KR20230081151A - Data processing apparatus for detecting respiratory event section according to polysomnography and operating method of the same - Google Patents

Abstract

The present invention relates to a data processing device for detecting a breathing event section according to polysomnography and an operating method thereof, and more particularly, to a technical idea of signal data processing for automatic determination of sleep state according to analysis of polysomnography results. According to one embodiment of the present invention, a data processing apparatus extracts a respiration signal from signal data detected by polysomnography, and changes the signal with respect to a respiratory event section determined from the extracted respiration signal. (Signal Excursion) A signal data processing unit for processing a calculation result of first candidate signal data and a duration calculation result according to a result of normalization processing for the signal variation calculation result as second candidate signal data, and the processed first Value excluding odd numbers from even numbers for the number of signal fluctuations in the candidate signal data (Mag), excluding odd numbers from even numbers for the number of durations in the processed second candidate signal data value (Delta), the number of sleep apnea durations, the number of sleep hypopnea durations, a threshold value corresponding to an average value of at least three of the signal fluctuations (M _th ) and a threshold time Sleep state in which the determined respiratory event section is detected as any one of the sleep apnea section, hypopnea section, RERA (Respiratory Effort Related Arousal) section, and normal breathing section. A detection processing unit may be included.

Description

Data processing device for detecting breathing event section according to polysomnography and its operation method

The present invention relates to a data processing device for detecting a breathing event section according to polysomnography and an operating method thereof, and more particularly, to a technical idea of signal data processing for automatic determination of sleep state according to analysis of polysomnography results. It is about.

Polysomnography is a test for diagnosing sleep disorders. It comprehensively measures brain waves, eye movements, muscle movements, breathing, electrocardiogram, etc. It is used to analyze records to diagnose sleep-related diseases and to determine treatment policies.

The aforementioned polysomnography can diagnose symptoms such as sleep apnea, sleep disorder, and sleep gait, and as indices for determining these diseases, sleep stage, apnea-hypopnea index (AHI) , the upper airway resistance syndrome (Respiratory Effort Related Arousal; RERA) index, etc. are used.

Polysomnography is a test performed to diagnose sleep disorders while a patient sleeps overnight at a well-equipped sleep center. At least 10 types of 24 sensors are attached to the test.

The test time varies depending on the sleeping time of each individual, but it is about 6 to 8 hours. In order to read the test results, it takes about 4 hours in general, even if a qualified expert reads the test results.

In Korea, polysomnography has been included in health insurance since July 2018, and the number of patients who have undergone polysomnography has increased rapidly. The number of patients receiving is rapidly increasing.

In Korea, if you look at the reimbursement standards for polysomnography, only sleep apnea and narcolepsy, which have proven their therapeutic usefulness, are recognized once at the time of diagnosis and once after diagnosis, positive airway pressure treatment and surgery.

Accordingly, there is an increasing demand in the market for automation and accuracy of diagnosis of sleep apnea-related sleep conditions, particularly in polysomnography.

The sleep state associated with sleep apnea can be divided into a sleep apnea state, a sleep hypoventilation state, a RERA state, and a normal breathing state.

Sleep apnea is defined as a decrease in the peak amplitude of the oronasal thermal flow sensor by more than 90% of the baseline and a reduction in the amplitude of apnea by more than 10 seconds in more than 90% of the event duration. In some cases, it can be classified as a sleep apnea interval.

Here, the baseline may be defined as the average amplitude of stable respiration and oxygen supply for 2 minutes before the occurrence of the event interval or the average amplitude of the three largest breaths for 2 minutes.

Sleep hypoventilation is defined as: 1) a decrease in the output of the nasal pressure sensor by more than 30% of the pre-event baseline, and 2) a decrease of more than 30% for a duration of 10 seconds above, and 3) a drop of 3% or more from the oxygen saturation of the respiratory curve reference value, or when arousal is accompanied.

In addition, sleep hypoventilation is defined as 1) when the output of the nasal pressure sensor decreases by 30% or more compared to the pre-event baseline, and 2) when the duration of the drop is 30% or more. 10 seconds or more, and 3) it may correspond to the case where the oxygen saturation of the breathing curve standard is more than 4% lower.

Looking at products released in the existing market, there is a problem in that they cannot detect the exact signal generation section like a sleep specialist in relation to the detection of sleep apnea and sleep hypopnea occurring between sleep.

Instead, it determines whether or not a breathing event is detected in units of 30-second epochs to derive an Apenea-Hypopnea index (AHI) index, which is a standard for diagnosing sleep disorders.

The AHI index is calculated by multiplying the sum of the number of apneas during sleep and the number of hypopneas during sleep by 60 and dividing it by the total sleep time. If so, an error occurs in the diagnosis of sleep apnea.

Therefore, accurate detection of breathing event intervals can be a very important factor in diagnosing sleep apnea, which is one of the major sleep disease indices.

RERA refers to continuous breathing of 10 seconds or more, which does not satisfy the criterion of apnea or hypoventilation and causes arousal during sleep in which the output of the pressure sensor is flattened.

Looking at the products released in the existing market, there is a problem that it is difficult to detect the exact signal generating section like a sleep expert when it comes to detecting the RERA event section that occurs between sleep.

Instead, it is possible to derive the RDI (Respiratory Disturbance Index) index used for diagnosing sleep disorders by discriminating only whether the RERA event section is detected in units of 30-second epochs.

The RDI index can be calculated by multiplying the sum of the number of inter-sleep RERA sections, the number of inter-sleep apnea sections, and the number of inter-sleep hypopnea sections by 60, and dividing it by the total sleep time.

In this case, if two or more RERA event sections exist within one epoch or RERA event sections exist between epochs, errors in RDI diagnosis inevitably occur.

Therefore, accurate detection of the RERA event interval can be a very important factor in identifying the RDI, one of the major sleep disorder indices.

Korean Patent Registration No. 10-1868888, "Sleep/wake classification device and method for patients with sleep breathing disorder using nasal pressure signal" Korean Patent Registration No. 10-2068484, "Method of generating sleep apnea prediction model and method of predicting sleep apnea using this model" Korean Patent Registration No. 10-2258726, "Data Processing Apparatus for Automatic Determination of Sleep Disorders Using Deep Learning and Operation Method thereof"

The present invention is data for automatic determination of sleep state according to polysomnography, which can minimize the effect of noise signals according to inter-individual differences and measurement environments after polysomnography through signal data processing to automate the analysis of polysomnography results. It is an object to provide a processing device and method.

An object of the present invention is to accurately detect sleep apnea and hypoventilation signals and to provide a result of detecting a breathing signal capable of generating a respiratory effort related arousal (RERA).

An object of the present invention is to detect the amplitude and duration of a breathing signal in order to detect a sleep apnea state interval, a sleep hypoventilation state interval, and a RERA interval.

