Integrated machine realizing physiological information detection and diaphragm muscle electrical stimulation, and control method thereof

Abstract

An integrated machine realizing physiological information detection and diaphragm muscle electrical stimulation, and a control method thereof. A non-contact physiological information detecting module,

Description

[0001] The present invention belongs to the technical field of life support integrated machine and relates to an integrated machine realizing physiological information detection and diaphragm muscle electrical stimulation, and a control method thereof. BACKGROUND

[0002] The description in this section merely provides background information related to the present invention and does not necessarily constitute the prior art.

[0003] Cardiac arrest is one of the leading causes of death worldwide. Cardiopulmonary resuscitation (CPR) is considered to be an effective treatment for providing a patient with cardiac arrest with minimal perfusion and cardiac and brain cell oxygen delivery. The CPR consists of three parts: external chest compression, defibrillation and ventilation. The external chest compression is provided by an external chest compressor. The external chest compressor ensures the brain perfusion of a patient by providing 100 - 120 times / min of chest compressions with a depth of 5 cm to a patient. The defibrillation is provided by a defibrillator, the defibrillator positions the R wave by detecting a ventricular fibrillation wave and performs a defibrillation operation to recovery normal electrocardio of a patient. The respiratory ventilation is provided by a respirator and the pressure or flow of the respirator is controlled to ensure cardiac and brain cell oxygen delivery during the CPR.

[0004] A photoplethysmography (PPG) technology has been widely applied in clinical applications as a noninvasive method for detecting multiple physiological parameters. The technique detects a pulse wave by wearing a pulse oximeter sensor on a fingertip or an earlobe so as to accurately measure various physiological parameters and has advantages of being noninvasive, convenient and accurate. However, since the sensor needs to be fixed on the earlobe or fingertip with a spring clip, wearing the sensor for a long time can bring human body discomfort and the sensor is particularly not suitable for using under the condition such as burn, scald or open wound. Therefore, how to develop a non-contact physiological parameter detecting method on the basis of the PPG technology is becoming a hot point of research. An imaging photoplethysmography (IPPG) technology has come under this background. The IPPG technology is based on the basic principle of PPG detection, utilizes imaging equipment as a sensor, can realize contact-type blood volume information capture, thus can obtain various physiological information and well makes up the defects of the PPG detection technology. The IPPG technology can simultaneously perform non-contact physiological information detection on various parameters such as blood pressure, blood oxygen, heart rate, respiratory rate and the like, has prominent advantages of being real-time, highly efficient, non-contact and the like, can complete real-time monitoring on multiple physiological parameters of a patient in the CPR process, and provides physiological feedback of various emergency equipment.

[0005] The external chest compressor, the defibrillator and the respirator are independent in the CPR process outside the hospital or in the hospital, cannot effectively communicate with each other and cannot cooperate with each other, and cannot perform real-time intelligent adjustment on the physiology of a patient. Meanwhile, the three emergency equipment are large in size and not beneficial to rapid emergency rescue. In addition to the large size of each emergency equipment and the incapability of communicating among the equipment to perform intelligent cooperative work in the CPR process, the CPR operation also has the defects. During the CPR process, the physiological parameters are not detected in real time and decision making and feedback guidance on the emergency operation are not realized all the time. The compression during the CPR reduces the tidal volume and increases the airway pressure during the ventilation all the time. SUMMARY

[0006] In order to solve the problems, the present invention provides an integrated machine realizing physiological information detection and diaphragm muscle electrical stimulation, and a control method thereof. The present invention integrates a noncontact physiological information detecting module, an external chest compression module, an external defibrillation module, a respiratory ventilation module, a diaphragm muscle electrical stimulation module and a man-machine interaction module. All the modules communicate under the same local area network, can complete intelligent decision making and automatic operation of the system, and can independently or cooperatively control an executing module after analyzing according to actually measured physiological state parameters, thereby realizing first aid and life support.

