CN115381432A - Single-mouth respiration waveform-based man-machine disorder detection method and system - Google Patents
Single-mouth respiration waveform-based man-machine disorder detection method and system Download PDFInfo
- Publication number
- CN115381432A CN115381432A CN202211055134.4A CN202211055134A CN115381432A CN 115381432 A CN115381432 A CN 115381432A CN 202211055134 A CN202211055134 A CN 202211055134A CN 115381432 A CN115381432 A CN 115381432A
- Authority
- CN
- China
- Prior art keywords
- data
- respiratory
- waveform
- mouth
- waveform data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
- A61B5/0816—Measuring devices for examining respiratory frequency
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
- A61B5/087—Measuring breath flow
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
- A61B5/087—Measuring breath flow
- A61B5/0871—Peak expiratory flowmeters
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Abstract
The invention discloses a human-computer disorder detection method, a human-computer disorder detection system, human-computer disorder detection equipment and a computer readable storage medium based on a single-mouth respiration waveform, wherein the method comprises the following steps: acquiring single-mouth respiratory waveform data of a person to be measured; the single-breath waveform data comprises flow rate waveform data and airway pressure waveform data; inputting the single-mouth respiratory waveform data of the person to be detected into a machine learning detection model to obtain the man-machine imbalance type of the single-mouth respiratory waveform data of the person to be detected; and outputting the man-machine imbalance type of the single-mouth respiratory waveform data of the person to be detected. The method can realize automatic segmentation of respiration based on real-time or off-line flow velocity waveforms, and effectively ensure the accuracy of the respiration segmentation; meanwhile, the method can effectively identify and classify the man-machine asynchrony or man-machine dyssynchrony based on the single-mouth respiration waveform.
Description
Technical Field
The invention relates to the field of respiration monitoring, in particular to a human-computer disorder detection method and a human-computer disorder detection system based on a single-mouth respiration waveform.
Background
Mechanical ventilation refers to the work of a ventilator to replace or assist the respiratory muscles when the respiratory organs are unable to maintain normal gas exchange, i.e. respiratory failure occurs. Mechanical ventilation strives for treatment time and creates conditions for respiratory failure caused by various clinical reasons and other various diseases needing respiratory function support.
Invasive mechanical ventilation therapy is an important treatment for severe patients with respiratory failure, however, inappropriate invasive mechanical ventilation may cause ventilator-related lung injury such as barotrauma and volume injury, and proper monitoring during mechanical ventilation helps to avoid adverse effects of mechanical ventilation. During invasive mechanical ventilation monitoring, the acquired flow rate and pressure waveforms are usually continuous waveforms, however, most monitoring parameters such as peak airway pressure, plateau airway pressure, positive end-expiratory pressure and the like are measured based on single-breath, so that it is important to accurately identify and segment each breath in the continuous ventilator waveform data, and the segmentation result directly influences the acquisition of the monitoring parameters during invasive mechanical ventilation.
During the invasive mechanical ventilation treatment, the breathing machine mainly depends on the opening and closing of the inhalation valve and the exhalation valve and the data monitored by the flow sensor to judge inhalation and exhalation, one complete inhalation process and one complete respiration process can be judged as one complete respiration, the beginning of the inhalation phase is defined as the beginning of the respiration, and the end of the exhalation phase (namely the beginning of the inhalation phase of the next breath) is defined as the end time of the respiration. At present, no technology for realizing automatic breath segmentation based on flow velocity waveforms exists; for the analysis of off-line data, the respiratory segmentation method mainly comprises artificial segmentation and respiratory segmentation based on the periodic variation rule and characteristics of flow rate or airway pressure waveform. The above-mentioned method mainly has the following defects: 1. the algorithm and the monitoring system of the breathing machine can automatically split breathing, but the algorithms of different breathing machine manufacturers are different and not public, so that the automatic breathing splitting results of different brands of breathing machines are different and have no comparability, and in addition, the automatic splitting results are difficult to derive to bring difficulty for subsequent off-line analysis and data processing; 2. the manual segmentation method has the highest accuracy, but wastes time and labor, and massive breath monitoring data generated beside a bed are difficult to segment one by one; 3. the segmentation of breathing based on the rule of flow rate or the periodic variation rule of airway pressure and characteristic can realize automation to a certain extent, but to having waveform disturbance, especially when having the PVA phenomenon, the rate of accuracy is not enough.
The phenomenon of human-computer asynchrony (PVA) caused by mismatching of the patient demand and the assistance provided by the breathing machine in amplitude or phase during mechanical ventilation can cause harm to the patient, and accurate breath segmentation is helpful for identification and classification of the PVA, so that the accuracy of the PVA automatic identification algorithm is improved, and the possibility of providing auxiliary treatment decisions for different PVA types is provided. And accurately identifying and detecting the type of man-machine asynchrony or man-machine dyssynchrony is very important for the treatment of patients.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides a human-computer disorder detection method based on single-mouth respiration waveform, which can realize automatic segmentation of respiration based on real-time or off-line flow velocity waveform and effectively ensure the accuracy of respiration segmentation; meanwhile, effective identification and classification are carried out on man-machine asynchronism or man-machine imbalance based on the single-mouth respiration waveform.