An object of the present invention is to more accurately detect and discriminate sleep apnea state intervals, sleep hypoventilation state intervals, and RERA intervals by using signal excursion calculation and signal normalization.

The present invention differentiates the output signal of a nasal pressure sensor, takes the absolute value of the differentiated output signal, and accurately detects a flattening signal through moving average filtering for the differential value. The purpose is to more accurately detect and discriminate the RERA section.

According to one embodiment of the present invention, the data processing device extracts a respiration signal from signal data detected by polysomnography, and detects signal excursions for a respiratory event section determined from the extracted respiration signal. In the signal data processing unit for processing the calculation result as the first candidate signal data and the duration calculation result according to the normalization process result for the signal variation calculation result as the second candidate signal data, and in the processed first candidate signal data A value excluding odd numbers from even numbers for the number of signal fluctuations (Mag), a value excluding odd numbers from even numbers for the number of durations in the processed second candidate signal data (Delta) , the number of sleep apnea durations, the number of sleep hypopnea durations, the threshold value corresponding to the average value of at least three of the signal fluctuations (M _th ) and the determined breathing using the threshold time Including a sleep state detection processor that detects the event (respiratory event) section as any one of the sleep state sections among the sleep apnea section, the hypopnea section, the RERA (Respiratory Effort Related Arousal) section, and the normal breathing section can do.

The sleep state detection processing unit may include a sleep apnea interval detection unit, a sleep hypoventilation interval detection unit, and a RERA interval detection unit.

The sleep state detection processing unit compares the first candidate signal data and the second candidate signal data, detects the amplitude and duration of the signal in the determined breathing event section, and AASM (American Academy of Sleep Medicine) standard, a threshold value (M _th ) corresponding to an average value of at least three signal fluctuations may be set as the threshold value (M _th ) of the signal fluctuation.

The sleep apnea interval detection unit determines that the sum of the value (Delta) and the apnea duration (A_Delta) is the apnea duration (A_Delta) unless the value (Mag) is less than the value obtained by dividing the threshold value (M _th ) by 10. If it is not equal to , it is detected as a determination target for sleep apnea, and when the apnea duration (A_Delta) exceeds the critical time of 10 seconds, the determined breathing event section can be detected as the sleep apnea section.

The sleep hypoventilation interval detector unit detects that the value (Mag) is not less than the value obtained by dividing the threshold value (M _th ) by 70, and the sum of the value (Delta) and the hypoventilation duration (H_Delta) is the hypoventilation duration When the time (H_Delta) is not the same, sleep hypoventilation is detected as a determination target, and when the hypopnea duration (H_Delta) exceeds the threshold time of 10 seconds, the determined breathing event section is set as the sleep hypoventilation. interval can be detected.

The signal data processing unit may include a signal data collection unit, a signal data extraction unit, and a signal data processing unit.

The signal data collection unit transmits at least one signal data of signal data of a nasal pressure sensor, signal data of a thermistor sensor, signal data of oxygen saturation, and arousal signal data to the polysomnography test. It can be collected as signal data detected by

The signal data extraction unit may extract a respiration signal after signal preprocessing of low pass filtering and DC canceling of the collected signal data.

The signal data processing unit extracts a positive peak signal and a negative peak signal from the extracted respiration signal to determine a respiratory event section in the extracted respiration signal, and for the determined respiratory event section A signal excursion may be calculated and processed into the first candidate signal data for the number of positive signal excursions corresponding to the positive peak signal and the number of negative signal excursions corresponding to the negative peak signal.

The signal data processor may normalize the calculated signal fluctuations, extract a positive peak signal and a negative peak signal for the normalized signal fluctuations, and process them as the second candidate signal data. .

According to an embodiment of the present invention, a method of operating a data processing apparatus includes extracting a respiration signal from signal data detected by polysomnography, and signal variation with respect to a respiratory event section determined from the extracted respiration signal. (signal excursion) processing a duration calculation result according to a result of normalization processing for the first candidate signal data and the signal variation calculation result as second candidate signal data, and processing the processed first candidate signal A value excluding odd numbers from even numbers for the number of signal fluctuations in data (Mag), a value excluding odd numbers from even numbers for the number of durations in the processed second candidate signal data ( Delta), the number of sleep apnea durations, the number of sleep hypopnea durations, and a threshold value corresponding to an average value of at least three of the signal fluctuations (M _th ) and a threshold time using the Detecting the determined respiratory event section as any one sleep state section among an apena section, a sleep hypopnea section, a Respiratory Effort Related Arousal (RERA) section, and a normal breathing section. can

The step of detecting the determined respiratory event section as any one sleep state section among a sleep apnea section, a sleep hypopnea section, a Respiratory Effort Related Arousal (RERA) section, and a normal breathing section, The first candidate signal data and the second candidate signal data are compared to detect the amplitude and duration of the signal in the determined respiratory event interval, and refer to AASM (American Academy of Sleep Medicine) standards. and setting a threshold value (M _th ) corresponding to an average value of at least three of the signal fluctuations to a threshold value (M _th ) of the detected magnitude.

The step of detecting the determined respiratory event section as any one sleep state section among a sleep apnea section, a sleep hypopnea section, a Respiratory Effort Related Arousal (RERA) section, and a normal breathing section, If the value (Mag) is not less than the value obtained by dividing the threshold value (M _th ) by 10 and the sum of the value (Delta) and the apnea duration (A_Delta) is not equal to the apnea duration (A_Delta) and detecting the determined breathing event section as the sleep apnea section when the apnea duration A_Delta exceeds the threshold time of 10 seconds.

The step of detecting the determined respiratory event section as any one sleep state section among a sleep apnea section, a sleep hypopnea section, a Respiratory Effort Related Arousal (RERA) section, and a normal breathing section, While the value (Mag) is not less than the value obtained by dividing the threshold value (M _th ) by 70, the sum of the value (Delta) and the hypopnea duration (H_Delta) is not equal to the hypoventilation duration (H_Delta) Otherwise, when the hypoventilation duration (H_Delta) exceeds the critical time of 10 seconds, detecting the determined breathing event interval as the sleep hypoventilation interval.

The present invention is data for automatic determination of sleep state according to polysomnography, which can minimize the effect of noise signals according to inter-individual differences and measurement environments after polysomnography through signal data processing to automate the analysis of polysomnography results. A processing device and method can be provided.

The present invention can accurately detect sleep apnea and hypoventilation signals and provide a result of detecting a breathing signal capable of generating a respiratory effort related arousal (RERA).

The present invention can detect the amplitude and duration of a breathing signal in order to detect a sleep apnea state interval, a sleep hypoventilation state interval, and a RERA interval.

