, the real-time respiratory data of the respiratory critically ill patient is analyzed, whether the respiratory critically ill patient has respiratory abnormal behavior is judged, and then the respiratory analysis result of the respiratory critically ill patient is determined, which can monitor the respiratory condition of the respiratory critically ill patient in real time, and facilitate timely early warning, reminding and intervention control of the respiratory critically ill patient.

[0119] The reminding intervention module is configured to perform early warning, reminding and intervention control on the respiratory abnormal behavior of the respiratory critically ill patient, so as to make the respiratory critically ill patient breathe normally.

[0120] In this embodiment, the reminding intervention module comprises:

[0121] The early warning reminding unit is configured to immediately issue early warning reminding information according to the respiratory analysis result of the respiratory critically ill patient, to perform early warning on the respiratory abnormal behavior of the respiratory critically ill patient, and to remind medical staff to pay attention to the respiratory critically ill patient in time.

[0122] The intervention control module is configured to perform intervention control on the respiratory abnormal behavior of the respiratory critically ill patient.

[0123] The device of the respiratory critical patient and the medical staff is connected through a wireless network, and the device of the respiratory critical patient and the medical staff is remotely intervened, the ventilator operation is controlled, and the respiratory critical patient is assisted to breathe normally.

[0124] In the embodiment, the reminding intervention module further comprises:

[0125] The record display unit is configured to record the real-time respiratory data and the early warning reminding information of the respiratory critical patient, and visually display the recorded real-time respiratory data and early warning reminding information of the respiratory critical patient, so that the medical staff can view and monitor the condition of the respiratory critical patient in real time.

[0126] In one embodiment, the respiratory data reminding system of the respiratory critical patient further comprises a supervision module configured to supervise and analyze the behavior of the associated personnel after the early warning reminding;

[0127] The supervision module supervises and analyzes the behavior of the associated personnel, including:

[0128] The location of the associated personnel is acquired and tracked, and it is determined whether the location change conforms to the preconfigured rule, and the reminding is performed again when it does not conform. Specifically, whether the location change conforms to the preconfigured rule is determined by: sampling the location change data for a preset number of times (3 times or more than 3 times), and the sampling time interval is set to any one of 1 second to 30 seconds; determining the distance of the location change data corresponding to the patient's location in each sampling, and when the distance obtained by adjacent two samplings gradually decreases, it is determined that it conforms to the preconfigured rule; when the distance obtained by adjacent two samplings gradually increases, it is determined that it does not conform to the preconfigured rule; when the number of times of distance increase in the total sampling times is less than or equal to the number of times of distance decrease, it is determined to conform; when the number of times of distance increase in the total sampling times is greater than the number of times of distance decrease, it is determined not to conform;

[0129] And / or,

[0130] Based on the location of the associated personnel and the preconfigured map, a path is planned; the map is preconfigured storage, and when the path is planned, the location of the associated personnel is taken as the starting point and the location of the patient for early warning reminding is taken as the end point to obtain multiple paths;

[0131] Based on the historical moving data of the associated personnel, the planned path is analyzed to determine the moving path; the analysis of the historical moving data mainly analyzes the personal preference of the associated personnel to obtain a moving path that conforms to the personal preference of the associated personnel; that is, when there are multiple paths, one of which is frequently sampled by the associated personnel, it is determined to be the moving path;

[0132] Based on the moving path and the moving speed, the arrival time is determined;

[0133] When the arrival time is within the threshold time configured for critically ill respiratory patients, no reminder will be given; otherwise, a reminder will be given. By reminding, the relevant personnel are urged to move as quickly as possible and increase the movement speed to reduce the corresponding movement time, thereby improving the effectiveness of the early warning reminder response;

[0134] The arrival time is determined based on the moving path and moving speed, including:

[0135] The mobile path is segmented based on path parameters and the corresponding moving speed of each segment is determined. Segment analysis is performed on different types of mobile path segments (stairs, corridors, elevators, before and after gates, etc.), which improves the accuracy and effectiveness of arrival time analysis.

