WO2022267382A1 - 一种呼吸机人机异步分类方法、系统、终端以及存储介质 - Google Patents
一种呼吸机人机异步分类方法、系统、终端以及存储介质 Download PDFInfo
- Publication number
- WO2022267382A1 WO2022267382A1 PCT/CN2021/137605 CN2021137605W WO2022267382A1 WO 2022267382 A1 WO2022267382 A1 WO 2022267382A1 CN 2021137605 W CN2021137605 W CN 2021137605W WO 2022267382 A1 WO2022267382 A1 WO 2022267382A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- data
- ventilator
- human
- machine asynchronous
- machine
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000000241 respiratory effect Effects 0.000 claims abstract description 60
- 210000004072 lung Anatomy 0.000 claims abstract description 22
- 238000013145 classification model Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 12
- 210000003281 pleural cavity Anatomy 0.000 claims abstract description 4
- 230000029058 respiratory gaseous exchange Effects 0.000 claims description 60
- 230000003434 inspiratory effect Effects 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000003066 decision tree Methods 0.000 claims description 10
- 238000007637 random forest analysis Methods 0.000 claims description 9
- 230000001960 triggered effect Effects 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000013480 data collection Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 239000006185 dispersion Substances 0.000 claims description 3
- 239000013589 supplement Substances 0.000 claims description 2
- 230000000747 cardiac effect Effects 0.000 abstract description 2
- 238000004422 calculation algorithm Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 206010001052 Acute respiratory distress syndrome Diseases 0.000 description 4
- 201000000028 adult respiratory distress syndrome Diseases 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 208000013616 Respiratory Distress Syndrome Diseases 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000005399 mechanical ventilation Methods 0.000 description 2
- 238000009423 ventilation Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000002612 cardiopulmonary effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 230000004118 muscle contraction Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 239000011664 nicotinic acid Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 210000003019 respiratory muscle Anatomy 0.000 description 1
- 230000036387 respiratory rate Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/40—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for data related to laboratory analysis, e.g. patient specimen analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
Definitions
- the invention belongs to the technical field of medical data processing, and in particular relates to a human-machine asynchronous classification method, system, terminal and storage medium of a ventilator.
- the present invention provides a human-machine asynchronous classification method, system, terminal and storage medium for a ventilator, aiming to solve one of the above-mentioned technical problems in the prior art at least to a certain extent.
- the present invention provides the following technical solutions:
- a ventilator man-machine asynchronous classification method comprising:
- the extracted features include any one of variance, mean, standard deviation, absolute value or square root;
- the human-machine asynchronous event of the ventilator is classified by the trained human-machine asynchronous classification model.
- the technical solution adopted by the embodiment of the present invention also includes: the collection of breathing data under the man-machine asynchronous event simulated by the simulated lung and the ventilator includes:
- the collected breathing data under human-machine asynchronous events include normal breathing, invalid inspiratory effort breathing and double-triggered breathing under three kinds of human-machine asynchronous events.
- the technical solution adopted by the embodiment of the present invention also includes: the collection of respiratory data under the man-machine asynchronous event simulated by the simulated lung and ventilator also includes:
- the collected respiratory data includes simulated flow channel, tidal volume channel, airway pressure, alveolar pressure, pleural cavity pressure, heart pressure and bellows position.
- the technical solution adopted by the embodiment of the present invention also includes: after the collection of the breathing data under the man-machine asynchronous event simulated by the simulated lung and the ventilator, it also includes:
- the respiration data are preprocessed to obtain sample data corresponding to normal respiration, invalid inspiratory effort respiration and dual-trigger respiration respectively.
- the preprocessing of the breathing data includes:
- the technical solution adopted in the embodiment of the present invention also includes: the feature extraction of the respiratory data is specifically:
- the variance represents the degree of dispersion of a set of data, and the calculation formula is:
- the mean value represents the amount of trend in a set of data, and the calculation formula is:
- x 1 , x 2 ... x n are individuals, and M is the average number;
- the standard deviation is the arithmetic mean root of the variance, and the calculation formula is:
- the absolute value refers to the distance from the point a corresponding to a number on the number axis to the origin b, and its formula is:
- the root mean square is used to analyze the noise, and the calculation formula is:
- the technical solution adopted by the embodiment of the present invention further includes: the network model includes a decision tree or a random forest classifier.
- a human-machine asynchronous classification system for a ventilator including:
- Data collection module used to collect respiratory data under the asynchronous events of man-machine simulated by simulated lung and ventilator;
- Feature extraction module used to perform feature extraction on the respiratory data, and generate sample data according to the extracted features; wherein, the extracted features include any one of variance, mean value, standard deviation, absolute value or square root;
- Asynchronous classification module used to input the sample data into the network model for training, obtain a trained human-machine asynchronous classification model, and classify ventilator human-machine asynchronous events through the trained human-machine asynchronous classification model.
- a terminal includes a processor and a memory coupled to the processor, wherein,
- the memory stores program instructions for implementing the ventilator-human-machine asynchronous classification method
- the processor is configured to execute the program instructions stored in the memory to control the human-machine asynchronous classification of the ventilator.
- Another technical solution adopted by the embodiment of the present invention is: a storage medium storing program instructions executable by a processor, and the program instructions are used to execute the human-machine asynchronous classification method for a ventilator.