The present invention can more accurately detect and discriminate sleep apnea state intervals, sleep hypoventilation state intervals, and RERA intervals by using signal excursion calculation and signal normalization.

The present invention differentiates the output signal of a nasal pressure sensor, takes the absolute value of the differentiated output signal, and accurately detects a flattening signal through moving average filtering for the differential value. The RERA section can be more accurately detected and distinguished.

1 is a diagram illustrating a data processing apparatus for automatically determining a sleep state according to an embodiment of the present invention.
2 is a diagram illustrating a signal data processing unit according to an embodiment of the present invention.
3 is a diagram illustrating a sleep state detection processing unit according to an embodiment of the present invention.
4A and 4B are diagrams illustrating an operation method of a signal data processing unit that calculates a signal excursion according to an embodiment of the present invention.
4C is a diagram illustrating an operating method of a signal data processing unit performing normalization processing of signal fluctuations according to an embodiment of the present invention.
5A illustrates an example of sleep hypoventilation detected according to an embodiment of the present invention.
5B to 5D illustrate examples of noise in sleep apnea and sleep hypoventilation intervals according to an embodiment of the present invention.
6A and 6B are views illustrating a respiratory effort related arousal (RERA) related breathing signal according to an embodiment of the present invention.
FIG. 7 is a diagram illustrating respiration signal processing for detecting a sleep state section in signal data according to an embodiment of the present invention.
8 to 10 are diagrams illustrating an operating method of a data processing apparatus for automatically determining a sleeping state according to an embodiment of the present invention.
11 is a diagram illustrating an example of a screen displaying a detected sleep state section by processing signal data in a data processing apparatus for automatically determining a sleep state according to an embodiment of the present invention.

Hereinafter, various embodiments of this document will be described with reference to the accompanying drawings.

Examples and terms used therein are not intended to limit the technology described in this document to specific embodiments, and should be understood to include various modifications, equivalents, and/or substitutes of the embodiments.

In the following description of various embodiments, if it is determined that a detailed description of a related known function or configuration may unnecessarily obscure the subject matter of the invention, the detailed description will be omitted.

In addition, terms to be described below are terms defined in consideration of functions in various embodiments, and may vary according to intentions or customs of users or operators. Therefore, the definition should be made based on the contents throughout this specification.

In connection with the description of the drawings, like reference numerals may be used for like elements.

Singular expressions may include plural expressions unless the context clearly dictates otherwise.

In this document, expressions such as "A or B" or "at least one of A and/or B" may include all possible combinations of the items listed together.

Expressions such as "first," "second," "first," or "second," may modify the corresponding components regardless of order or importance, and are used to distinguish one component from another. It is used only and does not limit the corresponding components.

When a (e.g., first) element is referred to as being "(functionally or communicatively) coupled to" or "connected to" another (e.g., second) element, that element refers to the other (e.g., second) element. It may be directly connected to the component or connected through another component (eg, a third component).

In this specification, "configured to (or configured to)" means "suitable for," "having the ability to," "changed to" depending on the situation, for example, hardware or software ," can be used interchangeably with "made to," "capable of," or "designed to."

In some contexts, the expression "device configured to" can mean that the device is "capable of" in conjunction with other devices or components.

For example, the phrase "a processor configured (or configured) to perform A, B, and C" may include a dedicated processor (eg, embedded processor) to perform the operation, or by executing one or more software programs stored in a memory device. , may mean a general-purpose processor (eg, CPU or application processor) capable of performing corresponding operations.

Also, the term 'or' means 'inclusive or' rather than 'exclusive or'.

That is, unless otherwise stated or clear from the context, the expression 'x employs a or b' means any one of the natural inclusive permutations.

Terms such as '..unit' and '..group' used below refer to a unit that processes at least one function or operation, and may be implemented by hardware or software, or a combination of hardware and software.

1 is a diagram illustrating a data processing apparatus for automatically determining a sleep state according to an embodiment of the present invention.

1 illustrates components of a data processing apparatus for automatically determining a sleep state according to an embodiment of the present invention.

For example, a data processing device for automatically determining a sleep state may include a data processing device for detecting a breathing event section according to polysomnography.

Referring to FIG. 1 , a data processing device 100 according to an embodiment of the present invention may include a signal data processing unit 110 and a sleep state detection processing unit 120 .

According to an embodiment of the present invention, the signal data processing unit 110 may collect signal data detected by polysomnography and pre-process the collected signal data to extract a respiration signal.

In addition, the signal data processor 110 determines a respiratory event section in the extracted respiration signal, calculates a signal excursion for the determined respiratory event section, and processes it as the first candidate signal data, A normalization process for the calculated signal variation may be performed and processed as second candidate signal data.

In other words, the signal data processing unit 110 maintains the signal excursion calculation result for the respiratory event section determined in the respiratory signal according to the normalization process result for the first candidate signal data and the signal excursion calculation result. The duration calculation result may be processed as second candidate signal data.

According to one embodiment of the present invention, the signal data processing unit 110 processes signal data to minimize the influence of noise signals according to interindividual differences and measurement environments after polysomnography into candidate signal data through signal variance calculation and normalization processing. As a result, the diagnosis of sleep apnea can be automated.

For example, the sleep state detection processing unit 120 uses the first candidate signal data and the second candidate signal data processed by the signal data processing unit 110 to convert a respiratory event period into a sleep apnea period, It can be detected as any one sleep state section among a hypopnea section, a respiratory effort related arousal (RERA) section, and a normal breathing section.

According to one embodiment of the present invention, the sleep state detection processing unit 120 compares the first candidate signal data and the second candidate signal data to determine the amplitude and duration of the signal in the determined breathing event section. can detect

In addition, the sleep state detection processor 120 compares the previously detected number of magnitudes with the threshold value of signal fluctuation, and compares the previously detected number of durations with the threshold value of duration to detect any one sleep state section. can do. For example, a threshold value of duration may be referred to as a threshold time.

According to an embodiment of the present invention, the sleep state detection processing unit 120 calculates a value (Mag) obtained by subtracting odd numbers from even numbers for the number of signal fluctuations in the first candidate signal data, and The value excluding the odd number from the even number for the number of durations (Delta) can be calculated.

In addition, the sleep state detection processor 120 may calculate the number of sleep apnea durations and the number of sleep hypopnea durations.

In addition, the sleep state detection processing unit 120 may set a threshold value (M _th ) and a threshold time corresponding to an average value of up to three signal fluctuations. For example, the threshold time may be 10 seconds.

As an example, the sleep state detection processing unit 120 is a value (Mag), a value (Delta), the number of sleep apnea (apena) duration, the number of sleep hypopnea (hypopnea) duration and threshold value (M _th ) and threshold Using time, a pre-determined respiratory event section is detected as any one sleep state section among the sleep apnea section, the sleep hypopnea section, the RERA (Respiratory Effort Related Arousal) section, and the normal breathing section. can do.