The application discloses a man-machine imbalance detection method based on single-mouth respiration waveform, which comprises the following steps:
acquiring single-mouth respiratory waveform data of a person to be measured; the single-ported respiratory waveform data comprises flow rate waveform data and airway pressure waveform data;
inputting the single-mouth respiratory waveform data of the person to be detected into a machine learning detection model to obtain the man-machine imbalance type of the single-mouth respiratory waveform data of the person to be detected;
and outputting the man-machine imbalance type of the single-mouth respiratory waveform data of the person to be detected.
The detection method further comprises the following steps: preprocessing the single-mouth respiratory waveform data of the person to be detected to obtain preprocessed single-mouth respiratory waveform data;
optionally, the determining manner of the machine learning detection model includes: inputting pre-labeled single-mouth respiratory waveform data, performing feature extraction on the pre-labeled single-mouth respiratory waveform data to obtain feature data after feature extraction, and constructing a machine learning detection model by using the feature data after feature extraction to obtain the machine learning detection model.
The detection method further comprises the following steps: obtaining or drawing FV ring and/or PV ring waveform image data according to the preprocessed single-mouth breathing waveform data, and outputting the FV ring and/or PV ring waveform image data; the single breath waveform data further comprises volume data derived based on the flow rate data;
performing feature extraction on the FV ring and/or PV ring waveform image data to obtain FV ring and/or PV ring waveform image data with extracted features as feature data; inputting the FV ring and/or PV ring waveform image data after the characteristic extraction into a machine learning detection model to obtain the man-machine imbalance type of the single-mouth respiratory waveform data of the person to be detected;
optionally, the FV ring waveform image data is obtained based on flow rate data and volume data, and the abscissa of the FV ring waveform image data is volume data V and the ordinate is flow rate data F; the PV ring waveform image data is obtained based on airway pressure data and volume data, the abscissa of the PV ring waveform image data is volume data V, and the ordinate is airway pressure data P;
optionally, the flow rate waveform data is based on a breath dotting time; the breath dotting Time is Time which is set according to the sampling frequency hz of the breathing machine and the serial number of the data, and the calculation formula is as follows: time = (number-1)/hz.
Optionally, the flow rate waveform data is flow rate waveform data with a Time abscissa and flow rate data with a flow rate ordinate;
optionally, the airway pressure waveform data is airway pressure waveform data with an abscissa of Time and an ordinate of airway pressure data;
optionally, the volume waveform data is volume waveform data with a Time abscissa and a volume data ordinate; the volume data is calculated by the formula:
the man-machine disorder type of the single-mouth respiratory waveform data of the testee comprises: normal/abnormal or normal/abnormal subtype.
The single-mouth respiratory waveform data of the person to be measured comprises: single-ported respiratory waveform data segmented based on flow velocity waveforms;
the method or the steps for acquiring the single-mouth respiration waveform data segmented based on the flow velocity waveform comprise the following steps:
acquiring respiratory waveform data of a person to be measured;
standardizing the respiratory waveform data of the person to be measured to obtain the respiratory waveform data after standardized treatment; the normalization processed respiratory waveform data comprises: searching for a point where the flow velocity crosses zero and the derivative is greater than zero from the flow velocity waveform data based on the respiration dotting time, and respectively recording the time indexes of the point to obtain the respiration waveform data after the normalization processing; optionally, the preprocessing is to traverse the respiratory waveform data in sequence, at least once;
cutting the respiratory waveform data subjected to the standardization processing into respiratory data with a plurality of respiratory cycles to obtain respiratory data subjected to the standardization processing and having a plurality of respiratory cycles; the cutting is to find all the flow velocity zero crossing points and the point of which the derivative is greater than zero; performing feature extraction on the respiratory data which are subjected to the standardization processing and have a plurality of respiratory cycles to obtain respiratory data which have a plurality of respiratory cycles and are subjected to feature extraction as feature data; and inputting the characteristic data of the person to be measured into a classification model to obtain a classification result of the characteristic data.
The normalizing the processed respiratory data having a plurality of respiratory cycles comprises: respectively segmenting adjacent points to form a waveform corresponding to each breath to obtain breath data of a plurality of breath cycles;
optionally, the adjacent points of the nth and n +1 are respectively taken, and a single breathing cycle is defined between the points of the nth and n + 1; wherein N is more than or equal to 1 and less than N-1, and N is the total number of the time indexes of all the points.
The feature data which is the feature data of the respiration data with a plurality of respiration cycles after the feature extraction includes: the respiration time interval of the single-mouth respiration, the flow rate change of the single-mouth respiration, the ratio of the expiration time of the single-mouth respiration to the total respiration time of the single-mouth respiration, and the rising slope of the expiration waveform of the single-mouth respiration;
optionally, the breathing time interval of the single mouth breathing is: the time interval a between the time indexes respectively corresponding to the adjacent points; the value range of a is made of 10 s-a-1s;
optionally, the flow rate variation of the single-mouth breath is: the flow rate change b between the time indexes respectively corresponding to the adjacent points; the value range of b is 0L/min < b <20L/min;
optionally, the ratio of the expiration time of the single-mouth breath to the total breath time of the single-mouth breath is: the expiration time between the time indexes respectively corresponding to the adjacent points accounts for the proportion c% of the total respiration time between the time indexes respectively corresponding to the adjacent points; the value range of c% is 20% -80%;
optionally, the rising slope of the expiratory waveform of the single mouth breath is: the rising slope d of the expiratory waveform between the time indexes respectively corresponding to the adjacent points; within the initial 100ms of inspiration, the value range of d is 10-50L/min/s.
