876 results about "Full Term Neonate" patented technology

The invention relates to the technical field of health assessment, in particular to a newborn health assessment method and system based on visual analysis, and the method comprises the following steps: obtaining a newborn image frame sequence, extracting a hue curve, recognizing a variation region to generate a layer, and extracting a mutation region bitmap group in combination with a heart rate RR interval difference value; and analyzing an included angle mapping grid between the center of gravity of the pigment and the heart rate slope, superposing a respiratory rate curvature, performing co-occurrence clustering to form a trend graph block, and evaluating a risk distribution interface formed by joint mutation. According to the method, a dynamic coupling relation between an image and a physiological signal is established through slope direction angle change and included angle deviation, cross-dimension mapping of heart rate trend change and visual feature change is achieved, the heart rate, skin color tracks and curvature change of respiratory frequency are fused, a trend gathering map is constructed, and the dynamic coupling relation between the image and the physiological signal is obtained. The risk judgment and display are completed according to the joint grading of the block density, the time span and the parameter quantity in the atlas, and the health level fluctuation trend is visually presented in the risk evolution sorting.

The invention discloses a continuous monitoring method for neonatal jaundice and a related device. The method comprises the steps that a sensor module arranged on a patch or a bracelet is used for percutaneously measuring the bilirubin level of a neonate; the measurement data of the photoelectric sensor is corrected according to the data of the temperature sensor, the bilirubin level of the newborn is calculated through a preset bilirubin model based on the corrected data of the photoelectric sensor, and the preset bilirubin model comprises a light absorption model and a dynamic correction model; establishing a relation model of light absorption and bilirubin concentration by the light absorption model; the dynamic correction model adjusts parameters of the light absorption model; and transmitting the bilirubin level to a remote server, and when the bilirubin level exceeds a preset alarm threshold, generating an alarm signal and pushing the alarm signal to a medical staff client and / or a parent client. According to the invention, personalized continuous monitoring of neonatal jaundice is realized through a dynamic correction model, an intelligent alarm threshold, closed-loop control and auxiliary treatment means.

An embodiment of the present disclosure provides a reflux-preventing cushion for preventing digestive reflux that occurs in a newborn, the reflux-preventing cushion including a backrest cushion configured to be inclined at a certain angle and allow the newborn to be laid to prevent the digestive reflux, and a buttocks cushion including a pair of bands configured to cover the newborn from both sides of the body of the newborn in a state in which the newborn is laid on the backrest cushion, wherein an uninclined backrest cushion is further included on an upper portion of an inclined backrest cushion.

The invention relates to the field of medical treatment, and discloses a full-process quality control management system for neonatal disease screening, which comprises a data real-time acquisition module for realizing data intercommunication and dynamic acquisition with a laboratory information system, detection equipment and a sample management system through a standardized API (Application Program Interface) and a data transmission protocol; the indoor quality control module is used for performing real-time monitoring and rule management on laboratory internal detection quality by applying a Westgard multi-rule control algorithm and a real-time data monitoring technology; and the interroom quality evaluation module is used for carrying out multi-laboratory detection result comparison and quality evaluation by adopting a data encryption and anonymization processing technology. Through cooperation of a cross-system docking unit and a dynamic data analysis unit of the data real-time acquisition module, data islands of a laboratory information system, detection equipment and a sample management system are broken through, and real-time intercommunication and standardized processing of sample information, detection data and process nodes are realized.

The invention relates to the technical field of pediatric medical treatment, and discloses a pediatric neonatal jaundice clinical phototherapy management system, which integrates illumination data in an equipment lamp box through a data integration module, extracts the illumination data acquired by the data integration module through a fusion analysis module, and fuses the operation duration of a lamp tube to obtain a phototherapy result. An equipment health state basic model is established, the current equipment health state is predicted through an equipment prediction module on the basis of the established health state basic model, a prediction result is fed back, a patient information system is connected through a personality support module, and basic physiotherapy data of a patient is acquired. And outputting recommended illumination intensity and recommended treatment time based on the basic physiotherapy data, and monitoring a plurality of pieces of monitoring information and feedback output results through a remote monitoring module. The system accurately solves the core problems of dynamic fluctuation of phototherapy intensity, calibration lag and lack of personalized adaptation, and finally achieves dual guarantee of phototherapy effect and safety.