- the beneficial effect produced by the embodiment of the present invention is that the ventilator-man-machine asynchronous classification method, system, terminal and storage medium in the embodiment of the present invention use simulated lung and ventilator to simulate man-machine asynchronous events, collect multiple Channel respiratory data, and extract the variance, mean, standard deviation, absolute value or square root of the respiratory data, and then input the extracted features into the network model for human-computer asynchronous classification.
- the present invention has at least the following beneficial effects:
- the collected respiratory data has less interference and is convenient to collect, which can be applied to the asynchronous classification of multiple cases.
- Fig. 1 is the flow chart of the ventilator man-machine asynchronous classification method of the embodiment of the present invention
- FIG. 2 is a schematic structural diagram of a human-machine asynchronous classification system for a ventilator according to an embodiment of the present invention
- FIG. 3 is a schematic structural diagram of a terminal according to an embodiment of the present invention.
- FIG. 4 is a schematic structural diagram of a storage medium according to an embodiment of the present invention.
- FIG. 1 is a flow chart of a method for man-machine asynchronous classification of a ventilator according to an embodiment of the present invention.
- the ventilator man-machine asynchronous classification method of the embodiment of the present invention comprises the following steps:
- the simulated lung is the TestChest (intelligent cardiopulmonary bionic system) simulated lung
- the ventilator is the Mindray SV300 ventilator
- the simulated disease type is ARDS (Acute respiratory distress syndrome, acute respiratory distress syndrome) patients.
- the TestChest simulated lung The frequency of the ventilator and Mindray SV300 were set to 50HZ, the simulated respiratory rate was set to 21 times per minute, and the ventilation mode of the ventilator was CPAR/PSV mode. It can be understood that the present invention is also applicable to other types of simulated lungs, disease types and ventilators, and the parameters of the simulated lungs and ventilators can also be set according to actual applications.
- the TestChest simulated lung can simulate the breathing of 15 channels, and the embodiment of the present invention only uses the simulated flow channel (Flow), tidal volume channel (Volume), airway pressure (Paw), alveolar pressure (Alveolar pressure), pleural cavity Intrapleural pressure, Cardiac pressure, and bellows position and other 7-channel respiratory data for man-machine asynchronous classification.
- the embodiment of the present invention is also applicable to the man-machine asynchronous classification of respiratory data of other channels.
- the collected multi-channel respiratory data includes the respiratory data of three human-machine asynchronous events: normal breathing, invalid inspiratory effort breathing, and double-triggered breathing.
- the classification of the three asynchronous events of Qi effort breathing and double-trigger breathing is also applicable to the classification of other human-machine asynchronous events such as automatic triggering and respiratory muscle contraction.
- S2 Preprocessing the collected multi-channel respiratory data to obtain the sample data corresponding to each man-machine asynchronous event
- preprocessing includes two parts: data segmentation and data labeling.
- the data segmentation is specifically as follows: first, the peak and trough detection of the tidal volume channel is performed on the respiratory data, and the respiratory cycle in the respiratory data is obtained (each exhalation and inhalation is a respiratory cycle), and then the respiratory data is processed according to the respiratory cycle. Segmentation processing to obtain segmented sample data; wherein, the segmented sample data includes 150 normal breathing cycles, 150 invalid inspiratory effort breathing cycles, and 150 double-triggered breathing cycles. The specific number of breathing cycles can be determined according to the actual operation to set.
- the data annotation is specifically: perform supplementary operation on the segmented sample data, set the sample data of each respiratory cycle to 98 data points, fill in zeros for the sample data that is less than 98 data points, and perform Label each sample data separately, set the sample data label of normal breathing to [1,0,0], set the sample data label of double-triggered breathing to [0,0,1], and set the sample data label of invalid inspiratory effort breathing Data labels are set to [0,1,0].
- the specific number of data points and labeling methods can be set according to the actual operation.
- S3 Extract any feature such as variance, mean, standard deviation, absolute value, or square root in the sample data corresponding to each man-machine asynchronous event, and convert the extracted features into one-dimensional data to generate new sample data ;
- the feature extraction is specifically: perform variance, mean, standard deviation, absolute value or square root feature extraction on the sample data of normal breathing, invalid inspiratory effort breathing, and double-trigger breathing, and analyze different asynchronous breathing data according to the extracted features difference between.
- the variance calculation formula is:
- n indicates the number of samples
- xi indicates individuals.
- Variance is used to represent the degree of dispersion of a set of data, and it is a measure of the difference between the source data and the expected value.
- the mean represents the magnitude of a trend in a set of data and is calculated as:
- x 1 , x 2 ... x n are individuals, n is the number of samples, and M is the mean.
- the standard deviation is the arithmetic mean root of the variance, calculated as:
- the absolute value refers to the distance from the point a corresponding to a number on the number axis to the origin b, and its formula is:
- the root mean square is used to analyze the noise, and the calculation formula is:
- x 1 , x 2 ... x n are individuals, and n represents the number of samples.
- the network model includes a decision tree or random forest classifier.
- the network model training process is as follows: divide the new sample data into a test set and a training set at a ratio of 1:1, that is, 50% is used as the training set for model training, and 50% is used as the test set for model testing.