According to one embodiment of the present invention, the sleep state detection processing unit 120 compares the first candidate signal data and the second candidate signal data to detect the amplitude and duration of the signal in the determined breathing event section. can do.

In addition, the sleep state detection processing unit 120 refers to the AASM (American Academy of Sleep Medicine) standard and sets the threshold value (M _th ) corresponding to the average value of up to three signal fluctuations to the number of detected magnitudes of the signal fluctuations. It can be set as a threshold value (M _th ).

Specifically, the average value for the maximum three is the threshold value (M _th ) determined by extracting the average value of the three maximum signal fluctuations in the 2 minutes before the point at which the negative peak signal at the start of the respiratory event interval is extracted. can be

According to one embodiment of the present invention, the sleep state detection processing unit 120 detects any one of the apneic interval detection signal, the hypoventilation interval detection signal, the RERA interval detection signal, and the normal breathing interval detection signal in relation to any one detected sleep state interval. One detection signal may be output as an output signal.

For example, the output signal is related to detection of the apneic interval, hypopnea interval, RERA interval, and normal breathing interval, the oxygen saturation related signal can be used to detect the hypoventilation interval, and the arousal related signal is low It can be used to detect the breathing section and the RERA section.

According to one embodiment of the present invention, the sleep state detection processor 120 compares sleep apnea and sleep hypopnea in a respiratory event section using the first candidate signal data, and uses the second candidate signal data It is possible to compare ranges related to the sleep apnea interval and the sleep hypoventilation interval in the determined respiratory event interval.

Therefore, the present invention provides an automatic determination of the sleep state according to polysomnography, which can minimize the influence of noise signals according to inter-individual differences and measurement environments after polysomnography through signal data processing to automate the analysis of polysomnography results. It is possible to provide a data processing device and method for

In addition, the present invention can detect the amplitude and duration of the breathing signal in order to detect the sleep apnea state period, the sleep hypoventilation state period, and the RERA period.

2 is a diagram illustrating a signal data processing unit according to an embodiment of the present invention.

Figure 2 illustrates the components of the signal data processing unit according to an embodiment of the present invention.

Referring to FIG. 2 , the signal data processing unit 200 according to an embodiment of the present invention includes a signal data collection unit 210 , a signal data extraction unit 220 and a signal data processing unit 230 .

For example, the signal data collection unit 210 includes at least one signal of signal data of a nasal pressure sensor, signal data of a temperature sensor, signal data of oxygen saturation, and arousal signal data. Data can be collected as signal data detected by polysomnography.

For example, the signal data detected by polysomnography is EEG (Electroencephalogram) sensor, EOG (Electrooculography) sensor, EMG (Electromyogram) sensor, EKG (Electrocardiogramme) sensor, PPG (Photoplethysmography) sensor, chest belt , an Abdomen belt, a thermister, a flow sensor, and a microphone.

Further, for example, signal data detected by polysomnography may be interpreted as data collected in real time, or may be interpreted as data recorded in a polysomnography database by previously performed polysomnography.

According to an embodiment of the present invention, the signal data extraction unit 220 may extract a respiration signal after signal preprocessing of low pass filtering and DC canceling of the collected signal data.

In other words, the signal data extractor 220 may use a 0.01 to 0.35 Hz band pass filter to extract only the respiration signal by removing the DC signal from the collected signal data corresponding to the input signal.

According to an embodiment of the present invention, the signal data processing unit 230 extracts a positive peak signal and a negative peak signal from the extracted respiratory signal to determine a respiratory event section in the extracted respiratory signal can

In addition, the signal data processing unit 230 calculates the signal excursion for the determined respiratory event interval, and calculates the number of positive signal excursions corresponding to the positive peak signal and the number of negative signal excursions corresponding to the negative peak signal. It can be processed as the first candidate signal data for .

That is, the first candidate signal data may include the number of positive signal fluctuations corresponding to the calculation result of the signal fluctuation and the number of negative signal fluctuations corresponding to the negative peak signal.

For example, a positive peak signal and a negative peak signal may be extracted by the signal data extraction unit 220 and transmitted to the signal data processing unit 230 .

According to one embodiment of the present invention, the signal data processing unit 230 normalizes the pre-calculated signal fluctuations, and then extracts a positive peak signal and a negative peak signal for the normalized signal fluctuations. 2 can be processed as candidate signal data.

That is, the signal data processing unit 230 processes the signal variation calculation result into first candidate signal data, and processes the duration calculation result according to the normalization process result for the signal variation calculation result into second candidate signal data. can be processed.

For example, the signal data processing unit 230 may differentiate a respiration signal based on a specific pressure sensor among respiration signals, and process the absolute value of the differentiated signal as RERA section determination data.

That is, the signal data processing unit 230 calculates the differential value for the respiration signal based on the nasal pressure sensor among the signal data of the polysomnography in order to detect the RERA section, and then calculates the absolute value to apply moving average filtering By taking , it is possible to prevent occurrence of a section in which a part of the flattening signal is greater than the differential value.

Accordingly, the present invention differentiates the output signal of the Nasal pressure sensor, takes the absolute value of the differentiated output signal, and obtains a flattening signal through moving average filtering on the differential value. By accurately detecting, the RERA section can be more accurately detected and distinguished.

3 is a diagram illustrating a sleep state detection processing unit according to an embodiment of the present invention.

3 illustrates components of a sleep state detection processing unit according to an embodiment of the present invention.

Referring to FIG. 3 , the sleep state detection processing unit 300 according to an embodiment of the present invention includes a sleep apnea interval detection unit 310, a sleep hypopnea interval detection unit 320, and a RERA interval detection unit 330. .

As an example, the sleep state detection processing unit 300 includes a sleep apnea interval detection unit 310, a sleep hypoventilation interval detection unit 320, and a RERA interval detection unit 330, The respiratory event section may be detected, and the detected breathing event section may be detected by classifying which section among the apnea section, the hypopnea section, the RERA section, and the normal breathing section.

The sleep apnea interval detection unit subtracts the odd number from the even number for the number of signal fluctuations in the first candidate signal data (Mag) for up to three signal fluctuations for 2 minutes immediately before the start of the signal fluctuation. It is determined whether it is less than (equal to or exceeds) the value obtained by dividing the threshold value (M _th ) corresponding to the average value by 10.

In addition, the sleep apnea interval detection unit 210 calculates that the sum of the apnea duration (A_Delta) and the value excluding the odd number from the even number for the number of durations in the second candidate signal data is the apnea duration. It is judged whether it corresponds to the case that is not equal to (A_Delta).

