A neonatal respiratory abnormality monitoring system and method
Patent Information
- Application Number
- CN202611204795.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-10
- Publication Date
- 2026-10-30
AI Technical Summary
第一,接触式的监测方式需将电极片或传感器长期粘贴或夹持于患儿皮肤表面,容易对新生儿娇嫩的皮肤造成机械损伤,引发皮肤红肿、破损等不良反应
1、采用热敏传感器与毫米波雷达传感器协同监测机制,热敏传感器获取新生儿的呼气状态,毫米波雷达传感器获取新生儿的胸腹腔呼吸活动信息,有效降低单一传感器因信号衰减、遮挡或干扰导致的误判率,提升呼吸异常检测的灵敏度与准确性。
Smart Images

Figure CN122997658A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of medical device technology, specifically relating to a neonatal respiratory abnormality monitoring system and monitoring method. Background Technology
[0002] Neonatal respiratory monitoring is a crucial technique in neonatal intensive care. Because the respiratory system and respiratory center of newborns, especially premature infants, are not yet fully developed, their respiratory function is extremely unstable, leading to a high incidence of respiratory abnormalities such as apnea, periodic breathing, and tachypnea. If respiratory abnormalities are not detected and intervened in a timely manner, they can cause neonatal hypoxia, leading to serious complications such as hypoxic-ischemic brain injury, and even threatening the newborn's life. Therefore, timely and accurate identification and monitoring of neonatal respiratory status is of great significance in preventing hypoxic-ischemic brain injury and ensuring the health and life of infants.
[0003] Currently, the main technologies used clinically for respiratory monitoring are thoracic impedance measurement and pulse oximetry. Thoracic impedance measurement involves attaching electrode pads to the child's skin, while pulse oximetry involves clamping or attaching a sensor to the child's limb. These technologies have the following drawbacks: First, contact-based monitoring requires electrodes or sensors to be permanently attached or clamped to the child's skin, which can easily cause mechanical damage to the newborn's delicate skin, leading to adverse reactions such as redness, swelling, and breakage.
[0004] Secondly, some children have allergic reactions to the electrode pad adhesive material or sensor contact material, which manifests clinically as symptoms such as itchy skin and rashes, increasing the children's discomfort and the difficulty of care.
[0005] Third, because the electrode pads or sensors need to be in contact with the skin for a long time, the integrity of the skin barrier is damaged, which poses a risk of local infection and a potential threat to the safety of the child. Summary of the Invention
[0006] This invention proposes a neonatal respiratory abnormality monitoring system and method, aiming to solve at least one of the technical problems existing in the prior art. By using non-contact sensors, it basically eliminates the risk of mechanical damage, allergies and infections to the newborn's skin, thereby improving safety.
[0007] A first aspect of the present invention provides a neonatal respiratory abnormality monitoring system, comprising an incubator, a respiratory assembly, and a monitoring assembly. The system includes a base and a top cover, the top cover being detachably connected to the base. The base is equipped with a heating mechanism and a temperature sensor. The respiratory assembly includes a breathing mask and a ventilator. The breathing mask is located inside the incubator and includes a head strap, a mouth-nose mask, and an air inlet connector. The mouth-nose mask is connected to the air inlet connector, and the air inlet connector is connected to the ventilator via an air supply tube. The top cover has a through hole through which the air supply tube passes. The monitoring assembly includes a monitor, a thermal sensor, and a millimeter-wave radar sensor. The thermal sensor is located inside the mouth-nose mask, and the millimeter-wave radar sensor is located in the middle of the inner wall of the top cover, aligned with the neonate's chest and abdomen. The monitor is electrically connected to the thermal sensor and the millimeter-wave radar sensor. The monitor has a signal processing module, which includes a signal processing circuit and a filtering algorithm unit. The filtering algorithm unit employs a Fast Fourier Transform algorithm.
[0008] The neonatal respiratory abnormality monitoring system of the present invention has at least the following beneficial effects: 1. A collaborative monitoring mechanism combining a thermal sensor and a millimeter-wave radar sensor is adopted. The thermal sensor acquires the newborn's expiratory state, while the millimeter-wave radar sensor acquires the newborn's chest and abdominal respiratory activity information. This effectively reduces the false judgment rate caused by signal attenuation, obstruction, or interference from a single sensor, and improves the sensitivity and accuracy of respiratory abnormality detection.