[0007] According to some embodiments, the present invention uses the following technical solutions:

[0008] An integrated machine realizing physiological information detection and diaphragm muscle electrical stimulation comprises:

[0009] a non-contact physiological information detecting module used for detecting parameters of blood pressure, blood oxygen, respiratory rate, heart rate and body temperature,

[0010] a minimum intelligent decision-making system used for determining whether sudden cardiac arrest occurs or not according to the non-contact physiological information detection parameters and starting a first life support deci si on-making state if the sudden cardiac arrest does not occur to provide a basic respiratory support for a patient;

[0011] entering a second life support decision-making state if the sudden cardiac arrest occurs, continuously performing external chest compression and respiratory ventilation, determining compression parameters and ventilation parameters according to the noncontact physiological information detection parameters, and meanwhile determining whether defibrillation of electrocardio can be performed or not and performing external defibrillation if the defibrillation can be performed; and determining whether high airway pressure occurs or not and starting diaphragm muscle electrical stimulation if the high airway pressure occurs; and

[0012] an executing mechanism used for performing external chest compression, ventilation or / and defibrillation according to the instruction of the minimum intelligent decision-making system.

[0013] As an alternative embodiment, the non-contact physiological information detecting module comprises an IPPG camera and a thermal imaging camera, wherein the IPPG camera is used for detecting the parameters of blood pressure, blood oxygen, respiratory rate and heart rate, and the thermal imaging camera is used for detecting the parameter of body temperature.

[0014] As an alternative embodiment, the executing mechanism comprises an external chest compressor module, an external defibrillation module, a respiratory ventilation module and a diaphragm muscle electrical stimulation module, wherein the external chest compressor module is used for adjusting the depth, the frequency and the compression duty ratio, the external defibrillation module is used for adjusting the defibrillation energy, the respiratory ventilation module is used for adjusting the respiratory flow, the airway pressure and the respiratory time, and the diaphragm muscle electrical stimulation module is used for adjusting the frequency, the waveform and the current amplitude.

[0015] As an alternative embodiment, the minimum intelligent decision-making system is configured to comprise a first deci si on-making subsystem and a second decisionmaking subsystem, wherein the first decision-making subsystem is configured to make a decision by using an expert knowledge base; the second decision-making subsystem is configured to make a decision by using a trained random forest trainer in combination with a multi-criteria decision-making manner; and

[0016] when the non-contact physiological information detection parameters and the information fed back by the executing mechanism meet the requirements of the expert knowledge base, the first decision-making subsystem is preferably selected for making a decision or the second decision-making subsystem is preferably selected for making a decision.

[0017] As an alternative embodiment, the second decision-making subsystem is configured to train the non-contact physiological information detection parameters by using the random forest trainer to obtain a plurality of groups of alternative schemes, determine an optimal decision-making scheme by using the multi-criteria decisionmaking manner, supplement the optimal decision-making scheme and the corresponding non-contact physiological information detection parameters into the expert knowledge base, and update the expert knowledge base.

[0018] As an alternative embodiment, the second decision-making subsystem is configured to form an initial decision-making matrix on the basis of the plurality of groups of alternative schemes, determine a normalized value for each tuple in the matrix, construct a recognition weighted normalized decision-making matrix on the basis of the normalized value, determine to find best and worst options, determine better and worse options, calculate the value of each option, and sort all the alternative schemes by maximizing the value to obtain the optimal decision-making scheme.

[0019] A method for controlling an integrated machine realizing physiological information detection and diaphragm muscle electrical stimulation comprises:

[0020] detecting non-contact physiological information detection parameters of blood pressure, blood oxygen, respiratory rate, heart rate and body temperature;

[0021] determining whether sudden cardiac arrest occurs or not according to the noncontact physiological information detection parameters and starting a first life support decision-making state if the sudden cardiac arrest does not occur to provide a basic respiratory support for a patient;

[0022] entering a second life support decision-making state if the sudden cardiac arrest occurs, continuously performing external chest compression and respiratory ventilation, determining compression parameters and ventilation parameters according to the noncontact physiological information detection parameters, and meanwhile determining whether defibrillation of electrocardio can be performed or not and performing external defibrillation if the defibrillation can be performed; determining whether high airway pressure occurs or not and starting diaphragm muscle electrical stimulation if the high airway pressure occurs; and

[0023] performing external chest compression, ventilation or / and defibrillation according to the instruction of the minimum intelligent decision-making system.