In addition, the sleep apnea interval detection unit 210 detects sleep apnea as a determination target when the above-described determination result is satisfied, and detects a breathing event interval when the apnea duration (A_Delta) exceeds the critical time of 10 seconds. It can be detected as a sleep apnea interval.

According to an embodiment of the present invention, the sleep hypopnea section detector 220 is a value (Mag) is not less than the value obtained by dividing the threshold value (M _th ) by 70, the value (Delta) and hypopnea duration (H_Delta ) is not equal to the hypoventilation duration (H_Delta).

In addition, the sleep hypopnea interval detection unit 220 detects the sleep hypoventilation determination target when corresponding to the condition, and the respiratory event interval determined when the hypoventilation duration (H_Delta) exceeds the critical time of 10 seconds. It can be detected by sleep hypopnea.

According to an embodiment of the present invention, the RERA section detection unit 330 has a value (Mag) of dividing the threshold value (M _th ) by 70 and is not less than the threshold value (M _th ), while the RERA section determination data is flattened If it is not less than the threshold value and the sum of the value (Delta) and the hypopnea duration (H_Delta) is not equal to the hypopnea duration (H_Delta), it is detected as an object of judgment by RERA.

In addition, the RERA section detection unit 330 may detect the respiratory event section determined when the hypoventilation duration (H_Delta) exceeds the critical time of 10 seconds as the RERA section.

Accordingly, the sleep state detection processing unit 300 according to an embodiment of the present invention calculates a value (Mag) obtained by subtracting odd numbers from even numbers for the number of signal fluctuations in the first candidate signal data, and second candidate signal data. for the number of durations in the even number minus the odd number (Delta), for the number of sleep apnea durations, for the number of sleep hypopnea durations, for up to three of the signal oscillations. The sleep apnea interval, the sleep hypoventilation interval, the _RERA interval and It can be detected as any one sleep state interval among normal breathing intervals. For example, the leveling threshold may correspond to a threshold voltage value (V _th ).

4A and 4B are diagrams illustrating an operation method of a signal data processing unit that calculates a signal excursion according to an embodiment of the present invention.

Referring to FIG. 4A, the output waveform of the graph 400 is the DC change due to noise caused by the external environment or the patient's movement in the signal data detected by the polysomnography corresponding to the input signal and the respiration signal. An example of a respiratory signal from which the signal has been removed.

The operation method of the signal data processor extracts a respiration signal from which signals other than the DC change and respiration signal due to noise caused by the external environment or the patient's movement are removed. The extracted output waveform may be as shown in graph 400. there is.

In the graph 400, a positive peak signal 401 and a negative peak signal 402 can be extracted by the signal data processor.

The operation method of the signal data processing unit is a section in which the magnitude of the waveforms of the positive peak signal 401 and the negative peak signal 402 are reduced along the extraction points of the positive peak signal 401 and the negative peak signal 402. Can be detected as a breathing event section (403).

Referring to FIG. 4B , an arrow in the graph 410 indicates a signal variation calculation result of a respiration signal.

The operation method of the signal data processing unit may calculate the signal variation calculation result for the respiration signal as shown in the graph 410.

In the graph 410, the signal variation calculation result for the positive peak signal 411 and the negative peak signal 412 may be calculated by the signal data processing unit.

According to the operation method of the signal data processing unit, the size of the signal variation calculation result of the positive peak signal 411 and the negative peak signal 412 according to the signal variation of the positive peak signal 411 and the negative peak signal 412. A decreasing period may be detected as a breathing event period 413 .

4C is a diagram illustrating an operating method of a signal data processing unit performing normalization processing of signal fluctuations according to an embodiment of the present invention.

Referring to FIG. 4C , arrows in the graph 420 indicate normalization processing results for the signal variation calculation results of the respiration signal.

The operation method of the signal data processing unit may calculate the normalization processing result of the signal variation calculation result for the respiration signal as shown in the graph 420.

In the graph 420, normalization processing of the signal variation calculation result for the positive peak signal 421 and the negative peak signal 422 may be performed by the signal data processing unit.

The operation method of the signal data processing unit is respiration according to the signal variation calculation result of the positive peak signal 421 and the negative peak signal 422 according to the signal variation of the positive peak signal 421 and the negative peak signal 422. The duration calculation result of the signal can be derived.

5A illustrates an example of sleep hypoventilation detected according to an embodiment of the present invention.

5A is an illustration of sleep hypoventilation detected according to an embodiment of the present invention.

Referring to FIG. 5A , an output screen 500 represents a breathing signal as a waveform, and referring to an area 501 in the displayed waveform, a sleep hypopnea section can be confirmed.

In area 501, it can be confirmed that the waveform corresponds to a case where the duration is 10 seconds or more while decreasing by 30% or more of the respiratory curve reference value, and the oxygen saturation of the respiratory curve reference value decreases by 3% or more accompanied by arousal or falls by 4% or more. there is.

5B to 5D illustrate examples of noise in sleep apnea and sleep hypopnea intervals according to an embodiment of the present invention.

5B illustrates a noise section in sleep hypoventilation detected according to an embodiment of the present invention.

Referring to FIG. 5B , the output screen 510 represents a breathing signal as a waveform, and referring to an area 511 in the displayed waveform, it can be confirmed that noise exists in the sleep hypopnea section.

Here, noise may act as a factor that causes an obstacle in the detection of the sleep hypoventilation interval.

5C illustrates a noise section in sleep apnea detected according to an embodiment of the present invention.

Referring to FIG. 5C , the output screen 520 represents a breathing signal as a waveform, and referring to an area 521 in the displayed waveform, it can be confirmed that noise exists in the sleep apnea section.

Here, noise may act as a factor that causes a failure in detecting the sleep apnea interval.

5D illustrates a noise section in sleep hypoventilation detected according to an embodiment of the present invention.

Referring to FIG. 5D , the output screen 530 represents the breathing signal as a waveform, and referring to the region 531 in the displayed waveform, noise exists in the sleep hypopnea section, and the peak signal 532 is relatively high due to noise. indicates output.

Here, noise may act as a factor that causes an obstacle in the detection of the sleep hypoventilation interval.

In other words, in order to detect an actual breathing event section, it is generally necessary to set a section by detecting a peak.

However, in the case of detecting only the peak signal, it is difficult to accurately detect the section due to noise.

Accordingly, as the value of the peak signal is output relatively high due to noise, it may be difficult to detect more respiratory event sections.

6A and 6B are views illustrating a respiratory effort related arousal (RERA) related breathing signal according to an embodiment of the present invention.

Figure 6a illustrates a comparison of the RERA interval detected according to an embodiment of the present invention with a normal breathing interval.

Referring to FIG. 6A , an output screen 600 illustrates a RERA section, and an output screen 610 illustrates a normal breathing section.