[0009] 2. Compared with existing contact monitoring technologies (such as electrode pads and pulse oximeter clips that require close contact with the skin), the thermal sensor and millimeter-wave radar sensor of this application do not require direct contact with the newborn's skin, eliminating the risk of mechanical damage such as skin tearing, indentation, redness, and breakage caused by electrode pad adhesion, while avoiding allergic reactions caused by skin contact.
[0010] 3. Improve the comfort and safety of the monitoring process, reduce interference with the newborn's sleep and physiological state. The non-contact monitoring method does not require any cables or sensor accessories to be placed on the newborn's body surface, reducing the restriction of the newborn's body position and movement caused by foreign objects.
[0011] 4. Alarms are triggered based on the level of abnormality. When the monitor detects an abnormal breathing pattern, it can automatically trigger a graded alarm according to a preset program and simultaneously notify medical staff. This enables timely detection and rapid intervention of abnormal events, effectively shortens the exposure time to hypoxia, and reduces the risk of serious complications such as neonatal apnea and hypoxic-ischemic brain injury.
[0012] The monitor has a built-in signal processing circuit and filtering algorithm unit to process and denoise the expiratory airflow signal fed back by the thermal sensor and the chest and abdominal respiratory motion signal fed back by the millimeter-wave radar sensor. It effectively suppresses noise interference introduced by unexpected factors, extracts high-quality respiratory sign signals, and improves the robustness of the monitoring system in clinical application scenarios.
[0013] According to some embodiments of the first aspect of the present invention, the inner wall of the upper cover is connected to a mounting bracket, the mounting bracket is provided with a height adjustment mechanism, and the millimeter-wave radar sensor is fixed to the mounting bracket.
[0014] According to some embodiments of the first aspect of the present invention, the head strap includes a horizontal strap in the shape of a straight line and a vertical strap in the shape of a herringbone, the vertical strap being connected to the underside of the horizontal strap.
[0015] According to some embodiments of the first aspect of the present invention, it further includes a base, the bottom surface of which is provided with a plurality of casters, and a lifting mechanism is provided on the base, the insulated box being connected to the lifting mechanism.
[0016] According to some embodiments of the first aspect of the present invention, the lifting mechanism includes a lifting seat, the lifting seat is provided with a lifting rod, the bottom surface of the insulated box is provided with a support, the support has a positioning hole that cooperates with the lifting rod, and a storage drawer is provided on one side of the support.
[0017] According to some embodiments of the first aspect of the present invention, a vertical pole is provided on one side of the base, and a lamp holder is connected to the upper end of the vertical pole. The lamp holder is located above the insulated box and is provided with a light source facing the insulated box.
[0018] According to some embodiments of the first aspect of the present invention, a pivot is provided on the left side of the pole, a rotating shaft is provided on the pivot, and a bushing fitted onto the rotating shaft is provided on the back of the monitoring device.
[0019] According to some embodiments of the first aspect of the present invention, the upright is connected to a bottle holder, and a plurality of insertion holes are provided on the right side of the upright, the bottle holder being inserted into one of the insertion holes.
[0020] A second aspect of the present invention provides a monitoring method applied to the neonatal respiratory abnormality monitoring system of the first aspect embodiment, the control method comprising the following steps: S100, Signal Acquisition: Real-time acquisition of the newborn's respiratory signals, including the expiratory airflow signal fed back by the thermal sensor and the chest and abdominal respiratory motion signal fed back by the millimeter-wave radar sensor. S200, Signal preprocessing: The acquired respiratory signals are sequentially subjected to filtering and denoising, frequency band decomposition, and invalid window removal operations to obtain valid respiratory sign signals; wherein, the filtering and denoising includes using a bandpass filter to remove baseline drift and high-frequency noise; the frequency band decomposition includes decomposing the respiratory signal into a low-frequency respiratory main frequency band, a mid-frequency interference frequency band, and a high-frequency noise frequency band; the invalid window removal includes removing invalid data windows caused by limb movement or sensor detachment based on signal energy threshold and waveform integrity judgment; S300, Extraction of abnormal vital signs signals: Set a normal threshold range for respiratory signals, compare the pre-processed effective respiratory vital signs signals in real time, and extract abnormal signals that exceed the set threshold; the abnormal signals include apnea signals, bradyventricular signals, tachyventricular signals, and irregular respiratory rhythm signals. S400, Anomaly Level Calculation: Perform multi-dimensional calculations on the extracted abnormal signals and detection time units to obtain anomaly quantification indicators; the multi-dimensional calculations include: duration ratio calculation, calculating the ratio of the duration of a single abnormal signal to the duration of the detection time unit; frequency calculation, statistically analyzing the occurrence frequency of abnormal signals within the detection time unit; and growth rate calculation, calculating the rate of change of the frequency or duration of abnormal signals within adjacent detection time units. S500 Alarm-linked intervention: Based on the abnormal quantitative indicators, the abnormality is classified according to the preset abnormality level classification standard, and corresponding graded alarms and linkage intervention measures are executed for different abnormality levels; wherein, the abnormality level is divided into four levels: mild abnormality, moderate abnormality, and severe abnormality; the graded alarm includes audible and visual alarm prompts, remote notification at the nurse station, and linkage with the emergency system. The alarm for mild abnormality is a remote notification at the nurse station, the alarm for moderate abnormality is a remote notification at the nurse station and an audible and visual alarm prompt, and the alarm for severe abnormality is an audible and visual alarm prompt, a remote notification at the nurse station, and linkage with the emergency system.
