Radar sensor integrated breathing machine and breathing event judgment method thereof

Abstract

The invention discloses a breathing machine integrated with a radar sensor and a breathing event judgment method thereof, and the breathing machine comprises a ventilation module, an airflow sensor and a pressure sensor, and further comprises the radar sensor used for monitoring thoracic movement and body movement in a non-contact manner; the respiration event judging module is used for judging the apnea and respiration stability degree; the control module is used for adjusting the ventilation pressure according to the event result. When the airflow signal declines and the radar signal does not have thoracic motion, central apnea is judged; when the airflow signal declines and thoracic motion exists in the radar signal, obstructive apnea is judged; when the respiratory effort is gradually increased and the radar signal has body movement, judging that the respiratory effort is awakened; when periodic stable breathing is detected and no obvious body movement exists in the radar signal, deep sleep is judged. Thoracic movement and body movement are monitored through a non-contact radar and fused with air path sensing signals, and accurate detection of respiratory events and sleep states is achieved.

Description

Technical Field

[0001] This invention relates to a medical device—a ventilator—and more particularly to a ventilator integrating a radar sensor and a method for determining respiratory events. The radar sensor enables non-contact respiratory detection and is used for real-time determination of respiratory events. Background Technology

[0002] Current ventilators typically use airflow sensors and pressure sensors to detect a patient's respiratory status and events, but they have the following shortcomings:

[0003] 1. It is difficult to determine the type of sleep apnea. Using pressure fluctuations generated by pulsed airflow to differentiate between obstructive sleep apnea (OSA) and central sleep apnea (CSA) has a low accuracy rate.

[0004] 2. It is difficult to judge respiratory effort-related awakening (RERA). The current mainstream judgment method is to judge by continuous airflow limitation and increased airflow amplitude (more than 50%), which has a high misjudgment rate.

[0005] 3. Insufficient assessment of sleep state: Current technology mainly relies on respiratory signals and lacks monitoring of limb movements, making it difficult to accurately determine whether a user has entered deep sleep.

[0006] In view of this, the present invention is hereby proposed. Summary of the Invention

[0007] The purpose of this invention is to provide a ventilator with integrated radar sensors and a method for determining respiratory events, so as to solve the above-mentioned technical problems existing in the prior art.

[0008] The objective of this invention is achieved through the following technical solution:

[0009] The ventilator with integrated radar sensor of the present invention includes a ventilation module, an airflow sensor and a pressure sensor, and further includes:

[0010] Radar sensors are used for non-contact monitoring of thoracic and body movements;

[0011] The respiratory event discrimination module is used to determine the degree of apnea and respiratory stability.

[0012] The control module is used to adjust the ventilation pressure based on the event outcome.

[0013] The above-mentioned method for determining respiratory events in a ventilator using an integrated radar sensor includes:

[0014] When the airflow signal decreases and the radar signal shows no chest movement, it is determined to be central sleep apnea.

[0015] When the airflow signal decreases and the radar signal shows chest movement, it is determined to be obstructive sleep apnea.

[0016] When breathing effort increases and there is body movement in the radar signal, it is determined to be a breathing effort awakening.

[0017] When periodic, stable breathing is detected and there is no obvious body movement in the radar signal, it is determined to be deep sleep.

[0018] Compared with existing technologies, the ventilator with integrated radar sensor and its respiratory event judgment method provided by the present invention achieves accurate detection of respiratory events and sleep state by monitoring chest wall movement and body movement with non-contact radar and fusing them with airway sensor signals. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of a ventilator with an integrated radar sensor provided in an embodiment of the present invention.

[0020] Figure 2 This is a schematic diagram of the judgment logic of the respiratory event judgment method provided in the embodiment of the present invention.

[0021] Figure 3 This is a schematic diagram illustrating the respiratory effort-related arousal method for determining respiratory events provided in an embodiment of the present invention.

[0022] Figure 4 This is a logical diagram illustrating the deep sleep state determination provided in an embodiment of the present invention. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them, and do not constitute a limitation on the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the protection scope of the present invention.