Comparing the output screen 600 and the output screen 610, the output screen 600 shows a RERA section in the area 601, but the output screen 600 confirms that the output waveform is repeated with the same size and duration. can

For example, it can be confirmed that the region 601 is output data of a Nasal Flow Sensor and is a flattening signal that is a rising curve part in the output waveform.

Figure 6b illustrates a comparison of the RERA interval detected according to an embodiment of the present invention with a normal breathing interval.

Referring to FIG. 6B , the output screen 620 illustrates the RERA section, and confirms that there is a point 621 where a peak occurs among the flattening signals in the RERA section.

In order to detect the RERA section, it is important to detect the section where the signal according to the definition of RERA is flattened.

In the case where the differential value is below a predetermined threshold value, it can be regarded as a flattening signal and a RERA section can be captured. Moving average filtering is required.

FIG. 7 is a diagram illustrating respiration signal processing for detecting a sleep state section in signal data according to an embodiment of the present invention.

7 illustrates a breathing signal processing for detecting a sleep state section in signal data according to an embodiment of the present invention using a graph.

Referring to FIG. 7 , a graph 700 shows a breathing signal extracted by collecting signal data detected by polysomnography and pre-processing the collected signal data.

A graph 710 enlarges and shows a respiration event section of the respiration signal of the graph 700 .

A graph 720 shows a signal variation calculation result for the graph 710 corresponding to a respiratory event section among the respiratory signals of the graph 700 .

More specifically, the graph 720 extracts the positive peak signals and the negative peak signals from the graph 710 and shows the signal variation calculation result for the extracted positive peak signals and negative peak signals.

For example, the graph 720 may correspond to the first candidate signal data.

The graph 720 shows odd and even numbers of signal fluctuations, odd numbers correspond to negative peak signals, and even numbers correspond to positive peak signals.

Graph 730 can be derived by normalizing using the signal variation calculated in graph 720 .

Graph 740 shows the signal variance calculation results for graph 730 .

More specifically, the graph 740 extracts the positive peak signals and the negative peak signals from the graph 730 and shows the signal variation calculation result for the extracted positive peak signals and negative peak signals.

For example, the graph 740 may correspond to the second candidate signal data.

The graph 740 shows odd and even numbers of signal fluctuations, odd numbers corresponding to the number of normalization results for negative peak signals, and even numbers corresponding to the number of normalization results for positive peak signals. .

According to an embodiment of the present invention, the operation method of the data processing apparatus may calculate the magnitude and duration of the signal in the respiratory event section using the graph 720 and the graph 740.

Here, since the starting criterion of the breathing event section is based on a negative peak signal, an algorithm for detecting a sleep apnea section and a sleep hypoventilation section and an algorithm for detecting a RERA section may be performed based on a negative peak signal.

An algorithm for detecting the sleep apnea interval and sleep hypoventilation interval is described with reference to FIG. 9 , and an algorithm for detecting the RERA interval is additionally described with reference to FIG. 10 .

8 to 10 are diagrams illustrating an operating method of a data processing apparatus for automatically determining a sleeping state according to an embodiment of the present invention.

FIG. 8 illustrates an embodiment in which a method of operating a data processing apparatus for automatically determining a sleep state according to an embodiment of the present invention detects a sleep state section using signal normalization and calculation of signal fluctuations.

Referring to FIG. 8 , in step 801, the method of operating the data processing apparatus according to an embodiment of the present invention collects polysomnography signal data.

That is, the operating method of the data processing device collects signal data detected by polysomnography.

Here, the collected signal data may include at least one signal data of signal data of a nasal pressure sensor, signal data of a temperature sensor, signal data of oxygen saturation, and arousal signal data. can

In step 802, the operating method of the data processing apparatus according to an embodiment of the present invention extracts a respiration signal by pre-processing the signal data.

That is, the operation method of the data processing apparatus may extract a respiration signal after signal pre-processing of low pass filtering and DC canceling of the signal data collected in step 801 .

In step 803, the operating method of the data processing apparatus according to an embodiment of the present invention determines a respiratory event section by extracting the first peak signal and the second peak signal of the respiration signal. Here, the first peak signal may represent a positive peak signal, and the second peak signal may represent a negative peak signal.

That is, the operating method of the data processing apparatus may extract a positive peak signal and a negative peak signal from a respiration signal to determine a respiratory event section corresponding to a section in which the size of a waveform in the extracted respiration signal rapidly decreases.

In step 804, the operating method of the data processing apparatus according to an embodiment of the present invention calculates the signal variation and processes it as the first candidate signal data.

That is, the operating method of the data processing device calculates the signal excursion for the respiratory event interval and calculates the number of positive signal excursions corresponding to a positive peak signal and the number of negative signal excursions corresponding to a negative peak signal. It can be processed as the first candidate signal data.

In step 805, the method of operating the data processing apparatus according to an embodiment of the present invention may process the signal variation calculated in step 804 as second candidate signal data through normalization processing.

That is, in the method of operating the data processing apparatus, after normalizing the calculated signal fluctuation, a positive peak signal and a negative peak signal for the normalized signal fluctuation may be extracted and processed as the second candidate signal data. there is.

In step 806, the operating method of the data processing apparatus according to an embodiment of the present invention detects a sleep state section using the first candidate signal data and the second candidate signal data.

That is, the operating method of the data processing device uses the first candidate signal data and the second candidate signal data to set the respiratory event interval to a sleep apnea interval, sleep hypopnea interval, RERA (Respiratory Effort It can be detected as a sleep state section of any one of related arousal) section and normal breathing section.

Therefore, the present invention can more accurately detect and discriminate sleep apnea state intervals, sleep hypoventilation state intervals, and RERA intervals by using signal excursion calculation and signal normalization.

9 is a method of operating a data processing apparatus for automatically determining a sleep state according to an embodiment of the present invention detects a sleep apnea state section and a sleep hypoventilation state section among sleep state intervals using signal fluctuation calculation and signal normalization An embodiment using the algorithm to do is exemplified.

In the method of operating a data processing apparatus for automatically determining a sleep state according to an embodiment of the present invention, the embodiment described in FIG. 9 may be performed after the signal processing step described in FIG. 7 has already been performed.

Referring to FIG. 9, in the method of operating the data processing apparatus according to an embodiment of the present invention, in step 901, a threshold value (M _th ) corresponding to an average value of a plurality of signal fluctuations prior to a respiratory event section is set. .

That is, the operating method of the data processing apparatus according to an embodiment of the present invention detects the amplitude and duration of the signal in the respiratory event section by comparing the first candidate signal data and the second candidate signal data. And, with reference to AASM (American Academy of Sleep Medicine) standards, a threshold value (M _th ) corresponding to the average value of up to three signal fluctuations may be set as the threshold value (M _th ) of signal fluctuation.