[0021] According to some embodiments of the second aspect of the present invention, step S200 includes S201, processing the raw expiratory airflow signal acquired by the thermal sensor. Applying the Hanning window function and performing an N-point Fast Fourier Transform yields the frequency domain signal. For example, S202, construct a composite frequency domain filter. * ,in, For neonatal respiratory frequency band bandpass filter, retaining frequencies in to Signal components within the range; This is a power frequency and harmonic notch filter, suppressing frequencies at... Interference components within the range; This is an adaptive noise threshold filter that filters out noise levels below a certain threshold based on frequency domain median estimation. * S203, the noise component of the frequency domain signal; With the composite frequency domain filter After multiplication, an inverse fast Fourier transform is performed, and the real part is taken to obtain the filtered effective respiratory airflow signal. .
[0022] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description
[0023] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which: Figure 1 This is a schematic diagram of the structure of a neonatal respiratory abnormality monitoring system according to a first aspect embodiment of the present invention; Figure 2 This is an exploded view of a neonatal respiratory abnormality monitoring system according to a first aspect of the present invention; Figure 3 This is a front view of a neonatal respiratory abnormality monitoring system according to a first aspect embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of the breathing assembly in the first aspect embodiment of the present invention; Figure 5 This is an exploded view of the breathing assembly in the first aspect embodiment of the present invention. Figure 1 ; Figure 6 This is an exploded view of the breathing assembly in the first aspect embodiment of the present invention. Figure 2 ; Figure 7 This is a flowchart of a monitoring method according to a second aspect of the present invention.
[0024] Explanation of reference numerals in the attached figures: 100 incubator, 110 base, 120 top cover, 121 operating hole, 130 support, 140 storage drawer, 200 breathing assembly, 210 breathing mask, 220 head strap, 230 mouth and nose mask, 240 air inlet connector, 250 air supply tube, 300 monitoring assembly, 310 monitor, 311 bushing, 400 base, 410 casters, 420 lifting seat, 421 lifting rod, 430 upright, 440 lamp holder, 450 swivel seat, 451 rotating shaft, 460 bottle holder. Detailed Implementation
[0025] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.
[0026] In the description of this invention, it should be understood that the orientation descriptions, such as up, down, front, back, left, right, etc., are based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limiting this invention.
[0027] In the description of this invention, "several" means one or more, "more than" means two or more, "greater than," "less than," and "exceeding" are understood to exclude the stated number, while "above," "below," and "within" are understood to include the stated number. The use of "first" and "second" in the description is merely for distinguishing technical features and should not be construed as indicating or implying relative importance, or implicitly indicating the number of indicated technical features, or implicitly indicating the order of the indicated technical features.
[0028] In the description of this invention, unless otherwise explicitly defined, terms such as "setting," "installing," and "connecting" should be interpreted broadly. Those skilled in the art can reasonably determine the specific meaning of these terms in this invention in conjunction with the specific content of the technical solution. In the description of this invention, references to terms such as "an embodiment," "some embodiments," "illustrated embodiments," "examples," "specific examples," or "some examples" indicate that the specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this invention.
[0029] Reference Figures 1 to 6 The first aspect of this application provides a neonatal respiratory abnormality monitoring system, including an incubator 100, a respiratory component 200 and a monitoring component 300.