[0024] As an alternative embodiment, when the non-contact physiological information detection parameters and the information fed back by the executing mechanism meet the requirements of the expert knowledge base, the expert knowledge base is preferably selected for making a decision or a trained random forest trainer in combination with a multi-criteria decision-making manner is preferably selected for making a decision.

[0025] As an alternative embodiment, the non-contact physiological information detection parameters are trained by using the random forest trainer to obtain a plurality of groups of alternative schemes, an optimal decision-making scheme is determined by using the multi-criteria decision-making manner, the optimal decision-making scheme and the corresponding non-contact physiological information detection parameters are supplemented into the expert knowledge base, and the expert knowledge base is updated.

[0026] As an alternative embodiment, an initial decision-making matrix is formed on the basis of the plurality of groups of alternative schemes, a normalized value for each tuple in the matrix is determined, a recognition weighted normalized decision-making matrix is constructed on the basis of the normalized value, best and worst options are determined to find, better and worse options are determined, the value of each option is calculated, and all the alternative schemes are sorted by maximizing the value to obtain the optimal decision-making scheme.

[0027] As an alternative embodiment, the specific process of constructing the recognition weighted normalized decision-making matrix comprises determining elements of the normalized matrix, determining the performance of each alternative scheme according to the elements of the determined normalized matrix, calculating the removal of the performance of each alternative scheme relative to each criterion, further calculating the removal effect of each criterion, and determining corresponding weights according to the ratio of the removal effect to the sum of the removal effects of all the criteria.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] The present invention constructs a fully automatic life support integrated machine realizing non-contact physiological information detection and diaphragm muscle electrical stimulation. The integrated machine integrates the physiological parameter non-contact detecting module, the external chest compressor module, the external defibrillation module, the respiratory ventilation module and the diaphragm muscle electrical stimulation module on hardware. All the modules communicate with one another and are cooperatively matched. A server can interact with all the modules simultaneously under the same local area network, including data transmission, processing, storage and feedback. The external chest compressor module, the external defibrillation module, the respiratory ventilation module and the diaphragm muscle electrical stimulation module are adjusted in real time according to the physiological parameters of a patient to provide an optimal life support scheme.

[0030] The present invention applies the diaphragm muscle electrical stimulation to the CPR process. After the respirator detects that the airway pressure exceeds the dangerous airway pressure of a set value, the integrated machine prompts the start of the diaphragm muscle electrical stimulation module to pace the external diaphragm muscle of a patient, reduces the airway pressure and increases the inspiration tidal volume.

[0031] The present invention can realize the closed-loop feedback of multi-physiological parameter input, multi-physiological parameter decision making and multi-mechanical parameter output, and realize automatic life support. The fully automatic life support integrated machine detects physiological parameters of blood pressure, blood oxygen, respiratory rate, body temperature and heart rate, classifies the state of an illness through the intelligent decision-making system, and autonomously adjusts mechanical parameters of an external chest compressor, an external defibrillator, a respirator and diaphragm muscle electrical stimulation to obtain personalized fully automatic life support emergency operation.

[0032] The present invention constructs a network knowledge base with self-learning ability and an expert knowledge base containing definite rules, introduces a random forest trainer used for receiving data which is not mentioned, incomplete or cannot be decided by the expert knowledge base and a data and method base, and solves the data to update the expert knowledge base. After training by the random forest trainer, a plurality of groups of life support schemes can be obtained, and an optimal scheme is determined by using a multi-criteria decision-making method to update the expert knowledge base so as to ensure the comprehensiveness, accuracy and rapidity of the decision making.