In step 902, the operating method of the data processing apparatus according to an embodiment of the present invention calculates a signal variation related variable (Mag) and a duration related variable (Delta) of the respiratory event section.

That is, the operating method of the data processing apparatus calculates a value (Mag) obtained by subtracting the odd number from the even number of the number of signal fluctuations in the first candidate signal data, and the number of durations in the second candidate signal data. You can calculate the value (Delta) excluding the odd number from the even number for .

In step 903, the operation method of the data processing apparatus according to an embodiment of the present invention is the sum of the variable (Delta) and the apnea duration (A_Delta) while the variable (Mag) is less than the value obtained by dividing the threshold value (Mth) by 10. It is determined whether this corresponds to the same case as the apnea duration (A_Delta).

The operation method of the data processing device returns to step 902 if the corresponding case is satisfied, and if not satisfied with the corresponding case, detects sleep apnea as a determination target and proceeds to step 904 or determines sleep hypoventilation. To proceed to step 907.

In step 904, the operating method of the data processing apparatus according to an embodiment of the present invention determines whether the apnea duration A_Delta exceeds the critical time of 10 seconds.

In the operation method of the data processing device, when the corresponding case is satisfied, the corresponding procedure is terminated while detecting the breathing event interval as the sleep apnea interval in step 905 .

Meanwhile, if the operating method of the data processing device is not satisfied with the corresponding case, the apnea duration A_Delta is determined to be 0 and returns to step 902.

In step 907, the operating method of the data processing apparatus according to an embodiment of the present invention is that the variable Mag is less than the value obtained by dividing the threshold value Mth by 70, and the variable Delta and hypopnea duration H_Delta It is determined whether the sum is equal to the hypoventilation duration (H_Delta).

The operation method of the data processing device returns to step 902 if the corresponding case is satisfied, and if the corresponding case is not satisfied, it is detected as an object of determination of sleep hypoventilation and proceeds to step 908 or step 911. proceed

In step 908, the operation method of the data processing apparatus according to an embodiment of the present invention determines whether the hypoventilation duration (H_Delta) corresponds to a case in which the critical time exceeds 10 seconds.

In the operation method of the data processing device, when the corresponding case is satisfied, the corresponding procedure is terminated while detecting the breathing event interval as the sleep hypoventilation interval in step 909 .

On the other hand, if the operating method of the data processing device is not satisfied with the corresponding case, it determines the hypoventilation duration (H_Delta) as 0 and returns to step 902.

In step 911, the operation method of the data processing device detects the breathing event section as a normal breathing section or a RERA section and ends the corresponding procedure.

10 illustrates an embodiment in which an operating method of a data processing apparatus for automatically determining a sleep state according to an embodiment of the present invention uses an algorithm for detecting a RERA state section among sleep state sections by using signal fluctuation calculation and signal normalization. foreshadow

In the method of operating a data processing apparatus for automatically determining a sleep state according to an embodiment of the present invention, the embodiment described in FIG. 10 may be performed after the signal processing step described in FIG. 7 has already been performed.

Referring to FIG. 10 , in step 1001, the method of operating the data processing device collects signal data of polysomnography.

That is, the operating method of the data processing device collects signal data detected by polysomnography.

Here, the collected signal data may include at least one signal data of signal data of a nasal pressure sensor, signal data of a temperature sensor, signal data of oxygen saturation, and arousal signal data. can

In step 1002, the operating method of the data processing apparatus according to an embodiment of the present invention differentiates the respiration signal based on the nasal pressure sensor during the signal day, and processes the absolute value of the differentiated respiration signal as RERA section determination data (flatten). do.

In step 1003, the operating method of the data processing apparatus according to an embodiment of the present invention sets a threshold value (M _th ) corresponding to an average value of a plurality of signal fluctuations before the respiratory event section.

That is, the operating method of the data processing apparatus compares the first candidate signal data and the second candidate signal data to detect the amplitude and duration of the signal in the respiratory event section, and AASM (American Academy of Sleep). Medicine) standard, the threshold value (M _th ) corresponding to the average value of up to three signal fluctuations can be set as the threshold value (M _th ) of the signal fluctuation.

In step 1004, the operating method of the data processing apparatus according to an embodiment of the present invention calculates a signal variation related variable (Mag) and a duration related variable (Delta) of the respiratory event section.

That is, the operating method of the data processing apparatus calculates a value (Mag) obtained by subtracting the odd number from the even number of the number of signal fluctuations in the first candidate signal data, and the number of durations in the second candidate signal data. You can calculate the value (Delta) excluding the odd number from the even number for .

In step 1005, the operating method of the data processing apparatus according to an embodiment of the present invention detects an apneic interval and hypopnea interval.

That is, the operation method of the data processing apparatus proceeds from step 903 to step 909 in FIG. 9 to detect the apneic interval and the hypoventilated interval.

In step 1006, in the operating method of the data processing apparatus according to an embodiment of the present invention, a variable (Mag) is a threshold value (M _th ) divided by 70 and a threshold value in order to distinguish and detect a normal breathing section and a RERA section. (M _th ), the RERA interval judgment data is less than the threshold voltage (V _th ) corresponding to the flattening threshold, and the sum of the variable (Delta) and the hypoventilation duration (H_Delta) is the hypoventilation duration (H_Delta) Determine whether it is the same as

When the above conditions are satisfied, the operation method of the data processing device returns to step 1005 and determines whether it is one of an apneic interval and a hypoventilated interval.

In step 1007, in the method of operating the data processing device according to an embodiment of the present invention, when the hypoventilation variable H_Delta is less than 10 seconds, it may be detected as a RERA interval or a normal breathing interval. Here, the hypopnea variable (H_Delta) is equal to the hypopnea duration (H_Delta).

In addition, the operation method of the data processing device determines that the hypopnea variable (H_Delta) is 0 when the hypopnea variable (H_Delta) is greater than 10 seconds and returns to step 1005 to determine whether it is one of the apneic interval and the hypopnea interval. can also judge.

For example, a data processing method for automatically determining a sleep state may include a data processing method for detecting a breathing event section according to polysomnography.

11 is a diagram illustrating an example of a screen displaying a detected sleep state section by processing signal data in a data processing apparatus for automatically determining a sleep state according to an embodiment of the present invention.

Referring to FIG. 11 , the output screen 1100 may output the waveform of the polysomnography data and provide the result as text content.

The data processing device for automatic determination of the sleep state displays the detected hypoventilation section through the area 1101 on the output screen 1100, and the type of breathing event, start time, end time, and duration of the breathing event through the area 1102. can be provided together as text content.