The method or the step of inputting the feature data of the person to be tested into the classification model to obtain the classification result of the feature data of the person to be tested comprises the following steps:
inputting the breathing time interval of the single breathing cycle of the person to be detected into a classification model, and judging whether the breathing time interval of the single breathing cycle of the person to be detected falls into a range; in the case where the breathing time interval of said single breathing cycle of said subject falls within a range, outputting yes and entering a phase of inputting the variation of the flow rate of said single breathing cycle of said subject into a classification model; otherwise, the output is not, and the operation is terminated;
inputting the flow rate change of the single breathing cycle of the person to be tested into a classification model, and judging whether the flow rate change of the single breathing cycle of the person to be tested falls into a range b or not; if the change of the flow rate of the single respiratory cycle of the testee falls into the range b, outputting yes, and inputting the ratio of the expiration time of the single respiratory cycle of the testee to the total respiration time of the single respiratory cycle into a classification model; otherwise, the output is no, and the operation is terminated;
inputting the ratio of the expiration time of the single respiration period of the person to be tested to the total respiration time of the single respiration period into a classification model, and judging whether the ratio of the expiration time of the single respiration period of the person to be tested to the total respiration time of the single respiration period falls within a range c; under the condition that the ratio of the expiration time of the single respiration period of the testee to the total respiration time of the single respiration period falls into a range c, outputting yes, and entering a stage of ascending a slope of an expiration waveform of the single respiration period of the testee to a classification model; otherwise, the output is not, and the operation is terminated;
inputting the rising slope of the expiratory waveform of the single respiratory cycle of the person to be detected into a classification model, and judging whether the rising slope of the expiratory waveform of the single respiratory cycle of the person to be detected falls into a range d; outputting yes and outputting a classification result of respiratory waveform data of the person to be tested under the condition that the rising slope of the respiratory waveform of the single respiratory cycle of the person to be tested falls into a range d; otherwise, the output is no, and the operation is terminated.
An apparatus for human-machine disorder detection based on a single-mouth respiratory waveform, the apparatus comprising: a memory and a processor;
the memory is to store program instructions;
the processor is configured to invoke program instructions that, when executed, perform the above-described method for detecting an imbalance between an individual and a human being based on a respiration waveform.
A system for detecting human-machine imbalance based on a single-mouth respiratory waveform, comprising:
the acquisition unit is used for acquiring single-mouth respiratory waveform data of a person to be measured; the single-ported respiratory waveform data comprises flow rate waveform data and airway pressure waveform data;
the processing unit is used for inputting the single-mouth respiratory waveform data of the person to be tested into a machine learning detection model to obtain the man-machine imbalance type of the single-mouth respiratory waveform data of the person to be tested;
and the classification unit is used for outputting the man-machine imbalance type of the single-mouth respiratory waveform data of the person to be detected.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the above-mentioned method of man-machine disorder detection based on a single-mouth respiration waveform.
The application of the device in the extraction of the breathing parameters; optionally, after each breath is segmented based on the real-time or off-line flow rate waveform, the airway pressure, esophageal pressure and volume change of each breath can be used for extracting parameters with a plurality of characteristics for monitoring respiratory therapy.
The application has the following beneficial effects:
1. the application innovatively discloses a man-machine imbalance detection method based on a single-mouth respiration waveform, the accuracy of single-mouth respiration segmentation is effectively guaranteed, a respiration segmentation result is standardized, and comparability is achieved; the asynchronous human-computer or man-computer disorder is effectively identified and classified based on the single-mouth breathing result with high segmentation result accuracy, so that the possibility of giving auxiliary treatment decisions aiming at different PVA types is provided;
2. the automatic breath segmentation method overcomes the defects that time and labor are wasted when manual segmentation is adopted, and the accuracy is insufficient when the breath segmentation is carried out by adopting rules based on the periodic change rule and the characteristics of flow velocity or airway pressure;
3. the application innovatively discloses an automatic respiration segmentation method based on real-time or off-line flow velocity waveforms, which automatically segments respiration waveforms into single-mouth respiration, so that doctors can conveniently and quickly identify whether the respiration of patients is normal, the diagnosis time of the doctors is greatly shortened, and valuable treatment time is won for ICU patients; in addition, by referring to the segmentation rule, the automatic segmentation of the respiratory waveform can be realized by using a computer program, so that the identification and monitoring of the respiratory waveform abnormity can be conveniently carried out subsequently.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a human-computer disorder detection method based on a single-mouth respiration waveform provided by the embodiment of the invention;
FIG. 2 is a schematic diagram of a human-machine disorder detection device based on a single-mouth respiration waveform provided by an embodiment of the invention;
FIG. 3 is a schematic flow chart of a human-machine imbalance detection system based on a single-breath waveform provided by an embodiment of the invention;
FIG. 4 is a flowchart illustrating a classification of a method for detecting human-computer disorders based on a single-breath waveform according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of the points where the flow rate crosses zero and the derivative is greater than zero according to the single-breath waveform-based dysregulation detection method provided by the embodiment of the invention;
FIG. 6 is a schematic diagram of a time interval a of a single-mouth respiration waveform-based human-computer disorder detection method provided by the embodiment of the invention;
FIG. 7 is a schematic diagram of the flow rate variation b of the method for detecting human-computer disorder based on single-mouth respiration waveform according to the embodiment of the present invention;
fig. 8 is a schematic diagram of the rising slope d of the expiratory waveform of the method for detecting human-computer disorder based on the single-mouth respiration waveform according to the embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention.