[0033] In order to make the above objectives, features, and advantages of the present invention more understandable, the following is described in detail by using preferred embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0034] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and descriptions thereof are used to explain the present invention, and do not constitute an improper limitation of the present invention.

[0035] FIG. 1 is a general structure of the fully automatic life support integrated machine of the embodiment;

[0036] FIG. 2 is a general block diagram of a system of the fully automatic life support integrated machine according to the embodiment;

[0037] FIG. 3 shows the ventilation strategy of the fully automatic life support integrated machine of the embodiment, which reduces the airway pressure by two schemes of maintaining the tidal volume unchanged in minutes by increasing the respiratory frequency and reducing diaphragm muscle electrical stimulation,

[0038] FIG. 4 is a closed-loop decision-making system of the fully automatic life support integrated machine of the embodiment, wherein the personalized life support operation is completed through multiple inputs, multiple feedbacks and multiple adjustments,

[0039] FIG. 5 is an intelligent decision making of the fully automatic life support integrated machine of the embodiment, wherein the defects of weak learning ability and difficulty in updating of expert decision making are overcome by combining a traditional expert knowledge base and a random forest trainer, and decision making of events in a non-expert base is completed; and

[0040] FIG. 6 is a minimum intelligent deci si on-making system of the fully automatic life support integrated machine of the embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] The present invention is described in further detail below with reference to the accompanying drawings and embodiments.

[0042] It should be pointed out that the following detailed descriptions are all illustrative and are intended to provide further descriptions of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those usually understood by a person of ordinary skill in the art to which the present invention belongs.

[0043] It should be noted that the terms used herein are merely used for describing specific implementations, and are not intended to limit exemplary implementations of the present invention. As used herein, the singular form is intended to include the plural form, unless the context clearly indicates otherwise. In addition, it should further be understood that terms "comprise" and / or "include" used in this description indicate that there are features, steps, operations, devices, components, and / or combinations thereof.

[0044] As shown in FIG. 1, a fully automatic life support integrated machine is integrated in a box body 1, and a non-contact physiological information detecting module comprises a camera 2, a local area network emitter 12, an integrated machine server 11 and a non-contact physiological information detecting module 3. The camera 2 is an IPPG camera and a thermal imaging camera, wherein the IPPG camera is used for detecting the parameters of blood pressure, blood oxygen, respiratory rate and heart rate, and the thermal imaging camera is used for detecting the parameter of body temperature. The local area network transmitter 12 establishes a local area network required by the integrated machine. The server 11 performs processing and storage of data, updating of emergency strategy, and controlling among the modules. Manmachine interaction is accomplished through a display screen 10. A compressor 5 provides external chest compression during a CPR process. An electrical defibrillation module contains a defibrillation accessory 4 and a defibrillator 9 for external defibrillation. The respiratory ventilation module contains a respirator accessory 6 and a respirator 7 for providing ventilation during the CPR process. A diaphragm muscle electrical stimulation module 8 provides diaphragm muscle electrical stimulation to reduce airway pressure during the CPR process.

[0045] Of course, in some embodiments, the above components may be selected from existing devices.

[0046] As shown in FIG. 2, all the modules are in the same local area network, the thermal imaging camera is connected to the server through a network cable, and the IPPG camera uploads image data through a USB 3.0. The fully automatic life support integrated machine is provided with a man-machine interaction interface so as to complete the monitoring and adjustment of a user on the server, each module and a client. The server is connected with an external chest compressor, a defibrillator, a respirator and diaphragm muscle electrical stimulation through a TCP network protocol. The external chest compressor is used for adjusting the depth, the frequency and the compression duty ratio. The defibrillator is for adjusting the defibrillation energy. The respirator is used for adjusting the respiratory flow, the airway pressure and the respiratory time. The diaphragm muscle electrical stimulation is used for adjusting the frequency, the waveform and the current amplitude.

[0047] The present embodiment provides two solutions to the problems of increased ventilation pressure and lack of tidal volume due to compression. (1) The compression frequency is adjusted to obtain a maximum tidal volume, and the airway pressure is reduced while the tidal volume is guaranteed by changing the ventilation frequency and the initially set tidal volume. The initial setting of the compressor of the fully automatic life support integrated machine is 120 times / min. The compression frequency of 120 times / min is considered to obtain higher tidal volume, and particularly 10%-20% of tidal volume is increased by 120 times / min of the compression when the preset tidal volume is below 500 ml.

[0048] (2) A ventilation strategy of the fully automatic life support integrated machine is shown in FIG. 3. Ventilation is initiated using the ventilation frequency of 10 times / min, the inspiratory time is 1 s, the tidal volume of the ventilation is preset at VI ml, the compression frequency is 120 times / min, and the airway pressure and flow parameters are monitored each ventilation. If over-high airway pressure does not occur in the ventilation process, the original ventilation strategy is kept; and if the over-high airway pressure occurs, the ventilation frequency is changed to 20 times / min, the inspiratory time is 1 s, and the tidal volume is V2 = O.7*V1. Whether the high airway pressure occurs or not is determined again after the new ventilation strategy. If the high airway pressure does not occur, the new ventilation strategy is kept unchanged; and if the high airway pressure occurs, diaphragm muscle electrical stimulation is started, such that the lungs breathe deeply, the active ventilation of a patient is started, the airway pressure is reduced, and the tidal volume is increased. Whether the high airway pressure occurs is determined again after the diaphragm muscle electrical stimulation is performed. If the high airway pressure does not occur, the original parameters of the diaphragm muscle electrical stimulation are kept; and if the high airway pressure occurs, the current intensity, the frequency and the waveform parameters of the electric stimulation are changed.

[0049] A closed-loop decision-making system of the integrated machine is shown in FIG. 4. After receiving a patient, non-contact physiological information detection is immediately performed to obtain the parameters of blood pressure, blood oxygen, heart rate, respiratory rate and body temperature of the patient, the obtained parameters are input into the intelligent decision-making system, and the intelligent decision-making system classifies the cases and starts corresponding life support equipment. Meanwhile, the life support equipment provides force, thoracic impedance, end-tidal carbon dioxide, airway pressure and tidal volume during the CPR process to be fed back to the intelligent decision-making system, such that the intelligent decision-making system performs comprehensive decision making by combining the blood pressure, blood oxygen, heart rate, respiratory rate, body temperature, force feedback, thoracic impedance parameters, end-tidal carbon dioxide, airway resistance and tidal volume parameters, updates the parameter setting of the life support equipment in real time and performs personalized life support.

[0050] An intelligent decision-making scheme of the closed-loop decision-making system is shown in FIG. 5. A system main body consists of two parts: a network knowledge base with self-learning ability and an expert system (or expert knowledge base) containing clear rules.

[0051] The expert system is a decision-making system that can solve life support operations like a human expert. The system effectively utilizes the experience accumulated by experts for many years and professional medical knowledge, and solves the actual medical problem by simulating the thinking process of the experts. However, a conventional expert system has some limitations in the decision-making process. The knowledge acquisition behaviors are static and passive, a self-learning mechanism is lacked, the actual decision-making problem can be analyzed and processed only according to established rules, the automatic accumulation of knowledge and experience is difficult to perform, the knowledge acquisition mode lacks flexibility and is poor in adaptability, and the knowledge base is difficult to update.