[0024] First, the following explanations are provided for the terms that may be used in this article:

[0025] The terms “including,” “contains,” “comprising,” “having,” or other similar semantic descriptions shall be interpreted as non-exclusive inclusion.

[0026] The contents not described in detail in the embodiments of this invention are prior art known to those skilled in the art. Where specific conditions are not specified in the embodiments of this invention, they shall be performed according to conventional conditions in the art or conditions recommended by the manufacturer. Where the manufacturers of the reagents or instruments used in the embodiments of this invention are not specified, they are all conventional products that can be purchased commercially.

[0027] The ventilator with integrated radar sensor of the present invention includes a ventilation module, an airflow sensor and a pressure sensor, and further includes:

[0028] Radar sensors are used for non-contact monitoring of thoracic and body movements;

[0029] The respiratory event discrimination module is used to determine the degree of apnea and respiratory stability.

[0030] The control module is used to adjust the ventilation pressure based on the event outcome.

[0031] The radar sensor is a millimeter-wave FMCW radar or a UWB radar.

[0032] The ventilation module is used to provide positive pressure ventilation;

[0033] The airflow sensor and pressure sensor are used to collect airway signals.

[0034] It also includes a signal processing module, which comprises a filtering unit, a feature extraction unit, and a data fusion algorithm unit.

[0035] It also includes a remote communication module for uploading gas path signals, radar signals, and event determination results to a cloud-based medical platform.

[0036] The above-mentioned method for determining respiratory events in a ventilator using an integrated radar sensor includes:

[0037] When the airflow signal decreases and the radar signal shows no chest movement, it is determined to be central sleep apnea.

[0038] When the airflow signal decreases and the radar signal shows chest movement, it is determined to be obstructive sleep apnea.

[0039] When respiratory effort increases and body movement is present in the radar signal, it is determined to be a state of awakened respiratory effort.

[0040] When periodic and stable breathing is detected and body movement is present in the radar signal, it is determined to be a deep sleep state.

[0041] In summary, the ventilator with integrated radar sensor and its respiratory event judgment method according to the embodiments of the present invention achieve accurate detection of respiratory events by monitoring chest wall movement and body movement with non-contact radar and fusing them with airway sensing signals.

[0042] To more clearly demonstrate the technical solution and its effects provided by the present invention, the embodiments of the present invention will be described in detail below with reference to specific examples.

[0043] Specific plan:

[0044] 1. Set up an integrated power supply and communication interface on the ventilator. A millimeter-wave radar module can be installed as an option, or the millimeter-wave radar can be integrated into the device.

[0045] 2. The radar signal is fused with the airflow / pressure signal, and a multimodal algorithm is used to distinguish between obstructive sleep apnea and central sleep apnea; the presence of respiratory effort-related arousal in the user is detected;

[0046] 3. The ventilator automatically adjusts the pressure based on the fusion results.

[0047] Beneficial effects:

[0048] 1. More accurate assessment of arousal related to breathing effort;

[0049] 2. Can distinguish between obstructive and central sleep apnea;

[0050] 3. Improve the reliability of monitoring in home environments;

[0051] 4. By identifying deep sleep states, it can help assess a user's sleep quality;

[0052] 5. Provide redundant monitoring pathways to facilitate clinical diagnosis and telemedicine.

[0053] Example 1

[0054] like Figure 1 As shown:

[0055] 1. Hardware integration, such as Figure 1 As shown:

[0056] 1) Radar module: Employs millimeter-wave radar, mounted on the side of the ventilator, facing the user;

[0057] 2) Ventilation section: Same as existing bilevel or automated CPAP ventilators.