The invention provides an atomizer for neonatal airway protection and atomization conveying, and belongs to the field of atomizers. Comprising an atomizer body, an alarm is installed on the atomizer body, a sealing cover is installed on the atomizer body in a clamped mode, the sealing cover communicates with a mist outlet pipe, a rotating disc is rotationally connected to the top surface of the mist outlet pipe, a plurality of rotating rods are rotationally connected into the rotating disc, and a fan-shaped blocking plate fixedly sleeves the rotating rods; a corrugated guide pipe is fixedly connected into the mounting frame, the connecting pipe rotates around the outer wall of the corrugated guide pipe, the end of the corrugated guide pipe is communicated with a transfer pipe, a buffer plug valve is installed on the transfer pipe, the end side of the transfer pipe is communicated with a mask shell, and an expandable air bag mask is installed in the mask shell. And a pressure sensor is fixed in the air bag mask. Good attachment of the mask can be achieved, medicine can be stably conveyed, abnormal conditions can be handled in time, comfort is improved, the treatment effect is guaranteed, and practicability and reliability are achieved.

The invention relates to the technical field of newborn medical big data risk assessment, and discloses a newborn disease risk assessment method based on big data analysis. The method comprises the following steps: acquiring an initial multi-modal health record of a newborn from a multi-heterogeneous medical data source; carrying out fusion analysis on the data, and constructing a risk assessment map driven by an event; starting a continuous risk tracking process, performing hierarchical risk scanning by using the map, and identifying a stable risk cluster, an evolution risk cluster and an isolated risk signal; deducing a hierarchical risk management and control plan based on the spatial distribution and time evolution mode of the risk cluster; at the end of each period, integrating latest clinical treatment feedback and monitoring readings, and carrying out reverse calibration on entity node states and relation edge strength in the atlas; and dynamically recombining a measure execution sequence and resource allocation in the plan according to the calibrated atlas. According to the invention, dynamic and continuous evaluation and self-adaptive intervention planning of the neonatal health risk are realized.

The invention discloses a neonatal severe illness management system and system based on an AI large model and electronic equipment, and relates to the technical field of artificial intelligence and health cross, and the system comprises a data access integration module, a model training module and a personalized health suggestion generation module; the data access integration module is used for acquiring multi-modal medical data and performing cross-source heterogeneous fusion processing on the multi-modal medical data to generate a data set; the model training module is used for training a preset large language model based on the data set to obtain a neonatal severe health management model; and the personalized health suggestion generation module is used for generating a corresponding personalized health management scheme according to the vital sign data of the target newborn by using the newborn severe health management model. According to the invention, a health management scheme accurately fitting the individual condition can be provided for each newborn, and the effect and quality of newborn intensive care management are significantly improved.

The invention discloses a newborn cry recognition system based on machine learning, which belongs to the technical field of intelligent newborn nursing and comprises a data acquisition module, a feature extraction module, a feature selection module, a newborn cry recognition module and a recognition result feedback module. According to the method, the improved badger optimization algorithm is adopted to perform feature selection on the cry audio feature set, key features beneficial to distinguishing different cry categories are automatically selected, manual intervention errors are avoided, feature selection can be better and flexibly adjusted according to individual differences, and it is ensured that the system has high recognition accuracy on different newborn cry; according to the method, the mixed kernel function support vector machine model combined with the K nearest neighbor algorithm is adopted to carry out newborn cry recognition, local similarity improvement between samples is captured, boundaries between different cry categories are accurately divided, and overlapping between the categories is avoided, so that different types of cry are recognized more accurately and efficiently, and the overall usability of cry recognition is improved.

The invention provides a newborn ear malformation intelligent diagnosis method and system based on multi-modal fusion, and relates to the technical field of image data processing, and the method comprises the steps: obtaining an auricle image of a newborn; constructing a newborn ear malformation diagnosis model; extracting geometric features of the auricle image, and outputting an ear region detection frame in the auricle image; extracting texture features of the auricle image; performing multi-modal fusion on the geometric features and the texture features to obtain fusion features of the auricle image; and according to the fusion feature of the auricle image, detecting whether the newborn has ear deformity, and outputting a deformity type. According to the method, multi-modal fusion can be carried out on the geometric features and the texture features in the newborn auricle image, local details of the ear are fully captured, complex morphological and texture differences are better captured, the distinguishing ability of the model for different ear malformation types is improved, and the accuracy of newborn ear malformation diagnosis is improved.

The invention discloses a neonatal jaundice health management system based on big data, and belongs to the technical field of jaundice health management, and the system specifically comprises the steps: collecting the transdermal jaundice measurement value, hemoglobin concentration, day age and weight data of a neonate through a data collection module; an individualized drift index is calculated based on the hemoglobin concentration and the day age data through a physiological parameter calibration module; inputting the transdermal jaundice measurement numerical value and the individualized drift index into a dynamic correction model through a dynamic prediction analysis module to generate a serum bilirubin prediction numerical value; a time sequence data processing module is used for smoothing the predicted numerical value and calculating the variable quantity of adjacent time points; constructing trend indexes and generating serum bilirubin change trend data through a trend analysis and detection module; and finally, generating a health management scheme based on the threshold level and the trend change point through an intelligent decision module. According to the invention, effective assessment and personalized management of the neonatal jaundice risk are realized.

The invention discloses a low-power-consumption newborn sleep management system, which relates to the technical field of newborn sleep management and comprises a multi-mode sensing module, a data processing and analyzing module, an environment regulation and control module and a power management module. The system collects environment and physiological data through a low-power-consumption sensor array, analyzes the sleep state in combination with layered feature extraction and dynamic threshold judgment technologies, and optimizes the sleep environment by using a closed-loop feedback mechanism. The power management module adopts an energy recovery and dynamic power supply strategy to reduce energy consumption. According to the application, comprehensive monitoring of the sleep state of the newborn and intelligent environment optimization are realized, the problems of high power consumption and poor real-time performance of an existing system are solved, and the requirements of low power consumption and high reliability are met.

The invention relates to a neonatal respiratory distress risk assessment construction method, which comprises the following steps of: implementing non-intrusive micro-disturbance operation on a neonatal, and detecting respiratory rhythm phase drift, respiratory driving force low-frequency suppression and physiological tremor window change under disturbance so as to identify a pre-instability signal regulated and controlled by a respiratory system; collecting nerve and respiration feedback path data, analyzing the time difference between respiration instruction conduction and actual respiration starting, and identifying an abnormal decoupling phenomenon; based on multiple times of perturbation induction and feedback acquisition results, continuously monitoring the micro-adaptive recovery capability of the respiratory system of the newborn, and identifying the hidden fatigue trend of the respiratory system by judging progressive extension of respiratory frequency recovery time and gradual upward movement of respiratory power consumption; the respiratory redundancy regulation capability in the stress regulation process is monitored, premature intervention and repeated activation of an auxiliary breathing mode or a respiratory muscle group are judged, and the redundancy regulation critical compression phenomenon of a respiratory regulation system is analyzed to complete evaluation construction of the neonatal respiratory distress risk.

The invention discloses a newborn health monitoring system based on multi-modal data fusion, and belongs to the technical field of medical monitoring. According to the system, aiming at the problem of misjudgment caused by complex background interference and newborn development difference, a background perception feature decoupling enhancement network is constructed, a dual-channel architecture is matched with an adversarial loss function, foreground skin and background features are forcibly separated, and weak pathological features are enhanced in combination with a color space attention mechanism. Meanwhile, a development stage self-adaptive classification network is utilized, the gestational age serves as prior information to generate development codes, and dynamic modulation and weighted evaluation are conducted on fusion features through a premature infant and full-term infant double-branch classifier. According to the invention, the influence of environmental noise is effectively eliminated, and differentiated accurate health state recognition and risk early warning are realized.

The invention relates to a prone position adjusting bracket for newborns, which belongs to the technical field of nursing instruments and comprises a base pad, an adjusting pad, a monitoring system and an executing mechanism. The adjusting pad is slidably mounted on the base pad and comprises multiple sections of supporting parts, and the monitoring system is mounted on the adjusting pad and monitors the supporting force of each section of supporting part; the monitoring system comprises a pressure sensing unit and an attitude analysis unit, the pressure sensing unit is used for synchronously collecting pressure distribution data of each supporting surface, the attitude analysis unit is connected with the pressure sensing unit, and the attitude analysis unit constructs a three-dimensional pressure cloud picture model based on the pressure distribution data of the pressure sensing unit. Based on the three-dimensional pressure cloud picture model and a preset standard prone position biological curve, the trunk inclination angle, the limb weighing proportion and the abdomen compression peak value of the infant are solved in real time; the executing mechanism is used for receiving the adjusting amount of the posture analysis unit and driving the supporting part to adjust the supporting height, and real-time optimization of the posture of the baby is achieved through monitoring and intelligent feedback adjustment.