- the accuracy rate, recall rate and F1 score of the human-machine asynchronous classification results output by the model are calculated through the decision tree or random forest algorithm to evaluate the model performance.
- the respiratory data of the ARDS patient were collected for experimental verification, and the patient's ventilation cycle per minute was set to 21 times, and 150 normal breaths and 150 invalid inhalations of the patient were collected respectively.
- Effort breathing, 150 double-trigger breathing, after performing variance, mean, standard deviation, absolute value and square root feature extraction on the breathing data output the human-machine asynchronous classification results through the human-machine asynchronous classification model, and use the decision tree algorithm and random The forest algorithm evaluates the classification results.
- the accuracy rate of classification by decision tree algorithm after extracting the mean is 98.5%, and the specificity is 0.973; the accuracy rate of classification by random forest algorithm is 0.956, and the specificity is 0.9666.
- the accuracy rate of classification by decision tree algorithm is as high as 0.926, and the specificity is 0.973; the accuracy rate of classification by random forest algorithm is 0.953, and the specificity is 0.9666.
- the accuracy rate of classification by decision tree algorithm was 0.956, and the specificity was 0.973; the accuracy rate of classification by random forest algorithm was 0.958, and the specificity was 0.9666.
- the accuracy rate of classification by decision tree algorithm was 0.944, and the specificity was 0.974; the accuracy rate of classification by random forest algorithm was 0.979, and the specificity was 0.9667.
- the accuracy rate of classification by decision tree algorithm was 0.924, and the specificity was 0.979; the accuracy rate of classification by random forest algorithm was 0.983, and the specificity was 0.9667.
- the ventilator-human-machine asynchronous classification method of the embodiment of the present invention uses simulated lungs and ventilators to simulate human-machine asynchronous events, collects multi-channel respiratory data, and performs variance, mean, standard deviation, absolute value or square root of the respiratory data After feature extraction, the extracted features are input into the network model for human-machine asynchronous classification.
- the present invention has at least the following beneficial effects:
- the collected respiratory data has less interference and is convenient to collect, which can be applied to the asynchronous classification of multiple cases.
- FIG. 2 is a schematic structural diagram of a human-machine asynchronous classification system for a ventilator according to an embodiment of the present invention.
- the ventilator man-machine asynchronous classification system 40 of the embodiment of the present invention includes:
- Data collection module 41 used to collect breathing data under the man-machine asynchronous event simulated by the simulated lung and the ventilator;
- Feature extraction module 42 used to perform feature extraction on respiratory data, and generate sample data according to the extracted features; the extracted features include variance, mean, standard deviation, absolute value or square root;
- Asynchronous classification module 43 used to input sample data into the network model for training, obtain a trained human-machine asynchronous classification model, and classify ventilator human-machine asynchronous events through the trained human-machine asynchronous classification model.
- the ventilator-human-machine asynchronous classification system of the embodiment of the present invention uses simulated lungs and ventilators to simulate man-machine asynchronous events, collects multi-channel respiratory data, and extracts features such as variance, mean, standard deviation, absolute value, or square root of the respiratory data Finally, the extracted features are input into the network model for human-machine asynchronous classification.
- the present invention has at least the following beneficial effects:
- the collected respiratory data has less interference and is convenient to collect, which can be applied to the asynchronous classification of multiple cases.
- FIG. 3 is a schematic diagram of a terminal structure according to an embodiment of the present invention.
- the terminal 50 includes a processor 51 and a memory 52 coupled to the processor 51 .
- the memory 52 stores program instructions for implementing the above-mentioned ventilator-human-machine asynchronous classification method.
- the processor 51 is used to execute the program instructions stored in the memory 52 to control the human-machine asynchronous classification of the ventilator.
- the processor 51 may also be referred to as a CPU (Central Processing Unit, central processing unit).
- the processor 51 may be an integrated circuit chip with signal processing capabilities.
- the processor 51 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components .
- a general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.
- FIG. 4 is a schematic structural diagram of a storage medium according to an embodiment of the present invention.
- the storage medium in the embodiment of the present invention stores a program file 61 capable of realizing all the above-mentioned methods, wherein the program file 61 can be stored in the above-mentioned storage medium in the form of a software product, and includes several instructions to make a computer device (which can It is a personal computer, a server, or a network device, etc.) or a processor (processor) that executes all or part of the steps of the methods in various embodiments of the present invention.
- a computer device which can It is a personal computer, a server, or a network device, etc.
- processor processor
- the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc., which can store program codes. , or terminal devices such as computers, servers, mobile phones, and tablets.