[0058] 2. Signal Processing:

[0059] 1) The radar signal is filtered and motion compensated to extract micro-motion signals and body motion signals;

[0060] The specific steps include:

[0061] (1) De-clutter / bandpass

[0062] Background cancellation (moving mean high-pass)

[0063]

[0064] Respiratory band duct (0.1~0.7Hz)

[0065]

[0066] (2) Motion compensation / body movement discrimination

[0067] Distance trajectory variance:

[0068]

[0069] Define the body movement index:

[0070]

[0071] (3) Micro-movement / respiratory intensity

[0072] Micro-kinetic energy:

[0073]

[0074] 2) Synchronize and align with airflow signals for data fusion;

[0075] (1) Unified timeline

[0076] Linear interpolation to common sampling rate Fs:

[0077]

[0078] (2) Fusion window and feature vector

[0079] Calculated using a sliding window W (e.g., 30–60 s):

[0080]

[0081] 3. Decision logic, such as Figure 2 As shown:

[0082] 1) Central sleep apnea

[0083] Airflow decreases by more than 80% and lasts for more than 10 seconds + radar shows no chest movement.

[0084] 2) Obstructive sleep apnea

[0085] Airflow decreases by more than 80% and lasts for more than 10 seconds; radar detects chest movement.

[0086] 4. Breathing effort-related arousal, such as Figure 3 As shown:

[0087] 1) Judging the increase in breathing effort by airflow

[0088]

[0089] Where: Flat represents the flatness of the intake phase airflow.

[0090]

[0091] IDR indicates the intake duty cycle.

[0092]

[0093] ΔFpk represents the decrease in inspiratory peak flow.

[0094]

[0095] 2) If a radar body motion signal appears near the peak of effort [t−τ1,t+τ2] (e.g., −5 s to +5 s), it is determined as RERA. The event timestamp is set to ta, and the event duration can be estimated from the start of the effort ascent phase to ta (typically 10-60 s).

[0096] 5. Determining deep sleep, such as... Figure 4 As shown:

[0097] set up:

[0098] At the start of inspiration in the nth respiratory cycle, calculate:

[0099] Tidal volume: V T (n)

[0100] Respiratory cycle duration: T c (n)

[0101] Peak inspiratory flow rate: F pk (n)

[0102] Trough expiratory flow rate: F min (n)

[0103] The ratio is defined as the value compared to the corresponding value in the previous period:

[0104]

[0105] Define the stability determination function:

[0106]

[0107] The stable respiratory count is then updated as follows:

[0108] C stable (n) = C stable (n-1)+S(n)

[0109] The judgment criteria are:

[0110] C stable When (n)>30 and there are no physical activity events, it is determined to be deep sleep.

[0111] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims. The information disclosed in the background section is intended only to enhance the understanding of the overall background technology of the present invention and should not be construed as an admission or implication in any way that such information constitutes prior art known to those skilled in the art.

Claims

1. A ventilator integrating radar sensors, comprising a ventilation module, an airflow sensor, and a pressure sensor, characterized in that, Also includes: Radar sensors are used for non-contact monitoring of thoracic and body movements; The respiratory event discrimination module is used to determine the degree of apnea and respiratory stability. The control module is used to adjust the ventilation pressure based on the event outcome.

2. The ventilator with integrated radar sensor according to claim 1, characterized in that: The radar sensor is a millimeter-wave radar or a UWB radar. The ventilation module is used to provide positive pressure ventilation; The airflow sensor and pressure sensor are used to collect airway signals.

3. The ventilator with integrated radar sensor according to claim 2, characterized in that, It also includes a signal processing module, which comprises a filtering unit, a feature extraction unit, and a data fusion algorithm unit.

4. The ventilator with integrated radar sensor according to claim 3, characterized in that, It also includes a remote communication module for uploading gas path signals, radar signals, and event determination results to a cloud-based medical platform.

5. A method for determining respiratory events in a ventilator using an integrated radar sensor as described in any one of claims 1 to 4, characterized in that, include: When the airflow signal decreases and the radar signal shows no chest movement, it is determined to be central sleep apnea. When the airflow signal decreases and the radar signal shows chest movement, it is determined to be obstructive sleep apnea. When breathing effort increases and there is body movement in the radar signal, it is determined to be a breathing effort awakening. When periodic and stable breathing is detected and body movement is present in the radar signal, it is determined to be a deep sleep state.

Images