A method for treating or reducing a likelihood of hypoxia-ischemia induced brain damage and neurobehavioral dysfunction in neonates utilizes a relative high dose of nasally administered insulin. In one aspect, the method includes intranasally administering, to a neonate in need thereof, an effective dose of insulin comprising between 350 U to 2000 U insulin.

The invention provides a neonatal pain classification method and system based on multi-modal evidence, and the method comprises the steps: collecting a neonatal video clip and an electrocardiosignal synchronized with the video, and constructing a neonatal pain multi-modal data set containing a pain label; constructing a neonatal pain classification model based on multi-modal evidence, wherein the model comprises a data processing module, an evidence extraction module, a category confidence and classification uncertainty estimation module and a decision fusion module; using a sample training model in the newborn pain multi-modal data set; and carrying out pain classification on newly input newborn videos and electrocardiosignals by utilizing the trained model. According to the method, by combining Dirichlet distribution and an evidence theory, pain category probability distribution and classification uncertainty of expressions, postures and electrocardio modes are predicted respectively, decision fusion is carried out on prediction results, classification uncertainty evaluation is provided while pain classification is realized, and the reliability and interpretability of the model are enhanced.

In neonates or infants, the system identifies Neonatal Abstinence Syndrome (NAS) and in adult patients the system monitors for and identifies withdrawal and / or relapse symptoms. The system can be used for NAS babies in hospitals as well as in the home for adults. The system obtains biosensor or behavioral information about a patient from a wearable device on the patient and makes a determinative recommendation based on algorithm driven calculations and takes appropriate action based on its evaluation. The biosensor and behavioral information are collected by way of a wearable device, high precision cameras, multi pitch microphones over progressive periods of time. When the data is indicative of a need for treatment because the patient is exhibiting symptoms or indicating relapse traits, this information is sent to the system where an AI module further predicts and recommends a delivery of treatment for the patient.

The invention relates to the technical field of data analysis, in particular to a newborn health data analysis system which comprises a physical sign data construction module, a trend recognition module, a weight distribution module, a nonlinear modeling module and a prediction curve output module. According to the method, the growth cycle of the newborn is subdivided into continuous stages with different physiological meanings, the change rates of the sign data between the adjacent stages are deeply calculated and compared, the dynamic trends such as acceleration, stability or slowing down of body weight and height changes can be accurately recognized, and then quantitative weights are given to the different growth trends; according to the method, the positive growth situation is more evaluated in subsequent analysis, the growth and slowdown situation is correspondingly adjusted, a nonlinear prediction model is constructed on the basis, the non-uniform-speed natural law of growth and development of the newborn can be fit, the staged trend can be dynamically fused into long-term change track prediction, and the prediction accuracy of the growth and development of the newborn is improved. And the health conditions of the newborn in different developmental window periods are disclosed.

The present invention discloses a neonatal atomizer device, which relates to the field of atomizers and solves the problem that the medicine residue in the atomizer bottle is difficult to be fully atomized when the existing neonatal atomizer device is used. The device comprises a bottle body, a balancing mechanism, a conveying mechanism, a vibrating mechanism and an atomizing mechanism. The balancing mechanism comprises a storage bucket, a first conical tube and a balancing member, the conveying mechanism comprises an air inlet pipe and a connecting member, and the vibrating mechanism comprises a wind wheel and a vibrating member. The present invention keeps the bottom end of the first conical tube in a vertical downward state at all times through the balancing member, and keeps the air inlet pipe and the bottom end of the first conical tube in a connected state at all times through the connecting member, so that when the bottle body is tilted, the medicine liquid will always accumulate at the bottom of the first conical tube for atomization operation, and when the air flow enters the first conical tube, the wind wheel is blown to rotate, thereby driving the vibrating member to make the storage bucket vibrate, and the water droplets adhering to the inner wall of the storage bucket are shaken off to the bottom of the storage bucket by the vibration assistance, so as to be fully atomized.

The invention belongs to the technical field of medical supplies, and discloses a newborn head shape correcting pillow which comprises a pillow body, a positioning seat is arranged at the top end of the pillow body, an air conveying port is fixed to the outer portion of the positioning seat, a self-adaptive mechanism is installed at the bottom end of the positioning seat, a traction mechanism is arranged in the positioning seat, and a measuring mechanism is installed in the pillow body. Through cooperation of micro motors, a winding drum, an elastic band and other structures, the device can make a flexible silica gel head ring sleeve the forehead of a newborn, the multiple sets of micro motors are started to drive the winding drum to wind the elastic band, the traction direction is cooperatively controlled through the double motors, vector adjustment in a three-dimensional space is achieved, and the device accurately acts on a skull malformation area; the intermittent traction force can activate osteoblast activity of skull sutures, increase the local bone deposition rate and correct the head shape of the newborn, so that the aim of conveniently improving the correction efficiency of the device is achieved.

