Method for unified analysis and synchronous presentation of intensive care multi-model ventilator data

Abstract

The application discloses a method for unified analysis and synchronous presentation of intensive care multi-model respirator data, and relates to the technical field of medical information processing.The internal data of multiple models of respirators are subjected to self-adaptive processing of respirator parameters to obtain comprehensive respirator internal processing coefficients, and when the comprehensive respirator internal processing coefficients are less than or equal to a preset respirator processing threshold, the internal data of the respirator is presented, otherwise, the state data of the respirator is acquired, comprehensive state calculation is performed based on the state data of the respirator, the respirator comprehensive state coefficient is obtained, the abnormal position in the internal data of the respirator is determined based on the size of the respirator comprehensive state coefficient, and the abnormal position in the internal data of the respirator is subjected to optimized processing, and finally the optimized internal data of the respirator is acquired and presented, so that the existing abnormalities of the respirator can be positioned and corrected, and the internal data of the respirator based on the optimized respirator can be uniformly analyzed and presented.

Description

Technical Field

[0001] This invention relates to the field of medical information processing technology, specifically a method for unified analysis and synchronous presentation of data from multiple models of ventilators in intensive care. Background Technology

[0002] In the Intensive Care Unit (ICU), ventilators are the core life support equipment. In order to conduct centralized monitoring, clinical decision support, and electronic medical record (EMR) recording, it is necessary to collect, analyze, and present data from these different models of ventilators in a unified manner.

[0003] Existing methods for unified data processing of ventilators only process data for a single type and model of ventilator. When dealing with data from multiple ventilator models, the lack of correlation between the data from different models leads to problems in unified data parsing and processing, making it impossible to locate and correct any anomalies in the ventilators. Summary of the Invention

[0004] To address the shortcomings mentioned in the background section, the present invention aims to provide a method for unified analysis and synchronous presentation of data from multiple ventilator models in intensive care.

[0005] Firstly, the objective of this invention can be achieved through the following technical solution: a method for unified analysis and synchronous presentation of data from multiple models of ventilators in intensive care, the method comprising the following steps: Acquire internal data from multiple ventilator models and preprocess it to obtain processed internal data from multiple ventilator models; Based on the processed internal data of multiple ventilators, adaptive processing of ventilator parameters is performed to obtain a comprehensive internal processing coefficient of the ventilator. If the comprehensive internal processing coefficient of the ventilator is less than or equal to the preset ventilator processing threshold, the internal data of the ventilator is presented; otherwise, the ventilator status data is obtained. Based on the ventilator status data, a comprehensive status calculation is performed to obtain the comprehensive status coefficient of the ventilator. Based on the magnitude of the comprehensive status coefficient, the abnormal location inside the ventilator is determined, and optimization processing is carried out in combination with the abnormal location inside the ventilator. The optimized internal data of the ventilator is then obtained and displayed.

[0006] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the preprocessing includes data cleaning and enhancement as well as time normalization.

[0007] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the time standardization adopts a combination of adaptive least common multiple resampling and cubic spline interpolation.

[0008] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the process of adaptively processing ventilator parameters based on processed internal data of multiple ventilator models, comprising: In the formula, Zhi is the integrated internal processing coefficient of the ventilator, Gi is the high-frequency waveform data label, Di is the low-frequency parameter data label, where i is the data number of the internal data of multiple ventilator models, and i=1, 2, 3, ..., n, n is the total number of data of the internal data of multiple ventilator models, G0 is the preset standard high-frequency waveform coefficient, D0 is the preset standard low-frequency parameter coefficient, A is the high-frequency waveform acquisition influence coefficient, and B is the low-frequency parameter acquisition influence coefficient.

[0009] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the process of performing comprehensive state calculation based on ventilator state data, as follows: Where Ztj is the overall ventilator status coefficient, V j For voltage data, L j For current data, Q j Here, j represents the number of data points in the ventilator status data, and j = 1, 2, 3, ..., m, where m is the total number of data points in the ventilator status data. α, β, and γ are all preset correction coefficients.

[0010] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the process of determining the location of the abnormality inside the ventilator based on the magnitude of the ventilator's overall state coefficient, comprising: Define the anomaly judgment set [Zmin, Zmax]; Zmin is the minimum coefficient of state evaluation, and Zmax is the maximum coefficient of state evaluation; If Ztj < Zmin, it indicates a problem with the air supply inside the ventilator, hence the ventilator's air supply port is abnormal. If Zmin≤Ztj≤Zmax, it indicates a problem with the power supply inside the ventilator, thus the power supply position of the ventilator is abnormal. If Ztj > Zmax, it indicates a problem with the airway control inside the ventilator, resulting in abnormal airway transmission.

[0011] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the internal data of the multi-model ventilator includes high-frequency waveform data and low-frequency parameter data, and the preprocessing includes data cleaning and enhancement as well as time standardization; The ventilator status data includes voltage data, current data, and gas supply data.

[0012] The beneficial effects of this invention are: This invention obtains a comprehensive ventilator internal processing coefficient by adaptively processing internal data from multiple ventilator models. When the comprehensive ventilator internal processing coefficient is less than or equal to a preset ventilator processing threshold, the ventilator internal data is presented; otherwise, ventilator status data is acquired, and a comprehensive status calculation is performed based on this data to obtain a comprehensive ventilator status coefficient. Based on the magnitude of this coefficient, the location of any abnormality within the ventilator is determined, and optimization processing is performed in conjunction with this abnormality location. Finally, the optimized internal data is obtained and displayed, thereby enabling the location and correction of ventilator abnormalities. The optimized internal data is then uniformly parsed and presented. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Figure 1 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0014] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0015] Example 1: like Figure 1 As shown, the method for unified analysis and synchronous presentation of data from multiple ventilator models in intensive care includes the following steps: S101: Acquire internal data of multiple ventilators and perform preprocessing to obtain processed internal data of multiple ventilators. The internal data of multiple ventilators includes high-frequency waveform data and low-frequency parameter data. The preprocessing includes data cleaning and enhancement as well as time standardization. Among them, the internal data of multiple ventilator models are associated with the internal data of each ventilator model, which makes it easier to directly identify the corresponding ventilator model after ventilator malfunction, thus improving the processing speed. The data collection process for multiple ventilator models includes: By arranging multiple sensors (including pressure sensors, flow sensors, and volume sensors) inside the ventilator, waveform parameters such as airway pressure, flow, and volume inside the ventilator are collected by the internal sensors and used as high-frequency waveform data of the ventilator. In this embodiment, the sampling frequency of each sensor is 100 Hz. After connecting the acquisition port to the data output port of the ventilator, the internal parameter data related to breathing collected by the ventilator are exported. The internal parameter data related to breathing includes ventilation parameters, oxygenation parameters, and respiratory pressure parameters. As low-frequency parameter data of the ventilator, in this embodiment, the sampling frequency is to collect data after each breath of the patient. The preprocessing of internal data from multiple ventilator models includes: After data cleaning and data enhancement of internal data from multiple models of ventilators, data impurities in the internal data of all models of ventilators were removed, and the validity of the data was improved, enhancing the presentation of the data. By standardizing the time synchronization and resampling of internal data from multiple ventilator models, the internal data of each ventilator model is aligned in time, improving the correlation between the internal data of each ventilator model. In one implementation, when processing the time-normalized data of multiple ventilator models, a method combining adaptive least common multiple resampling and cubic spline interpolation is used, based on a preset global output frequency. S102: Based on the processed internal data of multiple ventilators, adaptive processing of ventilator parameters is performed to obtain a comprehensive internal processing coefficient of the ventilator. If the comprehensive internal processing coefficient of the ventilator is less than or equal to the preset ventilator processing threshold, the internal data of the ventilator is presented; otherwise, the ventilator status data is obtained, which includes voltage data, current data and gas source data. Among them, gas source data are parameters that show the gas supply situation; The process of adaptively processing ventilator parameters based on processed internal data from multiple ventilator models includes: In the formula, Zhi is the integrated internal processing coefficient of the ventilator, Gi is the high-frequency waveform data label, Di is the low-frequency parameter data label, where i is the data number of the internal data of multiple ventilator models, and i=1, 2, 3, ..., n, n is the total number of data of the internal data of multiple ventilator models, G0 is the preset standard high-frequency waveform coefficient, D0 is the preset standard low-frequency parameter coefficient, A is the high-frequency waveform acquisition influence coefficient, and B is the low-frequency parameter acquisition influence coefficient; The calculated comprehensive internal processing coefficient of the ventilator serves as the benchmark for determining whether the internal state of the ventilator can operate normally during internal data acquisition. By comparing it with a preset threshold, it is determined whether the ventilator is in normal condition, thereby determining whether the acquired internal data of the ventilator can be output and presented normally. Furthermore, in the specific implementation process, the preset standard high-frequency waveform coefficients and preset standard low-frequency parameter coefficients are obtained by repeatedly simulating and calculating the average values ​​of the high-frequency waveform data and low-frequency parameter data collected daily. In this embodiment, the high-frequency waveform acquisition influence coefficient and the low-frequency parameter acquisition influence coefficient are calculated by comprehensively evaluating the influence of external factors when acquiring high-frequency waveform data and low-frequency parameter data on a daily basis. These factors include human factors, machine detection, and environmental factors, etc. Human factors refer to those caused by improper human operation or scanning. S103: Perform comprehensive state calculation based on ventilator state data to obtain the comprehensive state coefficient of the ventilator. Based on the magnitude of the comprehensive state coefficient of the ventilator, determine the abnormal location inside the ventilator, optimize the process based on the abnormal location inside the ventilator, and obtain the optimized internal data of the ventilator for presentation and display.