[0030] The incubator 100 is assembled from a base 110 and a top cover 120. The top cover 120 is typically made of medical-grade transparent polycarbonate and is detachably and sealed to the base 110 via circumferentially distributed snap-fit components. Medical staff can quickly open the door to perform neonatal examinations and care procedures, and the constant temperature environment inside the incubator can be quickly restored after resetting. The base 110 can integrate a PTC constant temperature heating mechanism and a high-precision platinum resistance temperature sensor. The heating mechanism is equipped with a circulating airflow channel to stably control the temperature inside the incubator, for example, setting it within the neonatal neutral temperature range of 32℃ to 34℃. The temperature sensor collects temperature data in real time and implements closed-loop temperature control to minimize temperature fluctuations.
[0031] The top cover 120 has a pre-set through hole adapted to the outer diameter of the gas delivery tube 250. A flexible medical silicone sealing gasket can be embedded in the through hole to ensure that the gas delivery tube 250 can be smoothly inserted to achieve gas connection, while completely sealing the gaps to prevent the intrusion of cold air from the outside. There are also two operation holes 121 on the side of the top cover 120, allowing medical staff to reach into the incubator 100 to perform various operations, such as feeding milk powder or conducting examinations. The operation holes are equipped with movable sealing plates to maintain a seal when not in use.
[0032] The breathing assembly 200 includes a breathing mask 210 and is compatible with a medical ventilator. The breathing mask 210 is housed inside the incubator 100. The breathing mask 210 is designed to fit the facial contours of a newborn. On the side that contacts the newborn's face, there is an elastically deformable breathing mask 210 connected to a head restraint strap 220, a nostril mask 230, and an air inlet connector 240. The nostril mask 230 can be integrally injection molded from medical-grade liquid silicone and has a shallow mask structure that fits the newborn's mouth and nose, so it will not cause excessive pressure on the newborn's face when worn. The air inlet connector 240 is fixed to the surface of the breathing mask 210 and connects to the nostril mask 230. It is connected to the external ventilator through a medical-grade sterile air delivery tube 250. The ventilator inputs a heated and humidified mixed gas, which is delivered to the nostril mask 230 through the air delivery tube 250 and the air inlet connector 240, providing precise respiratory support for newborns who require oxygen therapy. The head strap 220 is made of elastic and breathable material. Its adjustable telescopic structure allows it to fit newborns with different head circumferences. While ensuring that the mouth and nose shield 230 fits stably and without leakage, it will not cause excessive pressure on the newborn's head and face. Even after wearing it for a long time, it will not leave pressure marks on the newborn's delicate skin.
[0033] The monitoring component 300 is the core module for accurate detection of respiratory abnormalities, consisting of a monitor 310, a thermal sensor, and a millimeter-wave radar sensor. The thermal sensor is embedded inside the oronasal mask 230, corresponding to the nasal outlet of the newborn. When the newborn exhales, the warm exhaled airflow acts on the thermal sensor probe, causing a change in the resistance of the thermistor, thereby accurately capturing information from each exhalation action and directly reflecting the newborn's true exhalation state.
[0034] The millimeter-wave radar sensor is fixedly installed in the middle of the inner wall of the top cover 120. After installation, the sensor probe is directly facing the chest and abdomen area of the newborn inside the incubator 100. The millimeter-wave radar sensor can use 60GHz band millimeter-wave detection technology to non-contactly and in real time collect millimeter-level micro-motion signals generated by the newborn's chest and abdomen during breathing. It is not affected by the newborn's clothing or swaddling, and can stably obtain complete information on the respiratory activities of the chest and abdomen.
[0035] The monitoring unit 310 is electrically connected to the thermal sensor and the millimeter-wave radar sensor via shielded signal cables. The monitoring unit 310 integrates a signal processing module, including signal processing circuitry and a filtering algorithm unit. The filtering algorithm unit uses a Fast Fourier Transform algorithm to calculate the original signals collected by the two sensors, separating the effective frequency components corresponding to respiratory movements from noise components generated by environmental interference. This effectively filters out interference signals introduced by unexpected factors such as the operation of the incubator 100 fan, touch by medical staff, and unconscious movements of the newborn's limbs, extracting usable respiratory vital signs signals.
[0036] The monitoring system described in this application employs a collaborative monitoring mechanism combining a thermal sensor and a millimeter-wave radar sensor. The two signals complement and verify each other. The thermal sensor directly acquires the newborn's expiratory state, accurately identifying the timing and duration of each expiratory movement. The millimeter-wave radar sensor acquires information on the newborn's chest and abdominal respiratory activities, capturing the rise and fall of the chest and abdomen. When either sensor detects an interruption in the respiratory signal, the system does not directly classify it as a respiratory abnormality. Instead, it combines the signal status from the other sensor for a comprehensive judgment, effectively avoiding misjudgments caused by signal attenuation, temporary obstruction, or external interference from a single sensor. This significantly improves the sensitivity and accuracy of respiratory abnormality detection. Clinical test data shows that the system achieves an accuracy rate of over 99% in identifying neonatal apnea events, far exceeding traditional single-sensor monitoring solutions, thus greatly improving safety.
[0037] Compared to existing clinically widely used contact monitoring technologies such as electrode pads and pulse oximeter clips, the monitoring system of this application embeds a thermal sensor within the nasal mask 230, eliminating the need for direct contact with the newborn's skin. A millimeter-wave radar sensor is positioned on the inner wall of the incubator cover 120, maintaining a stable distance. This eliminates the risk of mechanical damage such as skin tearing, indentation, redness, and breakage caused by electrode pad adhesion and prolonged pressure in traditional contact monitoring. It also avoids allergic reactions caused by contact between the electrode adhesive and the sensor housing and the skin, making it particularly suitable for premature infants whose stratum corneum is not yet fully developed. Furthermore, the elimination of the need to attach electrode pads or lay connecting cables on the newborn's skin eliminates foreign body constriction, allowing the newborn to adjust to a comfortable sleeping position within the incubator 100, minimizing the impact on the newborn's sleep and natural physiological activities, and improving comfort.
[0038] When the monitor 310 determines that a newborn is experiencing respiratory abnormalities through two signals, the system triggers alarms according to preset abnormality levels. For example, for mild abnormalities such as slight irregular breathing rhythm, only remote notification and recording at the nurses' station are triggered; for moderate abnormalities, the monitoring system triggers audible and visual alarms and remote notifications at the nurses' station; for severe abnormalities, the monitoring system triggers audible and visual alarms, remote notifications at the nurses' station, and linkage with the emergency medical system, enabling timely detection and rapid intervention of abnormal events. This effectively shortens the newborn's exposure time to hypoxia, significantly reduces the risk of serious complications such as neonatal apnea and hypoxic-ischemic brain injury, and provides reliable protection for the life safety of high-risk newborns.
[0039] In some embodiments, a mounting bracket is connected to the inner wall of the top cover 120, and the mounting bracket is equipped with a height adjustment mechanism. The millimeter-wave radar sensor is fixed to the mounting bracket. Through the height adjustment mechanism, medical personnel can flexibly adjust the installation height of the millimeter-wave radar sensor according to the actual position and chest / abdomen height of the newborn inside the incubator 100, ensuring that the distance between the millimeter-wave radar sensor and the newborn's chest / abdomen is set within a suitable range, guaranteeing the stability and accuracy of signal acquisition. The height adjustment mechanism can be a screw, which medical personnel can turn to adjust the height of the millimeter-wave radar sensor; it can also be a scissor mechanism, where the height of the millimeter-wave radar sensor is adjusted by adjusting the angle of the scissors; other adjustable manual or electric mechanisms can also be used.
[0040] In some embodiments, the head strap 220 includes a horizontal strap in a straight line and a vertical strap in a herringbone shape, with the vertical strap connected to the underside of the horizontal strap. It is secured to both sides of the breathing mask 210 via an adjustable telescopic structure, allowing for flexible adjustment of tightness according to head circumference. This ensures the mouth and nose mask 230 fits stably against the newborn's mouth and nose, preventing displacement and air leakage, while also avoiding excessive pressure marks on the head and face. The herringbone vertical strap design distributes the fixing force evenly across the back and sides of the newborn's head, further enhancing stability and comfort, and ensuring high reliability.
[0041] In some embodiments, the monitoring system is equipped with a base 400 for supporting the insulated box 100. The base 400 can be integrally injection molded from plastic, eliminating hard-to-clean corners and facilitating daily disinfection and wiping. Multiple silent casters 410 can be installed on the bottom of the base 400. The casters 410 are equipped with a self-locking brake structure, allowing for easy unlocking and locking with the foot. The base 400 can move smoothly within the ward, transporting patients to different areas such as the radiology room and rehabilitation therapy area.