[0052] In order to solve the problem that the conventional expert system cannot update the decision-making knowledge base, the embodiment provides a solution. A random forest trainer is introduced to be used for receiving data which is not mentioned, incomplete or cannot be decided by the expert knowledge base and a data and method base, and the data is solved to update the expert knowledge base. After the training by the random forest trainer, a plurality of groups of life support schemes are obtained, the schemes are stored in a network database, and each scheme generates a plurality of different expected physiological state changes. In order to obtain an optimal life support scheme, multi-criteria decision making (MCDM) is incorporated into the system. Steps of the multi-criteria decision making are as follows:

[0053] step 1: forming an initial decision-making matrix, Xji .. • xln X = X21 ■ • x2n

[0054] _Xml •• Xnin_ (1),

[0055] wherein m is an alternative scheme, n is a standard number, and xmn is the value of the standard n in the alternative m;

[0056] step 2: determining a normalized value kij using the following formula: (2);

[0058] step 3: constructing a recognition weighted normalized deci si on-making matrix: (3);

[0060] step 4: finding a best option A+ and a worst option A- according to the following formula (4):

[0061] — pi, 4 ’

[0062] (4); and (5);

[0063] wherein J and 7 are a best value and a worst value of a criterion (j = 1, 2, ..., n); D D~

[0064] step 5: determining a best option 1 and a worst option 1

[0065] (6); and < = Jy" .(k+l?)2 i = 1. 2, ..., m

[0066] y

[0067] step 6: calculating the value Ri of each option according to the following method: = Dl z = 1, 2, ..., m; 0 <Rj <1

[0068] Di +Dt (8); and

[0069] step 7: sorting the alternative scheme according to the maximized R value: w ■

[0070] determining the standard weight 7 of formula 3 as follows:

[0071] step 1: forming an initial matrix as shown in formula (1):

[0072] step 2: determining elements of the normalized matrix: X- -

[0073] y a greater criterion j is better (9); and max x • -

[0074] a smaller criterion j is better (10)

[0075] step 3: calculating the performance of alternative Si according to the following formula:

[0076] (11)

[0077] step 4: calculating the performance of the i-th alternative ij relative to the removal of the criterion] by using the following formula:

[0078] 11 In i+(^k k^n(hn)\) (12)

[0079] step 5: calculating the removal effect of the criterion] Ej:

[0080] J 4—i i u 1 (13); and

[0081] step 6: determining the weight of each criterion by using the following formula: 7 y,Ek

[0082] k (14)

[0083] The trained network knowledge base, the updated expert knowledge base and the multi-criteria decision making are used to handle actual medical decision-making problems. On the basis of the provided deci si on-making resources, the system can reasonably select the expert system or a neural network to make an independent decision. When the physiological and mechanical information fed back by the noncontact physiological information detection and life support equipment meets the requirements of the expert system knowledge base, the system can preferably select the expert system to make a decision. However, when the acquired information cannot be matched with the expert knowledge base or cannot find a matching item in the knowledge base, the intelligent decision-making system transmits the physiological information to a well-trained random forest trainer, the well-trained neural network performs reasoning and decision making, and then the MCDM is used for performing preferred selection.

[0084] A minimum intelligent decision-making system of the fully automatic life support integrated machine is shown in FIG. 6. After a patient is received, the noncontact physiological information detecting module is used for detecting parameters. The intelligent decision-making system determines whether sudden cardiac arrest occurs or not, enters a low-level life support decision making state if the sudden cardiac arrest does not occur to provide a basic respiratory support for a patient, starts a high-level life support decision making if the sudden cardiac arrest occurs, and on the basis of continuous external chest compression and respiratory ventilation of the patients, meanwhile determines whether defibrillation of electrocardio can be performed or not and performs external defibrillation if the defibrillation can be performed, and determines whether high airway pressure occurs or not and starts diaphragm muscle electrical stimulation if the high airway pressure occurs.

[0085] A person skilled in the art should understand that the embodiments of the present invention may be provided as a method, a system, or a computer program product. Therefore, the present invention may use a form of hardware-only embodiments, software-only embodiments, or embodiments with a combination of software and hardware. Moreover, the present invention may use a form of a computer program product that is implemented on one or more computer-usable storage media (including but not limited to a disk memory, a compact disc read-only memory (CD-ROM), an optical memory, and the like) that include computer-usable program code.