[0016] The process of performing comprehensive status calculations based on ventilator status data is as follows: Where Ztj is the overall ventilator status coefficient, V j For voltage data, L j For current data, Q j For gas source data, j is the data number of ventilator status data, and j = 1, 2, 3, ..., m, where m is the total number of ventilator status data, and α, β, and γ are preset correction coefficients; The process of determining the location of abnormalities within the ventilator based on the magnitude of the overall ventilator status coefficient includes: Define the anomaly judgment set [Zmin, Zmax]; Zmin is the minimum coefficient of state evaluation, and Zmax is the maximum coefficient of state evaluation; Based on the setting of the abnormal judgment set, the calculated comprehensive state coefficient of the ventilator is compared with its internal parameters, and the abnormal location of the ventilator's gas supply, power supply and airway transmission is located according to the comparison results.

[0017] If Ztj < Zmin, it indicates a problem with the air supply inside the ventilator, hence the ventilator's air supply port is abnormal. If Zmin≤Ztj≤Zmax, it indicates a problem with the power supply inside the ventilator, thus the power supply position of the ventilator is abnormal. If Ztj > Zmax, it indicates a problem with the airway control inside the ventilator, resulting in abnormal airway transmission.

[0018] Based on the same inventive concept, this invention also provides a computer device, comprising: one or more processors, and a memory for storing one or more computer programs; the programs include program instructions, and the processor executes the program instructions stored in the memory. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, used to implement one or more instructions, specifically for loading and executing one or more instructions stored in a computer storage medium to implement the above-described method.

[0019] It should be further explained that, based on the same inventive concept, the present invention also provides a computer storage medium storing a computer program, which, when executed by a processor, performs the above-described method. This storage medium can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0020] The above formulas are all numerical calculations after removing dimensions. The formulas are obtained by software simulation based on a large amount of data and are closest to the real situation. The preset parameters and preset thresholds in the formulas are set by those skilled in the art according to the actual situation or obtained by simulation based on a large amount of data.

[0021] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0022] The foregoing has shown and described the basic principles, main features, and advantages of this disclosure. Those skilled in the art should understand that this disclosure is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of this disclosure. Various changes and modifications can be made to this disclosure without departing from its spirit and scope, and all such changes and modifications fall within the scope of this disclosure as claimed.

Claims

1. A method for unified analysis and synchronous presentation of data from multiple ventilator models in intensive care, characterized in that, The method includes the following steps: Acquire internal data from multiple ventilator models and preprocess it to obtain processed internal data from multiple ventilator models; Based on the processed internal data of multiple ventilators, adaptive processing of ventilator parameters is performed to obtain a comprehensive internal processing coefficient of the ventilator. If the comprehensive internal processing coefficient of the ventilator is less than or equal to the preset ventilator processing threshold, the internal data of the ventilator is presented; otherwise, the ventilator status data is obtained. Based on the ventilator status data, a comprehensive status calculation is performed to obtain the comprehensive status coefficient of the ventilator. Based on the magnitude of the comprehensive status coefficient, the abnormal location inside the ventilator is determined, and optimization processing is carried out in combination with the abnormal location inside the ventilator. The optimized internal data of the ventilator is then obtained and displayed.

2. The method for unified parsing and synchronous presentation of data from multiple ventilator models in intensive care as described in claim 1, characterized in that, The preprocessing includes data cleaning and enhancement, as well as time normalization.

3. The method for unified parsing and synchronous presentation of data from multiple ventilator models in intensive care as described in claim 2, characterized in that, The time standardization adopts a combination of adaptive least common multiple resampling and cubic spline interpolation.

4. The method for unified parsing and synchronous presentation of data from multiple ventilator models in intensive care as described in claim 1, characterized in that, The process of adaptively processing ventilator parameters based on processed internal data from multiple ventilator models includes: In the formula, Zhi is the integrated internal processing coefficient of the ventilator, Gi is the high-frequency waveform data label, Di is the low-frequency parameter data label, where i is the data number of the internal data of multiple ventilator models, and i=1, 2, 3, ..., n, n is the total number of data of the internal data of multiple ventilator models, G0 is the preset standard high-frequency waveform coefficient, D0 is the preset standard low-frequency parameter coefficient, A is the high-frequency waveform acquisition influence coefficient, and B is the low-frequency parameter acquisition influence coefficient.

5. The method for unified parsing and synchronous presentation of data from multiple ventilator models in intensive care as described in claim 1, characterized in that, The process of performing comprehensive status calculation based on ventilator status data is as follows: Where Ztj is the overall ventilator status coefficient, V j For voltage data, L j For current data, Q j Here, j represents the number of data points in the ventilator status data, and j = 1, 2, 3, ..., m, where m is the total number of data points in the ventilator status data. α, β, and γ are all preset correction coefficients.

6. The method for unified parsing and synchronous presentation of data from multiple ventilator models in intensive care as described in claim 1, characterized in that, The process of determining the location of abnormalities inside the ventilator based on the magnitude of the ventilator's overall state coefficient includes: Define the anomaly judgment set [Zmin, Zmax]; Zmin is the minimum coefficient of state evaluation, and Zmax is the maximum coefficient of state evaluation; If Ztj < Zmin, it indicates a problem with the air supply inside the ventilator, hence the ventilator's air supply port is abnormal. If Zmin≤Ztj≤Zmax, it indicates a problem with the power supply inside the ventilator, thus the power supply position of the ventilator is abnormal. If Ztj > Zmax, it indicates a problem with the airway control inside the ventilator, resulting in abnormal airway transmission.

7. The method for unified parsing and synchronous presentation of data from multiple ventilator models in intensive care as described in claim 1, characterized in that, The internal data of the various ventilators includes high-frequency waveform data and low-frequency parameter data. Preprocessing includes data cleaning and enhancement as well as time standardization. The ventilator status data includes voltage data, current data, and gas supply data.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, The memory stores a computer program that can run on the processor. When the processor loads and executes the computer program, it employs the method for unified parsing and synchronous presentation of data from multiple models of intensive care ventilators as described in any one of claims 1 to 7.

Images