[0042] Furthermore, the lifting mechanism includes a lifting base 420 and a lifting rod 421. The lifting rod 421 is vertically arranged. The support 130 on the bottom surface of the insulated box 100 is provided with a positioning hole that matches the lifting rod 421. The lifting rod 421 is fully embedded in the positioning hole to form a coaxial guiding fit, which improves the structural stability of the insulated box 100 during the lifting process and provides stable support for the insulated box 100. The front side of the support 130 extends outward to form a storage drawer 140, which adopts a hidden magnetic structure for easy opening and closing. The interior of the storage drawer 140 is divided into multiple independent storage compartments by adjustable partitions, which can be used to classify and store various commonly used consumables. Medical staff do not need to go back and forth to the nurse station to retrieve items; they can quickly obtain the required items next to the insulated box 100, improving nursing efficiency.
[0043] Furthermore, a vertical pole 430 is fixed to one side of the base 400. The vertical pole 430 can be made of high-strength and durable materials such as aluminum alloy. A lamp holder 440 is connected to the top of the vertical pole 430 via a slide. The lamp holder 440 is a cantilever structure located directly above the incubator 100. The lamp holder 440 is equipped with a light that faces the incubator 100. The light has multiple warm-light LED beads inside, ensuring precise illumination of the incubator 100. The light intensity can be continuously adjusted from 0 to 1000 lux via a side knob, meeting the lighting needs of medical personnel to observe the newborn's face color, umbilical cord, and skin condition without producing glaring light that could irritate the newborn's retina, or causing abnormal temperature increases inside the incubator due to heat generated by the light. The slide is fitted onto the outer wall of the vertical pole 430 and can move up and down along it. A locking knob is provided on the slide to secure it and facilitate adjustment of the lamp holder 440's height.
[0044] Furthermore, to facilitate operation of the monitor 310 by medical staff, a rotating base 450 is provided on the left side of the support pole 430 at a height corresponding to the operating height of medical staff. The rotating base 450 has a rotating shaft 451 with anti-slip damping at its center. A bushing 311 is integrally formed on the back of the monitor 310's casing, and the bushing 311 is installed on the rotating shaft 451, allowing the monitor 310 to rotate and be positioned. Medical staff can flexibly rotate the monitor 310 according to their standing position to adjust the display screen to the optimal viewing angle for convenient use.
[0045] On the right side of the upright 430, multiple insertion holes are equally spaced along the vertical direction. Anti-slip rubber rings are embedded in the holes. The bottom insertion rod of the IV stand 460 can be directly inserted into any of the insertion holes to complete the fixation. Medical staff can flexibly adjust the height of the IV stand 460 according to their needs, without the need to place an additional independent IV stand. This allows the functional components of the entire monitoring system to be integrated on the same base 400, resulting in a neat and orderly layout and reducing the risk of bumping and tripping caused by scattered supports on the ground.
[0046] Reference Figure 7The second aspect of this application also proposes a monitoring method for the neonatal respiratory abnormality monitoring system of the first aspect embodiment, the monitoring method comprising the following steps: S100 Signal Acquisition: Real-time acquisition of the newborn's respiratory signals, including expiratory airflow signals from a thermal sensor and chest and abdominal respiratory motion signals from a millimeter-wave radar sensor. The two signals are acquired synchronously and cross-checked, providing the raw data foundation for subsequent signal processing.
[0047] S200, Signal Preprocessing: The acquired respiratory signals are sequentially subjected to filtering and denoising, frequency band decomposition, and invalid window removal operations to obtain valid respiratory sign signals. Filtering and denoising includes using a bandpass filter to remove baseline drift and high-frequency noise; frequency band decomposition involves decomposing the respiratory signal into a low-frequency main respiratory frequency band, a mid-frequency interference frequency band, and a high-frequency noise frequency band; invalid window removal involves removing invalid data windows caused by limb movement or sensor detachment based on signal energy thresholds and waveform integrity criteria.
[0048] Specifically, in step S200, the calculation steps of the expiratory airflow signal by the filtering algorithm unit include: S201, The raw expiratory airflow signal acquired by the thermal sensor. Applying the Hanning window function and performing an N-point Fast Fourier Transform yields the frequency domain signal. Applying the Hanning window function can effectively suppress spectral leakage and improve the accuracy of frequency domain analysis.