[0086] The present invention is described with reference to the flowcharts and / or block diagrams of the method, the device (system), and the computer program product according to the embodiments of the present invention. It should be understood that computer program instructions can implement each procedure and / or block in the flowcharts and / or block diagrams and a combination of procedures and / or blocks in the flowcharts and / or block diagrams. These computer program instructions may be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or a processor of another programmable data processing device to generate a machine, such that an apparatus configured to implement functions specified in one or more procedures in the flowcharts and / or one or more blocks in the block diagrams is generated by using instructions executed by the computer or the processor of another programmable data processing device.

[0087] These computer program instructions may alternatively be stored in a computer-readable memory that can instruct a computer or another programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate an artifact that includes an instruction apparatus. The instruction apparatus implements a specific function in one or more procedures in the flowcharts and / or in one or more blocks in the block diagrams.

[0088] These computer program instructions may further be loaded onto a computer or another programmable data processing device, such that a series of operations and steps are performed on the computer or other programmable device, thereby generating computer-implemented processing. Therefore, the instructions executed on the computer or other programmable device provides steps for implementing a specific function in one or more processes in the flowcharts and / or in one or more blocks in the block diagrams.

[0089] The foregoing descriptions are merely preferred embodiments of the present invention, but are not intended to limit the present invention. A person skilled in the art may make various alterations and variations to the present invention. Any modification, equivalent replacement, or improvement made and the like within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

[0090] The specific implementations of the present invention are described above with reference to the accompanying drawings, but are not intended to limit the protection scope of the present invention. A person skilled in the art should understand that various modifications or deformations may be made without creative efforts on the basis of the technical solutions of the present invention, and such modifications or deformations shall fall within the protection scope of the present invention.

Claims

1. Integrated machine realizing physiological information detection and diaphragm muscle electrical stimulation, comprising:a non-contact physiological information detecting module used for detecting parameters of blood pressure, blood oxygen, respiratory rate, heart rate and body temperature;a minimum intelligent decision-making system used for determining whether sudden cardiac arrest occurs or not according to the non-contact physiological information detection parameters and starting a first life support decision-making state if the sudden cardiac arrest does not occur to provide a basic respiratory support for a patient;entering a second life support decision-making state if the sudden cardiac arrest occurs, continuously performing external chest compression and respiratory ventilation, determining compression parameters and ventilation parameters according to the noncontact physiological information detection parameters, and meanwhile determining whether defibrillation of electrocardio can be performed or not and performing external defibrillation if the defibrillation can be performed; and determining whether high airway pressure occurs or not and starting diaphragm muscle electrical stimulation if the high airway pressure occurs; andan executing mechanism used for performing external chest compression, ventilation or / and defibrillation according to the instruction of the minimum intelligent decision-making system.

2. The integrated machine realizing physiological information detection and diaphragm muscle electrical stimulation according to claim 1, wherein the non-contact physiological information detecting module comprises an IPPG camera and a thermal imaging camera, wherein the IPPG camera is used for detecting the parameters of blood pressure, blood oxygen, respiratory rate and heart rate, and the thermal imaging camera is used for detecting the parameter of body temperature.

3. The integrated machine realizing physiological information detection anddiaphragm muscle electrical stimulation according to claim 1, wherein the executing mechanism comprises an external chest compressor module, an external defibrillation module, a respiratory ventilation module and a diaphragm muscle electrical stimulation module, wherein the external chest compressor module is used for adjusting the depth, the frequency and the compression duty ratio, the external defibrillation module is used for adjusting the defibrillation energy, the respiratory ventilation module is used for adjusting the respiratory flow, the airway pressure and the respiratory time, and the diaphragm muscle electrical stimulation module is used for adjusting the frequency, the waveform and the current amplitude.