In some flows described in the present specification and claims and above figures, a number of operations are included that occur in a particular order, but it should be clearly understood that these operations may be performed out of order or in parallel as they occur herein, with the order of the operations being given as 101, 102, etc. merely to distinguish between various operations, and the order of the operations itself does not represent any order of performance. Additionally, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first", "second", etc. in this document are used for distinguishing different messages, devices, modules, etc., and do not represent a sequential order, nor limit the types of "first" and "second" to be different.
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a human-computer disorder detection method based on a single-mouth respiration waveform according to an embodiment of the present invention, specifically, the method includes the following steps:
101: acquiring single-mouth respiratory waveform data of a person to be measured; the single-breath waveform data comprises flow rate waveform data and airway pressure waveform data;
in one embodiment, the single-breath waveform data is at least flow rate waveform data and airway pressure waveform data, and information such as ventilator setting parameters, patient disease state, etc. may be added during specific use;
in one embodiment, the detection method further comprises: preprocessing the single-mouth respiratory waveform data of the person to be detected to obtain the preprocessed single-mouth respiratory waveform data; the preprocessing method is the conventional preprocessing of machine learning/deep learning training data, comprises the processes of data cleaning, data filling, data standardization and the like, and unifies the data format.
In one embodiment, the single-breath waveform data of the subject includes: single-ported respiratory waveform data segmented based on flow velocity waveforms;
the method or the step for acquiring the single-mouth respiratory waveform data segmented based on the flow velocity waveform comprises the following steps:
acquiring respiratory waveform data of a person to be measured; the respiratory waveform data includes: respiratory flow rate data based on breath strike time; the respiration Flow rate data based on the respiration dotting Time is Flow rate waveform data with the abscissa of Time(s) and the ordinate of Flow (L/min); the breath dotting Time is Time(s), the Time is set according to the sampling frequency hz of the breathing machine and the serial number of the data, and the calculation formula is as follows: time = (number-1)/hz; number is the serial number of the sample point.
Standardizing the respiratory waveform data of the person to be detected to obtain the standardized respiratory waveform data; the normalization processed respiratory waveform data comprises: searching for a point where the flow velocity crosses zero and the derivative is greater than zero from the flow velocity waveform data based on the respiration dotting time, and respectively recording the time indexes of the point to obtain the respiration waveform data after the normalization processing; optionally, the preprocessing is to traverse the respiratory waveform data in sequence, at least once;
cutting the respiratory waveform data subjected to the standardization processing into respiratory data with a plurality of respiratory cycles to obtain respiratory data subjected to the standardization processing and having a plurality of respiratory cycles; the division is to find all the flow rate zero-crossing points (one point is less than or equal to 0, and the other point is greater than or equal to 0) and the points with derivative greater than zero; this point is shown in FIG. 5 circle; performing feature extraction on the respiratory data which are subjected to the standardization processing and have a plurality of respiratory cycles to obtain respiratory data which have a plurality of respiratory cycles and are subjected to feature extraction as feature data; and inputting the characteristic data of the person to be measured into a classification model to obtain a classification result of the characteristic data.
The normalizing the processed respiratory data having a plurality of respiratory cycles comprises: respectively segmenting adjacent points to form a waveform corresponding to each breath to obtain breath data of a plurality of breath cycles;
each breath is a single breath, and the definition of the single breath is as follows: one complete inspiration phase plus one complete expiration phase; the change of inspiratory Flow (Flow) from negative to positive is recorded as the beginning of a breath; the termination of a breath is the previous sampling point from which the next breath begins.
Optionally, the adjacent points of the nth and n +1 are respectively taken, and a single breathing cycle is defined between the points of the nth and n + 1; wherein N is more than or equal to 1 and less than N-1, and N is the total number of the time indexes of all the points.
The feature data which is the feature data of the respiration data with a plurality of respiration cycles after the feature extraction includes: the respiration time interval of the single-mouth respiration, the flow rate change of the single-mouth respiration, the ratio of the expiration time of the single-mouth respiration to the total respiration time of the single-mouth respiration, and the rising slope of the expiration waveform of the single-mouth respiration;
optionally, the breathing time interval of the single-mouth breath is: the time interval a between the time indexes respectively corresponding to the adjacent points, i.e. the time interval between two adjacent circles, is shown by the arrow in fig. 6; the value range of a is made of 10 s-a-1s; the a is preferably 0 s-a-Ap-0.6s; the respiratory rate of normal persons is about 8-20 times/min, and the respiratory rate of patients can reach 30-60 times/min under pathological conditions, so the respiratory time a is in the range of 0 s-a-1s, and the extreme case that the respiratory rate is more than 100 times is extremely rare, so the preferred value range of a is 0 s-a-0.6s.