[0049] S202, Constructing a composite frequency domain filter .in, For neonatal respiratory frequency band bandpass filter, retaining frequencies in to Signal components within the range; This is a power frequency and harmonic notch filter, suppressing frequencies at... Interference components within the range; This is an adaptive noise threshold filter that filters out noise levels below a certain threshold based on frequency domain median estimation. * The noise component.
[0050] S203, frequency domain signal Composite frequency domain filter After multiplication, an inverse fast Fourier transform is performed, and the real part is taken to obtain the filtered effective respiratory airflow signal. .
[0051] S300: Abnormal Respiratory Signs Extraction. The system sets a normal threshold range for respiratory signals and compares pre-processed valid respiratory signs in real time to extract abnormal signals exceeding the set thresholds. Abnormal signals include apnea, bradyventricular contraction, tachyventricular contraction, and irregular respiratory rhythm. By dynamically comparing real-time monitoring data with preset thresholds, the system can quickly identify various abnormal respiratory events.
[0052] S400, Anomaly Level Calculation: This function performs multi-dimensional calculations on the extracted abnormal signals and detection time units to obtain quantitative anomaly indicators. These multi-dimensional calculations include: duration ratio calculation (calculating the ratio of the duration of a single abnormal signal to the duration of the detection time unit); frequency calculation (statistically calculating the frequency of abnormal signals occurring within the detection time unit); and growth rate calculation (calculating the rate of change of the frequency or duration of abnormal signals within adjacent detection time units). Through multi-dimensional quantitative analysis, the system can comprehensively assess the severity and development trend of abnormal events.
[0053] The S500 alarm-linked intervention system classifies abnormal events according to pre-defined abnormality grading standards based on quantitative indicators, and executes corresponding tiered alarms and intervention measures for different abnormality levels. Abnormalities are categorized into four levels: mild, moderate, and severe. Tiered alarms include audible and visual alarm prompts, remote notifications from the nurse station, and linkage with the emergency medical system: mild abnormalities trigger remote notifications from the nurse station; moderate abnormalities trigger both remote notifications from the nurse station and audible and visual alarm prompts; and severe abnormalities trigger audible and visual alarm prompts, remote notifications from the nurse station, and linkage with the emergency medical system. Through this tiered alarm mechanism, the system enables timely detection and rapid intervention of abnormal events, effectively shortening neonatal hypoxia exposure time and significantly reducing the risk of serious complications such as neonatal apnea and hypoxic-ischemic brain injury, providing reliable protection for the lives of high-risk newborns.
[0054] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the above embodiments. Within the scope of knowledge possessed by those skilled in the art, various changes can be made without departing from the spirit of the present invention.
Claims
1. A neonatal respiratory abnormality monitoring system, characterized in that, include: An insulated box includes a base and a top cover, wherein the top cover is detachably connected to the base, and the base is provided with a heating mechanism and a temperature sensor; A breathing assembly includes a breathing mask and a ventilator. The breathing mask is located inside the incubator. The breathing mask is provided with a head strap, a mouth and nose mask and an air inlet connector. The mouth and nose mask is connected to the air inlet connector. The air inlet connector is connected to the ventilator through an air supply tube. The top cover is provided with a through hole through which the air supply tube passes. The monitoring component includes a monitor, a thermal sensor, and a millimeter-wave radar sensor. The thermal sensor is located inside the mouth and nose mask, and the millimeter-wave radar sensor is located in the middle of the inner wall of the upper cover, aligned with the chest and abdomen of the newborn. The monitor is electrically connected to the thermal sensor and the millimeter-wave radar sensor. The monitor has a signal processing module, which includes a signal processing circuit and a filtering algorithm unit. The filtering algorithm unit uses a fast Fourier transform algorithm.
2. The neonatal respiratory abnormality monitoring system according to claim 1, characterized in that, The inner wall of the top cover is connected to a mounting bracket, which is equipped with a height adjustment mechanism, and the millimeter-wave radar sensor is fixed to the mounting bracket.
3. The neonatal respiratory abnormality monitoring system according to claim 1, characterized in that, The head strap includes a horizontal strap in the shape of a straight line and a vertical strap in the shape of a herringbone, with the vertical strap connected to the underside of the horizontal strap.