Accordingly, the present invention can accurately detect sleep apnea and hypoventilation signals and provide a result of detecting a breathing signal capable of generating respiratory effort related arousal (RERA).

The devices described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA), It may be implemented using one or more general purpose or special purpose computers, such as a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. You can command the device. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

As described above, although the embodiments have been described with limited drawings, those skilled in the art can make various modifications and variations from the above description. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

100: data processing unit
110: signal data processing unit 120: sleep state detection processing unit

Claims (14)

A respiration signal is extracted from signal data detected by polysomnography, and a result of calculating a signal excursion for a respiratory event section determined from the extracted respiration signal is calculated as first candidate signal data and the signal excursion. a signal data processing unit for processing a duration calculation result according to a normalization processing result for the calculation result as second candidate signal data; and
A value (Mag) obtained by subtracting the odd number from the even number of the number of signal fluctuations in the processed first candidate signal data, and the even number of the number of durations in the processed second candidate signal data. A threshold value (M _th ) corresponding to the average value of at least three of the above signal fluctuations, the number of sleep apnea durations, the number of sleep hypopnea durations, and the value excluding odd numbers (Delta). And using the threshold time, the determined respiratory event section is selected as one of a sleep apnea section, a sleep hypopnea section, a Respiratory Effort Related Arousal (RERA) section, and a normal breathing section. Characterized in that it comprises a sleep state detection processing unit for detecting
data processing unit. According to claim 1,
Characterized in that the sleep state detection processing unit includes a sleep apnea interval detection unit, a sleep hypoventilation interval detection unit, and a RERA interval detection unit
data processing unit. According to claim 2,
The sleep state detection processing unit compares the first candidate signal data and the second candidate signal data, detects the amplitude and duration of the signal in the determined breathing event section, and AASM (American Academy of Sleep Medicine) standard, the threshold value (M th ₎ corresponding to the average value of at least three of the signal fluctuations is set as the threshold value (M _th ) of the signal fluctuations by the number of detected magnitudes.
data processing unit. According to claim 3,
The sleep apnea interval detection unit determines that the sum of the value (Delta) and the apnea duration (A_Delta) is the apnea duration (A_Delta) unless the value (Mag) is less than the value obtained by dividing the threshold value (M _th ) by 10. If it is not equal to , it is detected as a determination target for sleep apnea, and when the apnea duration (A_Delta) exceeds the critical time of 10 seconds, the determined breathing event section is detected as the sleep apnea section. Characterized in that doing
data processing unit. According to claim 3,
The sleep hypoventilation interval detector unit detects that the value (Mag) is not less than the value obtained by dividing the threshold value (M _th ) by 70, and the sum of the value (Delta) and the hypoventilation duration (H_Delta) is the hypoventilation duration When the time (H_Delta) is not the same, sleep hypoventilation is detected as a determination target, and when the hypopnea duration (H_Delta) exceeds the threshold time of 10 seconds, the determined breathing event section is set as the sleep hypoventilation. Characterized in that it detects as a section
data processing unit. According to claim 1,
The signal data processing unit comprises a signal data collection unit, a signal data extraction unit and a signal data processing unit.
data processing unit. According to claim 6,
The signal data collection unit transmits at least one signal data of signal data of a nasal pressure sensor, signal data of a thermistor sensor, signal data of oxygen saturation, and arousal signal data to the polysomnography test. Characterized in that for collecting the signal data detected by
data processing unit. According to claim 7,
Characterized in that the signal data extraction unit extracts a respiration signal after signal preprocessing of low pass filtering and DC canceling of the collected signal data
data processing unit. According to claim 8,
The signal data processing unit extracts a positive peak signal and a negative peak signal from the extracted respiration signal to determine a respiratory event section in the extracted respiration signal, and for the determined respiratory event section A signal excursion is calculated and processed into the first candidate signal data for the number of positive signal excursions corresponding to the positive peak signal and the number of negative signal excursions corresponding to the negative peak signal. doing
data processing unit. According to claim 9,
The signal data processing unit normalizes the calculated signal fluctuations, and then extracts a positive peak signal and a negative peak signal for the normalized signal fluctuations and processes them as the second candidate signal data. to be
data processing unit. extracting a breathing signal from signal data detected by polysomnography;
The duration calculation result according to the normalization process result of the signal excursion calculation result for the first candidate signal data and the signal excursion calculation result for the respiratory event section determined from the extracted respiratory signal. processing as second candidate signal data; and
A value (Mag) obtained by subtracting the odd number from the even number of the number of signal fluctuations in the processed first candidate signal data, and the even number of the number of durations in the processed second candidate signal data. A threshold value (M _th ) corresponding to the average value of at least three of the above signal fluctuations, the number of sleep apnea durations, the number of sleep hypopnea durations, and the value excluding odd numbers (Delta). And using the threshold time, the determined respiratory event section is selected as one of a sleep apnea section, a sleep hypopnea section, a Respiratory Effort Related Arousal (RERA) section, and a normal breathing section. Characterized in that it comprises the step of detecting
A method of operating a data processing device. According to claim 11,
The step of detecting the determined respiratory event section as any one sleep state section among a sleep apnea section, a sleep hypopnea section, a Respiratory Effort Related Arousal (RERA) section, and a normal breathing section,
The first candidate signal data and the second candidate signal data are compared to detect the amplitude and duration of the signal in the determined respiratory event interval, and refer to AASM (American Academy of Sleep Medicine) standards. And setting a threshold value (M _th ) corresponding to an average value of at least three of the signal fluctuations as the threshold value (M _th ) of the signal fluctuations by the number of detected magnitudes.
A method of operating a data processing device. According to claim 12,
The step of detecting the determined respiratory event section as any one sleep state section among a sleep apnea section, a sleep hypopnea section, a Respiratory Effort Related Arousal (RERA) section, and a normal breathing section,
If the value (Mag) is not less than the value obtained by dividing the threshold value (M _th ) by 10 and the sum of the value (Delta) and the apnea duration (A_Delta) is not equal to the apnea duration (A_Delta) And detecting the determined breathing event section as the sleep apnea section when the apnea duration (A_Delta) exceeds the threshold time of 10 seconds.
A method of operating a data processing device. According to claim 12,
The step of detecting the determined respiratory event section as any one sleep state section among a sleep apnea section, a sleep hypopnea section, a Respiratory Effort Related Arousal (RERA) section, and a normal breathing section,
While the value (Mag) is not less than the value obtained by dividing the threshold value (M _th ) by 70, the sum of the value (Delta) and the hypopnea duration (H_Delta) is not equal to the hypoventilation duration (H_Delta) And detecting the determined breathing event section as the sleep hypopnea section when the hypoventilation duration (H_Delta) exceeds the threshold time of 10 seconds.
A method of operating a data processing device.

Images