[0136] Determine the transition method between each road section and determine the transition time based on the transition method and the pre-configured transition time mapping table. For example, the transition method may include passing through a gate or waiting for an elevator. When calculating the arrival time, the transition time is taken into account to further improve the accuracy of the arrival time prediction.

[0137] The arrival time is calculated based on the length of each road section, the moving speed, and the transition time between each road section. The calculation formula is as follows:

[0138] ;

[0139] Where, Indicates arrival time; Indicates the The length of the road section; Indicates the The moving speed of each road segment; Indicates the Section and The transition time between sections is configured. When ; Indicates the total number of road sections. The speed of the associated person on each road section. Except for the first section of the movement path, which is the current speed, the speed of the remaining sections is obtained based on the average speed of the associated person's historical movement data on the same type of road sections.

[0140] The supervision module in the embodiment is to analyze the behavior of the associated personnel after the early warning reminder, so as to determine whether it is necessary to make a second early warning reminder. The supervision can start from the position and the predicted arrival time. For the supervision of the position, it is mainly determined whether the associated personnel moves towards the position of the patient who makes the early warning reminder; and for the supervision of the arrival time, it is determined whether the associated personnel can arrive at the position of the patient who makes the early warning reminder in time, so as to effectively provide timely intervention measures for the patient.

[0141] In order to enable the associated personnel to effectively cope with the emergency of each associated patient, it is necessary to know the best standby position. How to determine the best standby position, in an embodiment, the supervision module is further used to analyze the state and position of all the associated patients of each associated personnel, determine the standby area, analyze the standby area, determine the best standby position and output;

[0142] The supervision module performs the following operations:

[0143] Based on the pre-configured patient analysis library, the state data of the patient is analyzed to determine the standby threshold radius and the standby area range; the specific analysis process is as follows: the feature parameters of the patient state data are extracted, and then the corresponding threshold radius of the associated personnel is retrieved from the patient analysis library based on the extracted feature parameters; wherein the extracted feature parameters include: parameters representing the type of surgery, parameters representing the time of surgery, parameters representing the age of the patient, parameters representing the weight of the patient, parameters representing the evaluation of the surgeon on the patient, etc.

[0144] The intersection area of the standby area ranges of the patients is taken as the standby area; the standby area belongs to the standby area range of each patient;

[0145] The standby area is sampled to obtain a plurality of analysis points; the standby area is segmented by a preset sampling grid, the intersection points between the grids are determined to obtain the points, and then the positions of the points are analyzed to determine whether they are listed as analysis points according to the analysis results; wherein the analysis steps are as follows: the preset area model is placed on the point of the intersection between the determined grids in the three-dimensional model diagram, and the points that cannot be placed are deleted; then the influence of the placement on the risk of passing is analyzed, and the points whose risk values are greater than the preset risk threshold are deleted, and the remaining points are taken as the analysis points; wherein the judgment of the influence of the placement on the risk of passing includes: determining the minimum width of the passing area after the placement, and determining the risk value based on the minimum width and the pre-configured risk increase table of the inherent parameters corresponding to the point; wherein the inherent parameters include: fields of parameters representing the type of position (passing area, indoor area, etc.), parameters representing the coordinates of the area in each position type, etc.; the area coordinates are obtained by coding the positions according to the relative positions after segmenting each position type.

[0146] According to the distance of each point to be analyzed from each patient and the distance of each point to be analyzed from each pre-configured facility point, a priority value of each point to be analyzed is evaluated, and the evaluation formula is as follows:

[0147]

[0148] In the formula, priority value is represented by P, the distance of the point to be analyzed from the first patient is represented by D1, the distance of the point to be analyzed from the first facility point is represented by D2, the conversion coefficient corresponding to the first patient is represented by K1, the conversion coefficient corresponding to the first facility point is represented by K2, the number of associated patients of the associated personnel is represented by N, and the total number of facility points is represented by M.

[0149] The point to be analyzed with the largest priority value is taken as the best standby position and output.

[0150] It should be noted that the relational terms herein such as first and second and the like are used solely to distinguish one entity or action from another, without necessarily requiring or implying any such actual relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0151] Although the embodiments of the present application have been shown and described, it is to be understood that various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.​​​​​​​​​​​​

Claims

1. A respiratory data reminder system for critically ill patients, characterized in that: include: A respiratory collection module is used to collect the respiratory status of critically ill patients in real time using smart sensors, and determine the real-time respiratory data of critically ill patients based on the smart sensors; A data processing module is used to clean the real-time respiratory data of the critically ill patients, remove inconsistent data, invalid values ​​and missing values ​​in the real-time respiratory data of the critically ill patients, and store the cleaned real-time respiratory data of the critically ill patients; A respiratory analysis module is used to analyze the real-time respiratory data of critically ill patients, determine whether the patients have abnormal breathing behavior, and determine the respiratory analysis results of the critically ill patients; The reminder and intervention module is used to provide early warning reminders and intervention control for abnormal breathing behavior of critically ill patients, so that critically ill patients can breathe normally; It also includes: a supervision module for conducting supervision and analysis on the behavior of related personnel after early warning reminders; The supervision module conducts supervision and analysis on the behavior of related personnel, including: Obtain the location of the associated person and track the location to determine whether the location change meets the pre-configured rules. If not, remind again; The supervision module is also used to analyze the status and location of all patients associated with each associated person and determine the standby area; analyze the standby area, determine the best standby location and output it; The supervision module performs the following operations: Based on the pre-configured patient analysis library, the patient's status data is analyzed to determine the threshold radius of the standby and the range of the standby area; The intersection area of ​​the waiting areas of each patient is taken as the waiting area; Conduct point sampling in the standby area to obtain multiple points to be analyzed; Based on the distance between each point to be analyzed and each patient, and the distance between each point to be analyzed and the pre-configured facility point, the priority value of each point to be analyzed is evaluated. The evaluation formula is as follows: ； Where, Indicates priority value; Indicates the distance between the point to be analyzed and the distance between patients; Indicates the distance between the point to be analyzed and the The distance between the facility locations; For pre-configured Conversion factor for each patient; For the pre-configured corresponding Conversion factor for each facility location; The number of patients associated with the associated person; is the total number of facility points; The point to be analyzed with the largest priority value is taken as the best standby position and output.

2. A respiratory data reminder system for critically ill patients according to claim 1, characterized in that: The respiratory collection module comprises: A frequency monitoring unit is used to monitor and continuously collect the respiratory rate of critically ill patients in real time based on intelligent sensors to obtain respiratory rate parameters of critically ill patients; Depth monitoring unit, used to monitor and continuously collect the breathing depth of critically ill patients in real time based on intelligent sensors, and obtain the breathing depth parameters of critically ill patients; A blood oxygen monitoring unit is used to monitor and continuously collect blood oxygen saturation parameters of critically ill respiratory patients in real time based on intelligent sensors; Arterial blood gas monitoring unit, which is used to monitor and continuously collect arterial blood gas of patients with critical respiratory illness in real time based on intelligent sensors, and obtain arterial blood gas parameters of patients with critical respiratory illness; Among them, the real-time respiratory data of critically ill respiratory patients based on smart sensors are determined based on respiratory rate parameters, respiratory depth parameters, blood oxygen saturation parameters and arterial blood gas parameters.

3. A respiratory data reminder system for critically ill patients according to claim 2, characterized in that: The data processing module includes: Data cleaning unit, used to clean real-time respiratory data of critically ill patients; Obtain real-time respiratory data from critically ill patients based on smart sensors; Perform consistency checks on each parameter of real-time respiratory data of critically ill patients; Checking whether there is inconsistent data in the real-time respiratory data of the critically ill patient that is useless for respiratory data reminder; if there is inconsistent data, removing the inconsistent data in the real-time respiratory data of the critically ill patient; Check invalid and missing values ​​for each parameter of real-time respiratory data of critically ill patients; Check whether there are invalid values ​​and missing values ​​in the real-time respiratory data of the critically ill patient that are useless for respiratory data reminders. If there are invalid values ​​and missing values, remove the invalid values ​​and missing values ​​in the real-time respiratory data of the critically ill patient; Identify real-time respiratory data of critically ill patients that would be useful for respiratory data alerts.

4. A respiratory data reminder system for critically ill patients according to claim 3, characterized in that: The data processing module further includes: A data storage unit, used for storing real-time respiratory data of critically ill patients; Acquire real-time respiratory data of critically ill patients that is useful for respiratory data reminders after cleaning; The real-time respiratory data of the critically ill patients with useful respiratory data reminders are grouped according to time, and the grouped real-time respiratory data of the critically ill patients are stored.

5. A respiratory data reminder system for critically ill patients according to claim 4, characterized in that: The respiratory analysis module comprises: A threshold setting unit, used to set threshold respiratory data for patients with critical respiratory illness; According to the respiratory data reminder requirements of the critically ill respiratory patients, the threshold respiratory data of the critically ill respiratory patients are pre-set, and the set threshold respiratory data of the critically ill respiratory patients are stored; Respiratory analysis unit, used to analyze real-time respiratory data of critically ill patients; Extract threshold respiratory data from critically ill patients; According to the threshold respiratory data of the critically ill respiratory patient, the real-time respiratory data of the critically ill respiratory patient is analyzed to determine whether the critically ill respiratory patient has abnormal respiratory behavior and determine the respiratory analysis result of the critically ill respiratory patient.

6. A respiratory data reminder system for critically ill patients according to claim 5, characterized in that: Determine whether critically ill patients have abnormal respiratory behavior, including: When the real-time respiratory data of the critically ill patient is within the threshold respiratory data range of the critically ill patient, the respiratory analysis result of the critically ill patient is that the critically ill patient does not have abnormal respiratory behavior; When the real-time respiratory data of the critically ill respiratory patient is not within the threshold respiratory data range of the critically ill respiratory patient, the respiratory analysis result of the critically ill respiratory patient is that the critically ill respiratory patient has abnormal respiratory behavior.

7. A respiratory data reminder system for critically ill patients according to claim 6, characterized in that: The reminder intervention module includes: The early warning reminder unit is used to immediately issue early warning reminder information based on the respiratory analysis results of critically ill patients, warn of abnormal respiratory behavior of critically ill patients, and remind medical staff to pay timely attention to the condition of critically ill patients; The intervention and control module is used to intervene and control abnormal respiratory behavior of patients with critical respiratory diseases; Connect the equipment of critically ill respiratory patients and medical staff through a wireless network, remotely intervene in the equipment of critically ill respiratory patients and medical staff, control the operation of the ventilator, and help critically ill respiratory patients breathe normally.

8. A respiratory data reminder system for critically ill patients according to claim 7, characterized in that: The reminder intervention module further includes: The recording and display unit is used to record the real-time respiratory data and early warning reminder information of critically ill respiratory patients, and to visually display the recorded real-time respiratory data and early warning reminder information of critically ill respiratory patients, so that medical staff can view and monitor the condition of critically ill respiratory patients in real time.

9. A respiratory data reminder system for critically ill patients according to claim 8, characterized in that: The supervision module conducts supervision and analysis on the behavior of related personnel, and also includes: Plan routes based on the locations of connected people and pre-configured maps; Analyze the planned path based on the historical movement data of the associated personnel to determine the movement path; Determine arrival time based on movement path and movement speed; When the arrival time is within the threshold time configured for patients with critical respiratory illness, no reminder will be given; otherwise, a reminder will be given; The arrival time is determined based on the moving path and moving speed, including: Segmenting the moving path based on the path parameters and determining the moving speed corresponding to each segment; Determine the transition mode between each road section and determine the transition time according to the transition mode and the pre-configured transition time correspondence table; The arrival time is calculated based on the length of each road section, the moving speed, and the transition time between each road section. The calculation formula is as follows: ； Where, Indicates arrival time; Indicates the The length of the road section; Indicates the The moving speed of each road segment; Indicates the Section and The transition time between sections is configured. When ; Indicates the total number of road segments.

Images