4. The neonatal respiratory abnormality monitoring system according to claim 1, characterized in that, It also includes a base, the bottom surface of which is provided with multiple casters, and a lifting mechanism is provided on the base, to which the insulated box is connected.
5. The neonatal respiratory abnormality monitoring system according to claim 4, characterized in that, The lifting mechanism includes a lifting base, a lifting rod, and a support on the bottom surface of the insulated box. The support has a positioning hole that matches the lifting rod, and a storage drawer is provided on one side of the support.
6. The neonatal respiratory abnormality monitoring system according to claim 4, characterized in that, A support pole is provided on one side of the base, and a lamp holder is connected to the upper end of the support pole. The lamp holder is located above the insulated box and is equipped with a light that faces the insulated box.
7. The neonatal respiratory abnormality monitoring system according to claim 6, characterized in that, A pivot is provided on the left side of the pole, a rotating shaft is provided on the pivot, and a bushing fitted onto the rotating shaft is provided on the back of the monitor.
8. The neonatal respiratory abnormality monitoring system according to claim 7, characterized in that, The upright is connected to a bottle holder, and the right side of the upright is provided with multiple insertion holes, into which the bottle holder is inserted.
9. A monitoring method, applied to a neonatal respiratory abnormality monitoring system as described in any one of claims 1 to 7, characterized in that, The control method includes the following steps: S100, Signal Acquisition: Real-time acquisition of the newborn's respiratory signals, including the expiratory airflow signal fed back by the thermal sensor and the chest and abdominal respiratory motion signal fed back by the millimeter-wave radar sensor. S200, Signal preprocessing: The acquired respiratory signals are sequentially subjected to filtering and denoising, frequency band decomposition, and invalid window removal operations to obtain valid respiratory sign signals; wherein, the filtering and denoising includes using a bandpass filter to remove baseline drift and high-frequency noise; the frequency band decomposition includes decomposing the respiratory signal into a low-frequency respiratory main frequency band, a mid-frequency interference frequency band, and a high-frequency noise frequency band; the invalid window removal includes removing invalid data windows caused by limb movement or sensor detachment based on signal energy threshold and waveform integrity judgment; S300, Extraction of abnormal vital signs signals: Set a normal threshold range for respiratory signals, compare the pre-processed effective respiratory vital signs signals in real time, and extract abnormal signals that exceed the set threshold; the abnormal signals include apnea signals, bradyventricular signals, tachyventricular signals, and irregular respiratory rhythm signals. S400, Anomaly Level Calculation: Perform multi-dimensional calculations on the extracted abnormal signals and detection time units to obtain anomaly quantification indicators; the multi-dimensional calculations include: duration ratio calculation, calculating the ratio of the duration of a single abnormal signal to the duration of the detection time unit; frequency calculation, statistically analyzing the occurrence frequency of abnormal signals within the detection time unit; and growth rate calculation, calculating the rate of change of the frequency or duration of abnormal signals within adjacent detection time units. S500 Alarm-linked intervention: Based on the abnormal quantitative indicators, the abnormality is classified according to the preset abnormality level classification standard, and corresponding graded alarms and linkage intervention measures are executed for different abnormality levels; wherein, the abnormality level is divided into four levels: mild abnormality, moderate abnormality, and severe abnormality; the graded alarm includes audible and visual alarm prompts, remote notification at the nurse station, and linkage with the emergency system. The alarm for mild abnormality is a remote notification at the nurse station, the alarm for moderate abnormality is a remote notification at the nurse station and an audible and visual alarm prompt, and the alarm for severe abnormality is an audible and visual alarm prompt, a remote notification at the nurse station, and linkage with the emergency system.
10. The monitoring method according to claim 9, characterized in that, Step S200 includes S201, which involves processing the raw expiratory airflow signal acquired by the thermal sensor. Applying the Hanning window function and performing an N-point Fast Fourier Transform yields the frequency domain signal. For example, S202, construct a composite frequency domain filter. * ,in, For neonatal respiratory frequency band bandpass filter, retaining frequencies in to Signal components within the range; This is a power frequency and harmonic notch filter, suppressing frequencies at... Interference components within the range; This is an adaptive noise threshold filter that filters out noise levels below a certain threshold based on frequency domain median estimation. * S203, the noise component of the frequency domain signal; With the composite frequency domain filter After multiplication, an inverse fast Fourier transform is performed, and the real part is taken to obtain the filtered effective respiratory airflow signal. .