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
一种呼吸机人机异步分类方法、系统、终端以及存储介质。所述呼吸机人机异步分类方法包括:采集由模拟肺和呼吸机模拟的人机异步事件下的模拟流量通道、潮气量通道、气道压力、肺泡压、胸膜腔内压、心脏压力以及当前功能残气量通道等多通道呼吸数据;对所述呼吸数据进行方差、均值、标准差、绝对值或平方根特征提取,并根据所提取的特征生成样本数据,根据样本数据训练得到人机异步分类模型;通过所述训练好的人机异步分类模型对呼吸机人机异步事件进行分类。本方法采集的呼吸数据干扰较小,采集方便,并使用方差、均值、标准差、绝对值或平方根等特征进行相邻通道的呼吸数据的差异性分析,提高了人机异步分类的准确度。
Description
本发明属医学数据处理技术领域,特别涉及一种呼吸机人机异步分类方法、系统、终端以及存储介质。
当呼吸机输送的呼吸相位与患者呼吸相位不匹配时,就存在患者-呼吸机之间的人机异步现象。人机异步对病人的治疗舒适度、机械通气持续时间、ICU停留时间、死亡率等都会产生不良影响。
在所有机械通气模式中,最普遍的异步现象是无效吸气努力和双触发。无效吸气努力为吸气肌用力后未达到呼吸机的触发阈值,没有产生呼吸机呼吸,导致患者的呼吸频率高于呼吸机的频率。双触发为由于过短的呼吸机吸气时间与病人的神经吸气时间不协调,从而使得患者一次吸气努力中出现两次呼吸机送气。因此准确的检测出人机异步现象是非常有必要的。目前关于机异步分类的研究数据都是通过临床获得,周期时间大,耗费人工时间多,且有较多的干扰因素,影响分类准确度。
发明内容
本发明提供了一种呼吸机人机异步分类方法、系统、终端以及存储介质,旨在至少在一定程度上解决现有技术中的上述技术问题之一。
为了解决上述问题,本发明提供了如下技术方案:
一种呼吸机人机异步分类方法,包括:
采集由模拟肺和呼吸机模拟的人机异步事件下的呼吸数据;
对所述呼吸数据进行特征提取,并根据所提取的特征生成样本数据;其中, 所提取的特征包括方差、均值、标准差、绝对值或平方根中的任意一种;
将所述样本数据输入网络模型进行训练,得到训练好的人机异步分类模型;
通过所述训练好的人机异步分类模型对呼吸机人机异步事件进行分类。
本发明实施例采取的技术方案还包括:所述采集由模拟肺和呼吸机模拟的人机异步事件下的呼吸数据包括:
所采集的人机异步事件下的呼吸数据包括正常呼吸、无效吸气努力呼吸和双触发呼吸三种人机异步事件下的呼吸数据。
本发明实施例采取的技术方案还包括:所述采集由模拟肺和呼吸机模拟的人机异步事件下的呼吸数据还包括:
所采集的呼吸数据包括模拟流量通道、潮气量通道、气道压力、肺泡压、胸膜腔内压、心脏压力以及波纹管位置的呼吸数据。
本发明实施例采取的技术方案还包括:所述采集由模拟肺和呼吸机模拟的人机异步事件下的呼吸数据后还包括:
对所述呼吸数据进行预处理,分别得到正常呼吸、无效吸气努力呼吸和双触发呼吸对应的样本数据。
本发明实施例采取的技术方案还包括:所述对所述呼吸数据进行预处理包括:
首先,对所述潮气量通道的呼吸数据进行波峰和波谷检测,获取呼吸数据中的呼吸周期,根据所述呼吸周期对呼吸数据进行分割处理,得到分割后的样本数据;所述分割的样本数据包括相同设定次数的正常呼吸周期、无效吸气努力呼吸周期以及双触发呼吸周期的呼吸数据;
然后,对所述分割后的样本数据进行补点操作,将每个呼吸周期的样本数据设为预设个数的数据点,对不够预设数据点个数的样本数据进行补零,并根据人机异步事件分别对每个样本数据进行标注。
本发明实施例采取的技术方案还包括:所述对所述呼吸数据进行特征提取具体为:
分别对正常呼吸、无效吸气努力呼吸、双触发呼吸的样本数据进行方差、 均值、标准差、绝对值或平方根特征提取;
所述方差表示一组数据的离散程度,计算公式为:
所述均值表示一组数据中趋势的量数,计算公式为:
其中,x
1、x
2……x
n为个体,M为平均数;
所述标准差是方差的算术平均根,计算公式为:
绝对值是指一个数在数轴上所对应点a到原点b的距离,其公式为:
A=|a-b|
均方根用于分析噪声,计算公式为:
本发明实施例采取的技术方案还包括:所述网络模型包括决策树或随机森林分类器。
本发明实施例采取的另一技术方案为:一种呼吸机人机异步分类系统,包括:
数据采集模块:用于采集由模拟肺和呼吸机模拟的人机异步事件下的呼吸数据;
特征提取模块:用于对所述呼吸数据进行特征提取,并根据所提取的特征生成样本数据;其中,所提取的特征包括方差、均值、标准差、绝对值或平方根中的任意一种;
异步分类模块:用于将所述样本数据输入网络模型进行训练,得到训练好的人机异步分类模型,通过所述训练好的人机异步分类模型对呼吸机人机异步事件进行分类。
本发明实施例采取的又一技术方案为:一种终端,所述终端包括处理器、与所述处理器耦接的存储器,其中,
所述存储器存储有用于实现所述呼吸机人机异步分类方法的程序指令;
所述处理器用于执行所述存储器存储的所述程序指令以控制呼吸机人机异步分类。
本发明实施例采取的又一技术方案为:一种存储介质,存储有处理器可运行的程序指令,所述程序指令用于执行所述呼吸机人机异步分类方法。
相对于现有技术,本发明实施例产生的有益效果在于:本发明实施例的呼吸机人机异步分类方法、系统、终端以及存储介质通过采用模拟肺和呼吸机模拟人机异步事件,采集多通道呼吸数据,并对呼吸数据进行方差、均值、标准差、绝对值或平方根特征提取后,将提取特征输入网络模型进行人机异步分类。相对于现有技术,本发明至少具有以下有益效果:
1、采集的呼吸数据干扰较小,且采集方便,可适用于多病例的人机异步分类。
2、采集多通道呼吸数据进行分析,有利于提高人机异步分类准确度。
3、使用方差、均值、标准差、绝对值以及平方根等特征,可以很好的识别出呼吸数据的差异性,进一步提高人机异步分类的准确度。
图1是本发明实施例的呼吸机人机异步分类方法的流程图;
图2为本发明实施例的呼吸机人机异步分类系统结构示意图;
图3为本发明实施例的终端结构示意图;
图4为本发明实施例的存储介质的结构示意图。