The invention relates to the technical field of neonatal respiration monitoring, and discloses a neonatal abnormal respiration early warning system. A physiological parameter acquisition module of the system acquires physiological parameter information of a target newborn in real time, and an analysis instruction is triggered after a physiological parameter abnormal signal is obtained; the breathing mode recognition module recognizes breathing mode characteristics and analyzes the breathing mode characteristics to obtain a breathing mode evaluation result; the abnormal feature extraction module extracts abnormal breathing features and analyzes the abnormal breathing features to obtain an abnormal feature evaluation value; the early warning grade evaluation module receives the result and the evaluation value, and obtains a low-risk early warning signal and a high-risk early warning signal through evaluation; the early warning signal generation module selects an early warning type according to the received signal, and obtains parameters of sound early warning and acousto-optic early warning which should be triggered. According to the system, dynamic monitoring and graded early warning of the neonatal breathing abnormity are achieved through multi-module cooperation, and support is provided for timely intervention of the neonatal breathing abnormity.

The invention discloses a virtual simulation operation system for neonatal enterostomy nursing. The virtual simulation operation system comprises a biomechanical simulation module which is used for simulating viscoelastic mechanical characteristics of neonatal abdominal wall tissues and hydrodynamic behaviors of enterostomy excreta in real time; the dynamic physiological simulation module generates a quantitative score by fusing operation normalization, complication prevention effect and injury occurrence rate, and maps a score result into a three-dimensional virtual scene in real time; the evaluation and data management module constructs a seamless connection system of hospital-community-home nursing scenes, supports continuous execution and data synchronization of nursing plans across the scenes, is internally provided with a complication dynamic evolution prediction model, and deduces the occurrence probability and severity of stoma stenosis and skin injury in real time according to the nursing operation quality; by simulating mechanical properties of newborn abdominal wall tissues and fluid dynamic behaviors of excreta, the system provides a highly realistic nursing operation environment, and the reality sense and effectiveness of training are enhanced.

The invention discloses a semi-supervised non-contact neonatal jaundice home intelligent early warning method based on image calibration, and the method comprises the steps: building a camera response function database, and building a color constancy depth model and a skin region segmentation network; designing a strong and weak enhancement strategy by using a large amount of label-free home data, constructing a time and context comparison learning module, and performing self-supervised training on a feature encoder; a small amount of labeled hospital data and a large amount of unlabeled family data are combined, and semi-supervised fine tuning is realized through pseudo label generation and supervised comparative learning; image sequences continuously uploaded by a user are input into the model, multi-day prediction of the bilirubin level is achieved, prediction uncertainty is quantified in combination with a Bayesian method, the risk boundary is dynamically adjusted, and personalized early warning is provided. According to the method, a user does not need to use a physical colorimetric card, color measurement errors caused by model differences of mobile equipment and variability of household illumination are inhibited from a data source, and the accuracy and robustness of subsequent jaundice assessment are improved; through a training framework combining self-supervised pre-training and semi-supervised fine tuning, the understanding ability and generalization performance of the model for the sequential characteristics of jaundice are improved.

The backflow enema anal tube comprises a hose body, an inner cavity of the hose body is divided into two channels through a separation part, and side holes communicated with the two channels respectively are formed in the side face of one end of the hose body. The other end of the hose body is connected with a liquid injection connecting pipe connected with an injector and a drainage connecting pipe connected with a drainage bag in a forked mode, the liquid injection connecting pipe and the drainage connecting pipe are communicated with the two channels respectively, and the tail end of the liquid injection connecting pipe is connected with a hard sleeving pipe. And the hard socketed pipe is detachably sleeved on the liquid outlet connector of the injector and is tightly matched with the liquid outlet connector. The backflow enema anal tube for the newborn is easy to operate, time-saving and labor-saving.