4. The integrated machine realizing physiological information detection and diaphragm muscle electrical stimulation according to claim 1, wherein the minimum intelligent decision-making system is configured to comprise a first decision-making subsystem and a second decision-making subsystem, wherein the first decision-making subsystem is configured to make a decision by using an expert knowledge base; the second decision-making subsystem is configured to make a decision by using a trained random forest trainer in combination with a multi-criteria decision-making manner; and when the non-contact physiological information detection parameters and the information fed back by the executing mechanism meet the requirements of the expert knowledge base, the first decision-making subsystem is preferably selected for making a decision or the second decision-making subsystem is preferably selected for making a decision.

5. The integrated machine realizing physiological information detection and diaphragm muscle electrical stimulation according to claim 4, wherein the second decision-making subsystem is configured to train the non-contact physiological information detection parameters by using the random forest trainer to obtain a plurality of groups of alternative schemes, determine an optimal decision-making scheme by using the multi-criteria decision-making manner, supplement the optimal decisionmaking scheme and the corresponding non-contact physiological information detection parameters into the expert knowledge base, and update the expert knowledge base.diaphragm muscle electrical stimulation according to claim 4 or 5, wherein the second decision-making subsystem is configured to form an initial decision-making matrix on the basis of the plurality of groups of alternative schemes, determine a normalized value for each tuple in the matrix, construct a recognition weighted normalized decisionmaking matrix on the basis of the normalized value, determine to find best and worst options, determine better and worse options, calculate the value of each option, and sort all the alternative schemes by maximizing the value to obtain the optimal decisionmaking scheme.

7. A method for controlling an integrated machine realizing physiological information detection and diaphragm muscle electrical stimulation, comprising:detecting non-contact physiological information detection parameters of blood pressure, blood oxygen, respiratory rate, heart rate and body temperature;determining whether sudden cardiac arrest occurs or not according to the noncontact physiological information detection parameters and starting a first life support decision-making state if the sudden cardiac arrest does not occur to provide a basic respiratory support for a patient;entering a second life support decision-making state if the sudden cardiac arrest occurs, continuously performing external chest compression and respiratory ventilation, determining compression parameters and ventilation parameters according to the noncontact physiological information detection parameters, and meanwhile determining whether defibrillation of electrocardio can be performed or not and performing external defibrillation if the defibrillation can be performed; determining whether high airway pressure occurs or not and starting diaphragm muscle electrical stimulation if the high airway pressure occurs; andperforming external chest compression, ventilation or / and defibrillation according to the instruction of the minimum intelligent decision-making system.

8. The control method according to claim 7, wherein when the non-contact physiological information detection parameters and the information fed back by the executing mechanism meet the requirements of the expert knowledge base, the expert knowledge base is preferably selected for making a decision or a trained random foresttrainer in combination with a multi-criteria decision-making manner is preferably selected for making a decision; andthe non-contact physiological information detection parameters are trained by using the random forest trainer to obtain a plurality of groups of alternative schemes, an optimal decision-making scheme is determined by using the multi-criteria decisionmaking manner, the optimal decision-making scheme and the corresponding noncontact physiological information detection parameters are supplemented into the expert knowledge base, and the expert knowledge base is updated.

9. The control method according to claim 8, wherein an initial decision-making matrix is formed on the basis of the plurality of groups of alternative schemes, a normalized value for each tuple in the matrix is determined, a recognition weighted normalized decision-making matrix is constructed on the basis of the normalized value, best and worst options are determined to find, better and worse options are determined, the value of each option is calculated, and all the alternative schemes are sorted by maximizing the value to obtain the optimal decision-making scheme.

10. The control method according to claim 9, wherein the specific process of constructing the recognition weighted normalized decision-making matrix comprises determining elements of the normalized matrix, determining the performance of each alternative scheme according to the elements of the determined normalized matrix, calculating the removal of the performance of each alternative scheme relative to each criterion, further calculating the removal effect of each criterion, and determining corresponding weights according to the ratio of the removal effect to the sum of the removal effects of all the criteria.

Images