Optionally, the flow rate variation of the single-mouth breath is: the flow rate change b between the time indexes respectively corresponding to the adjacent points; as indicated by the arrows in fig. 7; the value range of b is 0L/min < b <20L/min; said b is preferably 0L/min < b <10L/min; the inspiratory flow rate of normal people is 40-60L/min, the flow rate of children is 5-10L/min, so the flow rate change b between breaths has the value range of 0L/min < b <20L/min, and considering that the inspiratory power of partial patients is insufficient, the preferable value range of b is 0L/min < b <10L/min.
Optionally, the ratio of the expiration time (time when the flow rate is negative) of the single-mouth breath to the total respiration time (time between two adjacent circles) of the single-mouth breath is: the expiration time between the time indexes respectively corresponding to the adjacent points accounts for the proportion c% of the total respiration time between the time indexes respectively corresponding to the adjacent points; the value range of c% is 20% -80%; c is preferably 30% -50%; according to the definition of double triggering, the expiration time between two inspiration periods is less than half of the average inspiration time, the value range of c is 20-80%, wherein the preferable value range of c is 30-50%. The arrangement can well avoid the influence of double or multiple triggering conditions on the result; the clinical tachypnea breathes, when the breathing is abnormal, the breathing is carried out for 2 times in a short time, and the accuracy of calculating single breathing by the segmentation method is better; and judging once in the middle, and when an abnormal condition occurs, the method refers to effective assistance to process.
Optionally, the rising slope of the expiratory waveform of the single mouth breath is: the rising slope d of the expiratory waveform between the time indexes respectively corresponding to the adjacent points; as indicated by the block in fig. 8; within the initial 100ms of air suction, the value range of d is 10-50L/min/s; d is preferably 5-25L/min/s; the flow trigger setting is about 1-5L/min, d ranges from about 10-50L/min/s within 100ms of the initial inspiration, and preferably ranges from 5-25L/min/s in view of the fractional trigger delay.
The method or the step of inputting the feature data of the person to be measured into the classification model to obtain the classification result of the feature data of the person to be measured comprises the following steps:
inputting the breathing time interval of the single breathing cycle of the person to be detected into a classification model, and judging whether the breathing time interval of the single breathing cycle of the person to be detected falls into a range; in the case where the breathing time interval of said single breathing cycle of said subject falls within a range, outputting yes and entering a phase of inputting the variation of the flow rate of said single breathing cycle of said subject into a classification model; otherwise, the output is not, and the operation is terminated; a in this step is denoted by 1 in fig. 4;
inputting the flow rate change of the single respiratory cycle of the person to be detected into a classification model, and judging whether the flow rate change of the single respiratory cycle of the person to be detected falls into a range b; if the change of the flow rate of the single respiratory cycle of the testee falls into the range b, outputting yes, and inputting the ratio of the expiration time of the single respiratory cycle of the testee to the total respiration time of the single respiratory cycle into a classification model; otherwise, the output is not, and the operation is terminated; b in this step is denoted 2 in FIG. 4;
inputting the ratio of the expiration time of the single respiration period of the person to be tested to the total respiration time of the single respiration period into a classification model, and judging whether the ratio of the expiration time of the single respiration period of the person to be tested to the total respiration time of the single respiration period falls within a range c; under the condition that the ratio of the expiration time of the single respiration period of the testee to the total respiration time of the single respiration period falls within a range c, outputting yes, and entering a stage of enabling the rising slope of the expiration waveform of the single respiration period of the testee to be in a classification model; otherwise, the output is no, and the operation is terminated; c in this step is denoted 3 in fig. 4;
inputting the rising slope of the expiratory waveform of the single respiratory cycle of the person to be tested into a classification model, and judging whether the rising slope of the expiratory waveform of the single respiratory cycle of the person to be tested falls into a range d; if the rising slope of the expiratory waveform of the single respiratory cycle of the person to be detected falls within the range d, outputting yes and outputting a classification result of the respiratory waveform data of the person to be detected; otherwise, the output is no, and the operation is terminated. D in this step is denoted 4 in FIG. 4;
in one embodiment, the respiratory waveform data is respiratory waveform data having a continuous waveform signal.
In one embodiment, the respiratory waveform data further comprises: esophageal pressure waveform data based on breath dotting time; the esophagus pressure waveform data is esophagus pressure waveform data with the abscissa being Time and the ordinate being esophagus pressure data Pes (cmH 2O);
102: inputting the single-mouth respiratory waveform data of the person to be detected into a machine learning detection model to obtain the man-machine imbalance type of the single-mouth respiratory waveform data of the person to be detected;
optionally, the determining manner of the machine learning detection model includes: inputting pre-labeled single-mouth respiratory waveform data, performing feature extraction on the pre-labeled single-mouth respiratory waveform data to obtain feature data after feature extraction, and constructing a machine learning detection model by using the feature data after feature extraction to obtain the machine learning detection model. The pre-labeled single-mouth respiratory waveform data is single-mouth respiratory waveform data with an artificial labeling result.