The invention discloses a newborn noninvasive electrocardiogram chest lead electrode fixing device, which belongs to the field of fixing devices and comprises a first plate electrode, a second plate electrode, a third plate electrode, a fourth plate electrode, a fifth plate electrode, a sixth plate electrode and a lead wire. When the connecting insertion rods installed on the top faces of the six plate electrodes sequentially penetrate through the adjusting insertion holes formed in the corresponding connecting parts formed in the top face of the elastic binding belt, the positions of the plate electrodes can be adjusted through the adjusting insertion holes, and then the limiting sockets are screwed into the connecting insertion rods through the threaded grooves to be in threaded connection with the external threads. The flat plate electrode can be fixed to the corresponding position of the elastic binding belt, and finally, the flat plate electrode is worn on the newborn through the elastic binding belt and the hook-and-loop fastener loop face and the hook-and-loop fastener hook face on the elastic binding belt, so that the flat plate motor can be tightly attached to the corresponding position of the chest of the newborn under the elastic binding acting force of the elastic binding belt.

An intelligent neonatal ECMO transfer incubator comprises a transfer box body, damping springs, adjusting electric rods, a transfer bed and binding bands, the damping springs are fixed to the transfer box body, the transfer bed is fixed to the damping springs, the adjusting electric rods are hinged to the two sides of the transfer bed, the binding bands are fixed to the transfer bed, and fixing grooves are formed in the side faces of the transfer bed. A spring limiting rod is fixed to the tail end of the binding band, the spring limiting rod is composed of a spring rod and a rotating rod, the spring limiting rod is rotationally connected into the fixing groove, and a limiting block of the spring limiting rod is connected with the fixing groove. Due to the fact that the device is provided with the binding bands, the tightness degree of the binding bands can be adjusted according to the figure of the newborn, the device has the damping function, jolting in the transferring process can be effectively avoided, the effect of a rocking chair can be simulated in the transferring process, the newborn is stabilized, and secondary damage to the newborn in the transferring process is avoided.

The invention relates to the technical field of intelligent medical treatment, and discloses a neonatal wearable physical sign monitoring device which comprises a plurality of collection points used for collecting neonatal physical sign signals, and the collection points comprise PPG sensor units which are arranged at different key positions of neonatal socks and have independent monitoring functions; the PPG sensor unit transmits collected photoelectric pulse signals to the processor module for processing, the processor module carries out fusion calculation on the signals of all collection points, and the final output of the oxyhemoglobin saturation and the heart rate of the newborn is obtained by integrating the data of all the collection points; the technical problems that an existing monitoring device for monitoring newborn physiological data is poor in wearing stability and poor in monitoring result accuracy are solved.

The invention discloses an umbilical vein catheterization virtual-entity fusion training system based on a novel material, and relates to the technical field of medical simulation training. According to the system, a dynamic three-dimensional umbilical vein anatomical model is constructed through the virtual simulation unit, the entity operation unit adopts a bionic gradient material to simulate neonatal umbilical tissue, and the binding force feedback unit realizes tactile-visual dual-channel interaction. Comprising a multi-source coupling coordinate calibration algorithm, a viscoelastic layered deformation transmission algorithm and the like, and the problems of insufficient operation authenticity and feedback lagging in traditional training are solved by dynamically matching virtual and entity operation spaces and simulating real tissue mechanical response. The novel material preparation unit realizes mechanical property matching with human tissues through a nano-composite process, and the environment simulation unit can reproduce various pathological scenes. The immersion and effectiveness of operation training are remarkably improved, and the method is suitable for standardized training of medical staff in the neonatology department.

The invention provides a negative pressure suction device for a neonatal umbilical sinus tract, and belongs to the technical field of medical instruments. The device comprises an adhesive tape, the adhesive tape is arranged in a disc shape, and the bottom of the adhesive tape is fixedly connected with a hydrocolloid adhesive ring. During nursing, an adjusting valve is opened, cleaning liquid is added from a feeding hopper and flows into a tank body through guiding, a driving motor is started, a rotating shaft rotates reversely, a stirring plate is driven to stir medicine and liquid medicine, meanwhile, the liquid medicine is turned over through an auger rotating reversely, the mixing effect is enhanced, after stirring is completed, a flow valve is opened, the driving motor drives the auger to rotate forwards, and the medicine and the liquid medicine are mixed. Liquid medicine enters the sinus tract through the drainage pipe, the cleaning catheter and the injection cleaning cavity in sequence to be flushed and applied, the flow speed can be adjusted and controlled during flushing, a child patient is prevented from being stimulated, the independent cavity is adopted, liquid medicine pollution is prevented, frequent pipe replacement is not needed, thorough cleaning and suction are achieved, the sinus tract is effectively nursed, and the infection risk is reduced.