为了使本发明的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本发明进行进一步详细说明。应当理解,此处所描述的具体实施例仅用以解释本发明,并不用于限定本发明。
请参阅图1,是本发明实施例的呼吸机人机异步分类方法的流程图。本发 明实施例的呼吸机人机异步分类方法包括以下步骤:
S1:采集由模拟肺和呼吸机模拟的人机异步事件下的多通道呼吸数据;
本步骤中,模拟肺为TestChest(智能心肺仿生系统)模拟肺,呼吸机为迈瑞SV300呼吸机,模拟的疾病类型为ARDS(Acute respiratory distress syndrome,急性呼吸窘迫综合症)病人,其中,TestChest模拟肺和迈瑞SV300呼吸机的频率分别设置为50HZ,模拟的呼吸频率设置为每分钟21次,呼吸机通气模式为CPAR/PSV模式。可以理解,本发明同样适用于其他类型的模拟肺、疾病类型以及呼吸机,模拟肺以呼吸机参数也可根据实际应用进行设置。
TestChest模拟肺可模拟15个通道的呼吸,本发明实施例仅采用其中的模拟流量通道(Flow)、潮气量通道(Volume)、气道压力(Paw)、肺泡压(Alveolar pressure)、胸膜腔内压(Intrapleural pressure)、心脏压力(Cardiac pressure)以及波纹管位置等7个通道的呼吸数据进行人机异步分类。本发明实施例同样适用于其他通道的呼吸数据的人机异步分类。
本发明实施例中,采集的多通道呼吸数据包括正常呼吸、无效吸气努力呼吸以及双触发呼吸三种人机异步事件的呼吸数据,可以理解,本发明仅以较为常见的正常呼吸、无效吸气努力呼吸以及双触发呼吸三种异步事件的分类为例,同样适用于自动触发、呼吸肌肉收缩等其他人机异步事件的分类。
S2:对采集的多通道呼吸数据进行预处理,分别得到各人机异步事件对应的样本数据;
本步骤中,预处理包括数据分割和数据标注两个部分。数据分割具体为:首先,对呼吸数据进行潮气量通道的波峰和波谷检测,获取呼吸数据中的呼吸周期(每次呼气和吸气是一个呼吸周期),然后,根据呼吸周期对呼吸数据进行分割处理,得到分割后的样本数据;其中,分割的样本数据分别包括150次正常呼吸周期、150次无效吸气努力呼吸周期以及150次双触发呼吸周期的呼吸数据,具体呼吸周期次数可根据实际操作进行设定。
数据标注具体为:对分割后的样本数据进行补点操作,将每个呼吸周期的 样本数据设为98个数据点,对不够98个数据点的样本数据进行补零,并根据人机异步事件分别对每个样本数据进行标注,将正常呼吸的样本数据标签设置为[1,0,0],双触发呼吸的样本数据标签设置为[0,0,1],无效吸气努力呼吸的样本数据标签设置为[0,1,0]。具体数据点个数以及标注方式可根据实际操作进行设定。
S3:分别提取各人机异步事件对应的样本数据中的方差、均值、标准差、绝对值或平方根等任意一种特征,并分别将提取的特征转化为一维数据后,生成新的样本数据;
本步骤中,特征提取具体为:分别对正常呼吸、无效吸气努力呼吸、双触发呼吸的样本数据进行方差、均值、标准差、绝对值或平方根特征提取,根据提取的特征分析不同异步呼吸数据之间的差异性。其中,方差计算公式为:
均值表示一组数据中趋势的量数,计算公式为:
其中,x
1、x
2……x
n为个体,n表示样本的数量,M为平均数。
标准差是方差的算术平均根,计算公式为:
绝对值是指一个数在数轴上所对应的点a到原点b的距离,其公式为:
A=|a-b| (4)
均方根用于分析噪声,计算公式为:
其中,x
1、x
2……x
n为个体,n表示样本的数量。
S4:将新的样本数据输入网络模型进行训练,得到训练好的人机异步分类模型;
本步骤中,网络模型包括决策树或随机森林分类器。网络模型训练过程具体为:将新的样本数据按照1:1的比例进行测试集和训练集的划分,即50%作为用于模型训练的训练集,50%作为用于模型测试的测试集。完成模型训练后,通过决策树或随机森林算法对模型输出的人机异步分类结果进行准确率、召回率及F1分数计算,对模型性能进行评估。
S5:通过训练好的人机异步分类模型对呼吸机人机异步事件进行分类。
为了验证本发明实施例的可行性和有效性,采集了ARDS病人的呼吸数据进行实验验证,设定病人的每分钟通气周期为21次,分别采集病人的150次正常呼吸、150次无效吸气努力呼吸、150次双触发呼吸,分别对呼吸数据进行方差、均值、标准差、绝对值以及平方根特征提取后,通过人机异步分类模型输出人机异步分类结果,并分别利用决策树算法和随机森林算法对分类结果进行评估。其中,提取均值后通过决策树算法分类的准确率达98.5%,特异性为0.973;通过随机森林算法分类的准确率为0.956,特异性为0.9666。提取方差后通过决策树算法分类的准确率高达0.926,特异性为0.973;通过随机森林算法分类的准确率为0.953,特异性为0.9666。提取标准差后通过决策树算法分类的准确率达0.956,特异性为0.973;通过随机森林算法分类的准确率为0.958,特异性为0.9666。提取绝对值后通过决策树算法分类的准确率达0.944,特异性为0.974;通过随机森林算法分类的准确率为0.979,特异性为0.9667。提取均方根后通过决策树算法分类的准确率为0.924,特异性为0.979;通过随机森林算法分类的准确率为0.983,特异性为0.9667。实验结果表明,本发明实施例可以达到较高的分类精度。
基于上述,本发明实施例的呼吸机人机异步分类方法通过采用模拟肺和呼吸机模拟人机异步事件,采集多通道呼吸数据,并对呼吸数据进行方差、均值、 标准差、绝对值或平方根等特征提取后,将提取特征输入网络模型进行人机异步分类。相对于现有技术,本发明至少具有以下有益效果:
1、采集的呼吸数据干扰较小,且采集方便,可适用于多病例的人机异步分类。
2、采集多通道呼吸数据进行分析,有利于提高人机异步分类准确度。
3、使用方差、均值、标准差、绝对值以及平方根等特征,可以很好的识别出呼吸数据的差异性,进一步提高人机异步分类的准确度。
请参阅图2,为本发明实施例的呼吸机人机异步分类系统结构示意图。本发明实施例的呼吸机人机异步分类系统40包括:
数据采集模块41:用于采集由模拟肺和呼吸机模拟的人机异步事件下的呼吸数据;
特征提取模块42:用于对呼吸数据进行特征提取,并根据所提取的特征生成样本数据;所提取的特征包括方差、均值、标准差、绝对值或平方根;
异步分类模块43:用于将样本数据输入网络模型进行训练,得到训练好的人机异步分类模型,通过训练好的人机异步分类模型对呼吸机人机异步事件进行分类。
本发明实施例的呼吸机人机异步分类系统通过采用模拟肺和呼吸机模拟人机异步事件,采集多通道呼吸数据,并对呼吸数据进行方差、均值、标准差、绝对值或平方根等特征提取后,将提取特征输入网络模型进行人机异步分类。相对于现有技术,本发明至少具有以下有益效果:
1、采集的呼吸数据干扰较小,且采集方便,可适用于多病例的人机异步分类。
2、采集多通道呼吸数据进行分析,有利于提高人机异步分类准确度。
3、使用方差、均值、标准差、绝对值或平方根等特征,可以很好的识别出呼吸数据的差异性,进一步提高人机异步分类的准确度。
请参阅图3,为本发明实施例的终端结构示意图。该终端50包括处理器51、 与处理器51耦接的存储器52。
存储器52存储有用于实现上述呼吸机人机异步分类方法的程序指令。
处理器51用于执行存储器52存储的程序指令以控制呼吸机人机异步分类。
其中,处理器51还可以称为CPU(Central Processing Unit,中央处理单元)。处理器51可能是一种集成电路芯片,具有信号的处理能力。处理器51还可以是通用处理器、数字信号处理器(DSP)、专用集成电路(ASIC)、现成可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
请参阅图4,为本发明实施例的存储介质的结构示意图。本发明实施例的存储介质存储有能够实现上述所有方法的程序文件61,其中,该程序文件61可以以软件产品的形式存储在上述存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)或处理器(processor)执行本发明各个实施方式方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(ROM,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质,或者是计算机、服务器、手机、平板等终端设备。
对所公开的实施例的上述说明,使本领域专业技术人员能够实现或使用本发明。对这些实施例的多种修改对本领域的专业技术人员来说将是显而易见的,本发明中所定义的一般原理可以在不脱离本发明的精神或范围的情况下,在其它实施例中实现。因此,本发明将不会被限制于本发明所示的这些实施例,而是要符合与本发明所公开的原理和新颖特点相一致的最宽的范围。
Claims (10)
- 一种呼吸机人机异步分类方法,其特征在于,包括:采集由模拟肺和呼吸机模拟的人机异步事件下的呼吸数据;对所述呼吸数据进行特征提取,并根据所提取的特征生成样本数据;其中,所提取的特征包括方差、均值、标准差、绝对值或平方根中的任意一种;将所述样本数据输入网络模型进行训练,得到训练好的人机异步分类模型;通过所述训练好的人机异步分类模型对呼吸机人机异步事件进行分类。
- 根据权利要求1所述的呼吸机人机异步分类方法,其特征在于,所述采集由模拟肺和呼吸机模拟的人机异步事件下的呼吸数据包括:所采集的人机异步事件下的呼吸数据包括正常呼吸、无效吸气努力呼吸和双触发呼吸三种人机异步事件下的呼吸数据。
- 根据权利要求2所述的呼吸机人机异步分类方法,其特征在于,所述采集由模拟肺和呼吸机模拟的人机异步事件下的呼吸数据还包括:所采集的呼吸数据包括模拟流量通道、潮气量通道、气道压力、肺泡压、胸膜腔内压、心脏压力以及波纹管位置的呼吸数据。
- 根据权利要求3所述的呼吸机人机异步分类方法,其特征在于,所述采集由模拟肺和呼吸机模拟的人机异步事件下的呼吸数据后还包括:对所述呼吸数据进行预处理,分别得到正常呼吸、无效吸气努力呼吸和双触发呼吸对应的样本数据。
- 根据权利要求4所述的呼吸机人机异步分类方法,其特征在于,所述对所述呼吸数据进行预处理包括:首先,对所述潮气量通道的呼吸数据进行波峰和波谷检测,获取呼吸数据中的呼吸周期,根据所述呼吸周期对呼吸数据进行分割处理,得到分割后的样本数据;所述分割的样本数据包括相同设定次数的正常呼吸周期、无效吸气努力呼吸周期以及双触发呼吸周期的呼吸数据;然后,对所述分割后的样本数据进行补点操作,将每个呼吸周期的样本数据设为预设个数的数据点,对不够预设数据点个数的样本数据进行补零,并根据人机异步事件分别对每个样本数据进行标注。
- 根据权利要求1至6任一项所述的呼吸机人机异步分类方法,其特征在于,所述网络模型包括决策树或随机森林分类器。
- 一种呼吸机人机异步分类系统,其特征在于,包括:数据采集模块:用于采集由模拟肺和呼吸机模拟的人机异步事件下的呼吸数据;特征提取模块:用于对所述呼吸数据进行特征提取,并根据所提取的特征生成样本数据;其中,所提取的特征包括方差、均值、标准差、绝对值或平方根中的任意一种;异步分类模块:用于将所述样本数据输入网络模型进行训练,得到训练好的人机异步分类模型,通过所述训练好的人机异步分类模型对呼吸机人机异步 事件进行分类。
- 一种终端,其特征在于,所述终端包括处理器、与所述处理器耦接的存储器,其中,所述存储器存储有用于实现权利要求1-7任一项所述的呼吸机人机异步分类方法的程序指令;所述处理器用于执行所述存储器存储的所述程序指令以控制呼吸机人机异步分类。
- 一种存储介质,其特征在于,存储有处理器可运行的程序指令,所述程序指令用于执行权利要求1至7任一项所述呼吸机人机异步分类方法。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110708915.8A CN113539398A (zh) | 2021-06-25 | 2021-06-25 | 一种呼吸机人机异步分类方法、系统、终端以及存储介质 |
CN202110708915.8 | 2021-06-25 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022267382A1 true WO2022267382A1 (zh) | 2022-12-29 |
Family
ID=78096695
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2021/137605 WO2022267382A1 (zh) | 2021-06-25 | 2021-12-13 | 一种呼吸机人机异步分类方法、系统、终端以及存储介质 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN113539398A (zh) |
WO (1) | WO2022267382A1 (zh) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113539398A (zh) * | 2021-06-25 | 2021-10-22 | 中国科学院深圳先进技术研究院 | 一种呼吸机人机异步分类方法、系统、终端以及存储介质 |
CN114191665A (zh) * | 2021-12-01 | 2022-03-18 | 中国科学院深圳先进技术研究院 | 机械通气过程中人机异步现象的分类方法和分类装置 |
CN114216712B (zh) * | 2021-12-15 | 2024-03-08 | 深圳先进技术研究院 | 一种机械通气人机异步数据获取方法、检测方法及其设备 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120037159A1 (en) * | 2009-04-22 | 2012-02-16 | Resmed Ltd | Detection of asynchrony |
CN112560919A (zh) * | 2020-12-07 | 2021-03-26 | 杭州智瑞思科技有限公司 | 基于一维可解释卷积神经网络的人机不同步识别方法 |
CN112819093A (zh) * | 2021-02-24 | 2021-05-18 | 浙江工业大学 | 基于小数据集与卷积神经网络的人机不同步识别方法 |
CN113539398A (zh) * | 2021-06-25 | 2021-10-22 | 中国科学院深圳先进技术研究院 | 一种呼吸机人机异步分类方法、系统、终端以及存储介质 |
CN113521460A (zh) * | 2021-05-20 | 2021-10-22 | 深圳先进技术研究院 | 机械通气人机异步检测方法、装置及计算机可读存储介质 |
CN113539501A (zh) * | 2021-06-25 | 2021-10-22 | 中国科学院深圳先进技术研究院 | 一种呼吸机人机异步分类方法、系统、终端以及存储介质 |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2010097717A1 (en) * | 2009-02-25 | 2010-09-02 | Koninklijke Philips Electronics, N.V. | Patient-ventilator dyssynchrony detection |
EP3706845B1 (en) * | 2017-11-09 | 2023-10-18 | Autonomous Healthcare, Inc. | Clinical decision support system for patient-ventilator asynchrony detection and management |
US20190371460A1 (en) * | 2018-04-26 | 2019-12-05 | Respivar LLV | Detection and Display of Respiratory Rate Variability, Mechanical Ventilation Machine Learning, and Double Booking of Clinic Slots, System, Method, and Computer Program Product |
CN110290824A (zh) * | 2018-05-02 | 2019-09-27 | 东南大学附属中大医院 | 一种通气系统和呼吸同步监测方法、装置 |
CN109222978A (zh) * | 2018-09-22 | 2019-01-18 | 广州和普乐健康科技有限公司 | 一种呼吸努力检测方法 |
CN111738305B (zh) * | 2020-05-29 | 2022-06-24 | 浙江大学 | 一种基于dba-dtw-knn的机械通气人机不同步快速识别方法 |
-
2021
- 2021-06-25 CN CN202110708915.8A patent/CN113539398A/zh active Pending
- 2021-12-13 WO PCT/CN2021/137605 patent/WO2022267382A1/zh active Application Filing
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120037159A1 (en) * | 2009-04-22 | 2012-02-16 | Resmed Ltd | Detection of asynchrony |
CN112560919A (zh) * | 2020-12-07 | 2021-03-26 | 杭州智瑞思科技有限公司 | 基于一维可解释卷积神经网络的人机不同步识别方法 |
CN112819093A (zh) * | 2021-02-24 | 2021-05-18 | 浙江工业大学 | 基于小数据集与卷积神经网络的人机不同步识别方法 |
CN113521460A (zh) * | 2021-05-20 | 2021-10-22 | 深圳先进技术研究院 | 机械通气人机异步检测方法、装置及计算机可读存储介质 |
CN113539398A (zh) * | 2021-06-25 | 2021-10-22 | 中国科学院深圳先进技术研究院 | 一种呼吸机人机异步分类方法、系统、终端以及存储介质 |
CN113539501A (zh) * | 2021-06-25 | 2021-10-22 | 中国科学院深圳先进技术研究院 | 一种呼吸机人机异步分类方法、系统、终端以及存储介质 |
Also Published As
Publication number | Publication date |
---|---|
CN113539398A (zh) | 2021-10-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2022267381A1 (zh) | 一种呼吸机人机异步分类方法、系统、终端以及存储介质 | |
WO2022267382A1 (zh) | 一种呼吸机人机异步分类方法、系统、终端以及存储介质 | |
CN109893732B (zh) | 一种基于循环神经网络的机械通气人机不同步检测方法 | |
Gao et al. | An effective LSTM recurrent network to detect arrhythmia on imbalanced ECG dataset | |
WO2022242123A1 (zh) | 机械通气人机异步检测方法、装置及计算机可读存储介质 | |
CN110801221A (zh) | 基于无监督特征学习的睡眠呼吸暂停片段检测方法及设备 | |
CN111563451B (zh) | 基于多尺度小波特征的机械通气无效吸气努力识别方法 | |
Mondal et al. | A novel feature extraction technique for pulmonary sound analysis based on EMD | |
WO2021151295A1 (zh) | 患者治疗方案的确定方法、装置、计算机设备及介质 | |
CN106338597A (zh) | 呼吸气体测量的方法及系统 | |
WO2019113222A1 (en) | A data processing system for classifying keyed data representing inhaler device operation | |
Jayalakshmy et al. | CNN based Categorization of respiratory sounds using spectral descriptors | |
WO2023097780A1 (zh) | 机械通气过程中人机异步现象的分类方法和分类装置 | |
Pham et al. | Respiratory artefact removal in forced oscillation measurements: a machine learning approach | |
CN113941061B (zh) | 一种人机不同步识别方法、系统、终端以及存储介质 | |
WO2024152392A1 (zh) | 混合机械通气模式下人机不同步波形识别方法及相关设备 | |
Abushakra et al. | Efficient frequency-based classification of respiratory movements | |
CN114534041A (zh) | 检测人机通气不同步的呼吸波形分类模型训练方法及装置 | |
Sen et al. | Computerized Diagnosis of Respira tory Disorders | |
WO2023060478A1 (zh) | 一种人机不同步识别方法、系统、终端以及存储介质 | |
Sanchez-Perez et al. | Enabling Continuous Breathing-Phase Contextualization via Wearable-based Impedance Pneumography and Lung Sounds: A Feasibility Study | |
Qiao et al. | Research on Classification of Patient-ventilator Asynchrony Using Permutation Disalignment Index | |
Fatima et al. | Multi-Modality and Feature Fusion-Based COVID-19 Detection Through Long Short-Term Memory. | |
CN113730755B (zh) | 一种基于注意力机制的机械通气人机异步检测识别方法 | |
Ali et al. | Cough Detection Using Mobile Phone Accelerometer and Machine Learning Techniques |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21946856 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21946856 Country of ref document: EP Kind code of ref document: A1 |