The detection method further comprises the following steps: obtaining or drawing FV ring and/or PV ring waveform image data according to the preprocessed single-mouth respiratory waveform data, and outputting the FV ring and/or PV ring waveform image data; the single breath waveform data further comprises volume data derived based on the flow rate data;
performing feature extraction on the FV ring and/or PV ring waveform image data to obtain FV ring and/or PV ring waveform image data with extracted features as feature data; inputting the FV ring and/or PV ring waveform image data after the characteristic extraction into a machine learning detection model (deep learning detection model) to obtain the man-machine imbalance type of the single-mouth respiratory waveform data of the person to be detected;
optionally, the FV ring waveform image data is obtained based on flow rate data and volume data, and the abscissa of the FV ring waveform image data is volume data V and the ordinate is flow rate data F; the PV ring waveform image data is obtained based on air channel pressure data and volume data, the abscissa of the PV ring waveform image data is volume data V, and the ordinate of the PV ring waveform image data is air channel pressure data P;
optionally, the flow rate waveform data is based on a breath dotting time; the breath dotting Time is Time, the Time is set according to the sampling frequency hz of the breathing machine and the serial number of the data, and the calculation formula is as follows: time = (number-1)/hz.
Optionally, the flow rate waveform data is flow rate waveform data with a Time abscissa and flow rate data with a flow rate ordinate;
optionally, the airway pressure waveform data is airway pressure waveform data with an abscissa of Time and an ordinate of airway pressure data;
optionally, the abscissa of the volume waveform data is Time, and the ordinate of the volume waveform data is volume waveform data of the volume data; the volume data is calculated by the formula:
in one embodiment, the respiratory waveform data is respiratory waveform data having a continuous waveform signal.
The determination mode of the classification model comprises the following steps:
acquiring respiratory waveform data of normal people;
standardizing the respiratory waveform data to obtain the standardized respiratory waveform data; cutting the respiratory waveform data subjected to the standardization processing into respiratory data with a plurality of respiratory cycles to obtain respiratory data which are subjected to the standardization processing and have a plurality of respiratory cycles;
performing feature selection or feature extraction on the respiratory data which are subjected to the standardization processing and have a plurality of respiratory cycles to obtain the respiratory data which have a plurality of respiratory cycles and are subjected to the feature selection or feature extraction and serve as feature data;
and performing feature extraction on the feature data by adopting a machine learning method to obtain feature data after feature extraction, and constructing a classification model by using the feature data after feature extraction to obtain the constructed classification model.
103: and outputting the man-machine imbalance type of the single-mouth respiratory waveform data of the person to be detected.
The human-computer disorder type of the single-mouth respiratory waveform data of the testee comprises the following steps: normal/abnormal or normal/abnormal subtype.
The detection method further comprises determining a breathing abnormality detection result based on the output of the type of human-computer disorder.
FIG. 2 isThe embodiment of the invention provides a schematic diagram of man-machine disorder detection equipment based on a single-mouth respiration waveform, which comprises: a memory and a processor;
the memory is to store program instructions;
the processor is configured to invoke program instructions that, when executed, perform the above-described method for detecting an imbalance between an individual and a human being based on a respiration waveform.
FIG. 3 is a schematic view ofThe embodiment of the invention provides a schematic flow chart of a human-computer disorder detection system based on a single-mouth respiration waveform, which comprises the following steps:
an acquisition unit 301, configured to acquire single-mouth respiratory waveform data of a person to be measured; the single-breath waveform data comprises flow rate waveform data and airway pressure waveform data;
a first processing unit 302, configured to input the single breath waveform data of the subject into a machine learning detection model, so as to obtain a human-computer imbalance type of the single breath waveform data of the subject;
a classification unit 303, configured to output a human-computer imbalance type of the single breath waveform data of the subject.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the above-mentioned method for detecting a man-machine disorder based on a single-mouth respiration waveform.
The validation results of this validation example show that assigning an intrinsic weight to an indication can moderately improve the performance of the method relative to the default settings.
It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable storage medium, and the storage medium may include: read Only Memory (ROM), random Access Memory (RAM), magnetic or optical disks, and the like.
It will be understood by those skilled in the art that all or part of the steps in the method for implementing the above embodiments may be implemented by hardware that is instructed to implement by a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
While the invention has been described in detail with reference to specific embodiments thereof, it will be apparent to one skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention.
Claims (10)
1. A man-machine disorder detection method based on a single-mouth respiration waveform comprises the following steps:
acquiring single-mouth respiratory waveform data of a person to be measured; the single-ported respiratory waveform data comprises flow rate waveform data and airway pressure waveform data;
inputting the single-mouth respiratory waveform data of the person to be detected into a machine learning detection model to obtain the man-machine imbalance type of the single-mouth respiratory waveform data of the person to be detected;
and outputting the man-machine imbalance type of the single-mouth respiratory waveform data of the person to be detected.
2. The method of detecting human-computer disorder based on unioral respiration waveform of claim 1, further comprising: preprocessing the single-mouth respiratory waveform data of the person to be detected to obtain the preprocessed single-mouth respiratory waveform data;
optionally, the determining manner of the machine learning detection model includes: inputting pre-labeled single-mouth respiratory waveform data with an artificial labeling result, performing feature extraction on the pre-labeled single-mouth respiratory waveform data to obtain feature data after feature extraction, and constructing a machine learning detection model by using the feature data after feature extraction to obtain the machine learning detection model.
3. The method of claim 2, further comprising: obtaining or drawing FV ring and/or PV ring waveform image data according to the preprocessed single-mouth respiratory waveform data, and outputting the FV ring and/or PV ring waveform image data; the single-ported respiratory waveform data further comprises volumetric data derived based on flow rate data;
performing feature extraction on the FV ring and/or PV ring waveform image data to obtain FV ring and/or PV ring waveform image data with extracted features as feature data; inputting the FV ring and/or PV ring waveform image data after the characteristic extraction into a machine learning detection model to obtain the man-machine imbalance type of the single-mouth respiratory waveform data of the person to be detected;
optionally, the FV ring waveform image data is obtained based on flow rate data and volume data, and the abscissa of the FV ring waveform image data is volume data V and the ordinate is flow rate data F; the PV ring waveform image data is obtained based on air channel pressure data and volume data, the abscissa of the PV ring waveform image data is volume data V, and the ordinate of the PV ring waveform image data is air channel pressure data P;
optionally, the flow rate waveform data is based on a breath dotting time; the breath dotting Time is Time, the Time is set according to the sampling frequency hz of the breathing machine and the serial number of the data, and the calculation formula is as follows: time = (number-1)/hz;
optionally, the flow rate waveform data is flow rate waveform data with a Time abscissa and a flow rate data ordinate;
optionally, the airway pressure waveform data is airway pressure waveform data with a horizontal coordinate of Time and a vertical coordinate of airway pressure data;
optionally, the volume waveform data is volume waveform data with a Time abscissa and a volume data ordinate; the volume data is calculated by the formula:
4. the method of claim 1, wherein the type of disorder of the subject's single-breath waveform data comprises: normal/abnormal or normal/abnormal subtype.
5. The method of claim 1, wherein the data of the subject's single-breath waveform comprises: single-ported respiratory waveform data segmented based on flow velocity waveforms;
the method or the steps for acquiring the single-mouth respiration waveform data segmented based on the flow velocity waveform comprise the following steps:
acquiring respiratory waveform data of a person to be measured;
standardizing the respiratory waveform data of the person to be detected to obtain the standardized respiratory waveform data; the normalization processed respiratory waveform data comprises: searching for a point where the flow velocity crosses zero and the derivative is greater than zero from the flow velocity waveform data based on the respiration dotting time, and respectively recording the time indexes of the point to obtain the respiration waveform data after the normalization processing; optionally, the preprocessing is to traverse the respiratory waveform data in sequence, at least once; cutting the respiratory waveform data subjected to the standardization processing into respiratory data with a plurality of respiratory cycles to obtain respiratory data subjected to the standardization processing and having a plurality of respiratory cycles; the cutting is to find all the flow velocity zero crossing points and the point of which the derivative is greater than zero; performing feature extraction on the respiratory data which are subjected to the standardization processing and have a plurality of respiratory cycles to obtain respiratory data which have a plurality of respiratory cycles and are subjected to feature extraction as feature data; and inputting the characteristic data of the person to be tested into a classification model to obtain a classification result of the characteristic data.
6. The method of claim 2, wherein the normalizing the processed breathing data with a plurality of breathing cycles comprises: respectively cutting adjacent points to form a waveform corresponding to each breath to obtain breath data of the plurality of breath cycles;
optionally, the adjacent points of the nth and n +1 are respectively taken, and a single breathing cycle is defined between the points of the nth and n + 1; wherein N is more than or equal to 1 and less than N-1, and N is the total number of the time indexes of all the points;
the feature data which is the feature data of the respiration data with a plurality of respiration cycles after the feature extraction includes: the respiration time interval of the single-mouth respiration, the flow rate change of the single-mouth respiration, the ratio of the expiration time of the single-mouth respiration to the total respiration time of the single-mouth respiration, and the rising slope of the expiration waveform of the single-mouth respiration;
optionally, the breathing time interval of the single-mouth breath is: the time interval a between the time indexes respectively corresponding to the adjacent points; the value range of a is made of 10 s-a-1s;
optionally, the flow rate variation of the single-mouth breath is: the flow rate change b between the time indexes respectively corresponding to the adjacent points; the value range of b is 0L/min < b <20L/min;
optionally, the ratio of the expiration time of the single-mouth breath to the total breath time of the single-mouth breath is: the expiration time between the time indexes respectively corresponding to the adjacent points accounts for the proportion c% of the total respiration time between the time indexes respectively corresponding to the adjacent points; the value range of c% is 20% -80%;
optionally, the rising slope of the expiratory waveform of the single-mouth breath is: the rising slope d of the expiratory waveform between the time indexes respectively corresponding to the adjacent points; within the initial 100ms of inspiration, the value range of d is 10-50L/min/s.
7. The method for detecting human-computer disorder based on unioral respiration waveform according to any one of claims 1-6, wherein the method or step of inputting the feature data of the person to be tested into a classification model to obtain the classification result of the feature data of the person to be tested comprises:
inputting the breathing time interval of the single breathing cycle of the person to be detected into a classification model, and judging whether the breathing time interval of the single breathing cycle of the person to be detected falls into a range; in the case where the breathing time interval of said single breathing cycle of said subject falls within a range, outputting yes and entering a phase of inputting the variation of the flow rate of said single breathing cycle of said subject into a classification model;
otherwise, the output is not, and the operation is terminated;
inputting the flow rate change of the single breathing cycle of the person to be tested into a classification model, and judging whether the flow rate change of the single breathing cycle of the person to be tested falls into a range b or not; under the condition that the flow rate change of the single respiratory cycle of the testee falls into a range b, outputting yes, and inputting the ratio of the expiration time of the single respiratory cycle of the testee to the total respiration time of the single respiratory cycle into a classification model; otherwise, the output is not, and the operation is terminated;
inputting the ratio of the expiration time of the single respiratory cycle of the person to be detected to the total respiratory time of the single respiratory cycle into a classification model, and judging whether the ratio of the expiration time of the single respiratory cycle of the person to be detected to the total respiratory time of the single respiratory cycle falls within a range c; under the condition that the ratio of the expiration time of the single respiration period of the testee to the total respiration time of the single respiration period falls into a range c, outputting yes, and entering a stage of ascending a slope of an expiration waveform of the single respiration period of the testee to a classification model; otherwise, the output is no, and the operation is terminated;
inputting the rising slope of the expiratory waveform of the single respiratory cycle of the person to be detected into a classification model, and judging whether the rising slope of the expiratory waveform of the single respiratory cycle of the person to be detected falls into a range d; outputting yes and outputting a classification result of respiratory waveform data of the person to be tested under the condition that the rising slope of the respiratory waveform of the single respiratory cycle of the person to be tested falls into a range d; otherwise, outputting no, and ending the operation.
8. An apparatus for human-machine disorder detection based on a single-mouth respiratory waveform, the apparatus comprising: a memory and a processor;
the memory is to store program instructions;
the processor is configured to invoke program instructions, which when executed, are configured to perform the method of detecting an imbalance between humans and animals according to any one of claims 1 to 7.
9. A system for detecting human-machine imbalance based on a single-mouth respiratory waveform, comprising:
the acquisition unit is used for acquiring single-mouth respiratory waveform data of a person to be measured; the single-ported respiratory waveform data comprises flow rate waveform data and airway pressure waveform data;
the processing unit is used for inputting the single-mouth respiratory waveform data of the person to be detected into a machine learning detection model to obtain the man-machine imbalance type of the single-mouth respiratory waveform data of the person to be detected;
and the classification unit is used for outputting the man-machine disorder type of the single-mouth breathing waveform data of the person to be tested.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the method for detecting an imbalance between human and machine based on a unioral respiratory waveform of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211055134.4A CN115381432A (en) | 2022-08-31 | 2022-08-31 | Single-mouth respiration waveform-based man-machine disorder detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211055134.4A CN115381432A (en) | 2022-08-31 | 2022-08-31 | Single-mouth respiration waveform-based man-machine disorder detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115381432A true CN115381432A (en) | 2022-11-25 |
Family
ID=84123693
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211055134.4A Pending CN115381432A (en) | 2022-08-31 | 2022-08-31 | Single-mouth respiration waveform-based man-machine disorder detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115381432A (en) |
-
2022
- 2022-08-31 CN CN202211055134.4A patent/CN115381432A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109893732B (en) | Mechanical ventilation man-machine asynchrony detection method based on recurrent neural network | |
| US11291784B2 (en) | Detection of asynchrony | |
| EP1237477B1 (en) | Waveform interpreter for respiratory analysis | |
| CN103491872B (en) | Air flue checks status indicator in real time | |
| CN106456053A (en) | Selection, segmentation and analysis of exhaled breath for airway disorders assessment | |
| EP2536333A1 (en) | Nitric oxide measurement method and apparatus | |
| CN110533658A (en) | Intelligent pulmonary emphysema diagnostic message processing system and method, information data processing terminal | |
| CN111563451A (en) | Mechanical ventilation ineffective inspiration effort identification method based on multi-scale wavelet features | |
| WO2022267382A1 (en) | Human-machine asynchronous classification method and system for ventilator, terminal and storage medium | |
| CN111227792B (en) | Apnea detection method and system, electronic device and storage medium | |
| US10426426B2 (en) | Methods and apparatus for performing dynamic respiratory classification and tracking | |
| JP4904488B2 (en) | Lung sound diagnostic device | |
| CN115414026A (en) | Automatic breath segmentation method and system based on flow velocity waveform | |
| CN101125084A (en) | Fault-tolerant method and device in respiratory mechanics monitoring system | |
| CN115381432A (en) | Single-mouth respiration waveform-based man-machine disorder detection method and system | |
| CN100508884C (en) | Fault-tolerant method and device in respiratory mechanics monitoring system | |
| CN115381431A (en) | Method and system for extracting respiratory parameters | |
| CN114534041A (en) | Respiratory waveform classification model training method and device for detecting man-machine ventilation asynchronism | |
| CN108968964A (en) | Pulmonary function test (pft) system and test method | |
| CN115804585B (en) | Method and system for detecting high resistance of airway based on mechanical ventilation waveform | |
| CN113808078B (en) | Method for identifying ineffective inhalation effort based on electrical impedance tomography | |
| WO2015036013A1 (en) | Automatic quality control of forced spirometry | |
| Kazemi et al. | Assessment on methods used to detect asthmatic and non-asthmatic conditions using capnogram signal | |
| US20210022644A1 (en) | Method and system for indicating obstructive sleep apnea during wakefulness | |
| WO2022133942A1 (en) | Medical ventilation device and ventilation monitoring method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |